mutation_query_test: add test for result size calculation

Check that digest only and digest+data query calculate result size to be
the same.

Message-Id: <20180906153800.GK2326@scylladb.com>
(cherry picked from commit 9e438933a2)

.dockerignore

@@ -1,4 +0,0 @@
-.git
-build
-seastar/build
-testlog

.github/CODEOWNERS

@@ -1,81 +0,0 @@
-# AUTH
-auth/* @elcallio @vladzcloudius
-
-# CACHE
-row_cache* @tgrabiec @haaawk
-*mutation* @tgrabiec @haaawk
-tests/mvcc* @tgrabiec @haaawk
-
-# CDC
-cdc/* @haaawk @kbr- @elcallio @piodul @jul-stas
-test/cql/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
-test/boost/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
-
-# COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio
-db/batch* @elcallio
-
-# COORDINATOR
-service/storage_proxy* @gleb-cloudius
-
-# COMPACTION
-sstables/compaction* @raphaelsc @nyh
-
-# CQL TRANSPORT LAYER
-transport/* @penberg
-
-# CQL QUERY LANGUAGE
-cql3/* @tgrabiec @penberg @psarna
-
-# COUNTERS
-counters* @haaawk @jul-stas
-tests/counter_test* @haaawk @jul-stas
-
-# GOSSIP
-gms/* @tgrabiec @asias
-
-# DOCKER
-dist/docker/* @penberg
-
-# LSA
-utils/logalloc* @tgrabiec
-
-# MATERIALIZED VIEWS
-db/view/* @nyh @psarna
-cql3/statements/*view* @nyh @psarna
-test/boost/view_* @nyh @psarna
-
-# PACKAGING
-dist/* @syuu1228
-
-# REPAIR
-repair/* @tgrabiec @asias @nyh
-
-# SCHEMA MANAGEMENT
-db/schema_tables* @tgrabiec @nyh
-db/legacy_schema_migrator* @tgrabiec @nyh
-service/migration* @tgrabiec @nyh
-schema* @tgrabiec @nyh
-
-# SECONDARY INDEXES
-db/index/* @nyh @penberg @psarna
-cql3/statements/*index* @nyh @penberg @psarna
-test/boost/*index* @nyh @penberg @psarna
-
-# SSTABLES
-sstables/* @tgrabiec @raphaelsc @nyh
-
-# STREAMING
-streaming/* @tgrabiec @asias
-service/storage_service.* @tgrabiec @asias
-
-# ALTERNATOR
-alternator/* @nyh @psarna
-test/alternator/* @nyh @psarna
-
-# HINTED HANDOFF
-db/hints/* @haaawk @piodul @vladzcloudius
-
-# REDIS
-redis/* @nyh @syuu1228
-redis-test/* @nyh @syuu1228

.github/ISSUE_TEMPLATE.md

@@ -1,9 +1,3 @@
-This is Scylla's bug tracker, to be used for reporting bugs only.
-If you have a question about Scylla, and not a bug, please ask it in
-our mailing-list at scylladb-dev@googlegroups.com or in our slack channel.
-
-- [] I have read the disclaimer above, and I am reporting a suspected malfunction in Scylla.
-
 *Installation details*
 Scylla version (or git commit hash):
 Cluster size:

.gitignore

@@ -18,10 +18,3 @@ CMakeLists.txt.user
 *.egg-info
 __pycache__CMakeLists.txt.user
 .gdbinit
-resources
-.pytest_cache
-/expressions.tokens
-tags
-testlog
-test/*/*.reject
-.vscode

.gitmodules

@@ -6,18 +6,6 @@
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
-[submodule "libdeflate"]
-	path = libdeflate
-	url = ../libdeflate
-[submodule "abseil"]
-	path = abseil
-	url = ../abseil-cpp
-[submodule "scylla-jmx"]
-	path = tools/jmx
-	url = ../scylla-jmx
-[submodule "scylla-tools"]
-	path = tools/java
-	url = ../scylla-tools-java
-[submodule "scylla-python3"]
-	path = tools/python3
-	url = ../scylla-python3
+[submodule "dist/ami/files/scylla-ami"]
+	path = dist/ami/files/scylla-ami
+	url = ../scylla-ami

CMakeLists.txt

@@ -5,25 +5,13 @@
 cmake_minimum_required(VERSION 3.7)
 project(scylla)
 
-if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
-  message(STATUS "Setting build type to 'Release' as none was specified.")
-  set(CMAKE_BUILD_TYPE "Release" CACHE
-      STRING "Choose the type of build." FORCE)
-  # Set the possible values of build type for cmake-gui
-  set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
-    "Debug" "Release" "Dev" "Sanitize")
-endif()
-
-if(CMAKE_BUILD_TYPE)
-    string(TOLOWER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
-else()
-    set(BUILD_TYPE "release")
-endif()
-
 if (NOT DEFINED FOR_IDE AND NOT DEFINED ENV{FOR_IDE} AND NOT DEFINED ENV{CLION_IDE})
     message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in IDEs, please define FOR_IDE to acknowledge this.")
 endif()
 
+# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
+set(SEASTAR_INCLUDE_DIRS "seastar")
+
 # These paths are always available, since they're included in the repository. Additional DPDK headers are placed while
 # Seastar is built, and are captured in `SEASTAR_INCLUDE_DIRS` through parsing the Seastar pkg-config file (below).
 set(SEASTAR_DPDK_INCLUDE_DIRS
@@ -34,14 +22,9 @@ set(SEASTAR_DPDK_INCLUDE_DIRS
 
 find_package(PkgConfig REQUIRED)
 
-set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/build/${BUILD_TYPE}/seastar:$ENV{PKG_CONFIG_PATH}")
+set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
 pkg_check_modules(SEASTAR seastar)
 
-if(NOT SEASTAR_INCLUDE_DIRS)
-    # Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
-    set(SEASTAR_INCLUDE_DIRS "seastar/include")
-endif()
-
 find_package(Boost COMPONENTS filesystem program_options system thread)
 
 ##
@@ -87,7 +70,7 @@ scan_scylla_source_directories(
           seastar/json
           seastar/net
           seastar/rpc
-          seastar/testing
+          seastar/tests
           seastar/util)
 
 scan_scylla_source_directories(
@@ -110,12 +93,11 @@ scan_scylla_source_directories(
           io
           locator
           message
-          raft
           repair
           service
           sstables
           streaming
-          test
+          tests
           thrift
           tracing
           transport
@@ -124,7 +106,7 @@ scan_scylla_source_directories(
 scan_scylla_source_directories(
         VAR SCYLLA_GEN_SOURCE_FILES
         RECURSIVE
-        PATHS build/${BUILD_TYPE}/gen)
+        PATHS build/release/gen)
 
 set(SCYLLA_SOURCE_FILES
         ${SCYLLA_ROOT_SOURCE_FILES}
@@ -135,11 +117,15 @@ add_executable(scylla
         ${SEASTAR_SOURCE_FILES}
         ${SCYLLA_SOURCE_FILES})
 
+# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
+# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
+list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
+
 # If the Seastar pkg-config information is available, append to the default flags.
 #
 # For ease of browsing the source code, we always pretend that DPDK is enabled.
 target_compile_options(scylla PUBLIC
-        -std=gnu++20
+        -std=gnu++14
         -DHAVE_DPDK
         -DHAVE_HWLOC
         "${SEASTAR_CFLAGS}")
@@ -151,7 +137,4 @@ target_include_directories(scylla PUBLIC
         ${SEASTAR_DPDK_INCLUDE_DIRS}
         ${SEASTAR_INCLUDE_DIRS}
         ${Boost_INCLUDE_DIRS}
-        xxhash
-        libdeflate
-        abseil
-        build/${BUILD_TYPE}/gen)
+        build/release/gen)

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Asking questions or requesting help
 
-Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) for general questions and help.
 
 # Reporting an issue
 
@@ -8,4 +8,4 @@ Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to re
 
 # Contributing Code to Scylla
 
-To contribute code to Scylla, you need to sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

HACKING.md

@@ -18,36 +18,13 @@ $ git submodule update --init --recursive
 
 ### Dependencies
 
-Scylla is fairly fussy about its build environment, requiring a very recent
-version of the C++20 compiler and numerous tools and libraries to build.
+Scylla depends on the system package manager for its development dependencies.
 
-Run `./install-dependencies.sh` (as root) to use your Linux distributions's
-package manager to install the appropriate packages on your build machine.
-However, this will only work on very recent distributions. For example,
-currently Fedora users must upgrade to Fedora 32 otherwise the C++ compiler
-will be too old, and not support the new C++20 standard that Scylla uses.
-
-Alternatively, to avoid having to upgrade your build machine or install
-various packages on it, we provide another option - the **frozen toolchain**.
-This is a script, `./tools/toolchain/dbuild`, that can execute build or run
-commands inside a Docker image that contains exactly the right build tools and
-libraries. The `dbuild` technique is useful for beginners, but is also the way
-in which ScyllaDB produces official releases, so it is highly recommended.
-
-To use `dbuild`, you simply prefix any build or run command with it. Building
-and running Scylla becomes as easy as:
-
-```bash
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
-$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
-```
+Running `./install_dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
 
 ### Build system
 
-**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
-thread, and up to 3 GB per native thread while linking. GCC >= 10 is
-required.
+**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native thread, and up to 3 GB per native thread while linking.
 
 Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
 
@@ -66,9 +43,11 @@ The full suite of options for project configuration is available via
 $ ./configure.py --help
 ```
 
-The most important option is:
+The most important options are:
 
-- `--enable-dpdk`: [DPDK](http://dpdk.org/) is a set of libraries and drivers for fast packet processing. During development, it's not necessary to enable support even if it is supported by your platform.
+- `--mode={release,debug,all}`: Debug mode enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer) and allows for debugging with tools like GDB. Debugging builds are generally slower and generate much larger object files than release builds.
+
+- `--{enable,disable}-dpdk`: [DPDK](http://dpdk.org/) is a set of libraries and drivers for fast packet processing. During development, it's not necessary to enable support even if it is supported by your platform.
 
 Source files and build targets are tracked manually in `configure.py`, so the script needs to be updated when new files or targets are added or removed.
 
@@ -76,30 +55,6 @@ To save time -- for instance, to avoid compiling all unit tests -- you can also
 
 ```bash
 $ ninja-build build/release/tests/schema_change_test
-$ ninja-build build/release/service/storage_proxy.o
-```
-
-You can also specify a single mode. For example
-
-```bash
-$ ninja-build release
-```
-
-Will build everytihng in release mode. The valid modes are
-
-* Debug: Enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer)
-  and other sanity checks. It has no optimizations, which allows for debugging with tools like
-  GDB. Debugging builds are generally slower and generate much larger object files than release builds.
-* Release: Fewer checks and more optimizations. It still has debug info.
-* Dev: No optimizations or debug info. The objective is to compile and link as fast as possible.
-  This is useful for the first iterations of a patch.
-
-
-Note that by default unit tests binaries are stripped so they can't be used with gdb or seastar-addr2line.
-To include debug information in the unit test binary, build the test binary with a `_g` suffix. For example,
-
-```bash
-$ ninja-build build/release/tests/schema_change_test_g
 ```
 
 ### Unit testing
@@ -128,57 +83,9 @@ The `-c1 -m1G` arguments limit this Seastar-based test to a single system thread
 
 ### Preparing patches
 
-All changes to Scylla are submitted as patches to the public [mailing list](mailto:scylladb-dev@googlegroups.com). Once a patch is approved by one of the maintainers of the project, it is committed to the maintainers' copy of the repository at https://github.com/scylladb/scylla.
+All changes to Scylla are submitted as patches to the public mailing list. Once a patch is approved by one of the maintainers of the project, it is committed to the maintainers' copy of the repository at https://github.com/scylladb/scylla.
 
-Detailed instructions for formatting patches for the mailing list and advice on preparing good patches are available at the [ScyllaDB website](http://docs.scylladb.com/contribute/). There are also some guidelines that can help you make the patch review process smoother:
-
-1. Before generating patches, make sure your Git configuration points to `.gitorderfile`. You can do it by running
-
-```bash
-$ git config diff.orderfile .gitorderfile
-```
-
-2. If you are sending more than a single patch, push your changes into a new branch of your fork of Scylla on GitHub and add a URL pointing to this branch to your cover letter.
-
-3. If you are sending a new revision of an earlier patchset, add a brief summary of changes in this version, for example:
-```
-In v3:
-    - declared move constructor and move assignment operator as noexcept
-    - used std::variant instead of a union
-    ...
-```
-
-4. Add information about the tests run with this fix. It can look like
-```
-"Tests: unit ({mode}), dtest ({smp})"
-```
-
-The usual is "Tests: unit (dev)", although running debug tests is encouraged.
-
-5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.
-
-6. The Linux kernel's [Submitting Patches](https://www.kernel.org/doc/html/v4.19/process/submitting-patches.html) document offers excellent advice on how to prepare patches and patchsets for review. Since the Scylla development process is derived from the kernel's, almost all of the advice there is directly applicable.
-
-### Finding a person to review and merge your patches
-
-You can use the `scripts/find-maintainer` script to find a subsystem maintainer and/or reviewer for your patches. The script accepts a filename in the git source tree as an argument and outputs a list of subsystems the file belongs to and their respective maintainers and reviewers. For example, if you changed the `cql3/statements/create_view_statement.hh` file, run the script as follows:
-
-```bash
-$ ./scripts/find-maintainer cql3/statements/create_view_statement.hh
-```
-
-and you will get output like this:
-
-```
-CQL QUERY LANGUAGE
-  Tomasz Grabiec <tgrabiec@scylladb.com>   [maintainer]
-  Pekka Enberg <penberg@scylladb.com>      [maintainer]
-MATERIALIZED VIEWS
-  Pekka Enberg <penberg@scylladb.com>      [maintainer]
-  Duarte Nunes <duarte@scylladb.com>       [maintainer]
-  Nadav Har'El <nyh@scylladb.com>          [reviewer]
-  Duarte Nunes <duarte@scylladb.com>       [reviewer]
-```
+Detailed instructions for formatting patches for the mailing list and advice on preparing good patches are available at the [ScyllaDB website](http://docs.scylladb.com/contribute/).
 
 ### Running Scylla
 
@@ -211,29 +118,6 @@ On a development machine, one might run Scylla as
 $ SCYLLA_HOME=$HOME/scylla build/release/scylla --overprovisioned --developer-mode=yes
 ```
 
-To interact with scylla it is recommended to build our versions of
-cqlsh and nodetool. They are available at
-https://github.com/scylladb/scylla-tools-java and can be built with
-
-```bash
-$ sudo ./install-dependencies.sh
-$ ant jar
-```
-
-cqlsh should work out of the box, but nodetool depends on a running
-scylla-jmx (https://github.com/scylladb/scylla-jmx). It can be build
-with
-
-```bash
-$ mvn package
-```
-
-and must be started with
-
-```bash
-$ ./scripts/scylla-jmx
-```
-
 ### Branches and tags
 
 Multiple release branches are maintained on the Git repository at https://github.com/scylladb/scylla. Release 1.5, for instance, is tracked on the `branch-1.5` branch.
@@ -324,7 +208,7 @@ In this example, `10.0.0.2` will be sent up to 16 jobs and the local machine wil
 
 When a compilation is in progress, the status of jobs on all remote machines can be visualized in the terminal with `distccmon-text` or graphically as a GTK application with `distccmon-gnome`.
 
-One thing to keep in mind is that linking object files happens on the coordinating machine, which can be a bottleneck. See the next sections speeding up this process.
+One thing to keep in mind is that linking object files happens on the coordinating machine, which can be a bottleneck. See the next section speeding up this process.
 
 ### Using the `gold` linker
 
@@ -334,24 +218,6 @@ Linking Scylla can be slow. The gold linker can replace GNU ld and often speeds
 $ sudo alternatives --config ld
 ```
 
-### Using split dwarf
-
-With debug info enabled, most of the link time is spent copying and
-relocating it. It is possible to leave most of the debug info out of
-the link by writing it to a side .dwo file. This is done by passing
-`-gsplit-dwarf` to gcc.
-
-Unfortunately just `-gsplit-dwarf` would slow down `gdb` startup. To
-avoid that the gold linker can be told to create an index with
-`--gdb-index`.
-
-More info at https://gcc.gnu.org/wiki/DebugFission.
-
-Both options can be enable by passing `--split-dwarf` to configure.py.
-
-Note that distcc is *not* compatible with it, but icecream
-(https://github.com/icecc/icecream) is.
-
 ### Testing changes in Seastar with Scylla
 
 Sometimes Scylla development is closely tied with a feature being developed in Seastar. It can be useful to compile Scylla with a particular check-out of Seastar.
@@ -365,8 +231,3 @@ $ git remote add local /home/tsmith/src/seastar
 $ git remote update
 $ git checkout -t local/my_local_seastar_branch
 ```
-
-### Core dump debugging
-
-Slides:
-2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

NOTICE.txt

@@ -1,7 +1,2 @@
 This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
 especially Apache Cassandra.
-
-It includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
-These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.
-
-It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)

README-DPDK.md

@@ -0,0 +1,29 @@
+Seastar and DPDK
+================
+
+Seastar uses the Data Plane Development Kit to drive NIC hardware directly.  This
+provides an enormous performance boost.
+
+To enable DPDK, specify `--enable-dpdk` to `./configure.py`, and `--dpdk-pmd` as a
+run-time parameter.  This will use the DPDK package provided as a git submodule with the
+seastar sources.
+
+To use your own self-compiled DPDK package, follow this procedure:
+
+1. Setup host to compile DPDK:
+   - Ubuntu 
+     `sudo apt-get install -y build-essential linux-image-extra-$(uname -r)` 
+2. Prepare a DPDK SDK:
+   - Download the latest DPDK release: `wget http://dpdk.org/browse/dpdk/snapshot/dpdk-1.8.0.tar.gz`
+   - Untar it.
+   - Edit config/common_linuxapp: set CONFIG_RTE_MBUF_REFCNT and CONFIG_RTE_LIBRTE_KNI to 'n'.
+   - For DPDK 1.7.x: edit config/common_linuxapp: 
+     - Set CONFIG_RTE_LIBRTE_PMD_BOND  to 'n'.
+     - Set CONFIG_RTE_MBUF_SCATTER_GATHER to 'n'.
+     - Set CONFIG_RTE_LIBRTE_IP_FRAG to 'n'.
+   - Start the tools/setup.sh script as root.
+   - Compile a linuxapp target (option 9).
+   - Install IGB_UIO module (option 11).
+   - Bind some physical port to IGB_UIO (option 17).
+   - Configure hugepage mappings (option 14/15).
+3. Run a configure.py: `./configure.py --dpdk-target <Path to untared dpdk-1.8.0 above>/x86_64-native-linuxapp-gcc`.

README.md

@@ -1,113 +1,78 @@
 # Scylla
 
-[![Slack](https://img.shields.io/badge/slack-scylla-brightgreen.svg?logo=slack)](http://slack.scylladb.com)
-[![Twitter](https://img.shields.io/twitter/follow/ScyllaDB.svg?style=social&label=Follow)](https://twitter.com/intent/follow?screen_name=ScyllaDB)
-
-## What is Scylla?
-
-Scylla is the real-time big data database that is API-compatible with Apache Cassandra and Amazon DynamoDB.
-Scylla embraces a shared-nothing approach that increases throughput and storage capacity to realize order-of-magnitude performance improvements and reduce hardware costs.
-
-For more information, please see the [ScyllaDB web site].
-
-[ScyllaDB web site]: https://www.scylladb.com
-
-## Build Prerequisites
-
-Scylla is fairly fussy about its build environment, requiring very recent
-versions of the C++20 compiler and of many libraries to build. The document
-[HACKING.md](HACKING.md) includes detailed information on building and
-developing Scylla, but to get Scylla building quickly on (almost) any build
-machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md),
-This is a pre-configured Docker image which includes recent versions of all
-the required compilers, libraries and build tools. Using the frozen toolchain
-allows you to avoid changing anything in your build machine to meet Scylla's
-requirements - you just need to meet the frozen toolchain's prerequisites
-(mostly, Docker or Podman being available).
-
-## Building Scylla
-
-Building Scylla with the frozen toolchain `dbuild` is as easy as:
+## Quick-start
 
 ```bash
-$ git submodule update --init --force --recursive
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
+$ git submodule update --init --recursive
+$ sudo ./install-dependencies.sh
+$ ./configure.py --mode=release
+$ ninja-build -j4 # Assuming 4 system threads.
+$ ./build/release/scylla
+$ # Rejoice!
 ```
 
-For further information, please see:
-
-* [Developer documentation] for more information on building Scylla.
-* [Build documentation] on how to build Scylla binaries, tests, and packages.
-* [Docker image build documentation] for information on how to build Docker images.
-
-[developer documentation]: HACKING.md
-[build documentation]: docs/building.md
-[docker image build documentation]: dist/docker/redhat/README.md
+Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
 
 ## Running Scylla
 
-To start Scylla server, run:
+* Run Scylla
+```
+./build/release/scylla
 
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --workdir tmp --smp 1 --developer-mode 1
 ```
 
-This will start a Scylla node with one CPU core allocated to it and data files stored in the `tmp` directory.
-The `--developer-mode` is needed to disable the various checks Scylla performs at startup to ensure the machine is configured for maximum performance (not relevant on development workstations).
-Please note that you need to run Scylla with `dbuild` if you built it with the frozen toolchain.
+* run Scylla with one CPU and ./tmp as data directory
 
-For more run options, run:
-
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --help
+```
+./build/release/scylla --datadir tmp --commitlog-directory tmp --smp 1
 ```
 
-## Testing
+* For more run options:
+```
+./build/release/scylla --help
+```
 
-See [test.py manual](docs/testing.md).
+## Building Fedora RPM
 
-## Scylla APIs and compatibility
-By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
-Thrift. There is also support for the API of Amazon DynamoDB™,
-which needs to be enabled and configured in order to be used. For more
-information on how to enable the DynamoDB™ API in Scylla,
-and the current compatibility of this feature as well as Scylla-specific extensions, see
-[Alternator](docs/alternator/alternator.md) and
-[Getting started with Alternator](docs/alternator/getting-started.md).
+As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
 
-## Documentation
+```
+# Install mock:
+sudo yum install mock
 
-Documentation can be found in [./docs](./docs) and on the
-[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
-definition of what goes where, so when looking for something be sure to check
-both.
-Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
-User documentation can be found [here](https://docs.scylladb.com/).
+# Add user to the "mock" group:
+usermod -a -G mock $USER && newgrp mock
+```
 
-## Training 
+Then, to build an RPM, run:
 
-Training material and online courses can be found at [Scylla University](https://university.scylladb.com/). 
-The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling, 
-administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions, 
-multi-datacenters and how Scylla integrates with third-party applications.
+```
+./dist/redhat/build_rpm.sh
+```
+
+The built RPM is stored in ``/var/lib/mock/<configuration>/result`` directory.
+For example, on Fedora 21 mock reports the following:
+
+```
+INFO: Done(scylla-server-0.00-1.fc21.src.rpm) Config(default) 20 minutes 7 seconds
+INFO: Results and/or logs in: /var/lib/mock/fedora-21-x86_64/result
+```
+
+## Building Fedora-based Docker image
+
+Build a Docker image with:
+
+```
+cd dist/docker
+docker build -t <image-name> .
+```
+
+Run the image with:
+
+```
+docker run -p $(hostname -i):9042:9042 -i -t <image name>
+```
 
 ## Contributing to Scylla
 
-If you want to report a bug or submit a pull request or a patch, please read the [contribution guidelines].
-
-If you are a developer working on Scylla, please read the [developer guidelines].
-
-[contribution guidelines]: CONTRIBUTING.md
-[developer guidelines]: HACKING.md
-
-## Contact
-
-* The [users mailing list] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
-* The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
-
-[Users mailing list]: https://groups.google.com/forum/#!forum/scylladb-users
-
-[Slack channel]: http://slack.scylladb.com/
-
-[Developers mailing list]: https://groups.google.com/forum/#!forum/scylladb-dev
+[Guidelines for contributing](CONTRIBUTING.md)

SCYLLA-VERSION-GEN

@@ -1,7 +1,6 @@
 #!/bin/sh
 
-PRODUCT=scylla
-VERSION=4.3.7
+VERSION=2.1.6
 
 if test -f version
 then
@@ -19,16 +18,7 @@ else
 	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
-if [ -f build/SCYLLA-RELEASE-FILE ]; then
-	RELEASE_FILE=$(cat build/SCYLLA-RELEASE-FILE)
-	GIT_COMMIT_FILE=$(cat build/SCYLLA-RELEASE-FILE |cut -d . -f 3)
-	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
-		exit 0
-	fi
-fi
-
 echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
 mkdir -p build
 echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
 echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
-echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE

absl-flat_hash_map.cc

@@ -1,26 +0,0 @@
-/*
- * Copyright (C) 2020 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "absl-flat_hash_map.hh"
-
-size_t sstring_hash::operator()(std::string_view v) const noexcept {
-    return absl::Hash<std::string_view>{}(v);
-}

absl-flat_hash_map.hh

@@ -1,47 +0,0 @@
-/*
- * Copyright (C) 2020 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <absl/container/flat_hash_map.h>
-#include <seastar/core/sstring.hh>
-
-using namespace seastar;
-
-struct sstring_hash {
-    using is_transparent = void;
-    size_t operator()(std::string_view v) const noexcept;
-};
-
-struct sstring_eq {
-    using is_transparent = void;
-    bool operator()(std::string_view a, std::string_view b) const noexcept {
-        return a == b;
-    }
-};
-
-template <typename K, typename V, typename... Ts>
-struct flat_hash_map : public absl::flat_hash_map<K, V, Ts...> {
-};
-
-template <typename V>
-struct flat_hash_map<sstring, V>
-    : public absl::flat_hash_map<sstring, V, sstring_hash, sstring_eq> {};

alternator/auth.cc

@@ -1,147 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "alternator/error.hh"
-#include "log.hh"
-#include <string>
-#include <string_view>
-#include <gnutls/crypto.h>
-#include <seastar/util/defer.hh>
-#include "hashers.hh"
-#include "bytes.hh"
-#include "alternator/auth.hh"
-#include <fmt/format.h>
-#include "auth/common.hh"
-#include "auth/password_authenticator.hh"
-#include "auth/roles-metadata.hh"
-#include "cql3/query_processor.hh"
-#include "cql3/untyped_result_set.hh"
-
-namespace alternator {
-
-static logging::logger alogger("alternator-auth");
-
-static hmac_sha256_digest hmac_sha256(std::string_view key, std::string_view msg) {
-    hmac_sha256_digest digest;
-    int ret = gnutls_hmac_fast(GNUTLS_MAC_SHA256, key.data(), key.size(), msg.data(), msg.size(), digest.data());
-    if (ret) {
-        throw std::runtime_error(fmt::format("Computing HMAC failed ({}): {}", ret, gnutls_strerror(ret)));
-    }
-    return digest;
-}
-
-static hmac_sha256_digest get_signature_key(std::string_view key, std::string_view date_stamp, std::string_view region_name, std::string_view service_name) {
-    auto date = hmac_sha256("AWS4" + std::string(key), date_stamp);
-    auto region = hmac_sha256(std::string_view(date.data(), date.size()), region_name);
-    auto service = hmac_sha256(std::string_view(region.data(), region.size()), service_name);
-    auto signing = hmac_sha256(std::string_view(service.data(), service.size()), "aws4_request");
-    return signing;
-}
-
-static std::string apply_sha256(std::string_view msg) {
-    sha256_hasher hasher;
-    hasher.update(msg.data(), msg.size());
-    return to_hex(hasher.finalize());
-}
-
-static std::string format_time_point(db_clock::time_point tp) {
-    time_t time_point_repr = db_clock::to_time_t(tp);
-    std::string time_point_str;
-    time_point_str.resize(17);
-    ::tm time_buf;
-    // strftime prints the terminating null character as well
-    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", ::gmtime_r(&time_point_repr, &time_buf));
-    time_point_str.resize(16);
-    return time_point_str;
-}
-
-void check_expiry(std::string_view signature_date) {
-    //FIXME: The default 15min can be changed with X-Amz-Expires header - we should honor it
-    std::string expiration_str = format_time_point(db_clock::now() - 15min);
-    std::string validity_str = format_time_point(db_clock::now() + 15min);
-    if (signature_date < expiration_str) {
-        throw api_error::invalid_signature(
-                fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
-                signature_date, expiration_str));
-    }
-    if (signature_date > validity_str) {
-        throw api_error::invalid_signature(
-                fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
-                signature_date, validity_str));
-    }
-}
-
-std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
-        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
-    auto amz_date_it = signed_headers_map.find("x-amz-date");
-    if (amz_date_it == signed_headers_map.end()) {
-        throw api_error::invalid_signature("X-Amz-Date header is mandatory for signature verification");
-    }
-    std::string_view amz_date = amz_date_it->second;
-    check_expiry(amz_date);
-    std::string_view datestamp = amz_date.substr(0, 8);
-    if (datestamp != orig_datestamp) {
-        throw api_error::invalid_signature(
-                format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
-                        orig_datestamp, datestamp));
-    }
-    std::string_view canonical_uri = "/";
-
-    std::stringstream canonical_headers;
-    for (const auto& header : signed_headers_map) {
-        canonical_headers << fmt::format("{}:{}", header.first, header.second) << '\n';
-    }
-
-    std::string payload_hash = apply_sha256(body_content);
-    std::string canonical_request = fmt::format("{}\n{}\n{}\n{}\n{}\n{}", method, canonical_uri, query_string, canonical_headers.str(), signed_headers_str, payload_hash);
-
-    std::string_view algorithm = "AWS4-HMAC-SHA256";
-    std::string credential_scope = fmt::format("{}/{}/{}/aws4_request", datestamp, region, service);
-    std::string string_to_sign = fmt::format("{}\n{}\n{}\n{}", algorithm, amz_date, credential_scope,  apply_sha256(canonical_request));
-
-    hmac_sha256_digest signing_key = get_signature_key(secret_access_key, datestamp, region, service);
-    hmac_sha256_digest signature = hmac_sha256(std::string_view(signing_key.data(), signing_key.size()), string_to_sign);
-
-    return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
-}
-
-future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
-    static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
-            auth::meta::roles_table::qualified_name, auth::meta::roles_table::role_col_name);
-
-    auto cl = auth::password_authenticator::consistency_for_user(username);
-    auto& timeout = auth::internal_distributed_timeout_config();
-    return qp.execute_internal(query, cl, timeout, {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
-        auto res = f.get0();
-        auto salted_hash = std::optional<sstring>();
-        if (res->empty()) {
-            throw api_error::unrecognized_client(fmt::format("User not found: {}", username));
-        }
-        salted_hash = res->one().get_opt<sstring>("salted_hash");
-        if (!salted_hash) {
-            throw api_error::unrecognized_client(fmt::format("No password found for user: {}", username));
-        }
-        return make_ready_future<std::string>(*salted_hash);
-    });
-}
-
-}

alternator/auth.hh

@@ -1,46 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <string>
-#include <string_view>
-#include <array>
-#include "gc_clock.hh"
-#include "utils/loading_cache.hh"
-
-namespace cql3 {
-class query_processor;
-}
-
-namespace alternator {
-
-using hmac_sha256_digest = std::array<char, 32>;
-
-using key_cache = utils::loading_cache<std::string, std::string>;
-
-std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
-        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string);
-
-future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username);
-
-}

alternator/base64.cc

@@ -1,145 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-// The DynamoAPI dictates that "binary" (a.k.a. "bytes" or "blob") values
-// be encoded in the JSON API as base64-encoded strings. This is code to
-// convert byte arrays to base64-encoded strings, and back.
-
-#include "base64.hh"
-
-#include <ctype.h>
-
-
-// Arrays for quickly converting to and from an integer between 0 and 63,
-// and the character used in base64 encoding to represent it.
-static class base64_chars {
-public:
-    static constexpr const char to[] =
-            "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
-    int8_t from[255];
-    base64_chars() {
-        static_assert(sizeof(to) == 64 + 1);
-        for (int i = 0; i < 255; i++) {
-            from[i] = -1; // signal invalid character
-        }
-        for (int i = 0; i < 64; i++) {
-            from[(unsigned) to[i]] = i;
-        }
-    }
-} base64_chars;
-
-std::string base64_encode(bytes_view in) {
-    std::string ret;
-    ret.reserve(((4 * in.size() / 3) + 3) & ~3);
-    int i = 0;
-    unsigned char chunk3[3]; // chunk of input
-    for (auto byte : in) {
-        chunk3[i++] = byte;
-        if (i == 3) {
-            ret += base64_chars.to[ (chunk3[0] & 0xfc) >> 2 ];
-            ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
-            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
-            ret += base64_chars.to[ chunk3[2] & 0x3f ];
-            i = 0;
-        }
-    }
-    if (i) {
-        // i can be 1 or 2.
-        for(int j = i; j < 3; j++)
-            chunk3[j] = '\0';
-        ret += base64_chars.to[ ( chunk3[0] & 0xfc) >> 2 ];
-        ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
-        if (i == 2) {
-            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
-        } else {
-            ret += '=';
-        }
-        ret += '=';
-    }
-    return ret;
-}
-
-static std::string base64_decode_string(std::string_view in) {
-    int i = 0;
-    int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
-    std::string ret;
-    ret.reserve(in.size() * 3 / 4);
-    for (unsigned char c : in) {
-        uint8_t dc = base64_chars.from[c];
-        if (dc == 255) {
-            // Any unexpected character, include the "=" character usually
-            // used for padding, signals the end of the decode.
-            break;
-        }
-        chunk4[i++] = dc;
-        if (i == 4) {
-            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
-            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
-            ret += ((chunk4[2] & 0x3) << 6) + chunk4[3];
-            i = 0;
-        }
-    }
-    if (i) {
-        // i can be 2 or 3, meaning 1 or 2 more output characters
-        if (i>=2)
-            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
-        if (i==3)
-            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
-    }
-    return ret;
-}
-
-bytes base64_decode(std::string_view in) {
-    // FIXME: This copy is sad. The problem is we need back "bytes"
-    // but "bytes" doesn't have efficient append and std::string.
-    // To fix this we need to use bytes' "uninitialized" feature.
-    std::string ret = base64_decode_string(in);
-    return bytes(ret.begin(), ret.end());
-}
-
-static size_t base64_padding_len(std::string_view str) {
-    size_t padding = 0;
-    padding += (!str.empty() && str.back() == '=');
-    padding += (str.size() > 1 && *(str.end() - 2) == '=');
-    return padding;
-}
-
-size_t base64_decoded_len(std::string_view str) {
-    return str.size() / 4 * 3 - base64_padding_len(str);
-}
-
-bool base64_begins_with(std::string_view base, std::string_view operand) {
-    if (base.size() < operand.size() || base.size() % 4 != 0 || operand.size() % 4 != 0) {
-        return false;
-    }
-    if (base64_padding_len(operand) == 0) {
-        return base.starts_with(operand);
-    }
-    const std::string_view unpadded_base_prefix = base.substr(0, operand.size() - 4);
-    const std::string_view unpadded_operand = operand.substr(0, operand.size() - 4);
-    if (unpadded_base_prefix != unpadded_operand) {
-        return false;
-    }
-    // Decode and compare last 4 bytes of base64-encoded strings
-    const std::string base_remainder = base64_decode_string(base.substr(operand.size() - 4, operand.size()));
-    const std::string operand_remainder = base64_decode_string(operand.substr(operand.size() - 4));
-    return base_remainder.starts_with(operand_remainder);
-}

alternator/base64.hh

@@ -1,38 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <string_view>
-#include "bytes.hh"
-#include "utils/rjson.hh"
-
-std::string base64_encode(bytes_view);
-
-bytes base64_decode(std::string_view);
-
-inline bytes base64_decode(const rjson::value& v) {
-  return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
-}
-
-size_t base64_decoded_len(std::string_view str);
-
-bool base64_begins_with(std::string_view base, std::string_view operand);

alternator/conditions.cc

@@ -1,750 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <list>
-#include <map>
-#include <string_view>
-#include "alternator/conditions.hh"
-#include "alternator/error.hh"
-#include "cql3/constants.hh"
-#include <unordered_map>
-#include "utils/rjson.hh"
-#include "serialization.hh"
-#include "base64.hh"
-#include <stdexcept>
-#include <boost/algorithm/cxx11/all_of.hpp>
-#include <boost/algorithm/cxx11/any_of.hpp>
-#include "utils/overloaded_functor.hh"
-
-#include "expressions.hh"
-
-namespace alternator {
-
-static logging::logger clogger("alternator-conditions");
-
-comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator) {
-    static std::unordered_map<std::string, comparison_operator_type> ops = {
-            {"EQ", comparison_operator_type::EQ},
-            {"NE", comparison_operator_type::NE},
-            {"LE", comparison_operator_type::LE},
-            {"LT", comparison_operator_type::LT},
-            {"GE", comparison_operator_type::GE},
-            {"GT", comparison_operator_type::GT},
-            {"IN", comparison_operator_type::IN},
-            {"NULL", comparison_operator_type::IS_NULL},
-            {"NOT_NULL", comparison_operator_type::NOT_NULL},
-            {"BETWEEN", comparison_operator_type::BETWEEN},
-            {"BEGINS_WITH", comparison_operator_type::BEGINS_WITH},
-            {"CONTAINS", comparison_operator_type::CONTAINS},
-            {"NOT_CONTAINS", comparison_operator_type::NOT_CONTAINS},
-    };
-    if (!comparison_operator.IsString()) {
-        throw api_error::validation(format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
-    }
-    std::string op = comparison_operator.GetString();
-    auto it = ops.find(op);
-    if (it == ops.end()) {
-        throw api_error::validation(format("Unsupported comparison operator {}", op));
-    }
-    return it->second;
-}
-
-namespace {
-
-struct size_check {
-    // True iff size passes this check.
-    virtual bool operator()(rapidjson::SizeType size) const = 0;
-    // Check description, such that format("expected array {}", check.what()) is human-readable.
-    virtual sstring what() const = 0;
-};
-
-class exact_size : public size_check {
-    rapidjson::SizeType _expected;
-  public:
-    explicit exact_size(rapidjson::SizeType expected) : _expected(expected) {}
-    bool operator()(rapidjson::SizeType size) const override { return size == _expected; }
-    sstring what() const override { return format("of size {}", _expected); }
-};
-
-struct empty : public size_check {
-    bool operator()(rapidjson::SizeType size) const override { return size < 1; }
-    sstring what() const override { return "to be empty"; }
-};
-
-struct nonempty : public size_check {
-    bool operator()(rapidjson::SizeType size) const override { return size > 0; }
-    sstring what() const override { return "to be non-empty"; }
-};
-
-} // anonymous namespace
-
-// Check that array has the expected number of elements
-static void verify_operand_count(const rjson::value* array, const size_check& expected, const rjson::value& op) {
-    if (!array && expected(0)) {
-        // If expected() allows an empty AttributeValueList, it is also fine
-        // that it is missing.
-        return;
-    }
-    if (!array || !array->IsArray()) {
-        throw api_error::validation("With ComparisonOperator, AttributeValueList must be given and an array");
-    }
-    if (!expected(array->Size())) {
-        throw api_error::validation(
-                        format("{} operator requires AttributeValueList {}, instead found list size {}",
-                               op, expected.what(), array->Size()));
-    }
-}
-
-struct rjson_engaged_ptr_comp {
-    bool operator()(const rjson::value* p1, const rjson::value* p2) const {
-        return rjson::single_value_comp()(*p1, *p2);
-    }
-};
-
-// It's not enough to compare underlying JSON objects when comparing sets,
-// as internally they're stored in an array, and the order of elements is
-// not important in set equality. See issue #5021
-static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2) {
-    if (!set1.IsArray() || !set2.IsArray() || set1.Size() != set2.Size()) {
-        return false;
-    }
-    std::set<const rjson::value*, rjson_engaged_ptr_comp> set1_raw;
-    for (auto it = set1.Begin(); it != set1.End(); ++it) {
-        set1_raw.insert(&*it);
-    }
-    for (const auto& a : set2.GetArray()) {
-        if (!set1_raw.contains(&a)) {
-            return false;
-        }
-    }
-    return true;
-}
-// Moreover, the JSON being compared can be a nested document with outer
-// layers of lists and maps and some inner set - and we need to get to that
-// inner set to compare it correctly with check_EQ_for_sets() (issue #8514).
-static bool check_EQ(const rjson::value* v1, const rjson::value& v2);
-static bool check_EQ_for_lists(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsArray() || !list2.IsArray() || list1.Size() != list2.Size()) {
-        return false;
-    }
-    auto it1 = list1.Begin();
-    auto it2 = list2.Begin();
-    while (it1 != list1.End()) {
-        // Note: Alternator limits an item's depth (rjson::parse() limits
-        // it to around 37 levels), so this recursion is safe.
-        if (!check_EQ(&*it1, *it2)) {
-            return false;
-        }
-        ++it1;
-        ++it2;
-    }
-    return true;
-}
-static bool check_EQ_for_maps(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsObject() || !list2.IsObject() || list1.MemberCount() != list2.MemberCount()) {
-        return false;
-    }
-    for (auto it1 = list1.MemberBegin(); it1 != list1.MemberEnd(); ++it1) {
-        auto it2 = list2.FindMember(it1->name);
-        if (it2 == list2.MemberEnd() || !check_EQ(&it1->value, it2->value)) {
-            return false;
-        }
-    }
-    return true;
-}
-
-// Check if two JSON-encoded values match with the EQ relation
-static bool check_EQ(const rjson::value* v1, const rjson::value& v2) {
-    if (v1 && v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
-        auto it1 = v1->MemberBegin();
-        auto it2 = v2.MemberBegin();
-        if (it1->name != it2->name) {
-            return false;
-        }
-        if (it1->name == "SS" || it1->name == "NS" || it1->name == "BS") {
-            return check_EQ_for_sets(it1->value, it2->value);
-        } else if(it1->name == "L") {
-            return check_EQ_for_lists(it1->value, it2->value);
-        } else if(it1->name == "M") {
-            return check_EQ_for_maps(it1->value, it2->value);
-        } else {
-            // Other, non-nested types (number, string, etc.) can be compared
-            // literally, comparing their JSON representation.
-            return it1->value == it2->value;
-        }
-    } else {
-        // If v1 and/or v2 are missing (IsNull()) the result should be false.
-        // In the unlikely case that the object is malformed (issue #8070),
-        // let's also return false.
-        return false;
-    }
-}
-
-// Check if two JSON-encoded values match with the NE relation
-static bool check_NE(const rjson::value* v1, const rjson::value& v2) {
-    return !check_EQ(v1, v2);
-}
-
-// Check if two JSON-encoded values match with the BEGINS_WITH relation
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
-                       bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
-        if (v1_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v1->MemberBegin()->name != "S" && v1->MemberBegin()->name != "B") {
-        if (v1_from_query) {
-            throw api_error::validation(format("begins_with supports only string or binary type, got: {}", *v1));
-        } else {
-            bad = true;
-        }
-    }
-    if (!v2.IsObject() || v2.MemberCount() != 1) {
-        if (v2_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
-        if (v2_from_query) {
-            throw api_error::validation(format("begins_with() supports only string or binary type, got: {}", v2));
-        } else {
-            bad = true;
-        }
-    }
-    if (bad) {
-        return false;
-    }
-    auto it1 = v1->MemberBegin();
-    auto it2 = v2.MemberBegin();
-    if (it1->name != it2->name) {
-        return false;
-    }
-    if (it2->name == "S") {
-        return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
-    } else /* it2->name == "B" */ {
-        return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
-    }
-}
-
-static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
-    return (type2 == "S" && type1 == "SS") || (type2 == "N" && type1 == "NS") || (type2 == "B" && type1 == "BS");
-}
-
-// Check if two JSON-encoded values match with the CONTAINS relation
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
-    if (!v1) {
-        return false;
-    }
-    const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
-    if (kv1.name == "S" && kv2.name == "S") {
-        return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
-    } else if (kv1.name == "B" && kv2.name == "B") {
-        return base64_decode(kv1.value).find(base64_decode(kv2.value)) != bytes::npos;
-    } else if (is_set_of(kv1.name, kv2.name)) {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (*i == kv2.value) {
-                return true;
-            }
-        }
-    } else if (kv1.name == "L") {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (!i->IsObject() || i->MemberCount() != 1) {
-                clogger.error("check_CONTAINS received a list whose element is malformed");
-                return false;
-            }
-            const auto& el = *i->MemberBegin();
-            if (el.name == kv2.name && el.value == kv2.value) {
-                return true;
-            }
-        }
-    }
-    return false;
-}
-
-// Check if two JSON-encoded values match with the NOT_CONTAINS relation
-static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
-    if (!v1) {
-        return false;
-    }
-    return !check_CONTAINS(v1, v2);
-}
-
-// Check if a JSON-encoded value equals any element of an array, which must have at least one element.
-static bool check_IN(const rjson::value* val, const rjson::value& array) {
-    if (!array[0].IsObject() || array[0].MemberCount() != 1) {
-        throw api_error::validation(
-                        format("IN operator encountered malformed AttributeValue: {}", array[0]));
-    }
-    const auto& type = array[0].MemberBegin()->name;
-    if (type != "S" && type != "N" && type != "B") {
-        throw api_error::validation(
-                        "IN operator requires AttributeValueList elements to be of type String, Number, or Binary ");
-    }
-    if (!val) {
-        return false;
-    }
-    bool have_match = false;
-    for (const auto& elem : array.GetArray()) {
-        if (!elem.IsObject() || elem.MemberCount() != 1 || elem.MemberBegin()->name != type) {
-            throw api_error::validation(
-                            "IN operator requires all AttributeValueList elements to have the same type ");
-        }
-        if (!have_match && *val == elem) {
-            // Can't return yet, must check types of all array elements. <sigh>
-            have_match = true;
-        }
-    }
-    return have_match;
-}
-
-// Another variant of check_IN, this one for ConditionExpression. It needs to
-// check whether the first element in the given vector is equal to any of the
-// others.
-static bool check_IN(const std::vector<rjson::value>& array) {
-    const rjson::value* first = &array[0];
-    for (unsigned i = 1; i < array.size(); i++) {
-        if (check_EQ(first, array[i])) {
-            return true;
-        }
-    }
-    return false;
-}
-
-static bool check_NULL(const rjson::value* val) {
-    return val == nullptr;
-}
-
-static bool check_NOT_NULL(const rjson::value* val) {
-    return val != nullptr;
-}
-
-// Only types S, N or B (string, number or bytes) may be compared by the
-// various comparion operators - lt, le, gt, ge, and between.
-// Note that in particular, if the value is missing (v->IsNull()), this
-// check returns false.
-static bool check_comparable_type(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return false;
-    }
-    const rjson::value& type = v.MemberBegin()->name;
-    return type == "S" || type == "N" || type == "B";
-}
-
-// Check if two JSON-encoded values match with cmp.
-template <typename Comparator>
-bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp,
-                   bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !check_comparable_type(*v1)) {
-        if (v1_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
-    }
-    if (!check_comparable_type(v2)) {
-        if (v2_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
-    }
-    if (bad) {
-        return false;
-    }
-    const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
-    if (kv1.name != kv2.name) {
-        return false;
-    }
-    if (kv1.name == "N") {
-        return cmp(unwrap_number(*v1, cmp.diagnostic), unwrap_number(v2, cmp.diagnostic));
-    }
-    if (kv1.name == "S") {
-        return cmp(std::string_view(kv1.value.GetString(), kv1.value.GetStringLength()),
-                   std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
-    }
-    if (kv1.name == "B") {
-        return cmp(base64_decode(kv1.value), base64_decode(kv2.value));
-    }
-    // cannot reach here, as check_comparable_type() verifies the type is one
-    // of the above options.
-    return false;
-}
-
-struct cmp_lt {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs; }
-    // We cannot use the normal comparison operators like "<" on the bytes
-    // type, because they treat individual bytes as signed but we need to
-    // compare them as *unsigned*. So we need a specialization for bytes.
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) < 0; }
-    static constexpr const char* diagnostic = "LT operator";
-};
-
-struct cmp_le {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs <= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) <= 0; }
-    static constexpr const char* diagnostic = "LE operator";
-};
-
-struct cmp_ge {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs >= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) >= 0; }
-    static constexpr const char* diagnostic = "GE operator";
-};
-
-struct cmp_gt {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs > rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) > 0; }
-    static constexpr const char* diagnostic = "GT operator";
-};
-
-// True if v is between lb and ub, inclusive.  Throws or returns false
-// (depending on bounds_from_query parameter) if lb > ub.
-template <typename T>
-static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from_query) {
-    if (cmp_lt()(ub, lb)) {
-        if (bounds_from_query) {
-            throw api_error::validation(
-                format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
-        } else {
-            return false;
-        }
-    }
-    return cmp_ge()(v, lb) && cmp_le()(v, ub);
-}
-
-static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub,
-                          bool v_from_query, bool lb_from_query, bool ub_from_query) {
-    if ((v && v_from_query && !check_comparable_type(*v)) ||
-        (lb_from_query && !check_comparable_type(lb)) ||
-        (ub_from_query && !check_comparable_type(ub))) {
-        throw api_error::validation("between allow only the types String, Number, or Binary");
-
-    }
-    if (!v || !v->IsObject() || v->MemberCount() != 1 ||
-        !lb.IsObject() || lb.MemberCount() != 1 ||
-        !ub.IsObject() || ub.MemberCount() != 1) {
-        return false;
-    }
-
-    const auto& kv_v = *v->MemberBegin();
-    const auto& kv_lb = *lb.MemberBegin();
-    const auto& kv_ub = *ub.MemberBegin();
-    bool bounds_from_query = lb_from_query && ub_from_query;
-    if (kv_lb.name != kv_ub.name) {
-        if (bounds_from_query) {
-           throw api_error::validation(
-                format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
-                       kv_lb.name, kv_ub.name));
-        } else {
-            return false;
-        }
-    }
-    if (kv_v.name != kv_lb.name) { // Cannot compare different types, so v is NOT between lb and ub.
-        return false;
-    }
-    if (kv_v.name == "N") {
-        const char* diag = "BETWEEN operator";
-        return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag), bounds_from_query);
-    }
-    if (kv_v.name == "S") {
-        return check_BETWEEN(std::string_view(kv_v.value.GetString(), kv_v.value.GetStringLength()),
-                             std::string_view(kv_lb.value.GetString(), kv_lb.value.GetStringLength()),
-                             std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()),
-                             bounds_from_query);
-    }
-    if (kv_v.name == "B") {
-        return check_BETWEEN(base64_decode(kv_v.value), base64_decode(kv_lb.value), base64_decode(kv_ub.value), bounds_from_query);
-    }
-    if (v_from_query) {
-        throw api_error::validation(
-            format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
-               kv_lb.name));
-    } else {
-        return false;
-    }
-}
-
-// Verify one Expect condition on one attribute (whose content is "got")
-// for the verify_expected() below.
-// This function returns true or false depending on whether the condition
-// succeeded - it does not throw ConditionalCheckFailedException.
-// However, it may throw ValidationException on input validation errors.
-static bool verify_expected_one(const rjson::value& condition, const rjson::value* got) {
-    const rjson::value* comparison_operator = rjson::find(condition, "ComparisonOperator");
-    const rjson::value* attribute_value_list = rjson::find(condition, "AttributeValueList");
-    const rjson::value* value = rjson::find(condition, "Value");
-    const rjson::value* exists = rjson::find(condition, "Exists");
-    // There are three types of conditions that Expected supports:
-    // A value, not-exists, and a comparison of some kind. Each allows
-    // and requires a different combinations of parameters in the request
-    if (value) {
-        if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
-            throw api_error::validation("Cannot combine Value with Exists!=true");
-        }
-        if (comparison_operator) {
-            throw api_error::validation("Cannot combine Value with ComparisonOperator");
-        }
-        return check_EQ(got, *value);
-    } else if (exists) {
-        if (comparison_operator) {
-            throw api_error::validation("Cannot combine Exists with ComparisonOperator");
-        }
-        if (!exists->IsBool() || exists->GetBool() != false) {
-            throw api_error::validation("Exists!=false requires Value");
-        }
-        // Remember Exists=false, so we're checking that the attribute does *not* exist:
-        return !got;
-    } else {
-        if (!comparison_operator) {
-            throw api_error::validation("Missing ComparisonOperator, Value or Exists");
-        }
-        comparison_operator_type op = get_comparison_operator(*comparison_operator);
-        switch (op) {
-        case comparison_operator_type::EQ:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_EQ(got, (*attribute_value_list)[0]);
-        case comparison_operator_type::NE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_NE(got, (*attribute_value_list)[0]);
-        case comparison_operator_type::LT:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_lt{}, false, true);
-        case comparison_operator_type::LE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_le{}, false, true);
-        case comparison_operator_type::GT:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_gt{}, false, true);
-        case comparison_operator_type::GE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_ge{}, false, true);
-        case comparison_operator_type::BEGINS_WITH:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_BEGINS_WITH(got, (*attribute_value_list)[0], false, true);
-        case comparison_operator_type::IN:
-            verify_operand_count(attribute_value_list, nonempty(), *comparison_operator);
-            return check_IN(got, *attribute_value_list);
-        case comparison_operator_type::IS_NULL:
-            verify_operand_count(attribute_value_list, empty(), *comparison_operator);
-            return check_NULL(got);
-        case comparison_operator_type::NOT_NULL:
-            verify_operand_count(attribute_value_list, empty(), *comparison_operator);
-            return check_NOT_NULL(got);
-        case comparison_operator_type::BETWEEN:
-            verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
-            return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1],
-                                 false, true, true);
-        case comparison_operator_type::CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_CONTAINS(got, arg);
-            }
-        case comparison_operator_type::NOT_CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "NOT_CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_NOT_CONTAINS(got, arg);
-            }
-        }
-        throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
-    }
-}
-
-conditional_operator_type get_conditional_operator(const rjson::value& req) {
-    const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
-    if (!conditional_operator) {
-        return conditional_operator_type::MISSING;
-    }
-    if (!conditional_operator->IsString()) {
-        throw api_error::validation("'ConditionalOperator' parameter, if given, must be a string");
-    }
-    auto s = rjson::to_string_view(*conditional_operator);
-    if (s == "AND") {
-        return conditional_operator_type::AND;
-    } else if (s == "OR") {
-        return conditional_operator_type::OR;
-    } else {
-        throw api_error::validation(
-                format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
-    }
-}
-
-// Check if the existing values of the item (previous_item) match the
-// conditions given by the Expected and ConditionalOperator parameters
-// (if they exist) in the request (an UpdateItem, PutItem or DeleteItem).
-// This function can throw an ValidationException API error if there
-// are errors in the format of the condition itself.
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item) {
-    const rjson::value* expected = rjson::find(req, "Expected");
-    auto conditional_operator = get_conditional_operator(req);
-    if (conditional_operator != conditional_operator_type::MISSING &&
-        (!expected || (expected->IsObject() && expected->GetObject().ObjectEmpty()))) {
-            throw api_error::validation("'ConditionalOperator' parameter cannot be specified for missing or empty Expression");
-    }
-    if (!expected) {
-        return true;
-    }
-    if (!expected->IsObject()) {
-        throw api_error::validation("'Expected' parameter, if given, must be an object");
-    }
-    bool require_all = conditional_operator != conditional_operator_type::OR;
-    return verify_condition(*expected, require_all, previous_item);
-}
-
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item) {
-    for (auto it = condition.MemberBegin(); it != condition.MemberEnd(); ++it) {
-        const rjson::value* got = nullptr;
-        if (previous_item) {
-            got = rjson::find(*previous_item, rjson::to_string_view(it->name));
-        }
-        bool success = verify_expected_one(it->value, got);
-        if (success && !require_all) {
-            // When !require_all, one success is enough!
-            return true;
-        } else if (!success && require_all) {
-            // When require_all, one failure is enough!
-            return false;
-        }
-    }
-    // If we got here and require_all, none of the checks failed, so succeed.
-    // If we got here and !require_all, all of the checks failed, so fail.
-    return require_all;
-}
-
-static bool calculate_primitive_condition(const parsed::primitive_condition& cond,
-        const rjson::value* previous_item) {
-    std::vector<rjson::value> calculated_values;
-    calculated_values.reserve(cond._values.size());
-    for (const parsed::value& v : cond._values) {
-        calculated_values.push_back(calculate_value(v,
-                cond._op == parsed::primitive_condition::type::VALUE ?
-                        calculate_value_caller::ConditionExpressionAlone :
-                        calculate_value_caller::ConditionExpression,
-                previous_item));
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::BETWEEN:
-        if (calculated_values.size() != 3) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
-        }
-        return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2],
-                             cond._values[0].is_constant(), cond._values[1].is_constant(), cond._values[2].is_constant());
-    case parsed::primitive_condition::type::IN:
-        return check_IN(calculated_values);
-    case parsed::primitive_condition::type::VALUE:
-        if (calculated_values.size() != 1) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Unexpected values in primitive_condition", cond._values.size()));
-        }
-        // Unwrap the boolean wrapped as the value (if it is a boolean)
-        if (calculated_values[0].IsObject() && calculated_values[0].MemberCount() == 1) {
-            auto it = calculated_values[0].MemberBegin();
-            if (it->name == "BOOL" && it->value.IsBool()) {
-                return it->value.GetBool();
-            }
-        }
-        throw api_error::validation(
-                format("ConditionExpression: condition results in a non-boolean value: {}",
-                        calculated_values[0]));
-    default:
-        // All the rest of the operators have exactly two parameters (and unless
-        // we have a bug in the parser, that's what we have in the parsed object:
-        if (calculated_values.size() != 2) {
-            throw std::logic_error(format("Wrong number of values {} in primitive_condition object", cond._values.size()));
-        }
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::EQ:
-        return check_EQ(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::NE:
-        return check_NE(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::GT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::GE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_le{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    default:
-        // Shouldn't happen unless we have a bug in the parser
-        throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
-    }
-}
-
-// Check if the existing values of the item (previous_item) match the
-// conditions given by the given parsed ConditionExpression.
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item) {
-    if (condition_expression.empty()) {
-        return true;
-    }
-    bool ret = std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) -> bool {
-            return calculate_primitive_condition(cond, previous_item);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) -> bool {
-            auto verify_condition = [&] (const parsed::condition_expression& e) {
-                return verify_condition_expression(e, previous_item);
-            };
-            switch (list.op) {
-            case '&':
-                return boost::algorithm::all_of(list.conditions, verify_condition);
-            case '|':
-                return boost::algorithm::any_of(list.conditions, verify_condition);
-            default:
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("bad operator in condition_list");
-            }
-        }
-    }, condition_expression._expression);
-    return condition_expression._negated ? !ret : ret;
-}
-
-}

alternator/conditions.hh

@@ -1,61 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-/*
- * This file contains definitions and functions related to placing conditions
- * on Alternator queries (equivalent of CQL's restrictions).
- *
- * With conditions, it's possible to add criteria to selection requests (Scan, Query)
- * and use them for narrowing down the result set, by means of filtering or indexing.
- *
- * Ref: https://docs.aws.amazon.com/amazondynamodb/latest/APIReference/API_Condition.html
- */
-
-#pragma once
-
-#include "cql3/restrictions/statement_restrictions.hh"
-#include "serialization.hh"
-#include "expressions_types.hh"
-
-namespace alternator {
-
-enum class comparison_operator_type {
-    EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, NOT_CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
-};
-
-comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
-
-enum class conditional_operator_type {
-    AND, OR, MISSING
-};
-conditional_operator_type get_conditional_operator(const rjson::value& req);
-
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
-
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
-
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item);
-
-}

alternator/error.hh

@@ -1,86 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <seastar/http/httpd.hh>
-#include "seastarx.hh"
-
-namespace alternator {
-
-// api_error contains a DynamoDB error message to be returned to the user.
-// It can be returned by value (see executor::request_return_type) or thrown.
-// The DynamoDB's error messages are described in detail in
-// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
-// An error message has an HTTP code (almost always 400), a type, e.g.,
-// "ResourceNotFoundException", and a human readable message.
-// Eventually alternator::api_handler will convert a returned or thrown
-// api_error into a JSON object, and that is returned to the user.
-class api_error final {
-public:
-    using status_type = httpd::reply::status_type;
-    status_type _http_code;
-    std::string _type;
-    std::string _msg;
-    api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request)
-        : _http_code(std::move(http_code))
-        , _type(std::move(type))
-        , _msg(std::move(msg))
-    { }
-
-    // Factory functions for some common types of DynamoDB API errors
-    static api_error validation(std::string msg) {
-        return api_error("ValidationException", std::move(msg));
-    }
-    static api_error resource_not_found(std::string msg) {
-        return api_error("ResourceNotFoundException", std::move(msg));
-    }
-    static api_error resource_in_use(std::string msg) {
-        return api_error("ResourceInUseException", std::move(msg));
-    }
-    static api_error invalid_signature(std::string msg) {
-        return api_error("InvalidSignatureException", std::move(msg));
-    }
-    static api_error unrecognized_client(std::string msg) {
-        return api_error("UnrecognizedClientException", std::move(msg));
-    }
-    static api_error unknown_operation(std::string msg) {
-        return api_error("UnknownOperationException", std::move(msg));
-    }
-    static api_error access_denied(std::string msg) {
-        return api_error("AccessDeniedException", std::move(msg));
-    }
-    static api_error conditional_check_failed(std::string msg) {
-        return api_error("ConditionalCheckFailedException", std::move(msg));
-    }
-    static api_error expired_iterator(std::string msg) {
-        return api_error("ExpiredIteratorException", std::move(msg));
-    }
-    static api_error trimmed_data_access_exception(std::string msg) {
-        return api_error("TrimmedDataAccessException", std::move(msg));
-    }
-    static api_error internal(std::string msg) {
-        return api_error("InternalServerError", std::move(msg), reply::status_type::internal_server_error);
-    }
-};
-
-}
-

alternator/executor.hh

@@ -1,154 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <seastar/core/future.hh>
-#include <seastar/http/httpd.hh>
-#include "seastarx.hh"
-#include <seastar/json/json_elements.hh>
-#include <seastar/core/sharded.hh>
-
-#include "service/storage_proxy.hh"
-#include "service/migration_manager.hh"
-#include "service/client_state.hh"
-#include "db/timeout_clock.hh"
-
-#include "alternator/error.hh"
-#include "stats.hh"
-#include "utils/rjson.hh"
-
-namespace db {
-    class system_distributed_keyspace;
-}
-
-namespace query {
-class partition_slice;
-class result;
-}
-
-namespace cql3::selection {
-    class selection;
-}
-
-namespace service {
-    class storage_service;
-}
-
-namespace alternator {
-
-class rmw_operation;
-
-struct make_jsonable : public json::jsonable {
-    rjson::value _value;
-public:
-    explicit make_jsonable(rjson::value&& value);
-    std::string to_json() const override;
-};
-struct json_string : public json::jsonable {
-    std::string _value;
-public:
-    explicit json_string(std::string&& value);
-    std::string to_json() const override;
-};
-
-class executor : public peering_sharded_service<executor> {
-    service::storage_proxy& _proxy;
-    service::migration_manager& _mm;
-    db::system_distributed_keyspace& _sdks;
-    service::storage_service& _ss;
-    // An smp_service_group to be used for limiting the concurrency when
-    // forwarding Alternator request between shards - if necessary for LWT.
-    smp_service_group _ssg;
-
-public:
-    using client_state = service::client_state;
-    using request_return_type = std::variant<json::json_return_type, api_error>;
-    stats _stats;
-    static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
-    static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
-    static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";
-
-    executor(service::storage_proxy& proxy, service::migration_manager& mm, db::system_distributed_keyspace& sdks, service::storage_service& ss, smp_service_group ssg)
-        : _proxy(proxy), _mm(mm), _sdks(sdks), _ss(ss), _ssg(ssg) {}
-
-    future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tables(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_endpoints(client_state& client_state, service_permit permit, rjson::value request, std::string host_header);
-    future<request_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_streams(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_stream(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_shard_iterator(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_records(client_state& client_state, tracing::trace_state_ptr, service_permit permit, rjson::value request);
-
-    future<> start();
-    future<> stop() { return make_ready_future<>(); }
-
-    future<> create_keyspace(std::string_view keyspace_name);
-
-    static tracing::trace_state_ptr maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
-
-    static sstring table_name(const schema&);
-    static db::timeout_clock::time_point default_timeout();
-    static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
-
-private:
-    friend class rmw_operation;
-
-    static bool is_alternator_keyspace(const sstring& ks_name);
-    static sstring make_keyspace_name(const sstring& table_name);
-    static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
-    static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
-    
-public:    
-    static std::optional<rjson::value> describe_single_item(schema_ptr,
-        const query::partition_slice&,
-        const cql3::selection::selection&,
-        const query::result&,
-        const std::unordered_set<std::string>&);
-
-    static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<bytes_opt>&,
-        const std::unordered_set<std::string>&,
-        rjson::value&,
-        bool = false);
-
-
-
-    void add_stream_options(const rjson::value& stream_spec, schema_builder&) const;
-    void supplement_table_info(rjson::value& descr, const schema& schema) const;
-    void supplement_table_stream_info(rjson::value& descr, const schema& schema) const;
-};
-
-}

alternator/expressions.cc

@@ -1,684 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "expressions.hh"
-#include "serialization.hh"
-#include "base64.hh"
-#include "conditions.hh"
-#include "alternator/expressionsLexer.hpp"
-#include "alternator/expressionsParser.hpp"
-#include "utils/overloaded_functor.hh"
-#include "error.hh"
-
-#include "seastarx.hh"
-
-#include <seastar/core/print.hh>
-#include <seastar/util/log.hh>
-
-#include <boost/algorithm/cxx11/any_of.hpp>
-#include <boost/algorithm/cxx11/all_of.hpp>
-
-#include <functional>
-#include <unordered_map>
-
-namespace alternator {
-
-template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
-Result do_with_parser(std::string input, Func&& f) {
-    expressionsLexer::InputStreamType input_stream{
-        reinterpret_cast<const ANTLR_UINT8*>(input.data()),
-        ANTLR_ENC_UTF8,
-        static_cast<ANTLR_UINT32>(input.size()),
-        nullptr };
-    expressionsLexer lexer(&input_stream);
-    expressionsParser::TokenStreamType tstream(ANTLR_SIZE_HINT, lexer.get_tokSource());
-    expressionsParser parser(&tstream);
-
-    auto result = f(parser);
-    return result;
-}
-
-parsed::update_expression
-parse_update_expression(std::string query) {
-    try {
-        return do_with_parser(query,  std::mem_fn(&expressionsParser::update_expression));
-    } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing UpdateExpression '{}': {}", query, std::current_exception()));
-    }
-}
-
-std::vector<parsed::path>
-parse_projection_expression(std::string query) {
-    try {
-        return do_with_parser(query,  std::mem_fn(&expressionsParser::projection_expression));
-    } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing ProjectionExpression '{}': {}", query, std::current_exception()));
-    }
-}
-
-parsed::condition_expression
-parse_condition_expression(std::string query) {
-    try {
-        return do_with_parser(query,  std::mem_fn(&expressionsParser::condition_expression));
-    } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
-    }
-}
-
-namespace parsed {
-
-void update_expression::add(update_expression::action a) {
-    std::visit(overloaded_functor {
-        [&] (action::set&)    { seen_set = true; },
-        [&] (action::remove&) { seen_remove = true; },
-        [&] (action::add&)    { seen_add = true; },
-        [&] (action::del&)    { seen_del = true; }
-    }, a._action);
-    _actions.push_back(std::move(a));
-}
-
-void update_expression::append(update_expression other) {
-    if ((seen_set && other.seen_set) ||
-        (seen_remove && other.seen_remove) ||
-        (seen_add && other.seen_add) ||
-        (seen_del && other.seen_del)) {
-        throw expressions_syntax_error("Each of SET, REMOVE, ADD, DELETE may only appear once in UpdateExpression");
-    }
-    std::move(other._actions.begin(), other._actions.end(), std::back_inserter(_actions));
-    seen_set |= other.seen_set;
-    seen_remove |= other.seen_remove;
-    seen_add |= other.seen_add;
-    seen_del |= other.seen_del;
-}
-
-void condition_expression::append(condition_expression&& a, char op) {
-    std::visit(overloaded_functor {
-        [&] (condition_list& x) {
-            // If 'a' has a single condition, we could, instead of inserting
-            // it insert its single condition (possibly negated if a._negated)
-            // But considering it we don't evaluate these expressions many
-            // times, this optimization is not worth extra code complexity.
-            if (!x.conditions.empty() && x.op != op) {
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("condition_expression::append called with mixed operators");
-            }
-            x.conditions.push_back(std::move(a));
-            x.op = op;
-        },
-        [&] (primitive_condition& x) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error("condition_expression::append called on primitive_condition");
-        }
-    }, _expression);
-}
-
-} // namespace parsed
-
-// The following resolve_*() functions resolve references in parsed
-// expressions of different types. Resolving a parsed expression means
-// replacing:
-//  1. In parsed::path objects, replace references like "#name" with the
-//     attribute name from ExpressionAttributeNames,
-//  2. In parsed::constant objects, replace references like ":value" with
-//     the value from ExpressionAttributeValues.
-// These function also track which name and value references were used, to
-// allow complaining if some remain unused.
-// Note that the resolve_*() functions modify the expressions in-place,
-// so if we ever intend to cache parsed expression, we need to pass a copy
-// into this function.
-//
-// Doing the "resolving" stage before the evaluation stage has two benefits.
-// First, it allows us to be compatible with DynamoDB in catching unused
-// names and values (see issue #6572). Second, in the FilterExpression case,
-// we need to resolve the expression just once but then use it many times
-// (once for each item to be filtered).
-
-static void resolve_path(parsed::path& p,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    const std::string& column_name = p.root();
-    if (column_name.size() > 0 && column_name.front() == '#') {
-        if (!expression_attribute_names) {
-            throw api_error::validation(
-                    format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
-        }
-        const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
-        if (!value || !value->IsString()) {
-            throw api_error::validation(
-                    format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
-        }
-        used_attribute_names.emplace(column_name);
-        p.set_root(std::string(rjson::to_string_view(*value)));
-    }
-}
-
-static void resolve_constant(parsed::constant& c,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (const std::string& valref) {
-            if (!expression_attribute_values) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
-            }
-            const rjson::value* value = rjson::find(*expression_attribute_values, valref);
-            if (!value) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
-            }
-            if (value->IsNull()) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
-            }
-            validate_value(*value, "ExpressionAttributeValues");
-            used_attribute_values.emplace(valref);
-            c.set(*value);
-        },
-        [&] (const parsed::constant::literal& lit) {
-            // Nothing to do, already resolved
-        }
-    }, c._value);
-
-}
-
-void resolve_value(parsed::value& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::constant& c) {
-            resolve_constant(c, expression_attribute_values, used_attribute_values);
-        },
-        [&] (parsed::value::function_call& f) {
-            for (parsed::value& value : f._parameters) {
-                resolve_value(value, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            }
-        },
-        [&] (parsed::path& p) {
-            resolve_path(p, expression_attribute_names, used_attribute_names);
-        }
-    }, rhs._value);
-}
-
-void resolve_set_rhs(parsed::set_rhs& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    resolve_value(rhs._v1, expression_attribute_names, expression_attribute_values,
-            used_attribute_names, used_attribute_values);
-    if (rhs._op != 'v') {
-        resolve_value(rhs._v2, expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::update_expression::action& action : ue.actions()) {
-        resolve_path(action._path, expression_attribute_names, used_attribute_names);
-        std::visit(overloaded_functor {
-            [&] (parsed::update_expression::action::set& a) {
-                resolve_set_rhs(a._rhs, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::remove& a) {
-                // nothing to do
-            },
-            [&] (parsed::update_expression::action::add& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::del& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            }
-        }, action._action);
-    }
-}
-
-static void resolve_primitive_condition(parsed::primitive_condition& pc,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::value& value : pc._values) {
-        resolve_value(value,
-                expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::primitive_condition& cond) {
-            resolve_primitive_condition(cond,
-                    expression_attribute_names, expression_attribute_values,
-                    used_attribute_names, used_attribute_values);
-        },
-        [&] (parsed::condition_expression::condition_list& list) {
-            for (parsed::condition_expression& cond : list.conditions) {
-                resolve_condition_expression(cond,
-                        expression_attribute_names, expression_attribute_values,
-                            used_attribute_names, used_attribute_values);
-
-            }
-        }
-    }, ce._expression);
-}
-
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    for (parsed::path& p : pe) {
-        resolve_path(p, expression_attribute_names, used_attribute_names);
-    }
-}
-
-// condition_expression_on() checks whether a condition_expression places any
-// condition on the given attribute. It can be useful, for example, for
-// checking whether the condition tries to restrict a key column.
-
-static bool value_on(const parsed::value& v, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) {
-            return false;
-        },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                if (value_on(value, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        },
-        [&] (const parsed::path& p) {
-            return p.root() == attribute;
-        }
-    }, v._value);
-}
-
-static bool primitive_condition_on(const parsed::primitive_condition& pc, std::string_view attribute) {
-    for (const parsed::value& value : pc._values) {
-        if (value_on(value, attribute)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            return primitive_condition_on(cond, attribute);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                if (condition_expression_on(cond, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        }
-    }, ce._expression);
-}
-
-// for_condition_expression_on() runs a given function over all the attributes
-// mentioned in the expression. If the same attribute is mentioned more than
-// once, the function will be called more than once for the same attribute.
-
-static void for_value_on(const parsed::value& v, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) { },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::path& p) {
-            func(p.root());
-        }
-    }, v._value);
-}
-
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            for (const parsed::value& value : cond._values) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                for_condition_expression_on(cond, func);
-            }
-        }
-    }, ce._expression);
-}
-
-// The following calculate_value() functions calculate, or evaluate, a parsed
-// expression. The parsed expression is assumed to have been "resolved", with
-// the matching resolve_* function.
-
-// Take two JSON-encoded list values (remember that a list value is
-// {"L": [...the actual list]}) and return the concatenation, again as
-// a list value.
-static rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
-    const rjson::value* list1 = unwrap_list(v1);
-    const rjson::value* list2 = unwrap_list(v2);
-    if (!list1 || !list2) {
-        throw api_error::validation("UpdateExpression: list_append() given a non-list");
-    }
-    rjson::value cat = rjson::copy(*list1);
-    for (const auto& a : list2->GetArray()) {
-        rjson::push_back(cat, rjson::copy(a));
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::set(ret, "L", std::move(cat));
-    return ret;
-}
-
-// calculate_size() is ConditionExpression's size() function, i.e., it takes
-// a JSON-encoded value and returns its "size" as defined differently for the
-// different types - also as a JSON-encoded number.
-// It return a JSON-encoded "null" value if this value's type has no size
-// defined. Comparisons against this non-numeric value will later fail.
-static rjson::value calculate_size(const rjson::value& v) {
-    // NOTE: If v is improperly formatted for our JSON value encoding, it
-    // must come from the request itself, not from the database, so it makes
-    // sense to throw a ValidationException if we see such a problem.
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("invalid object: {}", v));
-    }
-    auto it = v.MemberBegin();
-    int ret;
-    if (it->name == "S") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid string: {}", v));
-        }
-        ret = it->value.GetStringLength();
-    } else if (it->name == "NS" || it->name == "SS" || it->name == "BS" || it->name == "L") {
-        if (!it->value.IsArray()) {
-            throw api_error::validation(format("invalid set: {}", v));
-        }
-        ret = it->value.Size();
-    } else if (it->name == "M") {
-        if (!it->value.IsObject()) {
-            throw api_error::validation(format("invalid map: {}", v));
-        }
-        ret = it->value.MemberCount();
-    } else if (it->name == "B") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid byte string: {}", v));
-        }
-        ret = base64_decoded_len(rjson::to_string_view(it->value));
-    } else {
-        rjson::value json_ret = rjson::empty_object();
-        rjson::set(json_ret, "null", rjson::value(true));
-        return json_ret;
-    }
-    rjson::value json_ret = rjson::empty_object();
-    rjson::set(json_ret, "N", rjson::from_string(std::to_string(ret)));
-    return json_ret;
-}
-
-static const rjson::value& calculate_value(const parsed::constant& c) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant::literal& v) -> const rjson::value& {
-            return *v;
-        },
-        [&] (const std::string& valref) -> const rjson::value& {
-            // Shouldn't happen, we should have called resolve_value() earlier
-            // and replaced the value reference by the literal constant.
-            throw std::logic_error("calculate_value() called before resolve_value()");
-        }
-    }, c._value);
-}
-
-static rjson::value to_bool_json(bool b) {
-    rjson::value json_ret = rjson::empty_object();
-    rjson::set(json_ret, "BOOL", rjson::value(b));
-    return json_ret;
-}
-
-static bool known_type(std::string_view type) {
-    static thread_local const std::unordered_set<std::string_view> types = {
-            "N", "S", "B", "NS", "SS", "BS", "L", "M", "NULL", "BOOL"
-    };
-    return types.contains(type);
-}
-
-using function_handler_type = rjson::value(calculate_value_caller, const rjson::value*, const parsed::value::function_call&);
-static const
-std::unordered_map<std::string_view, function_handler_type*> function_handlers {
-    {"list_append", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: list_append() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: list_append() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return list_concatenate(v1, v2);
-        }
-    },
-    {"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() must include path as its first argument", caller));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return v1.IsNull() ? std::move(v2) : std::move(v1);
-        }
-    },
-    {"size", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpression) {
-                throw api_error::validation(
-                        format("{}: size() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return calculate_size(v);
-        }
-    },
-    {"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(!v.IsNull());
-        }
-    },
-    {"attribute_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(v.IsNull());
-        }
-    },
-    {"attribute_type", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_type() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: attribute_type() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            // There is no real reason for the following check (not
-            // allowing the type to come from a document attribute), but
-            // DynamoDB does this check, so we do too...
-            if (!f._parameters[1].is_constant()) {
-                throw api_error::validation(
-                        format("{}: attribute_types()'s first parameter must be an expression attribute", caller));
-            }
-            rjson::value v0 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v1 = calculate_value(f._parameters[1], caller, previous_item);
-            if (v1.IsObject() && v1.MemberCount() == 1 && v1.MemberBegin()->name == "S") {
-                // If the type parameter is not one of the legal types
-                // we should generate an error, not a failed condition:
-                if (!known_type(rjson::to_string_view(v1.MemberBegin()->value))) {
-                    throw api_error::validation(
-                            format("{}: attribute_types()'s second parameter, {}, is not a known type",
-                                    caller, v1.MemberBegin()->value));
-                }
-                if (v0.IsObject() && v0.MemberCount() == 1) {
-                    return to_bool_json(v1.MemberBegin()->value == v0.MemberBegin()->name);
-                } else {
-                    return to_bool_json(false);
-                }
-            } else {
-                throw api_error::validation(
-                        format("{}: attribute_type() second parameter must refer to a string, got {}", caller, v1));
-            }
-        }
-    },
-    {"begins_with", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: begins_with() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: begins_with() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_BEGINS_WITH(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
-        }
-    },
-    {"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: contains() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: contains() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2));
-        }
-    },
-};
-
-// Given a parsed::value, which can refer either to a constant value from
-// ExpressionAttributeValues, to the value of some attribute, or to a function
-// of other values, this function calculates the resulting value.
-// "caller" determines which expression - ConditionExpression or
-// UpdateExpression - is asking for this value. We need to know this because
-// DynamoDB allows a different choice of functions for different expressions.
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) -> rjson::value {
-            return rjson::copy(calculate_value(c));
-        },
-        [&] (const parsed::value::function_call& f) -> rjson::value {
-            auto function_it = function_handlers.find(std::string_view(f._function_name));
-            if (function_it == function_handlers.end()) {
-                throw api_error::validation(
-                        format("UpdateExpression: unknown function '{}' called.", f._function_name));
-            }
-            return function_it->second(caller, previous_item, f);
-        },
-        [&] (const parsed::path& p) -> rjson::value {
-            if (!previous_item) {
-                return rjson::null_value();
-            }
-            std::string update_path = p.root();
-            if (p.has_operators()) {
-                // FIXME: support this
-                throw api_error::validation("Reading attribute paths not yet implemented");
-            }
-            const rjson::value* previous_value = rjson::find(*previous_item, update_path);
-            return previous_value ? rjson::copy(*previous_value) : rjson::null_value();
-        }
-    }, v._value);
-}
-
-// Same as calculate_value() above, except takes a set_rhs, which may be
-// either a single value, or v1+v2 or v1-v2.
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item) {
-    switch (rhs._op) {
-    case 'v':
-        return calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-    case '+': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_add(v1, v2);
-    }
-    case '-': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_subtract(v1, v2);
-    }
-    }
-    // Can't happen
-    return rjson::null_value();
-}
-
-} // namespace alternator

alternator/expressions.g

@@ -1,265 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- *
- * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
- * top-level directory for licensing information.
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-/*
- * The DynamoDB protocol is based on JSON, and most DynamoDB requests
- * describe the operation and its parameters via JSON objects such as maps
- * and lists. Nevertheless, in some types of requests an "expression" is
- * passed as a single string, and we need to parse this string. These
- * cases include:
- *  1. Attribute paths, such as "a[3].b.c", are used in projection
- *     expressions as well as inside other expressions described below.
- *  2. Condition expressions, such as "(NOT (a=b OR c=d)) AND e=f",
- *     used in conditional updates, filters, and other places.
- *  3. Update expressions, such as "SET #a.b = :x, c = :y DELETE d"
- *
- * All these expression syntaxes are very simple: Most of them could be
- * parsed as regular expressions, and the parenthesized condition expression
- * could be done with a simple hand-written lexical analyzer and recursive-
- * descent parser. Nevertheless, we decided to specify these parsers in the
- * ANTLR3 language already used in the Scylla project, hopefully making these
- * parsers easier to reason about, and easier to change if needed - and
- * reducing the amount of boiler-plate code.
- */
-
-grammar expressions;
-
-options {
-    language = Cpp;
-}
-
-@parser::namespace{alternator}
-@lexer::namespace{alternator}
-
-/* TODO: explain what these traits things are. I haven't seen them explained
- * in any document... Compilation fails without these fail because a definition
- * of "expressionsLexerTraits" and "expressionParserTraits" is needed.
- */
-@lexer::traits {
-    class expressionsLexer;
-    class expressionsParser;
-    typedef antlr3::Traits<expressionsLexer, expressionsParser> expressionsLexerTraits;
-}
-@parser::traits {
-    typedef expressionsLexerTraits expressionsParserTraits;
-}
-
-@lexer::header {
-	#include "alternator/expressions.hh"
-	// ANTLR generates a bunch of unused variables and functions. Yuck...
-    #pragma GCC diagnostic ignored "-Wunused-variable"
-    #pragma GCC diagnostic ignored "-Wunused-function"
-}
-@parser::header {
-	#include "expressionsLexer.hpp"
-}
-
-/* By default, ANTLR3 composes elaborate syntax-error messages, saying which
- * token was unexpected, where, and so on on, but then dutifully writes these
- * error messages to the standard error, and returns from the parser as if
- * everything was fine, with a half-constructed output object! If we define
- * the "displayRecognitionError" method, it will be called upon to build this
- * error message, and we can instead throw an exception to stop the parsing
- * immediately. This is good enough for now, for our simple needs, but if
- * we ever want to show more information about the syntax error, Cql3.g
- * contains an elaborate implementation (it would be nice if we could reuse
- * it, not duplicate it).
- * Unfortunately, we have to repeat the same definition twice - once for the
- * parser, and once for the lexer.
- */
-@parser::context {
-    void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
-        throw expressions_syntax_error("syntax error");
-    }
-}
-@lexer::context {
-    void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
-        throw expressions_syntax_error("syntax error");
-    }
-}
-
-/*
- * Lexical analysis phase, i.e., splitting the input up to tokens.
- * Lexical analyzer rules have names starting in capital letters.
- * "fragment" rules do not generate tokens, and are just aliases used to
- * make other rules more readable.
- * Characters *not* listed here, e.g., '=', '(', etc., will be handled
- * as individual tokens on their own right.
- * Whitespace spans are skipped, so do not generate tokens.
- */
-WHITESPACE: (' ' | '\t' | '\n' | '\r')+ { skip(); };
-
-/* shortcuts for case-insensitive keywords */
-fragment A:('a'|'A');
-fragment B:('b'|'B');
-fragment C:('c'|'C');
-fragment D:('d'|'D');
-fragment E:('e'|'E');
-fragment F:('f'|'F');
-fragment G:('g'|'G');
-fragment H:('h'|'H');
-fragment I:('i'|'I');
-fragment J:('j'|'J');
-fragment K:('k'|'K');
-fragment L:('l'|'L');
-fragment M:('m'|'M');
-fragment N:('n'|'N');
-fragment O:('o'|'O');
-fragment P:('p'|'P');
-fragment Q:('q'|'Q');
-fragment R:('r'|'R');
-fragment S:('s'|'S');
-fragment T:('t'|'T');
-fragment U:('u'|'U');
-fragment V:('v'|'V');
-fragment W:('w'|'W');
-fragment X:('x'|'X');
-fragment Y:('y'|'Y');
-fragment Z:('z'|'Z');
-/* These keywords must be appear before the generic NAME token below,
- * because NAME matches too, and the first to match wins.
- */
-SET: S E T;
-REMOVE: R E M O V E;
-ADD: A D D;
-DELETE: D E L E T E;
-
-AND: A N D;
-OR: O R;
-NOT: N O T;
-BETWEEN: B E T W E E N;
-IN: I N;
-
-fragment ALPHA: 'A'..'Z' | 'a'..'z';
-fragment DIGIT: '0'..'9';
-fragment ALNUM: ALPHA | DIGIT | '_';
-INTEGER: DIGIT+;
-NAME: ALPHA ALNUM*;
-NAMEREF: '#' ALNUM+;
-VALREF: ':' ALNUM+;
-
-/*
- * Parsing phase - parsing the string of tokens generated by the lexical
- * analyzer defined above.
- */
-
-path_component: NAME | NAMEREF;
-path returns [parsed::path p]:
-    root=path_component           { $p.set_root($root.text); }
-    (   '.' name=path_component   { $p.add_dot($name.text); }
-      | '[' INTEGER ']'           { $p.add_index(std::stoi($INTEGER.text)); }
-    )*;
-
-value returns [parsed::value v]:
-      VALREF       { $v.set_valref($VALREF.text); }
-    | path         { $v.set_path($path.p); }
-    | NAME         { $v.set_func_name($NAME.text); }
-     '(' x=value   { $v.add_func_parameter($x.v); }
-     (',' x=value  { $v.add_func_parameter($x.v); })*
-     ')'
-    ;
-
-update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value  { $rhs.set_value(std::move($v.v)); }
-    (   '+' v=value  { $rhs.set_plus(std::move($v.v)); }
-      | '-' v=value  { $rhs.set_minus(std::move($v.v)); }
-    )?
-    ;
-
-update_expression_set_action returns [parsed::update_expression::action a]:
-    path '=' rhs=update_expression_set_rhs { $a.assign_set($path.p, $rhs.rhs); };
-
-update_expression_remove_action returns [parsed::update_expression::action a]:
-    path { $a.assign_remove($path.p); };
-
-update_expression_add_action returns [parsed::update_expression::action a]:
-    path VALREF { $a.assign_add($path.p, $VALREF.text); };
-
-update_expression_delete_action returns [parsed::update_expression::action a]:
-    path VALREF { $a.assign_del($path.p, $VALREF.text); };
-
-update_expression_clause returns [parsed::update_expression e]:
-      SET s=update_expression_set_action { $e.add(s); }
-      (',' s=update_expression_set_action { $e.add(s); })*
-    | REMOVE r=update_expression_remove_action { $e.add(r); }
-      (',' r=update_expression_remove_action { $e.add(r); })*
-    | ADD a=update_expression_add_action { $e.add(a); }
-      (',' a=update_expression_add_action { $e.add(a); })*
-    | DELETE d=update_expression_delete_action { $e.add(d); }
-      (',' d=update_expression_delete_action { $e.add(d); })*
-    ;
-
-// Note the "EOF" token at the end of the update expression. We want to the
-//  parser to match the entire string given to it - not just its beginning!
-update_expression returns [parsed::update_expression e]:
-    (update_expression_clause { e.append($update_expression_clause.e); })* EOF;
-
-projection_expression returns [std::vector<parsed::path> v]:
-    p=path      { $v.push_back(std::move($p.p)); }
-    (',' p=path { $v.push_back(std::move($p.p)); } )* EOF;
-
-
-primitive_condition returns [parsed::primitive_condition c]:
-      v=value         { $c.add_value(std::move($v.v));
-                        $c.set_operator(parsed::primitive_condition::type::VALUE); }
-      (  (  '='       { $c.set_operator(parsed::primitive_condition::type::EQ); }
-          | '<' '>'   { $c.set_operator(parsed::primitive_condition::type::NE); }
-          | '<'       { $c.set_operator(parsed::primitive_condition::type::LT); }
-          | '<' '='   { $c.set_operator(parsed::primitive_condition::type::LE); }
-          | '>'       { $c.set_operator(parsed::primitive_condition::type::GT); }
-          | '>' '='   { $c.set_operator(parsed::primitive_condition::type::GE); }
-         )
-         v=value      { $c.add_value(std::move($v.v)); }
-       | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value      { $c.add_value(std::move($v.v)); }
-         AND
-         v=value      { $c.add_value(std::move($v.v)); }
-       | IN '('       { $c.set_operator(parsed::primitive_condition::type::IN); }
-         v=value      { $c.add_value(std::move($v.v)); }
-         (',' v=value { $c.add_value(std::move($v.v)); })*
-         ')'
-      )?
-    ;
-
-// The following rules for parsing boolean expressions are verbose and
-// somewhat strange because of Antlr 3's limitations on recursive rules,
-// common rule prefixes, and (lack of) support for operator precedence.
-// These rules could have been written more clearly using a more powerful
-// parser generator - such as Yacc.
-boolean_expression returns [parsed::condition_expression e]:
-	  b=boolean_expression_1       { $e.append(std::move($b.e), '|'); }
-	  (OR b=boolean_expression_1   { $e.append(std::move($b.e), '|'); } )*
-	;
-boolean_expression_1 returns [parsed::condition_expression e]:
-	  b=boolean_expression_2       { $e.append(std::move($b.e), '&'); }
-	  (AND b=boolean_expression_2  { $e.append(std::move($b.e), '&'); } )*
-	;
-boolean_expression_2 returns [parsed::condition_expression e]:
-	  p=primitive_condition        { $e.set_primitive(std::move($p.c)); }
-	| NOT b=boolean_expression_2   { $e = std::move($b.e); $e.apply_not(); }
-	| '(' b=boolean_expression ')' { $e = std::move($b.e); }
-    ;
-
-condition_expression returns [parsed::condition_expression e]:
-    boolean_expression { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -1,102 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <string>
-#include <stdexcept>
-#include <vector>
-#include <unordered_set>
-#include <string_view>
-
-#include <seastar/util/noncopyable_function.hh>
-
-#include "expressions_types.hh"
-#include "utils/rjson.hh"
-
-namespace alternator {
-
-class expressions_syntax_error : public std::runtime_error {
-public:
-    using runtime_error::runtime_error;
-};
-
-parsed::update_expression parse_update_expression(std::string query);
-std::vector<parsed::path> parse_projection_expression(std::string query);
-parsed::condition_expression parse_condition_expression(std::string query);
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names);
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-
-void validate_value(const rjson::value& v, const char* caller);
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute);
-
-// for_condition_expression_on() runs the given function on the attributes
-// that the expression uses. It may run for the same attribute more than once
-// if the same attribute is used more than once in the expression.
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func);
-
-// calculate_value() behaves slightly different (especially, different
-// functions supported) when used in different types of expressions, as
-// enumerated in this enum:
-enum class calculate_value_caller {
-    UpdateExpression, ConditionExpression, ConditionExpressionAlone
-};
-
-inline std::ostream& operator<<(std::ostream& out, calculate_value_caller caller) {
-    switch (caller) {
-        case calculate_value_caller::UpdateExpression:
-            out << "UpdateExpression";
-            break;
-        case calculate_value_caller::ConditionExpression:
-            out << "ConditionExpression";
-            break;
-        case calculate_value_caller::ConditionExpressionAlone:
-            out << "ConditionExpression";
-            break;
-        default:
-            out << "unknown type of expression";
-            break;
-    }
-    return out;
-}
-
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item);
-
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item);
-
-
-} /* namespace alternator */

alternator/expressions_types.hh

@@ -1,255 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <vector>
-#include <string>
-#include <variant>
-
-#include <seastar/core/shared_ptr.hh>
-
-#include "utils/rjson.hh"
-
-/*
- * Parsed representation of expressions and their components.
- *
- * Types in alternator::parse namespace are used for holding the parse
- * tree - objects generated by the Antlr rules after parsing an expression.
- * Because of the way Antlr works, all these objects are default-constructed
- * first, and then assigned when the rule is completed, so all these types
- * have only default constructors - but setter functions to set them later.
- */
-
-namespace alternator {
-namespace parsed {
-
-// "path" is an attribute's path in a document, e.g., a.b[3].c.
-class path {
-    // All paths have a "root", a top-level attribute, and any number of
-    // "dereference operators" - each either an index (e.g., "[2]") or a
-    // dot (e.g., ".xyz").
-    std::string _root;
-    std::vector<std::variant<std::string, unsigned>> _operators;
-public:
-    void set_root(std::string root) {
-        _root = std::move(root);
-    }
-    void add_index(unsigned i) {
-        _operators.emplace_back(i);
-    }
-    void add_dot(std::string(name)) {
-        _operators.emplace_back(std::move(name));
-    }
-    const std::string& root() const {
-        return _root;
-    }
-    bool has_operators() const {
-        return !_operators.empty();
-    }
-};
-
-// When an expression is first parsed, all constants are references, like
-// ":val1", into ExpressionAttributeValues. This uses std::string() variant.
-// The resolve_value() function replaces these constants by the JSON item
-// extracted from the ExpressionAttributeValues.
-struct constant {
-    // We use lw_shared_ptr<rjson::value> just to make rjson::value copyable,
-    // to make this entire object copyable as ANTLR needs.
-    using literal = lw_shared_ptr<rjson::value>;
-    std::variant<std::string, literal> _value;
-    void set(const rjson::value& v) {
-        _value = make_lw_shared<rjson::value>(rjson::copy(v));
-    }
-    void set(std::string& s) {
-        _value = s;
-    }
-};
-
-// "value" is is a value used in the right hand side of an assignment
-// expression, "SET a = ...". It can be a constant (a reference to a value
-// included in the request, e.g., ":val"), a path to an attribute from the
-// existing item (e.g., "a.b[3].c"), or a function of other such values.
-// Note that the real right-hand-side of an assignment is actually a bit
-// more general - it allows either a value, or a value+value or value-value -
-// see class set_rhs below.
-struct value {
-    struct function_call {
-        std::string _function_name;
-        std::vector<value> _parameters;
-    };
-    std::variant<constant, path, function_call> _value;
-    void set_constant(constant c) {
-        _value = std::move(c);
-    }
-    void set_valref(std::string s) {
-        _value = constant { std::move(s) };
-    }
-    void set_path(path p) {
-        _value = std::move(p);
-    }
-    void set_func_name(std::string s) {
-        _value = function_call {std::move(s), {}};
-    }
-    void add_func_parameter(value v) {
-        std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
-    }
-    bool is_constant() const {
-        return std::holds_alternative<constant>(_value);
-    }
-    bool is_path() const {
-        return std::holds_alternative<path>(_value);
-    }
-    bool is_func() const {
-        return std::holds_alternative<function_call>(_value);
-    }
-};
-
-// The right-hand-side of a SET in an update expression can be either a
-// single value (see above), or value+value, or value-value.
-class set_rhs {
-public:
-    char _op;  // '+', '-', or 'v''
-    value _v1;
-    value _v2;
-    void set_value(value&& v1) {
-        _op = 'v';
-        _v1 = std::move(v1);
-    }
-    void set_plus(value&& v2) {
-        _op = '+';
-        _v2 = std::move(v2);
-    }
-    void set_minus(value&& v2) {
-        _op = '-';
-        _v2 = std::move(v2);
-    }
-};
-
-class update_expression {
-public:
-    struct action {
-        path _path;
-        struct set {
-            set_rhs _rhs;
-        };
-        struct remove {
-        };
-        struct add {
-            constant _valref;
-        };
-        struct del {
-            constant _valref;
-        };
-        std::variant<set, remove, add, del> _action;
-
-        void assign_set(path p, set_rhs rhs) {
-            _path = std::move(p);
-            _action = set { std::move(rhs) };
-        }
-        void assign_remove(path p) {
-            _path = std::move(p);
-            _action = remove { };
-        }
-        void assign_add(path p, std::string v) {
-            _path = std::move(p);
-            _action = add { constant { std::move(v) } };
-        }
-        void assign_del(path p, std::string v) {
-            _path = std::move(p);
-            _action = del { constant { std::move(v) } };
-        }
-    };
-private:
-    std::vector<action> _actions;
-    bool seen_set = false;
-    bool seen_remove = false;
-    bool seen_add = false;
-    bool seen_del = false;
-public:
-    void add(action a);
-    void append(update_expression other);
-    bool empty() const {
-        return _actions.empty();
-    }
-    const std::vector<action>& actions() const {
-        return _actions;
-    }
-    std::vector<action>& actions() {
-        return _actions;
-    }
-};
-
-// A primitive_condition is a condition expression involving one condition,
-// while the full condition_expression below adds boolean logic over these
-// primitive conditions.
-// The supported primitive conditions are:
-// 1. Binary operators - v1 OP v2, where OP is =, <>, <, <=, >, or >= and
-//    v1 and v2 are values - from the item (an attribute path), the query
-//    (a ":val" reference), or a function of the the above (only the size()
-//    function is supported).
-// 2. Ternary operator - v1 BETWEEN v2 and v3 (means v1 >= v2 AND v1 <= v3).
-// 3. N-ary operator - v1 IN ( v2, v3, ... )
-// 4. A single function call (attribute_exists etc.). The parser actually
-//    accepts a more general "value" here but later stages reject a value
-//    which is not a function call (because DynamoDB does it too).
-class primitive_condition {
-public:
-    enum class type {
-        UNDEFINED, VALUE, EQ, NE, LT, LE, GT, GE, BETWEEN, IN
-    };
-    type _op = type::UNDEFINED;
-    std::vector<value> _values;
-    void set_operator(type op) {
-        _op = op;
-    }
-    void add_value(value&& v) {
-        _values.push_back(std::move(v));
-    }
-    bool empty() const {
-        return _op == type::UNDEFINED;
-    }
-};
-
-class condition_expression {
-public:
-    bool _negated = false; // If true, the entire condition is negated
-    struct condition_list {
-        char op = '|'; // '&' or '|'
-        std::vector<condition_expression> conditions;
-    };
-    std::variant<primitive_condition, condition_list> _expression = condition_list();
-
-    void set_primitive(primitive_condition&& p) {
-        _expression = std::move(p);
-    }
-    void append(condition_expression&& c, char op);
-    void apply_not() {
-        _negated = !_negated;
-    }
-    bool empty() const {
-        return std::holds_alternative<condition_list>(_expression) &&
-               std::get<condition_list>(_expression).conditions.empty();
-    }
-};
-
-} // namespace parsed
-} // namespace alternator

alternator/rmw_operation.hh

@@ -1,128 +0,0 @@
-/*
- * Copyright 2020 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include "service/storage_proxy.hh"
-#include "service/storage_proxy.hh"
-#include "utils/rjson.hh"
-#include "executor.hh"
-
-namespace alternator {
-
-// An rmw_operation encapsulates the common logic of all the item update
-// operations which may involve a read of the item before the write
-// (so-called Read-Modify-Write operations). These operations include PutItem,
-// UpdateItem and DeleteItem: All of these may be conditional operations (the
-// "Expected" parameter) which requir a read before the write, and UpdateItem
-// may also have an update expression which refers to the item's old value.
-//
-// The code below supports running the read and the write together as one
-// transaction using LWT (this is why rmw_operation is a subclass of
-// cas_request, as required by storage_proxy::cas()), but also has optional
-// modes not using LWT.
-class rmw_operation : public service::cas_request, public enable_shared_from_this<rmw_operation> {
-public:
-    // The following options choose which mechanism to use for isolating
-    // parallel write operations:
-    // * The FORBID_RMW option forbids RMW (read-modify-write) operations
-    //   such as conditional updates. For the remaining write-only
-    //   operations, ordinary quorum writes are isolated enough.
-    // * The LWT_ALWAYS option always uses LWT (lightweight transactions)
-    //   for any write operation - whether or not it also has a read.
-    // * The LWT_RMW_ONLY option uses LWT only for RMW operations, and uses
-    //   ordinary quorum writes for write-only operations.
-    //   This option is not safe if the user may send both RMW and write-only
-    //   operations on the same item.
-    // * The UNSAFE_RMW option does read-modify-write operations as separate
-    //   read and write. It is unsafe - concurrent RMW operations are not
-    //   isolated at all. This option will likely be removed in the future.
-    enum class write_isolation {
-        FORBID_RMW, LWT_ALWAYS, LWT_RMW_ONLY, UNSAFE_RMW
-    };
-    static constexpr auto WRITE_ISOLATION_TAG_KEY = "system:write_isolation";
-
-    static write_isolation get_write_isolation_for_schema(schema_ptr schema);
-
-    static write_isolation default_write_isolation;
-public:
-    static void set_default_write_isolation(std::string_view mode);
-
-protected:
-    // The full request JSON
-    rjson::value _request;
-    // All RMW operations involve a single item with a specific partition
-    // and optional clustering key, in a single table, so the following
-    // information is common to all of them:
-    schema_ptr _schema;
-    partition_key _pk = partition_key::make_empty();
-    clustering_key _ck = clustering_key::make_empty();
-    write_isolation _write_isolation;
-
-    // All RMW operations can have a ReturnValues parameter from the following
-    // choices. But note that only UpdateItem actually supports all of them:
-    enum class returnvalues {
-        NONE, ALL_OLD, UPDATED_OLD, ALL_NEW, UPDATED_NEW
-    } _returnvalues;
-    static returnvalues parse_returnvalues(const rjson::value& request);
-    // When _returnvalues != NONE, apply() should store here, in JSON form,
-    // the values which are to be returned in the "Attributes" field.
-    // The default null JSON means do not return an Attributes field at all.
-    // This field is marked "mutable" so that the const apply() can modify
-    // it (see explanation below), but note that because apply() may be
-    // called more than once, if apply() will sometimes set this field it
-    // must set it (even if just to the default empty value) every time.
-    mutable rjson::value _return_attributes;
-public:
-    // The constructor of a rmw_operation subclass should parse the request
-    // and try to discover as many input errors as it can before really
-    // attempting the read or write operations.
-    rmw_operation(service::storage_proxy& proxy, rjson::value&& request);
-    // rmw_operation subclasses (update_item_operation, put_item_operation
-    // and delete_item_operation) shall implement an apply() function which
-    // takes the previous value of the item (if it was read) and creates the
-    // write mutation. If the previous value of item does not pass the needed
-    // conditional expression, apply() should return an empty optional.
-    // apply() may throw if it encounters input errors not discovered during
-    // the constructor.
-    // apply() may be called more than once in case of contention, so it must
-    // not change the state saved in the object (issue #7218 was caused by
-    // violating this). We mark apply() "const" to let the compiler validate
-    // this for us. The output-only field _return_attributes is marked
-    // "mutable" above so that apply() can still write to it.
-    virtual std::optional<mutation> apply(std::unique_ptr<rjson::value> previous_item, api::timestamp_type ts) const = 0;
-    // Convert the above apply() into the signature needed by cas_request:
-    virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts) override;
-    virtual ~rmw_operation() = default;
-    schema_ptr schema() const { return _schema; }
-    const rjson::value& request() const { return _request; }
-    rjson::value&& move_request() && { return std::move(_request); }
-    future<executor::request_return_type> execute(service::storage_proxy& proxy,
-            service::client_state& client_state,
-            tracing::trace_state_ptr trace_state,
-            service_permit permit,
-            bool needs_read_before_write,
-            stats& stats);
-    std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
-};
-
-} // namespace alternator

alternator/serialization.cc

@@ -1,375 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "base64.hh"
-#include "log.hh"
-#include "serialization.hh"
-#include "error.hh"
-#include "rapidjson/writer.h"
-#include "concrete_types.hh"
-#include "cql3/type_json.hh"
-
-static logging::logger slogger("alternator-serialization");
-
-namespace alternator {
-
-type_info type_info_from_string(std::string_view type) {
-    static thread_local const std::unordered_map<std::string_view, type_info> type_infos = {
-        {"S", {alternator_type::S, utf8_type}},
-        {"B", {alternator_type::B, bytes_type}},
-        {"BOOL", {alternator_type::BOOL, boolean_type}},
-        {"N", {alternator_type::N, decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
-    };
-    auto it = type_infos.find(type);
-    if (it == type_infos.end()) {
-        return {alternator_type::NOT_SUPPORTED_YET, utf8_type};
-    }
-    return it->second;
-}
-
-type_representation represent_type(alternator_type atype) {
-    static thread_local const std::unordered_map<alternator_type, type_representation> type_representations = {
-        {alternator_type::S, {"S", utf8_type}},
-        {alternator_type::B, {"B", bytes_type}},
-        {alternator_type::BOOL, {"BOOL", boolean_type}},
-        {alternator_type::N, {"N", decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
-    };
-    auto it = type_representations.find(atype);
-    if (it == type_representations.end()) {
-        throw std::runtime_error(format("Unknown alternator type {}", int8_t(atype)));
-    }
-    return it->second;
-}
-
-struct from_json_visitor {
-    const rjson::value& v;
-    bytes_ostream& bo;
-
-    void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), from_json_visitor{v, bo}); };
-    void operator()(const string_type_impl& t) {
-        bo.write(t.from_string(rjson::to_string_view(v)));
-    }
-    void operator()(const bytes_type_impl& t) const {
-        bo.write(base64_decode(v));
-    }
-    void operator()(const boolean_type_impl& t) const {
-        bo.write(boolean_type->decompose(v.GetBool()));
-    }
-    void operator()(const decimal_type_impl& t) const {
-        try {
-            bo.write(t.from_string(rjson::to_string_view(v)));
-        } catch (const marshal_exception& e) {
-            throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", v));
-        }
-    }
-    // default
-    void operator()(const abstract_type& t) const {
-        bo.write(from_json_object(t, v, cql_serialization_format::internal()));
-    }
-};
-
-bytes serialize_item(const rjson::value& item) {
-    if (item.IsNull() || item.MemberCount() != 1) {
-        throw api_error::validation(format("An item can contain only one attribute definition: {}", item));
-    }
-    auto it = item.MemberBegin();
-    type_info type_info = type_info_from_string(rjson::to_string_view(it->name)); // JSON keys are guaranteed to be strings
-
-    if (type_info.atype == alternator_type::NOT_SUPPORTED_YET) {
-        slogger.trace("Non-optimal serialization of type {}", it->name);
-        return bytes{int8_t(type_info.atype)} + to_bytes(rjson::print(item));
-    }
-
-    bytes_ostream bo;
-    bo.write(bytes{int8_t(type_info.atype)});
-    visit(*type_info.dtype, from_json_visitor{it->value, bo});
-
-    return bytes(bo.linearize());
-}
-
-struct to_json_visitor {
-    rjson::value& deserialized;
-    const std::string& type_ident;
-    bytes_view bv;
-
-    void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), to_json_visitor{deserialized, type_ident, bv}); };
-    void operator()(const decimal_type_impl& t) const {
-        auto s = to_json_string(*decimal_type, bytes(bv));
-        //FIXME(sarna): unnecessary copy
-        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(s));
-    }
-    void operator()(const string_type_impl& t) {
-        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
-    }
-    void operator()(const bytes_type_impl& t) const {
-        std::string b64 = base64_encode(bv);
-        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(b64));
-    }
-    // default
-    void operator()(const abstract_type& t) const {
-        rjson::set_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
-    }
-};
-
-rjson::value deserialize_item(bytes_view bv) {
-    rjson::value deserialized(rapidjson::kObjectType);
-    if (bv.empty()) {
-        throw api_error::validation("Serialized value empty");
-    }
-
-    alternator_type atype = alternator_type(bv[0]);
-    bv.remove_prefix(1);
-
-    if (atype == alternator_type::NOT_SUPPORTED_YET) {
-        slogger.trace("Non-optimal deserialization of alternator type {}", int8_t(atype));
-        return rjson::parse(std::string_view(reinterpret_cast<const char *>(bv.data()), bv.size()));
-    }
-    type_representation type_representation = represent_type(atype);
-    visit(*type_representation.dtype, to_json_visitor{deserialized, type_representation.ident, bv});
-
-    return deserialized;
-}
-
-std::string type_to_string(data_type type) {
-    static thread_local std::unordered_map<data_type, std::string> types = {
-        {utf8_type, "S"},
-        {bytes_type, "B"},
-        {boolean_type, "BOOL"},
-        {decimal_type, "N"}, // FIXME: use a specialized Alternator number type instead of the general decimal_type
-    };
-    auto it = types.find(type);
-    if (it == types.end()) {
-        // fall back to string, in order to be able to present
-        // internal Scylla types in a human-readable way
-        return "S";
-    }
-    return it->second;
-}
-
-bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
-    std::string column_name = column.name_as_text();
-    const rjson::value* key_typed_value = rjson::find(item, column_name);
-    if (!key_typed_value) {
-        throw api_error::validation(format("Key column {} not found", column_name));
-    }
-    return get_key_from_typed_value(*key_typed_value, column);
-}
-
-// Parses the JSON encoding for a key value, which is a map with a single
-// entry, whose key is the type (expected to match the key column's type)
-// and the value is the encoded value.
-bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column) {
-    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
-            !key_typed_value.MemberBegin()->value.IsString()) {
-        throw api_error::validation(
-                format("Malformed value object for key column {}: {}",
-                        column.name_as_text(), key_typed_value));
-    }
-
-    auto it = key_typed_value.MemberBegin();
-    if (it->name != type_to_string(column.type)) {
-        throw api_error::validation(
-                format("Type mismatch: expected type {} for key column {}, got type {}",
-                        type_to_string(column.type), column.name_as_text(), it->name));
-    }
-    std::string_view value_view = rjson::to_string_view(it->value);
-    if (value_view.empty()) {
-        throw api_error::validation(
-                format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
-    }
-    if (column.type == bytes_type) {
-        return base64_decode(it->value);
-    } else {
-        return column.type->from_string(rjson::to_string_view(it->value));
-    }
-
-}
-
-rjson::value json_key_column_value(bytes_view cell, const column_definition& column) {
-    if (column.type == bytes_type) {
-        std::string b64 = base64_encode(cell);
-        return rjson::from_string(b64);
-    } if (column.type == utf8_type) {
-        return rjson::from_string(std::string(reinterpret_cast<const char*>(cell.data()), cell.size()));
-    } else if (column.type == decimal_type) {
-        // FIXME: use specialized Alternator number type, not the more
-        // general "decimal_type". A dedicated type can be more efficient
-        // in storage space and in parsing speed.
-        auto s = to_json_string(*decimal_type, bytes(cell));
-        return rjson::from_string(s);
-    } else {
-        // Support for arbitrary key types is useful for parsing values of virtual tables,
-        // which can involve any type supported by Scylla.
-        // In order to guarantee that the returned type is parsable by alternator clients,
-        // they are represented simply as strings.
-        return rjson::from_string(column.type->to_string(bytes(cell)));
-    }
-}
-
-
-partition_key pk_from_json(const rjson::value& item, schema_ptr schema) {
-    std::vector<bytes> raw_pk;
-    // FIXME: this is a loop, but we really allow only one partition key column.
-    for (const column_definition& cdef : schema->partition_key_columns()) {
-        bytes raw_value = get_key_column_value(item, cdef);
-        raw_pk.push_back(std::move(raw_value));
-    }
-   return partition_key::from_exploded(raw_pk);
-}
-
-clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
-    if (schema->clustering_key_size() == 0) {
-        return clustering_key::make_empty();
-    }
-    std::vector<bytes> raw_ck;
-    // FIXME: this is a loop, but we really allow only one clustering key column.
-    for (const column_definition& cdef : schema->clustering_key_columns()) {
-        bytes raw_value = get_key_column_value(item,  cdef);
-        raw_ck.push_back(std::move(raw_value));
-    }
-
-    return clustering_key::from_exploded(raw_ck);
-}
-
-big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("{}: invalid number object", diagnostic));
-    }
-    auto it = v.MemberBegin();
-    if (it->name != "N") {
-        throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
-    }
-    try {
-        if (it->value.IsNumber()) {
-             // FIXME(sarna): should use big_decimal constructor with numeric values directly:
-            return big_decimal(rjson::print(it->value));
-        }
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
-        }
-        return big_decimal(rjson::to_string_view(it->value));
-    } catch (const marshal_exception& e) {
-        throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", it->value));
-    }
-}
-
-const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return {"", nullptr};
-    }
-    auto it = v.MemberBegin();
-    const std::string it_key = it->name.GetString();
-    if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
-        return {"", nullptr};
-    }
-    return std::make_pair(it_key, &(it->value));
-}
-
-const rjson::value* unwrap_list(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return nullptr;
-    }
-    auto it = v.MemberBegin();
-    if (it->name != std::string("L")) {
-        return nullptr;
-    }
-    return &(it->value);
-}
-
-// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
-// sum, again as a JSON-encoded number.
-rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
-    auto n1 = unwrap_number(v1, "UpdateExpression");
-    auto n2 = unwrap_number(v2, "UpdateExpression");
-    rjson::value ret = rjson::empty_object();
-    std::string str_ret = std::string((n1 + n2).to_string());
-    rjson::set(ret, "N", rjson::from_string(str_ret));
-    return ret;
-}
-
-rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
-    auto n1 = unwrap_number(v1, "UpdateExpression");
-    auto n2 = unwrap_number(v2, "UpdateExpression");
-    rjson::value ret = rjson::empty_object();
-    std::string str_ret = std::string((n1 - n2).to_string());
-    rjson::set(ret, "N", rjson::from_string(str_ret));
-    return ret;
-}
-
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
-// return the sum of both sets, again as a set value.
-rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
-    auto [set1_type, set1] = unwrap_set(v1);
-    auto [set2_type, set2] = unwrap_set(v2);
-    if (set1_type != set2_type) {
-        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
-    }
-    if (!set1 || !set2) {
-        throw api_error::validation("UpdateExpression: ADD operation for sets must be given sets as arguments");
-    }
-    rjson::value sum = rjson::copy(*set1);
-    std::set<rjson::value, rjson::single_value_comp> set1_raw;
-    for (auto it = sum.Begin(); it != sum.End(); ++it) {
-        set1_raw.insert(rjson::copy(*it));
-    }
-    for (const auto& a : set2->GetArray()) {
-        if (!set1_raw.contains(a)) {
-            rjson::push_back(sum, rjson::copy(a));
-        }
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::set_with_string_name(ret, set1_type, std::move(sum));
-    return ret;
-}
-
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
-// return the difference of s1 - s2, again as a set value.
-// DynamoDB does not allow empty sets, so if resulting set is empty, return
-// an unset optional instead.
-std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2) {
-    auto [set1_type, set1] = unwrap_set(v1);
-    auto [set2_type, set2] = unwrap_set(v2);
-    if (set1_type != set2_type) {
-        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
-    }
-    if (!set1 || !set2) {
-        throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");
-    }
-    std::set<rjson::value, rjson::single_value_comp> set1_raw;
-    for (auto it = set1->Begin(); it != set1->End(); ++it) {
-        set1_raw.insert(rjson::copy(*it));
-    }
-    for (const auto& a : set2->GetArray()) {
-        set1_raw.erase(a);
-    }
-    if (set1_raw.empty()) {
-        return std::nullopt;
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::set_with_string_name(ret, set1_type, rjson::empty_array());
-    rjson::value& result_set = ret[set1_type];
-    for (const auto& a : set1_raw) {
-        rjson::push_back(result_set, rjson::copy(a));
-    }
-    return ret;
-}
-
-}

alternator/serialization.hh

@@ -1,89 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <string>
-#include <string_view>
-#include "types.hh"
-#include "schema_fwd.hh"
-#include "keys.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-
-namespace alternator {
-
-enum class alternator_type : int8_t {
-    S, B, BOOL, N, NOT_SUPPORTED_YET
-};
-
-struct type_info {
-    alternator_type atype;
-    data_type dtype;
-};
-
-struct type_representation {
-    std::string ident;
-    data_type dtype;
-};
-
-type_info type_info_from_string(std::string_view type);
-type_representation represent_type(alternator_type atype);
-
-bytes serialize_item(const rjson::value& item);
-rjson::value deserialize_item(bytes_view bv);
-
-std::string type_to_string(data_type type);
-
-bytes get_key_column_value(const rjson::value& item, const column_definition& column);
-bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column);
-rjson::value json_key_column_value(bytes_view cell, const column_definition& column);
-
-partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
-clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
-
-// If v encodes a number (i.e., it is a {"N": [...]}, returns an object representing it.  Otherwise,
-// raises ValidationException with diagnostic.
-big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
-
-// Check if a given JSON object encodes a set (i.e., it is a {"SS": [...]}, or "NS", "BS"
-// and returns set's type and a pointer to that set. If the object does not encode a set,
-// returned value is {"", nullptr}
-const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v);
-
-// Check if a given JSON object encodes a list (i.e., it is a {"L": [...]}
-// and returns a pointer to that list.
-const rjson::value* unwrap_list(const rjson::value& v);
-
-// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
-// sum, again as a JSON-encoded number.
-rjson::value number_add(const rjson::value& v1, const rjson::value& v2);
-rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
-// return the sum of both sets, again as a set value.
-rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
-// return the difference of s1 - s2, again as a set value.
-// DynamoDB does not allow empty sets, so if resulting set is empty, return
-// an unset optional instead.
-std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2);
-
-}

alternator/server.cc

@@ -1,498 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "alternator/server.hh"
-#include "log.hh"
-#include <seastar/http/function_handlers.hh>
-#include <seastar/json/json_elements.hh>
-#include "seastarx.hh"
-#include "error.hh"
-#include "utils/rjson.hh"
-#include "auth.hh"
-#include <cctype>
-#include "cql3/query_processor.hh"
-#include "service/storage_service.hh"
-#include "utils/overloaded_functor.hh"
-
-static logging::logger slogger("alternator-server");
-
-using namespace httpd;
-
-namespace alternator {
-
-static constexpr auto TARGET = "X-Amz-Target";
-
-inline std::vector<std::string_view> split(std::string_view text, char separator) {
-    std::vector<std::string_view> tokens;
-    if (text == "") {
-        return tokens;
-    }
-
-    while (true) {
-        auto pos = text.find_first_of(separator);
-        if (pos != std::string_view::npos) {
-            tokens.emplace_back(text.data(), pos);
-            text.remove_prefix(pos + 1);
-        } else {
-            tokens.emplace_back(text);
-            break;
-        }
-    }
-    return tokens;
-}
-
-// DynamoDB HTTP error responses are structured as follows
-// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
-// Our handlers throw an exception to report an error. If the exception
-// is of type alternator::api_error, it unwrapped and properly reported to
-// the user directly. Other exceptions are unexpected, and reported as
-// Internal Server Error.
-class api_handler : public handler_base {
-public:
-    api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle) : _f_handle(
-         [this, _handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
-         return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped([this, rep = std::move(rep)](future<executor::request_return_type> resf) mutable {
-             if (resf.failed()) {
-                 // Exceptions of type api_error are wrapped as JSON and
-                 // returned to the client as expected. Other types of
-                 // exceptions are unexpected, and returned to the user
-                 // as an internal server error:
-                 try {
-                     resf.get();
-                 } catch (api_error &ae) {
-                     generate_error_reply(*rep, ae);
-                 } catch (rjson::error & re) {
-                     generate_error_reply(*rep,
-                             api_error::validation(re.what()));
-                 } catch (...) {
-                     generate_error_reply(*rep,
-                             api_error::internal(format("Internal server error: {}", std::current_exception())));
-                 }
-                 return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-             }
-             auto res = resf.get0();
-             std::visit(overloaded_functor {
-                 [&] (const json::json_return_type& json_return_value) {
-                     slogger.trace("api_handler success case");
-                     if (json_return_value._body_writer) {
-                         rep->write_body("json", std::move(json_return_value._body_writer));
-                     } else {
-                         rep->_content += json_return_value._res;
-                     }
-                 },
-                 [&] (const api_error& err) {
-                     generate_error_reply(*rep, err);
-                 }
-             }, res);
-
-             return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-         });
-    }), _type("json") { }
-
-    api_handler(const api_handler&) = default;
-    future<std::unique_ptr<reply>> handle(const sstring& path,
-            std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        return _f_handle(std::move(req), std::move(rep)).then(
-                [this](std::unique_ptr<reply> rep) {
-                    rep->done(_type);
-                    return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-                });
-    }
-
-protected:
-    void generate_error_reply(reply& rep, const api_error& err) {
-        rep._content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + err._type + "\"," +
-                "\"message\":\"" + err._msg + "\"}";
-        rep._status = err._http_code;
-        slogger.trace("api_handler error case: {}", rep._content);
-    }
-
-    future_handler_function _f_handle;
-    sstring _type;
-};
-
-class gated_handler : public handler_base {
-    seastar::gate& _gate;
-public:
-    gated_handler(seastar::gate& gate) : _gate(gate) {}
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) = 0;
-    virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) final override {
-        return with_gate(_gate, [this, &path, req = std::move(req), rep = std::move(rep)] () mutable {
-            return do_handle(path, std::move(req), std::move(rep));
-        });
-    }
-};
-
-class health_handler : public gated_handler {
-public:
-    health_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        rep->set_status(reply::status_type::ok);
-        rep->write_body("txt", format("healthy: {}", req->get_header("Host")));
-        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-    }
-};
-
-class local_nodelist_handler : public gated_handler {
-public:
-    local_nodelist_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        rjson::value results = rjson::empty_array();
-        // It's very easy to get a list of all live nodes on the cluster,
-        // using gms::get_local_gossiper().get_live_members(). But getting
-        // just the list of live nodes in this DC needs more elaborate code:
-        sstring local_dc = locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(
-                utils::fb_utilities::get_broadcast_address());
-        std::unordered_set<gms::inet_address> local_dc_nodes =
-                service::get_local_storage_service().get_token_metadata().
-                get_topology().get_datacenter_endpoints().at(local_dc);
-        for (auto& ip : local_dc_nodes) {
-            if (gms::get_local_gossiper().is_alive(ip)) {
-                rjson::push_back(results, rjson::from_string(ip.to_sstring()));
-            }
-        }
-        rep->set_status(reply::status_type::ok);
-        rep->set_content_type("json");
-        rep->_content = rjson::print(results);
-        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-    }
-};
-
-future<> server::verify_signature(const request& req) {
-    if (!_enforce_authorization) {
-        slogger.debug("Skipping authorization");
-        return make_ready_future<>();
-    }
-    auto host_it = req._headers.find("Host");
-    if (host_it == req._headers.end()) {
-        throw api_error::invalid_signature("Host header is mandatory for signature verification");
-    }
-    auto authorization_it = req._headers.find("Authorization");
-    if (authorization_it == req._headers.end()) {
-        throw api_error::invalid_signature("Authorization header is mandatory for signature verification");
-    }
-    std::string host = host_it->second;
-    std::vector<std::string_view> credentials_raw = split(authorization_it->second, ' ');
-    std::string credential;
-    std::string user_signature;
-    std::string signed_headers_str;
-    std::vector<std::string_view> signed_headers;
-    for (std::string_view entry : credentials_raw) {
-        std::vector<std::string_view> entry_split = split(entry, '=');
-        if (entry_split.size() != 2) {
-            if (entry != "AWS4-HMAC-SHA256") {
-                throw api_error::invalid_signature(format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
-            }
-            continue;
-        }
-        std::string_view auth_value = entry_split[1];
-        // Commas appear as an additional (quite redundant) delimiter
-        if (auth_value.back() == ',') {
-            auth_value.remove_suffix(1);
-        }
-        if (entry_split[0] == "Credential") {
-            credential = std::string(auth_value);
-        } else if (entry_split[0] == "Signature") {
-            user_signature = std::string(auth_value);
-        } else if (entry_split[0] == "SignedHeaders") {
-            signed_headers_str = std::string(auth_value);
-            signed_headers = split(auth_value, ';');
-            std::sort(signed_headers.begin(), signed_headers.end());
-        }
-    }
-    std::vector<std::string_view> credential_split = split(credential, '/');
-    if (credential_split.size() != 5) {
-        throw api_error::validation(format("Incorrect credential information format: {}", credential));
-    }
-    std::string user(credential_split[0]);
-    std::string datestamp(credential_split[1]);
-    std::string region(credential_split[2]);
-    std::string service(credential_split[3]);
-
-    std::map<std::string_view, std::string_view> signed_headers_map;
-    for (const auto& header : signed_headers) {
-        signed_headers_map.emplace(header, std::string_view());
-    }
-    for (auto& header : req._headers) {
-        std::string header_str;
-        header_str.resize(header.first.size());
-        std::transform(header.first.begin(), header.first.end(), header_str.begin(), ::tolower);
-        auto it = signed_headers_map.find(header_str);
-        if (it != signed_headers_map.end()) {
-            it->second = std::string_view(header.second);
-        }
-    }
-
-    auto cache_getter = [] (std::string username) {
-        return get_key_from_roles(cql3::get_query_processor().local(), std::move(username));
-    };
-    return _key_cache.get_ptr(user, cache_getter).then([this, &req,
-                                                    user = std::move(user),
-                                                    host = std::move(host),
-                                                    datestamp = std::move(datestamp),
-                                                    signed_headers_str = std::move(signed_headers_str),
-                                                    signed_headers_map = std::move(signed_headers_map),
-                                                    region = std::move(region),
-                                                    service = std::move(service),
-                                                    user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
-        std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
-                datestamp, signed_headers_str, signed_headers_map, req.content, region, service, "");
-
-        if (signature != std::string_view(user_signature)) {
-            _key_cache.remove(user);
-            throw api_error::unrecognized_client("The security token included in the request is invalid.");
-        }
-    });
-}
-
-future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
-    _executor._stats.total_operations++;
-    sstring target = req->get_header(TARGET);
-    std::vector<std::string_view> split_target = split(target, '.');
-    //NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
-    std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
-    slogger.trace("Request: {} {} {}", op, req->content, req->_headers);
-    return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
-        auto callback_it = _callbacks.find(op);
-        if (callback_it == _callbacks.end()) {
-            _executor._stats.unsupported_operations++;
-            throw api_error::unknown_operation(format("Unsupported operation {}", op));
-        }
-        return with_gate(_pending_requests, [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] () mutable {
-            //FIXME: Client state can provide more context, e.g. client's endpoint address
-            // We use unique_ptr because client_state cannot be moved or copied
-            return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()),
-                    [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
-                tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
-                tracing::trace(trace_state, op);
-                // JSON parsing can allocate up to roughly 2x the size of the raw document, + a couple of bytes for maintenance.
-                // FIXME: by this time, the whole HTTP request was already read, so some memory is already occupied.
-                // Once HTTP allows working on streams, we should grab the permit *before* reading the HTTP payload.
-                size_t mem_estimate = req->content.size() * 3 + 8000;
-                auto units_fut = get_units(*_memory_limiter, mem_estimate);
-                if (_memory_limiter->waiters()) {
-                    ++_executor._stats.requests_blocked_memory;
-                }
-                return units_fut.then([this, callback_it = std::move(callback_it), &client_state, trace_state, req = std::move(req)] (semaphore_units<> units) mutable {
-                    return _json_parser.parse(req->content).then([this, callback_it = std::move(callback_it), &client_state, trace_state,
-                            units = std::move(units), req = std::move(req)] (rjson::value json_request) mutable {
-                        return callback_it->second(_executor, *client_state, trace_state, make_service_permit(std::move(units)), std::move(json_request), std::move(req)).finally([trace_state] {});
-                    });
-                });
-            });
-        });
-    });
-}
-
-void server::set_routes(routes& r) {
-    api_handler* req_handler = new api_handler([this] (std::unique_ptr<request> req) mutable {
-        return handle_api_request(std::move(req));
-    });
-
-    r.put(operation_type::POST, "/", req_handler);
-    r.put(operation_type::GET, "/", new health_handler(_pending_requests));
-    // The "/localnodes" request is a new Alternator feature, not supported by
-    // DynamoDB and not required for DynamoDB compatibility. It allows a
-    // client to enquire - using a trivial HTTP request without requiring
-    // authentication - the list of all live nodes in the same data center of
-    // the Alternator cluster. The client can use this list to balance its
-    // request load to all the nodes in the same geographical region.
-    // Note that this API exposes - openly without authentication - the
-    // information on the cluster's members inside one data center. We do not
-    // consider this to be a security risk, because an attacker can already
-    // scan an entire subnet for nodes responding to the health request,
-    // or even just scan for open ports.
-    r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests));
-}
-
-//FIXME: A way to immediately invalidate the cache should be considered,
-// e.g. when the system table which stores the keys is changed.
-// For now, this propagation may take up to 1 minute.
-server::server(executor& exec)
-        : _http_server("http-alternator")
-        , _https_server("https-alternator")
-        , _executor(exec)
-        , _key_cache(1024, 1min, slogger)
-        , _enforce_authorization(false)
-        , _enabled_servers{}
-        , _pending_requests{}
-      , _callbacks{
-        {"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.create_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DescribeTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DeleteTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.delete_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"UpdateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"PutItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.put_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"UpdateItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"GetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DeleteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.delete_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"ListTables", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_tables(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"Scan", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.scan(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_endpoints(client_state, std::move(permit), std::move(json_request), req->get_header("Host"));
-        }},
-        {"BatchWriteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.batch_write_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"BatchGetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.batch_get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"Query", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.query(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"TagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.tag_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"UntagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.untag_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"ListTagsOfResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_tags_of_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"ListStreams", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_streams(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"DescribeStream", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_stream(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"GetShardIterator", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_shard_iterator(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"GetRecords", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_records(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-    } {
-}
-
-future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-        bool enforce_authorization, semaphore* memory_limiter) {
-    _memory_limiter = memory_limiter;
-    _enforce_authorization = enforce_authorization;
-    if (!port && !https_port) {
-        return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
-                " must be specified in order to init an alternator HTTP server instance"));
-    }
-    return seastar::async([this, addr, port, https_port, creds] {
-        try {
-            _executor.start().get();
-
-            if (port) {
-                set_routes(_http_server._routes);
-                _http_server.set_content_length_limit(server::content_length_limit);
-                _http_server.listen(socket_address{addr, *port}).get();
-                _enabled_servers.push_back(std::ref(_http_server));
-            }
-            if (https_port) {
-                set_routes(_https_server._routes);
-                _https_server.set_content_length_limit(server::content_length_limit);
-                _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
-                    if (ep) {
-                        slogger.warn("Exception loading {}: {}", files, ep);
-                    } else {
-                        slogger.info("Reloaded {}", files);
-                    }
-                }).get0());
-                _https_server.listen(socket_address{addr, *https_port}).get();
-                _enabled_servers.push_back(std::ref(_https_server));
-            }
-        } catch (...) {
-            slogger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
-                    addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF", std::current_exception());
-            std::throw_with_nested(std::runtime_error(
-                    format("Failed to set up Alternator HTTP server on {} port {}, TLS port {}",
-                            addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF")));
-        }
-    });
-}
-
-future<> server::stop() {
-    return parallel_for_each(_enabled_servers, [] (http_server& server) {
-        return server.stop();
-    }).then([this] {
-        return _pending_requests.close();
-    }).then([this] {
-        return _json_parser.stop();
-    });
-}
-
-server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
-        while (true) {
-            _document_waiting.wait().get();
-            if (_as.abort_requested()) {
-                return;
-            }
-            try {
-                _parsed_document = rjson::parse_yieldable(_raw_document);
-                _current_exception = nullptr;
-            } catch (...) {
-                _current_exception = std::current_exception();
-            }
-            _document_parsed.signal();
-        }
-    })) {
-}
-
-future<rjson::value> server::json_parser::parse(std::string_view content) {
-    if (content.size() < yieldable_parsing_threshold) {
-        return make_ready_future<rjson::value>(rjson::parse(content));
-    }
-    return with_semaphore(_parsing_sem, 1, [this, content] {
-        _raw_document = content;
-        _document_waiting.signal();
-        return _document_parsed.wait().then([this] {
-            if (_current_exception) {
-                return make_exception_future<rjson::value>(_current_exception);
-            }
-            return make_ready_future<rjson::value>(std::move(_parsed_document));
-        });
-    });
-}
-
-future<> server::json_parser::stop() {
-    _as.request_abort();
-    _document_waiting.signal();
-    _document_parsed.broken();
-    return std::move(_run_parse_json_thread);
-}
-
-}
-

alternator/server.hh

@@ -1,83 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include "alternator/executor.hh"
-#include <seastar/core/future.hh>
-#include <seastar/http/httpd.hh>
-#include <seastar/net/tls.hh>
-#include <optional>
-#include "alternator/auth.hh"
-#include "utils/small_vector.hh"
-#include <seastar/core/units.hh>
-
-namespace alternator {
-
-class server {
-    static constexpr size_t content_length_limit = 16*MB;
-    using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
-            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
-    using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
-
-    http_server _http_server;
-    http_server _https_server;
-    executor& _executor;
-
-    key_cache _key_cache;
-    bool _enforce_authorization;
-    utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
-    gate _pending_requests;
-    alternator_callbacks_map _callbacks;
-
-    semaphore* _memory_limiter;
-
-    class json_parser {
-        static constexpr size_t yieldable_parsing_threshold = 16*KB;
-        std::string_view _raw_document;
-        rjson::value _parsed_document;
-        std::exception_ptr _current_exception;
-        semaphore _parsing_sem{1};
-        condition_variable _document_waiting;
-        condition_variable _document_parsed;
-        abort_source _as;
-        future<> _run_parse_json_thread;
-    public:
-        json_parser();
-        future<rjson::value> parse(std::string_view content);
-        future<> stop();
-    };
-    json_parser _json_parser;
-
-public:
-    server(executor& executor);
-
-    future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-            bool enforce_authorization, semaphore* memory_limiter);
-    future<> stop();
-private:
-    void set_routes(seastar::httpd::routes& r);
-    future<> verify_signature(const seastar::httpd::request& r);
-    future<executor::request_return_type> handle_api_request(std::unique_ptr<request>&& req);
-};
-
-}
-

alternator/stats.cc

@@ -1,109 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "stats.hh"
-#include "utils/histogram_metrics_helper.hh"
-#include <seastar/core/metrics.hh>
-
-namespace alternator {
-
-const char* ALTERNATOR_METRICS = "alternator";
-
-stats::stats() : api_operations{} {
-    // Register the
-    seastar::metrics::label op("op");
-
-    _metrics.add_group("alternator", {
-#define OPERATION(name, CamelCaseName) \
-                seastar::metrics::make_total_operations("operation", api_operations.name, \
-                        seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
-#define OPERATION_LATENCY(name, CamelCaseName) \
-                seastar::metrics::make_histogram("op_latency", \
-                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return to_metrics_histogram(api_operations.name);}),
-            OPERATION(batch_write_item, "BatchWriteItem")
-            OPERATION(create_backup, "CreateBackup")
-            OPERATION(create_global_table, "CreateGlobalTable")
-            OPERATION(create_table, "CreateTable")
-            OPERATION(delete_backup, "DeleteBackup")
-            OPERATION(delete_item, "DeleteItem")
-            OPERATION(delete_table, "DeleteTable")
-            OPERATION(describe_backup, "DescribeBackup")
-            OPERATION(describe_continuous_backups, "DescribeContinuousBackups")
-            OPERATION(describe_endpoints, "DescribeEndpoints")
-            OPERATION(describe_global_table, "DescribeGlobalTable")
-            OPERATION(describe_global_table_settings, "DescribeGlobalTableSettings")
-            OPERATION(describe_limits, "DescribeLimits")
-            OPERATION(describe_table, "DescribeTable")
-            OPERATION(describe_time_to_live, "DescribeTimeToLive")
-            OPERATION(get_item, "GetItem")
-            OPERATION(list_backups, "ListBackups")
-            OPERATION(list_global_tables, "ListGlobalTables")
-            OPERATION(list_tables, "ListTables")
-            OPERATION(list_tags_of_resource, "ListTagsOfResource")
-            OPERATION(put_item, "PutItem")
-            OPERATION(query, "Query")
-            OPERATION(restore_table_from_backup, "RestoreTableFromBackup")
-            OPERATION(restore_table_to_point_in_time, "RestoreTableToPointInTime")
-            OPERATION(scan, "Scan")
-            OPERATION(tag_resource, "TagResource")
-            OPERATION(transact_get_items, "TransactGetItems")
-            OPERATION(transact_write_items, "TransactWriteItems")
-            OPERATION(untag_resource, "UntagResource")
-            OPERATION(update_continuous_backups, "UpdateContinuousBackups")
-            OPERATION(update_global_table, "UpdateGlobalTable")
-            OPERATION(update_global_table_settings, "UpdateGlobalTableSettings")
-            OPERATION(update_item, "UpdateItem")
-            OPERATION(update_table, "UpdateTable")
-            OPERATION(update_time_to_live, "UpdateTimeToLive")
-            OPERATION_LATENCY(put_item_latency, "PutItem")
-            OPERATION_LATENCY(get_item_latency, "GetItem")
-            OPERATION_LATENCY(delete_item_latency, "DeleteItem")
-            OPERATION_LATENCY(update_item_latency, "UpdateItem")
-            OPERATION(list_streams, "ListStreams")
-            OPERATION(describe_stream, "DescribeStream")
-            OPERATION(get_shard_iterator, "GetShardIterator")
-            OPERATION(get_records, "GetRecords")
-            OPERATION_LATENCY(get_records_latency, "GetRecords")
-    });
-    _metrics.add_group("alternator", {
-            seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
-                    seastar::metrics::description("number of unsupported operations via Alternator API")),
-            seastar::metrics::make_total_operations("total_operations", total_operations,
-                    seastar::metrics::description("number of total operations via Alternator API")),
-            seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
-                    seastar::metrics::description("number of performed read-before-write operations")),
-            seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
-                    seastar::metrics::description("number of writes that used LWT")),
-            seastar::metrics::make_total_operations("shard_bounce_for_lwt", shard_bounce_for_lwt,
-                    seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
-            seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
-                    seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
-            seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
-                    seastar::metrics::description("number of rows read during filtering operations")),
-            seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,
-                    seastar::metrics::description("number of rows read and matched during filtering operations")),
-            seastar::metrics::make_total_operations("filtered_rows_dropped_total", [this] { return cql_stats.filtered_rows_read_total - cql_stats.filtered_rows_matched_total; },
-                    seastar::metrics::description("number of rows read and dropped during filtering operations")),
-    });
-}
-
-
-}

alternator/stats.hh

@@ -1,103 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <cstdint>
-
-#include <seastar/core/metrics_registration.hh>
-#include "seastarx.hh"
-#include "utils/estimated_histogram.hh"
-#include "cql3/stats.hh"
-
-namespace alternator {
-
-// Object holding per-shard statistics related to Alternator.
-// While this object is alive, these metrics are also registered to be
-// visible by the metrics REST API, with the "alternator" prefix.
-class stats {
-public:
-    stats();
-    // Count of DynamoDB API operations by types
-    struct {
-        uint64_t batch_get_item = 0;
-        uint64_t batch_write_item = 0;
-        uint64_t create_backup = 0;
-        uint64_t create_global_table = 0;
-        uint64_t create_table = 0;
-        uint64_t delete_backup = 0;
-        uint64_t delete_item = 0;
-        uint64_t delete_table = 0;
-        uint64_t describe_backup = 0;
-        uint64_t describe_continuous_backups = 0;
-        uint64_t describe_endpoints = 0;
-        uint64_t describe_global_table = 0;
-        uint64_t describe_global_table_settings = 0;
-        uint64_t describe_limits = 0;
-        uint64_t describe_table = 0;
-        uint64_t describe_time_to_live = 0;
-        uint64_t get_item = 0;
-        uint64_t list_backups = 0;
-        uint64_t list_global_tables = 0;
-        uint64_t list_tables = 0;
-        uint64_t list_tags_of_resource = 0;
-        uint64_t put_item = 0;
-        uint64_t query = 0;
-        uint64_t restore_table_from_backup = 0;
-        uint64_t restore_table_to_point_in_time = 0;
-        uint64_t scan = 0;
-        uint64_t tag_resource = 0;
-        uint64_t transact_get_items = 0;
-        uint64_t transact_write_items = 0;
-        uint64_t untag_resource = 0;
-        uint64_t update_continuous_backups = 0;
-        uint64_t update_global_table = 0;
-        uint64_t update_global_table_settings = 0;
-        uint64_t update_item = 0;
-        uint64_t update_table = 0;
-        uint64_t update_time_to_live = 0;
-        uint64_t list_streams = 0;
-        uint64_t describe_stream = 0;
-        uint64_t get_shard_iterator = 0;
-        uint64_t get_records = 0;
-
-        utils::time_estimated_histogram put_item_latency;
-        utils::time_estimated_histogram get_item_latency;
-        utils::time_estimated_histogram delete_item_latency;
-        utils::time_estimated_histogram update_item_latency;
-        utils::time_estimated_histogram get_records_latency;
-    } api_operations;
-    // Miscellaneous event counters
-    uint64_t total_operations = 0;
-    uint64_t unsupported_operations = 0;
-    uint64_t reads_before_write = 0;
-    uint64_t write_using_lwt = 0;
-    uint64_t shard_bounce_for_lwt = 0;
-    uint64_t requests_blocked_memory = 0;
-    // CQL-derived stats
-    cql3::cql_stats cql_stats;
-private:
-    // The metric_groups object holds this stat object's metrics registered
-    // as long as the stats object is alive.
-    seastar::metrics::metric_groups _metrics;
-};
-
-}

alternator/tags_extension.hh

@@ -1,53 +0,0 @@
-/*
- * Copyright 2019 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU Affero General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include "serializer.hh"
-#include "schema.hh"
-#include "db/extensions.hh"
-
-namespace alternator {
-
-class tags_extension : public schema_extension {
-public:
-    static constexpr auto NAME = "scylla_tags";
-
-    tags_extension() = default;
-    explicit tags_extension(const std::map<sstring, sstring>& tags) : _tags(std::move(tags)) {}
-    explicit tags_extension(bytes b) : _tags(tags_extension::deserialize(b)) {}
-    explicit tags_extension(const sstring& s) {
-        throw std::logic_error("Cannot create tags from string");
-    }
-    bytes serialize() const override {
-        return ser::serialize_to_buffer<bytes>(_tags);
-    }
-    static std::map<sstring, sstring> deserialize(bytes_view buffer) {
-        return ser::deserialize_from_buffer(buffer, boost::type<std::map<sstring, sstring>>());
-    }
-    const std::map<sstring, sstring>& tags() const {
-        return _tags;
-    }
-private:
-    std::map<sstring, sstring> _tags;
-};
-
-}

api/api-doc/cache_service.json

@@ -13,7 +13,7 @@
             {
                "method":"GET",
                "summary":"get row cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -35,7 +35,7 @@
                      "description":"row cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -48,7 +48,7 @@
             {
                "method":"GET",
                "summary":"get key cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_key_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -70,7 +70,7 @@
                      "description":"key cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -83,7 +83,7 @@
             {
                "method":"GET",
                "summary":"get counter cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_counter_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -105,7 +105,7 @@
                      "description":"counter cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -118,7 +118,7 @@
             {
                "method":"GET",
                "summary":"get row cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -140,7 +140,7 @@
                      "description":"row cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -153,7 +153,7 @@
             {
                "method":"GET",
                "summary":"get key cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_key_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -175,7 +175,7 @@
                      "description":"key cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -188,7 +188,7 @@
             {
                "method":"GET",
                "summary":"get counter cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_counter_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -210,7 +210,7 @@
                      "description":"counter cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -448,7 +448,7 @@
         {
           "method": "GET",
           "summary": "Get key entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_key_entries",
           "produces": [
             "application/json"
@@ -568,7 +568,7 @@
         {
           "method": "GET",
           "summary": "Get row entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_row_entries",
           "produces": [
             "application/json"
@@ -688,7 +688,7 @@
         {
           "method": "GET",
           "summary": "Get counter entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_counter_entries",
           "produces": [
             "application/json"

api/api-doc/column_family.json

@@ -70,7 +70,7 @@
             {
                "method":"POST",
                "summary":"Force a major compaction of this column family",
-               "type":"void",
+               "type":"string",
                "nickname":"force_major_compaction",
                "produces":[
                   "application/json"
@@ -121,7 +121,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -172,7 +172,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -223,7 +223,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   },
                   {
@@ -231,7 +231,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -380,54 +380,16 @@
          "operations":[
             {
                "method":"GET",
-               "summary":"check if the auto_compaction property is enabled for a given table",
+               "summary":"check if the auto compaction disabled",
                "type":"boolean",
-               "nickname":"get_auto_compaction",
+               "nickname":"is_auto_compaction_disabled",
                "produces":[
                   "application/json"
                ],
                "parameters":[
                   {
                      "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"POST",
-               "summary":"Enable table auto compaction",
-               "type":"void",
-               "nickname":"enable_auto_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Disable table auto compaction",
-               "type":"void",
-               "nickname":"disable_auto_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
+                     "description":"The column family name in keyspace:name format",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -493,7 +455,7 @@
          "operations":[
             {
                "method":"GET",
-               "summary":"Returns a list of sstable filenames that contain the given partition key on this node",
+               "summary":"Returns a list of filenames that contain the given key on this node",
                "type":"array",
                "items":{
                   "type":"string"
@@ -513,7 +475,7 @@
                   },
                   {
                      "name":"key",
-                     "description":"The partition key. In a composite-key scenario, use ':' to separate the columns in the key.",
+                     "description":"The key",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -582,7 +544,7 @@
                "summary":"sstable count for each level. empty unless leveled compaction is used",
                "type":"array",
                "items":{
-                  "type": "long"
+                  "type":"int"
                },
                "nickname":"get_sstable_count_per_level",
                "produces":[
@@ -649,54 +611,6 @@
             }
          ]
       },
-      {
-         "path":"/column_family/toppartitions/{name}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Toppartitions query",
-               "type":"toppartitions_query_results",
-               "nickname":"toppartitions",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The column family name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"duration",
-                     "description":"Duration (in milliseconds) of monitoring operation",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  },
-                  {
-                    "name":"list_size",
-                    "description":"number of the top partitions to list",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 },
-                 {
-                    "name":"capacity",
-                    "description":"capacity of stream summary: determines amount of resources used in query processing",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 }
-              ]
-            }
-         ]
-      },
       {
          "path":"/column_family/metrics/memtable_columns_count/",
          "operations":[
@@ -959,7 +873,7 @@
             {
                "method":"GET",
                "summary":"Get memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -983,7 +897,7 @@
             {
                "method":"GET",
                "summary":"Get all memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -1120,7 +1034,7 @@
             {
                "method":"GET",
                "summary":"Get read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_read_latency",
                "produces":[
                   "application/json"
@@ -1273,7 +1187,7 @@
             {
                "method":"GET",
                "summary":"Get all read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_read_latency",
                "produces":[
                   "application/json"
@@ -1289,7 +1203,7 @@
             {
                "method":"GET",
                "summary":"Get range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_range_latency",
                "produces":[
                   "application/json"
@@ -1313,7 +1227,7 @@
             {
                "method":"GET",
                "summary":"Get all range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_range_latency",
                "produces":[
                   "application/json"
@@ -1329,7 +1243,7 @@
             {
                "method":"GET",
                "summary":"Get write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_write_latency",
                "produces":[
                   "application/json"
@@ -1482,7 +1396,7 @@
             {
                "method":"GET",
                "summary":"Get all write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_write_latency",
                "produces":[
                   "application/json"
@@ -1498,7 +1412,7 @@
             {
                "method":"GET",
                "summary":"Get pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_flushes",
                "produces":[
                   "application/json"
@@ -1522,7 +1436,7 @@
             {
                "method":"GET",
                "summary":"Get all pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_flushes",
                "produces":[
                   "application/json"
@@ -1538,7 +1452,7 @@
             {
                "method":"GET",
                "summary":"Get pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_compactions",
                "produces":[
                   "application/json"
@@ -1562,7 +1476,7 @@
             {
                "method":"GET",
                "summary":"Get all pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_compactions",
                "produces":[
                   "application/json"
@@ -1578,7 +1492,7 @@
             {
                "method":"GET",
                "summary":"Get live ss table count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_ss_table_count",
                "produces":[
                   "application/json"
@@ -1602,7 +1516,7 @@
             {
                "method":"GET",
                "summary":"Get all live ss table count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_live_ss_table_count",
                "produces":[
                   "application/json"
@@ -1618,7 +1532,7 @@
             {
                "method":"GET",
                "summary":"Get live disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_disk_space_used",
                "produces":[
                   "application/json"
@@ -1642,7 +1556,7 @@
             {
                "method":"GET",
                "summary":"Get all live disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_live_disk_space_used",
                "produces":[
                   "application/json"
@@ -1658,7 +1572,7 @@
             {
                "method":"GET",
                "summary":"Get total disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_disk_space_used",
                "produces":[
                   "application/json"
@@ -1682,7 +1596,7 @@
             {
                "method":"GET",
                "summary":"Get all total disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_disk_space_used",
                "produces":[
                   "application/json"
@@ -2138,7 +2052,7 @@
             {
                "method":"GET",
                "summary":"Get speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_speculative_retries",
                "produces":[
                   "application/json"
@@ -2162,7 +2076,7 @@
             {
                "method":"GET",
                "summary":"Get all speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_speculative_retries",
                "produces":[
                   "application/json"
@@ -2242,7 +2156,7 @@
             {
                "method":"GET",
                "summary":"Get row cache hit out of range",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_hit_out_of_range",
                "produces":[
                   "application/json"
@@ -2266,7 +2180,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache hit out of range",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_hit_out_of_range",
                "produces":[
                   "application/json"
@@ -2282,7 +2196,7 @@
             {
                "method":"GET",
                "summary":"Get row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2306,7 +2220,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2322,7 +2236,7 @@
             {
                "method":"GET",
                "summary":"Get row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2346,7 +2260,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2362,7 +2276,7 @@
             {
                "method":"GET",
                "summary":"Get cas prepare",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_prepare",
                "produces":[
                   "application/json"
@@ -2386,7 +2300,7 @@
             {
                "method":"GET",
                "summary":"Get cas propose",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_propose",
                "produces":[
                   "application/json"
@@ -2410,7 +2324,7 @@
             {
                "method":"GET",
                "summary":"Get cas commit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_commit",
                "produces":[
                   "application/json"
@@ -2902,44 +2816,6 @@
                "description":"The column family type"
             }
          }
-      },
-      "toppartitions_record":{
-         "id":"toppartitions_record",
-         "description":"nodetool toppartitions query record",
-         "properties":{
-            "partition":{
-               "type":"string",
-               "description":"Partition key"
-            },
-            "count":{
-               "type":"long",
-               "description":"Number of read/write operations"
-            },
-            "error":{
-               "type":"long",
-               "description":"Indication of inaccuracy in counting PKs"
-            }
-         }
-      },
-      "toppartitions_query_results":{
-         "id":"toppartitions_query_results",
-         "description":"nodetool toppartitions query results",
-         "properties":{
-            "read":{
-               "type":"array",
-               "items":{
-                  "type":"toppartitions_record"
-               },
-               "description":"Read results"
-            },
-            "write":{
-               "type":"array",
-               "items":{
-                  "type":"toppartitions_record"
-               },
-               "description":"Write results"
-            }
-         }
       }
    }
 }

api/api-doc/compaction_manager.json

@@ -118,7 +118,7 @@
         {
           "method": "GET",
           "summary": "Get pending tasks",
-          "type": "long",
+          "type": "int",
           "nickname": "get_pending_tasks",
           "produces": [
             "application/json"
@@ -127,24 +127,6 @@
         }
       ]
     },
-    {
-      "path": "/compaction_manager/metrics/pending_tasks_by_table",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get pending tasks by table name",
-          "type": "array",
-          "items": {
-              "type": "pending_compaction"
-           },
-          "nickname": "get_pending_tasks_by_table",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
     {
       "path": "/compaction_manager/metrics/completed_tasks",
       "operations": [
@@ -181,7 +163,7 @@
         {
           "method": "GET",
           "summary": "Get bytes compacted",
-          "type": "long",
+          "type": "int",
           "nickname": "get_bytes_compacted",
           "produces": [
             "application/json"
@@ -197,7 +179,7 @@
          "description":"A row merged information",
          "properties":{
             "key":{
-               "type": "long",
+               "type":"int",
                "description":"The number of sstable"
             },
             "value":{
@@ -262,23 +244,6 @@
             }
          }
       },
-      "pending_compaction": {
-        "id": "pending_compaction",
-        "properties": {
-            "cf": {
-               "type": "string",
-               "description": "The column family name"
-            },
-            "ks": {
-               "type":"string",
-               "description": "The keyspace name"
-            },
-            "task": {
-               "type":"long",
-               "description": "The number of pending tasks"
-            }
-        }
-      },
       "history": {
       "id":"history",
       "description":"Compaction history information",

api/api-doc/config.json

@@ -1,30 +0,0 @@
-"/v2/config/{id}": {
-      "get": {
-        "description": "Return a config value",
-        "operationId": "find_config_id",
-        "produces": [
-          "application/json"
-        ],
-        "tags": ["config"],
-        "parameters": [
-          {
-            "name": "id",
-            "in": "path",
-            "description": "ID of config to return",
-            "required": true,
-            "type": "string"
-          }
-        ],
-        "responses": {
-          "200": {
-            "description": "Config value"
-          },
-          "default": {
-            "description": "unexpected error",
-            "schema": {
-              "$ref": "#/definitions/ErrorModel"
-            }
-          }
-        }
-      }
-}

api/api-doc/error_injection.json

@@ -1,90 +0,0 @@
-{
-   "apiVersion":"0.0.1",
-   "swaggerVersion":"1.2",
-   "basePath":"{{Protocol}}://{{Host}}",
-   "resourcePath":"/error_injection",
-   "produces":[
-      "application/json"
-   ],
-   "apis":[
-      {
-         "path":"/v2/error_injection/injection/{injection}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Activate an injection that triggers an error in code",
-               "type":"void",
-               "nickname":"enable_injection",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"injection",
-                     "description":"injection name, should correspond to an injection added in code",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"one_shot",
-                     "description":"boolean flag indicating whether the injection should be enabled to trigger only once",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Deactivate an injection previously activated by the API",
-               "type":"void",
-               "nickname":"disable_injection",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"injection",
-                     "description":"injection name",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/v2/error_injection/injection",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"List all enabled injections on all shards, i.e. injections that will trigger an error in the code",
-               "type":"array",
-               "items":{
-                  "type":"string"
-               },
-               "nickname":"get_enabled_injections_on_all",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Deactivate all injections previously activated on all shards by the API",
-               "type":"void",
-               "nickname":"disable_on_all",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      }
-   ]
-}

api/api-doc/failure_detector.json

@@ -110,7 +110,7 @@
             {
                "method":"GET",
                "summary":"Get count down endpoint",
-               "type": "long",
+               "type":"int",
                "nickname":"get_down_endpoint_count",
                "produces":[
                   "application/json"
@@ -126,7 +126,7 @@
             {
                "method":"GET",
                "summary":"Get count up endpoint",
-               "type": "long",
+               "type":"int",
                "nickname":"get_up_endpoint_count",
                "produces":[
                   "application/json"
@@ -180,11 +180,11 @@
                     "description": "The endpoint address"
                 },
                 "generation": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The heart beat generation"
                 },
                 "version": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The heart beat version"
                 },
                 "update_time": {
@@ -209,7 +209,7 @@
            "description": "Holds a version value for an application state",
                "properties": {
                 "application_state": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The application state enum index"
                 },
                 "value": {
@@ -217,7 +217,7 @@
                     "description": "The version value"
                 },
                 "version": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The application state version"
                 }
             }

api/api-doc/gossiper.json

@@ -75,7 +75,7 @@
             {
                "method":"GET",
                "summary":"Returns files which are pending for archival attempt. Does NOT include failed archive attempts",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_generation_number",
                "produces":[
                   "application/json"
@@ -99,7 +99,7 @@
             {
                "method":"GET",
                "summary":"Get heart beat version for a node",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_heart_beat_version",
                "produces":[
                   "application/json"

api/api-doc/hinted_handoff.json

@@ -99,7 +99,7 @@
         {
           "method": "GET",
           "summary": "Get create hint count",
-          "type": "long",
+          "type": "int",
           "nickname": "get_create_hint_count",
           "produces": [
             "application/json"
@@ -123,7 +123,7 @@
         {
           "method": "GET",
           "summary": "Get not stored hints count",
-          "type": "long",
+          "type": "int",
           "nickname": "get_not_stored_hints_count",
           "produces": [
             "application/json"

api/api-doc/messaging_service.json

@@ -191,7 +191,7 @@
             {
                "method":"GET",
                "summary":"Get the version number",
-               "type": "long",
+               "type":"int",
                "nickname":"get_version",
                "produces":[
                   "application/json"
@@ -249,7 +249,7 @@
                  "MIGRATION_REQUEST",
                  "PREPARE_MESSAGE",
                  "PREPARE_DONE_MESSAGE",
-                 "UNUSED__STREAM_MUTATION",
+                 "STREAM_MUTATION",
                  "STREAM_MUTATION_DONE",
                  "COMPLETE_MESSAGE",
                  "REPAIR_CHECKSUM_RANGE",

api/api-doc/storage_proxy.json

@@ -105,7 +105,7 @@
             {
                "method":"GET",
                "summary":"Get the max hint window",
-               "type": "long",
+               "type":"int",
                "nickname":"get_max_hint_window",
                "produces":[
                   "application/json"
@@ -128,7 +128,7 @@
                      "description":"max hint window in ms",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -141,7 +141,7 @@
             {
                "method":"GET",
                "summary":"Get max hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_max_hints_in_progress",
                "produces":[
                   "application/json"
@@ -164,7 +164,7 @@
                      "description":"max hints in progress",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -177,7 +177,7 @@
             {
                "method":"GET",
                "summary":"get hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_hints_in_progress",
                "produces":[
                   "application/json"
@@ -602,7 +602,7 @@
         {
           "method": "GET",
           "summary": "Get cas write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_write_metrics_unfinished_commit",
           "produces": [
             "application/json"
@@ -632,7 +632,7 @@
         {
           "method": "GET",
           "summary": "Get cas write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_write_metrics_condition_not_met",
           "produces": [
             "application/json"
@@ -641,28 +641,13 @@
         }
       ]
     },
-    {
-      "path": "/storage_proxy/metrics/cas_write/failed_read_round_optimization",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get cas write metrics",
-          "type": "long",
-          "nickname": "get_cas_write_metrics_failed_read_round_optimization",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
     {
       "path": "/storage_proxy/metrics/cas_read/unfinished_commit",
       "operations": [
         {
           "method": "GET",
           "summary": "Get cas read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_read_metrics_unfinished_commit",
           "produces": [
             "application/json"
@@ -686,13 +671,28 @@
         }
       ]
     },
+    {
+      "path": "/storage_proxy/metrics/cas_read/condition_not_met",
+      "operations": [
+        {
+          "method": "GET",
+          "summary": "Get cas read metrics",
+          "type": "int",
+          "nickname": "get_cas_read_metrics_condition_not_met",
+          "produces": [
+            "application/json"
+          ],
+          "parameters": []
+        }
+      ]
+    },
     {
       "path": "/storage_proxy/metrics/read/timeouts",
       "operations": [
         {
           "method": "GET",
           "summary": "Get read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_read_metrics_timeouts",
           "produces": [
             "application/json"
@@ -707,7 +707,7 @@
         {
           "method": "GET",
           "summary": "Get read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_read_metrics_unavailables",
           "produces": [
             "application/json"
@@ -791,36 +791,6 @@
         }
       ]
     },
-    {
-      "path": "/storage_proxy/metrics/cas_read/moving_average_histogram",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get CAS read rate and latency histogram",
-          "$ref": "#/utils/rate_moving_average_and_histogram",
-          "nickname": "get_cas_read_metrics_latency_histogram",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
-    {
-      "path": "/storage_proxy/metrics/view_write/moving_average_histogram",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get view write rate and latency histogram",
-          "$ref": "#/utils/rate_moving_average_and_histogram",
-          "nickname": "get_view_write_metrics_latency_histogram",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
     {
       "path": "/storage_proxy/metrics/range/moving_average_histogram",
       "operations": [
@@ -842,7 +812,7 @@
         {
           "method": "GET",
           "summary": "Get range metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_range_metrics_timeouts",
           "produces": [
             "application/json"
@@ -857,7 +827,7 @@
         {
           "method": "GET",
           "summary": "Get range metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_range_metrics_unavailables",
           "produces": [
             "application/json"
@@ -902,7 +872,7 @@
         {
           "method": "GET",
           "summary": "Get write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_write_metrics_timeouts",
           "produces": [
             "application/json"
@@ -917,7 +887,7 @@
         {
           "method": "GET",
           "summary": "Get write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_write_metrics_unavailables",
           "produces": [
             "application/json"
@@ -986,21 +956,6 @@
         }
       ]
     },
-    {
-      "path": "/storage_proxy/metrics/cas_write/moving_average_histogram",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get CAS write rate and latency histogram",
-          "$ref": "#/utils/rate_moving_average_and_histogram",
-          "nickname": "get_cas_write_metrics_latency_histogram",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
     {
          "path":"/storage_proxy/metrics/read/estimated_histogram/",
          "operations":[
@@ -1023,7 +978,7 @@
             {
                "method":"GET",
                "summary":"Get read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_read_latency",
                "produces":[
                   "application/json"
@@ -1055,7 +1010,7 @@
             {
                "method":"GET",
                "summary":"Get write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_write_latency",
                "produces":[
                   "application/json"
@@ -1087,7 +1042,7 @@
             {
                "method":"GET",
                "summary":"Get range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_range_latency",
                "produces":[
                   "application/json"

api/api-doc/storage_service.json

@@ -458,7 +458,7 @@
             {
                "method":"GET",
                "summary":"Return the generation value for this node.",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_generation_number",
                "produces":[
                   "application/json"
@@ -511,21 +511,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/cdc_streams_check_and_repair",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Checks that CDC streams reflect current cluster topology and regenerates them if not.",
-               "type":"void",
-               "nickname":"cdc_streams_check_and_repair",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
       {
          "path":"/storage_service/snapshots",
          "operations":[
@@ -597,15 +582,7 @@
                   },
                   {
                      "name":"kn",
-                     "description":"Comma seperated keyspaces name that their snapshot will be deleted",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"an optional table name that its snapshot will be deleted",
+                     "description":"Comma seperated keyspaces name to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -669,7 +646,7 @@
             {
                "method":"POST",
                "summary":"Trigger a cleanup of keys on a single keyspace",
-               "type": "long",
+               "type":"int",
                "nickname":"force_keyspace_cleanup",
                "produces":[
                   "application/json"
@@ -701,7 +678,7 @@
             {
                "method":"GET",
                "summary":"Scrub (deserialize + reserialize at the latest version, skipping bad rows if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false",
-               "type": "long",
+               "type":"int",
                "nickname":"scrub",
                "produces":[
                   "application/json"
@@ -749,7 +726,7 @@
             {
                "method":"GET",
                "summary":"Rewrite all sstables to the latest version. Unlike scrub, it doesn't skip bad rows and do not snapshot sstables first.",
-               "type": "long",
+               "type":"int",
                "nickname":"upgrade_sstables",
                "produces":[
                   "application/json"
@@ -815,68 +792,13 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/active_repair/",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Return an array with the ids of the currently active repairs",
-               "type":"array",
-               "items":{
-                  "type": "long"
-               },
-               "nickname":"get_active_repair_async",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
-      {
-         "path":"/storage_service/repair_status/",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Query the repair status and return when the repair is finished or timeout",
-               "type":"string",
-               "enum":[
-                  "RUNNING",
-                  "SUCCESSFUL",
-                  "FAILED"
-               ],
-               "nickname":"repair_await_completion",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"id",
-                     "description":"The repair ID to check for status",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"timeout",
-                     "description":"Seconds to wait before the query returns even if the repair is not finished. The value -1 or not providing this parameter means no timeout",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/storage_service/repair_async/{keyspace}",
          "operations":[
             {
                "method":"POST",
                "summary":"Invoke repair asynchronously. You can track repair progress by using the get supplying id",
-               "type": "long",
+               "type":"int",
                "nickname":"repair_async",
                "produces":[
                   "application/json"
@@ -1007,7 +929,7 @@
                      "description":"The repair ID to check for status",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -1337,18 +1259,18 @@
                   },
                   {
                      "name":"dynamic_update_interval",
-                     "description":"interval in ms (default 100)",
+                     "description":"integer, in ms (default 100)",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"long",
+                     "type":"integer",
                      "paramType":"query"
                   },
                   {
                      "name":"dynamic_reset_interval",
-                     "description":"interval in ms (default 600,000)",
+                     "description":"integer, in ms (default 600,000)",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"long",
+                     "type":"integer",
                      "paramType":"query"
                   },
                   {
@@ -1553,7 +1475,7 @@
                      "description":"Stream throughput",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -1561,7 +1483,7 @@
             {
                "method":"GET",
                "summary":"Get stream throughput mb per sec",
-               "type": "long",
+               "type":"int",
                "nickname":"get_stream_throughput_mb_per_sec",
                "produces":[
                   "application/json"
@@ -1577,7 +1499,7 @@
             {
                "method":"GET",
                "summary":"get compaction throughput mb per sec",
-               "type": "long",
+               "type":"int",
                "nickname":"get_compaction_throughput_mb_per_sec",
                "produces":[
                   "application/json"
@@ -1599,7 +1521,7 @@
                      "description":"compaction throughput",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2003,7 +1925,7 @@
             {
                "method":"GET",
                "summary":"Returns the threshold for warning of queries with many tombstones",
-               "type": "long",
+               "type":"int",
                "nickname":"get_tombstone_warn_threshold",
                "produces":[
                   "application/json"
@@ -2025,7 +1947,7 @@
                      "description":"tombstone debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2038,7 +1960,7 @@
             {
                "method":"GET",
                "summary":"",
-               "type": "long",
+               "type":"int",
                "nickname":"get_tombstone_failure_threshold",
                "produces":[
                   "application/json"
@@ -2060,7 +1982,7 @@
                      "description":"tombstone debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2073,7 +1995,7 @@
             {
                "method":"GET",
                "summary":"Returns the threshold for rejecting queries due to a large batch size",
-               "type": "long",
+               "type":"int",
                "nickname":"get_batch_size_failure_threshold",
                "produces":[
                   "application/json"
@@ -2095,7 +2017,7 @@
                      "description":"batch size debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2119,7 +2041,7 @@
                      "description":"throttle in kb",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2132,7 +2054,7 @@
             {
                "method":"GET",
                "summary":"Get load",
-               "type": "long",
+               "type":"int",
                "nickname":"get_metrics_load",
                "produces":[
                   "application/json"
@@ -2148,7 +2070,7 @@
             {
                "method":"GET",
                "summary":"Get exceptions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_exceptions",
                "produces":[
                   "application/json"
@@ -2164,7 +2086,7 @@
             {
                "method":"GET",
                "summary":"Get total hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_hints_in_progress",
                "produces":[
                   "application/json"
@@ -2180,7 +2102,7 @@
             {
                "method":"GET",
                "summary":"Get total hints",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_hints",
                "produces":[
                   "application/json"
@@ -2189,77 +2111,7 @@
                ]
             }
          ]
-      },
-      {
-         "path":"/storage_service/view_build_statuses/{keyspace}/{view}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Gets the progress of a materialized view build",
-               "type":"array",
-               "items":{
-                  "type":"mapper"
-               },
-               "nickname":"view_build_statuses",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"view",
-                     "description":"View name",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/storage_service/sstable_info",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"SSTable information",
-               "type":"array",
-               "items":{
-                  "type":"table_sstables"
-               },
-               "nickname":"sstable_info",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"column family name",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      }      
+      }
    ],
    "models":{
       "mapper":{
@@ -2323,11 +2175,11 @@
                "description":"The column family"
             },
             "total":{
-               "type":"long",
+               "type":"int",
                "description":"The total snapshot size"
             },
             "live":{
-               "type":"long",
+               "type":"int",
                "description":"The live snapshot size"
             }
          }
@@ -2419,92 +2271,6 @@
                "description":"The endpoint details"
             }
          }
-      },
-      "named_maps":{
-        "id":"named_maps",
-        "properties":{
-            "group":{
-                "type":"string"
-            },
-            "attributes":{
-                "type":"array",
-                "items":{
-                    "type":"mapper"
-                }
-            }
-        }
-      },
-      "sstable":{
-        "id":"sstable",
-        "properties":{
-            "size":{
-               "type":"long",
-               "description":"Total size in bytes of sstable"
-            },
-            "data_size":{
-                "type":"long",
-                "description":"The size in bytes on disk of data"
-            },
-            "index_size":{
-               "type":"long",
-               "description":"The size in bytes on disk of index"
-            },
-            "filter_size":{
-               "type":"long",
-               "description":"The size in bytes on disk of filter"
-            },
-            "timestamp":{
-                "type":"datetime",
-                "description":"File creation time"
-            },
-            "generation":{
-                "type":"long",
-                "description":"SSTable generation"
-            },
-            "level":{
-               "type":"long",
-               "description":"SSTable level"
-            },
-            "version":{
-               "type":"string",
-               "enum":[
-                  "ka", "la", "mc", "md"
-               ],
-               "description":"SSTable version"
-            },
-            "properties":{
-                "type":"array",
-                "description":"SSTable attributes",
-                "items":{
-                    "type":"mapper"
-                }
-            },
-            "extended_properties":{
-                "type":"array",
-                "description":"SSTable extended attributes",
-                "items":{
-                    "type":"named_maps"
-                }
-            }
-        }
-      },
-      "table_sstables":{
-        "id":"table_sstables",
-        "description":"Per-table SSTable info and attributes",
-        "properties":{
-            "keyspace":{
-                "type":"string"
-            },
-            "table":{
-                "type":"string"
-            },
-            "sstables":{
-                "type":"array",
-                "items":{
-                    "$ref":"sstable"
-                }
-            }
-        }
       }
    }
 }

api/api-doc/stream_manager.json

@@ -32,7 +32,7 @@
             {
                "method":"GET",
                "summary":"Get number of active outbound streams",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_active_streams_outbound",
                "produces":[
                   "application/json"
@@ -48,7 +48,7 @@
             {
                "method":"GET",
                "summary":"Get total incoming bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_incoming_bytes",
                "produces":[
                   "application/json"
@@ -72,7 +72,7 @@
             {
                "method":"GET",
                "summary":"Get all total incoming bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_incoming_bytes",
                "produces":[
                   "application/json"
@@ -88,7 +88,7 @@
             {
                "method":"GET",
                "summary":"Get total outgoing bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_outgoing_bytes",
                "produces":[
                   "application/json"
@@ -112,7 +112,7 @@
             {
                "method":"GET",
                "summary":"Get all total outgoing bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_outgoing_bytes",
                "produces":[
                   "application/json"
@@ -154,7 +154,7 @@
                "description":"The peer"
             },
             "session_index":{
-               "type": "long",
+               "type":"int",
                "description":"The session index"
             },
             "connecting":{
@@ -211,7 +211,7 @@
                "description":"The ID"
             },
             "files":{
-               "type": "long",
+               "type":"int",
                "description":"Number of files to transfer. Can be 0 if nothing to transfer for some streaming request."
             },
             "total_size":{
@@ -242,7 +242,7 @@
                "description":"The peer address"
             },
             "session_index":{
-               "type": "long",
+               "type":"int",
                "description":"The session index"
             },
             "file_name":{

api/api-doc/swagger20_header.json

@@ -1,29 +0,0 @@
-{
-  "swagger": "2.0",
-  "info": {
-    "version": "1.0.0",
-    "title": "Scylla API",
-    "description": "The scylla API version 2.0",
-    "termsOfService": "http://www.scylladb.com/tos/",
-    "contact": {
-      "name": "Scylla Team",
-      "email": "info@scylladb.com",
-      "url": "http://scylladb.com"
-    },
-    "license": {
-      "name": "AGPL",
-      "url": "https://github.com/scylladb/scylla/blob/master/LICENSE.AGPL"
-    }
-  },
-  "host": "{{Host}}",
-  "basePath": "/v2",
-  "schemes": [
-    "http"
-  ],
-  "consumes": [
-    "application/json"
-  ],
-  "produces": [
-    "application/json"
-  ],
-  "paths": {

api/api-doc/system.json

@@ -52,21 +52,6 @@
             }
          ]
       },
-      {
-         "path":"/system/uptime_ms",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get system uptime, in milliseconds",
-               "type":"long",
-               "nickname":"get_system_uptime",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
       {
          "path":"/system/logger/{name}",
          "operations":[

api/api.cc

@@ -20,9 +20,9 @@
  */
 
 #include "api.hh"
-#include <seastar/http/file_handler.hh>
-#include <seastar/http/transformers.hh>
-#include <seastar/http/api_docs.hh>
+#include "http/file_handler.hh"
+#include "http/transformers.hh"
+#include "http/api_docs.hh"
 #include "storage_service.hh"
 #include "commitlog.hh"
 #include "gossiper.hh"
@@ -36,13 +36,9 @@
 #include "endpoint_snitch.hh"
 #include "compaction_manager.hh"
 #include "hinted_handoff.hh"
-#include "error_injection.hh"
-#include <seastar/http/exception.hh>
+#include "http/exception.hh"
 #include "stream_manager.hh"
 #include "system.hh"
-#include "api/config.hh"
-
-logging::logger apilog("api");
 
 namespace api {
 
@@ -58,30 +54,20 @@ static std::unique_ptr<reply> exception_reply(std::exception_ptr eptr) {
 
 future<> set_server_init(http_context& ctx) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-    auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
 
-    return ctx.http_server.set_routes([rb, &ctx, rb02](routes& r) {
+    return ctx.http_server.set_routes([rb, &ctx](routes& r) {
         r.register_exeption_handler(exception_reply);
         r.put(GET, "/ui", new httpd::file_handler(ctx.api_dir + "/index.html",
                 new content_replace("html")));
         r.add(GET, url("/ui").remainder("path"), new httpd::directory_handler(ctx.api_dir,
                 new content_replace("html")));
         rb->set_api_doc(r);
-        rb02->set_api_doc(r);
-        rb02->register_api_file(r, "swagger20_header");
         rb->register_function(r, "system",
                 "The system related API");
         set_system(ctx, r);
     });
 }
 
-future<> set_server_config(http_context& ctx) {
-    auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
-    return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
-        set_config(rb02, ctx, r);
-    });
-}
-
 static future<> register_api(http_context& ctx, const sstring& api_name,
         const sstring api_desc,
         std::function<void(http_context& ctx, routes& r)> f) {
@@ -93,42 +79,10 @@ static future<> register_api(http_context& ctx, const sstring& api_name,
     });
 }
 
-future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl) {
-    return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_transport_controller(ctx, r, ctl); });
-}
-
-future<> unset_transport_controller(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_transport_controller(ctx, r); });
-}
-
-future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl) {
-    return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_rpc_controller(ctx, r, ctl); });
-}
-
-future<> unset_rpc_controller(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_rpc_controller(ctx, r); });
-}
-
 future<> set_server_storage_service(http_context& ctx) {
     return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
 }
 
-future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms) {
-    return ctx.http_server.set_routes([&ctx, &ms] (routes& r) { set_repair(ctx, r, ms); });
-}
-
-future<> unset_server_repair(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_repair(ctx, r); });
-}
-
-future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl) {
-    return ctx.http_server.set_routes([&ctx, &snap_ctl] (routes& r) { set_snapshot(ctx, r, snap_ctl); });
-}
-
-future<> unset_server_snapshot(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_snapshot(ctx, r); });
-}
-
 future<> set_server_snitch(http_context& ctx) {
     return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
 }
@@ -143,14 +97,9 @@ future<> set_server_load_sstable(http_context& ctx) {
                 "The column family API", set_column_family);
 }
 
-future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms) {
+future<> set_server_messaging_service(http_context& ctx) {
     return register_api(ctx, "messaging_service",
-                "The messaging service API", [&ms] (http_context& ctx, routes& r) {
-                    set_messaging_service(ctx, r, ms);
-                });
-}
-future<> unset_server_messaging_service(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_messaging_service(ctx, r); });
+                "The messaging service API", set_messaging_service);
 }
 
 future<> set_server_storage_proxy(http_context& ctx) {
@@ -163,11 +112,6 @@ future<> set_server_stream_manager(http_context& ctx) {
                 "The stream manager API", set_stream_manager);
 }
 
-future<> set_server_cache(http_context& ctx) {
-    return register_api(ctx, "cache_service",
-            "The cache service API", set_cache_service);
-}
-
 future<> set_server_gossip_settle(http_context& ctx) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 
@@ -175,6 +119,9 @@ future<> set_server_gossip_settle(http_context& ctx) {
         rb->register_function(r, "failure_detector",
                 "The failure detector API");
         set_failure_detector(ctx,r);
+        rb->register_function(r, "cache_service",
+                "The cache service API");
+        set_cache_service(ctx,r);
     });
 }
 
@@ -197,9 +144,6 @@ future<> set_server_done(http_context& ctx) {
         rb->register_function(r, "collectd",
                 "The collectd API");
         set_collectd(ctx, r);
-        rb->register_function(r, "error_injection",
-                "The error injection API");
-        set_error_injection(ctx, r);
     });
 }
 

api/api.hh

@@ -21,15 +21,13 @@
 
 #pragma once
 
-#include <seastar/json/json_elements.hh>
-#include <type_traits>
+#include "json/json_elements.hh"
 #include <boost/lexical_cast.hpp>
 #include <boost/algorithm/string/split.hpp>
 #include <boost/algorithm/string/classification.hpp>
-#include <boost/units/detail/utility.hpp>
 #include "api/api-doc/utils.json.hh"
 #include "utils/histogram.hh"
-#include <seastar/http/exception.hh>
+#include "http/exception.hh"
 #include "api_init.hh"
 #include "seastarx.hh"
 
@@ -218,44 +216,4 @@ std::vector<T> concat(std::vector<T> a, std::vector<T>&& b) {
     return a;
 }
 
-template <class T, class Base = T>
-class req_param {
-public:
-    sstring name;
-    sstring param;
-    T value;
-
-    req_param(const request& req, sstring name, T default_val) : name(name) {
-        param = req.get_query_param(name);
-        if (param.empty()) {
-            value = default_val;
-            return;
-        }
-        try {
-            // boost::lexical_cast does not use boolalpha. Converting a
-            // true/false throws exceptions. We don't want that.
-            if constexpr (std::is_same_v<Base, bool>) {
-                // Cannot use boolalpha because we (probably) want to
-                // accept 1 and 0 as well as true and false. And True. And fAlse.
-                std::transform(param.begin(), param.end(), param.begin(), ::tolower);
-                if (param == "true" || param == "1") {
-                    value = T(true);
-                } else if (param == "false" || param == "0") {
-                    value = T(false);
-                } else {
-                    throw boost::bad_lexical_cast{};
-                }
-            } else {
-                value = T{boost::lexical_cast<Base>(param)};
-            }
-        } catch (boost::bad_lexical_cast&) {
-            throw bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
-        }
-    }
-
-    operator T() const { return value; }
-};
-
-utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val);
-
 }

api/api_init.hh

@@ -19,16 +19,9 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 #pragma once
-#include "database_fwd.hh"
+#include "database.hh"
 #include "service/storage_proxy.hh"
-#include <seastar/http/httpd.hh>
-
-namespace service { class load_meter; }
-namespace locator { class token_metadata; }
-namespace cql_transport { class controller; }
-class thrift_controller;
-namespace db { class snapshot_ctl; }
-namespace netw { class messaging_service; }
+#include "http/httpd.hh"
 
 namespace api {
 
@@ -38,36 +31,22 @@ struct http_context {
     httpd::http_server_control http_server;
     distributed<database>& db;
     distributed<service::storage_proxy>& sp;
-    service::load_meter& lmeter;
-    const sharded<locator::token_metadata>& token_metadata;
-
     http_context(distributed<database>& _db,
-            distributed<service::storage_proxy>& _sp,
-            service::load_meter& _lm, const sharded<locator::token_metadata>& _tm)
-            : db(_db), sp(_sp), lmeter(_lm), token_metadata(_tm) {
+            distributed<service::storage_proxy>& _sp)
+            : db(_db), sp(_sp) {
     }
 };
 
 future<> set_server_init(http_context& ctx);
-future<> set_server_config(http_context& ctx);
 future<> set_server_snitch(http_context& ctx);
 future<> set_server_storage_service(http_context& ctx);
-future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms);
-future<> unset_server_repair(http_context& ctx);
-future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
-future<> unset_transport_controller(http_context& ctx);
-future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
-future<> unset_rpc_controller(http_context& ctx);
-future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
-future<> unset_server_snapshot(http_context& ctx);
 future<> set_server_gossip(http_context& ctx);
 future<> set_server_load_sstable(http_context& ctx);
-future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms);
-future<> unset_server_messaging_service(http_context& ctx);
+future<> set_server_messaging_service(http_context& ctx);
 future<> set_server_storage_proxy(http_context& ctx);
 future<> set_server_stream_manager(http_context& ctx);
 future<> set_server_gossip_settle(http_context& ctx);
-future<> set_server_cache(http_context& ctx);
 future<> set_server_done(http_context& ctx);
 
+
 }

api/cache_service.cc

@@ -208,11 +208,9 @@ void set_cache_service(http_context& ctx, routes& r) {
     });
 
     cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](database& db) -> uint64_t {
-            return db.row_cache_tracker().region().occupancy().used_space();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
+            return cf.get_row_cache().get_cache_tracker().region().occupancy().used_space();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -253,19 +251,15 @@ void set_cache_service(http_context& ctx, routes& r) {
     cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         // In origin row size is the weighted size.
         // We currently do not support weights, so we use num entries instead
-        return ctx.db.map_reduce0([](database& db) -> uint64_t {
-            return db.row_cache_tracker().partitions();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, 0, [](const column_family& cf) {
+            return cf.get_row_cache().partitions();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](database& db) -> uint64_t {
-            return db.row_cache_tracker().partitions();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, 0, [](const column_family& cf) {
+            return cf.get_row_cache().partitions();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_counter_capacity.set(r, [] (std::unique_ptr<request> req) {

api/collectd.cc

@@ -21,8 +21,8 @@
 
 #include "collectd.hh"
 #include "api/api-doc/collectd.json.hh"
-#include <seastar/core/scollectd.hh>
-#include <seastar/core/scollectd_api.hh>
+#include "core/scollectd.hh"
+#include "core/scollectd_api.hh"
 #include "endian.h"
 #include <boost/range/irange.hpp>
 #include <regex>
@@ -64,7 +64,7 @@ static const char* str_to_regex(const sstring& v) {
 void set_collectd(http_context& ctx, routes& r) {
     cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
 
-        auto id = ::make_shared<scollectd::type_instance_id>(req->param["pluginid"],
+        auto id = make_shared<scollectd::type_instance_id>(req->param["pluginid"],
                 req->get_query_param("instance"), req->get_query_param("type"),
                 req->get_query_param("type_instance"));
 

api/column_family.cc

@@ -22,14 +22,10 @@
 #include "column_family.hh"
 #include "api/api-doc/column_family.json.hh"
 #include <vector>
-#include <seastar/http/exception.hh>
+#include "http/exception.hh"
 #include "sstables/sstables.hh"
 #include "utils/estimated_histogram.hh"
 #include <algorithm>
-#include "db/system_keyspace_view_types.hh"
-#include "db/data_listeners.hh"
-
-extern logging::logger apilog;
 
 namespace api {
 using namespace httpd;
@@ -38,7 +34,7 @@ using namespace std;
 using namespace json;
 namespace cf = httpd::column_family_json;
 
-std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
+const utils::UUID& get_uuid(const sstring& name, const database& db) {
     auto pos = name.find("%3A");
     size_t end;
     if (pos == sstring::npos) {
@@ -50,22 +46,14 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
     } else {
         end = pos + 3;
     }
-    return std::make_tuple(name.substr(0, pos), name.substr(end));
-}
-
-const utils::UUID& get_uuid(const sstring& ks, const sstring& cf, const database& db) {
     try {
-        return db.find_uuid(ks, cf);
+        return db.find_uuid(name.substr(0, pos), name.substr(end));
     } catch (std::out_of_range& e) {
-        throw bad_param_exception(format("Column family '{}:{}' not found", ks, cf));
+        throw bad_param_exception("Column family '" + name.substr(0, pos) + ":"
+                + name.substr(end) + "' not found");
     }
 }
 
-const utils::UUID& get_uuid(const sstring& name, const database& db) {
-    auto [ks, cf] = parse_fully_qualified_cf_name(name);
-    return get_uuid(ks, cf, db);
-}
-
 future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(column_family&)> f) {
     auto uuid = get_uuid(name, ctx.db.local());
 
@@ -75,28 +63,28 @@ future<> foreach_column_family(http_context& ctx, const sstring& name, function<
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t column_family_stats::*f) {
+        int64_t column_family::stats::*f) {
     return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
         return cf.get_stats().*f;
     }, std::plus<int64_t>());
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t column_family_stats::*f) {
+        int64_t column_family::stats::*f) {
     return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
         return cf.get_stats().*f;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
         return (cf.get_stats().*f).hist.count;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     auto uuid = get_uuid(name, ctx.db.local());
     return ctx.db.map_reduce0([uuid, f](database& db) {
         // Histograms information is sample of the actual load
@@ -112,14 +100,14 @@ static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const
 
 
 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx,
-        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
         return (cf.get_stats().*f).hist.count;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     utils::UUID uuid = get_uuid(name, ctx.db.local());
     return ctx.db.map_reduce0([f, uuid](const database& p) {
         return (p.find_column_family(uuid).get_stats().*f).hist;},
@@ -130,7 +118,7 @@ static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const
     });
 }
 
-static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     std::function<utils::ihistogram(const database&)> fun = [f] (const database& db)  {
         utils::ihistogram res;
         for (auto i : db.get_column_families()) {
@@ -146,7 +134,7 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
 }
 
 static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     utils::UUID uuid = get_uuid(name, ctx.db.local());
     return ctx.db.map_reduce0([f, uuid](const database& p) {
         return (p.find_column_family(uuid).get_stats().*f).rate();},
@@ -157,7 +145,7 @@ static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& c
     });
 }
 
-static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
     std::function<utils::rate_moving_average_and_histogram(const database&)> fun = [f] (const database& db)  {
         utils::rate_moving_average_and_histogram res;
         for (auto i : db.get_column_families()) {
@@ -178,27 +166,27 @@ static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ct
     }, std::plus<int64_t>());
 }
 
-static int64_t min_partition_size(column_family& cf) {
+static int64_t min_row_size(column_family& cf) {
     int64_t res = INT64_MAX;
     for (auto i: *cf.get_sstables() ) {
-        res = std::min(res, i->get_stats_metadata().estimated_partition_size.min());
+        res = std::min(res, i->get_stats_metadata().estimated_row_size.min());
     }
     return (res == INT64_MAX) ? 0 : res;
 }
 
-static int64_t max_partition_size(column_family& cf) {
+static int64_t max_row_size(column_family& cf) {
     int64_t res = 0;
     for (auto i: *cf.get_sstables() ) {
-        res = std::max(i->get_stats_metadata().estimated_partition_size.max(), res);
+        res = std::max(i->get_stats_metadata().estimated_row_size.max(), res);
     }
     return res;
 }
 
-static integral_ratio_holder mean_partition_size(column_family& cf) {
+static integral_ratio_holder mean_row_size(column_family& cf) {
     integral_ratio_holder res;
     for (auto i: *cf.get_sstables() ) {
-        auto c = i->get_stats_metadata().estimated_partition_size.count();
-        res.sub += i->get_stats_metadata().estimated_partition_size.mean() * c;
+        auto c = i->get_stats_metadata().estimated_row_size.count();
+        res.sub += i->get_stats_metadata().estimated_row_size.mean() * c;
         res.total += c;
     }
     return res;
@@ -249,22 +237,17 @@ static future<json::json_return_type> sum_sstable(http_context& ctx, bool total)
     });
 }
 
-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f) {
-    return map_reduce_cf_raw(ctx, name, utils::time_estimated_histogram(), f, utils::time_estimated_histogram_merge).then([](const utils::time_estimated_histogram& res) {
-        return make_ready_future<json::json_return_type>(time_to_json_histogram(res));
-    });
-}
-
 template <typename T>
 class sum_ratio {
     uint64_t _n = 0;
     T _total = 0;
 public:
-    void operator()(T value) {
+    future<> operator()(T value) {
         if (value > 0) {
             _total += value;
             _n++;
         }
+        return make_ready_future<>();
     }
     // Returns average value of all registered ratios.
     T get() && {
@@ -331,15 +314,15 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t{0}, [](column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], 0, [](column_family& cf) {
             return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
     });
 
     cf::get_all_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t{0}, [](column_family& cf) {
+        return map_reduce_cf(ctx, 0, [](column_family& cf) {
             return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
     });
 
     cf::get_memtable_on_heap_size.set(r, [] (const_req req) {
@@ -413,31 +396,29 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family::stats::memtable_switch_count);
     });
 
     cf::get_all_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx, &column_family::stats::memtable_switch_count);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             utils::estimated_histogram res(0);
             for (auto i: *cf.get_sstables() ) {
-                res.merge(i->get_stats_metadata().estimated_partition_size);
+                res.merge(i->get_stats_metadata().estimated_row_size);
             }
             return res;
         },
         utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             uint64_t res = 0;
             for (auto i: *cf.get_sstables() ) {
-                res += i->get_stats_metadata().estimated_partition_size.count();
+                res += i->get_stats_metadata().estimated_row_size.count();
             }
             return res;
         },
@@ -448,7 +429,7 @@ void set_column_family(http_context& ctx, routes& r) {
         return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             utils::estimated_histogram res(0);
             for (auto i: *cf.get_sstables() ) {
-                res.merge(i->get_stats_metadata().estimated_cells_count);
+                res.merge(i->get_stats_metadata().estimated_column_count);
             }
             return res;
         },
@@ -462,67 +443,67 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::pending_flushes);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family::stats::pending_flushes);
     });
 
     cf::get_all_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &column_family_stats::pending_flushes);
+        return get_cf_stats(ctx, &column_family::stats::pending_flushes);
     });
 
     cf::get_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx,req->param["name"] ,&column_family_stats::reads);
+        return get_cf_stats_count(ctx,req->param["name"] ,&column_family::stats::reads);
     });
 
     cf::get_all_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &column_family_stats::reads);
+        return get_cf_stats_count(ctx, &column_family::stats::reads);
     });
 
     cf::get_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, req->param["name"] ,&column_family_stats::writes);
+        return get_cf_stats_count(ctx, req->param["name"] ,&column_family::stats::writes);
     });
 
     cf::get_all_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &column_family_stats::writes);
+        return get_cf_stats_count(ctx, &column_family::stats::writes);
     });
 
     cf::get_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::reads);
+        return get_cf_histogram(ctx, req->param["name"], &column_family::stats::reads);
     });
 
     cf::get_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::reads);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::reads);
     });
 
     cf::get_read_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx,req->param["name"] ,&column_family_stats::reads);
+        return get_cf_stats_sum(ctx,req->param["name"] ,&column_family::stats::reads);
     });
 
     cf::get_write_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx, req->param["name"] ,&column_family_stats::writes);
+        return get_cf_stats_sum(ctx, req->param["name"] ,&column_family::stats::writes);
     });
 
     cf::get_all_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family::stats::writes);
     });
 
     cf::get_all_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
     });
 
     cf::get_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::writes);
+        return get_cf_histogram(ctx, req->param["name"], &column_family::stats::writes);
     });
 
     cf::get_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::writes);
     });
 
     cf::get_all_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family::stats::writes);
     });
 
     cf::get_all_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
     });
 
     cf::get_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -538,11 +519,11 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, req->param["name"], &column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, req->param["name"], &column_family::stats::live_sstable_count);
     });
 
     cf::get_all_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, &column_family::stats::live_sstable_count);
     });
 
     cf::get_unleveled_sstables.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -565,36 +546,30 @@ void set_column_family(http_context& ctx, routes& r) {
         return sum_sstable(ctx, true);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_partition_size, min_int64);
+        return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_row_size, min_int64);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_all_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, INT64_MAX, min_partition_size, min_int64);
+        return map_reduce_cf(ctx, INT64_MAX, min_row_size, min_int64);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_partition_size, max_int64);
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_row_size, max_int64);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_all_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), max_partition_size, max_int64);
+        return map_reduce_cf(ctx, int64_t(0), max_row_size, max_int64);
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         // Cassandra 3.x mean values are truncated as integrals.
-        return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
+        return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
     });
 
-    // FIXME: this refers to partitions, not rows.
     cf::get_all_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         // Cassandra 3.x mean values are truncated as integrals.
-        return map_reduce_cf(ctx, integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
+        return map_reduce_cf(ctx, integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
     });
 
     cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -656,7 +631,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+                return sst->filter_size();
             });
         }, std::plus<uint64_t>());
     });
@@ -664,7 +639,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+                return sst->filter_size();
             });
         }, std::plus<uint64_t>());
     });
@@ -672,7 +647,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+                return sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
     });
@@ -680,7 +655,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_all_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+                return sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
     });
@@ -688,7 +663,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+                return sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
     });
@@ -696,7 +671,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_all_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
             return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+                return sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
     });
@@ -801,22 +776,25 @@ void set_column_family(http_context& ctx, routes& r) {
 
     });
 
-    cf::get_cas_prepare.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
-            return cf.get_stats().estimated_cas_prepare;
-        });
+    cf::get_cas_prepare.set(r, [] (std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        //auto id = get_uuid(req->param["name"], ctx.db.local());
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    cf::get_cas_propose.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
-            return cf.get_stats().estimated_cas_accept;
-        });
+    cf::get_cas_propose.set(r, [] (std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        //auto id = get_uuid(req->param["name"], ctx.db.local());
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    cf::get_cas_commit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
-            return cf.get_stats().estimated_cas_learn;
-        });
+    cf::get_cas_commit.set(r, [] (std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        //auto id = get_uuid(req->param["name"], ctx.db.local());
+        return make_ready_future<json::json_return_type>(0);
     });
 
     cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -827,11 +805,11 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_tombstone_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::tombstone_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family::stats::tombstone_scanned);
     });
 
     cf::get_live_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::live_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family::stats::live_scanned);
     });
 
     cf::get_col_update_time_delta_histogram.set(r, [] (std::unique_ptr<request> req) {
@@ -842,51 +820,19 @@ void set_column_family(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(res);
     });
 
-    cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
-        const utils::UUID& uuid = get_uuid(req.param["name"], ctx.db.local());
-        column_family& cf = ctx.db.local().find_column_family(uuid);
-        return !cf.is_auto_compaction_disabled_by_user();
+    cf::is_auto_compaction_disabled.set(r, [] (const_req req) {
+        // FIXME
+        // currently auto compaction is disable
+        // it should be changed when it would have an API
+        return true;
     });
 
-    cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
-            cf.enable_auto_compaction();
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
+    cf::get_built_indexes.set(r, [](const_req) {
+        // FIXME
+        // Currently there are no index support
+        return std::vector<sstring>();
     });
 
-    cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
-            cf.disable_auto_compaction();
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    cf::get_built_indexes.set(r, [&ctx](std::unique_ptr<request> req) {
-        auto ks_cf = parse_fully_qualified_cf_name(req->param["name"]);
-        auto&& ks = std::get<0>(ks_cf);
-        auto&& cf_name = std::get<1>(ks_cf);
-        return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_build_progress>& vb) mutable {
-            std::set<sstring> vp;
-            for (auto b : vb) {
-                if (b.view.first == ks) {
-                    vp.insert(b.view.second);
-                }
-            }
-            std::vector<sstring> res;
-            auto uuid = get_uuid(ks, cf_name, ctx.db.local());
-            column_family& cf = ctx.db.local().find_column_family(uuid);
-            res.reserve(cf.get_index_manager().list_indexes().size());
-            for (auto&& i : cf.get_index_manager().list_indexes()) {
-                if (!vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
-                    res.emplace_back(i.metadata().name());
-                }
-            }
-            return make_ready_future<json::json_return_type>(res);
-        });
-    });
 
     cf::get_compression_metadata_off_heap_memory_used.set(r, [](const_req) {
         // FIXME
@@ -914,15 +860,17 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_read_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             return cf.get_stats().estimated_read;
-        });
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_write_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             return cf.get_stats().estimated_write;
-        });
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -957,70 +905,5 @@ void set_column_family(http_context& ctx, routes& r) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
-
-    cf::get_sstables_for_key.set(r, [&ctx](std::unique_ptr<request> req) {
-        auto key = req->get_query_param("key");
-        auto uuid = get_uuid(req->param["name"], ctx.db.local());
-
-        return ctx.db.map_reduce0([key, uuid] (database& db) {
-            return db.find_column_family(uuid).get_sstables_by_partition_key(key);
-        }, std::unordered_set<sstring>(),
-            [](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
-            a.insert(b.begin(),b.end());
-            return a;
-        }).then([](const std::unordered_set<sstring>& res) {
-            return make_ready_future<json::json_return_type>(container_to_vec(res));
-        });
-    });
-
-    cf::toppartitions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        auto name_param = req->param["name"];
-        auto [ks, cf] = parse_fully_qualified_cf_name(name_param);
-
-        api::req_param<std::chrono::milliseconds, unsigned> duration{*req, "duration", 1000ms};
-        api::req_param<unsigned> capacity(*req, "capacity", 256);
-        api::req_param<unsigned> list_size(*req, "list_size", 10);
-
-        apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
-            name_param, duration.param, list_size.param, capacity.param);
-
-        return seastar::do_with(db::toppartitions_query(ctx.db, ks, cf, duration.value, list_size, capacity), [&ctx](auto& q) {
-            return q.scatter().then([&q] {
-                return sleep(q.duration()).then([&q] {
-                    return q.gather(q.capacity()).then([&q] (auto topk_results) {
-                        apilog.debug("toppartitions query: processing results");
-                        cf::toppartitions_query_results results;
-
-                        for (auto& d: topk_results.read.top(q.list_size())) {
-                            cf::toppartitions_record r;
-                            r.partition = sstring(d.item);
-                            r.count = d.count;
-                            r.error = d.error;
-                            results.read.push(r);
-                        }
-                        for (auto& d: topk_results.write.top(q.list_size())) {
-                            cf::toppartitions_record r;
-                            r.partition = sstring(d.item);
-                            r.count = d.count;
-                            r.error = d.error;
-                            results.write.push(r);
-                        }
-                        return make_ready_future<json::json_return_type>(results);
-                    });
-                });
-            });
-        });
-    });
-
-    cf::force_major_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        if (req->get_query_param("split_output") != "") {
-            fail(unimplemented::cause::API);
-        }
-        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
-            return cf.compact_all_sstables();
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
 }
 }

api/column_family.hh

@@ -24,8 +24,6 @@
 #include "api.hh"
 #include "api/api-doc/column_family.json.hh"
 #include "database.hh"
-#include <seastar/core/future-util.hh>
-#include <any>
 
 namespace api {
 
@@ -39,15 +37,9 @@ template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer) {
     auto uuid = get_uuid(name, ctx.db.local());
-    using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
-    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
-        return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
-    }), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
-        return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
-    })).then([] (std::unique_ptr<std::any> r) {
-        return std::any_cast<I>(std::move(*r));
-    });
+    return ctx.db.map_reduce0([mapper, uuid](database& db) {
+        return mapper(db.find_column_family(uuid));
+    }, init, reducer);
 }
 
 
@@ -59,46 +51,35 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
     });
 }
 
+template<class Mapper, class I, class Reducer, class Result>
+future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
+        Mapper mapper, Reducer reducer, Result result) {
+    auto uuid = get_uuid(name, ctx.db.local());
+    return ctx.db.map_reduce0([mapper, uuid](database& db) {
+        return mapper(db.find_column_family(uuid));
+    }, init, reducer);
+}
+
+
 template<class Mapper, class I, class Reducer, class Result>
 future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer, Result result) {
-    return map_reduce_cf_raw(ctx, name, init, mapper, reducer).then([result](const I& res) mutable {
+    return map_reduce_cf_raw(ctx, name, init, mapper, reducer, result).then([result](const I& res) mutable {
         result = res;
         return make_ready_future<json::json_return_type>(result);
     });
 }
 
-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f);
-
-struct map_reduce_column_families_locally {
-    std::any init;
-    std::function<std::unique_ptr<std::any>(column_family&)> mapper;
-    std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
-    future<std::unique_ptr<std::any>> operator()(database& db) const {
-        auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
-        return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
-            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
-        }).then([res] {
-            return std::move(*res);
-        });
-    }
-};
-
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, I init,
         Mapper mapper, Reducer reducer) {
-    using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
-    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
-        return std::make_unique<std::any>(I(mapper(cf)));
-    });
-    auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
-        return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
-    });
-    return ctx.db.map_reduce0(map_reduce_column_families_locally{init,
-            std::move(wrapped_mapper), wrapped_reducer}, std::make_unique<std::any>(init), wrapped_reducer).then([] (std::unique_ptr<std::any> res) {
-        return std::any_cast<I>(std::move(*res));
-    });
+    return ctx.db.map_reduce0([mapper, init, reducer](database& db) {
+        auto res = init;
+        for (auto i : db.get_column_families()) {
+            res = reducer(res, mapper(*i.second.get()));
+        }
+        return res;
+    }, init, reducer);
 }
 
 
@@ -111,9 +92,9 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t column_family_stats::*f);
+        int64_t column_family::stats::*f);
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t column_family_stats::*f);
+        int64_t column_family::stats::*f);
 
 }

api/commitlog.cc

@@ -20,18 +20,17 @@
  */
 
 #include "commitlog.hh"
-#include "db/commitlog/commitlog.hh"
+#include <db/commitlog/commitlog.hh>
 #include "api/api-doc/commitlog.json.hh"
-#include "database.hh"
 #include <vector>
 
 namespace api {
 
-template<typename T>
-static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
-    typedef T ret_type;
+template<typename Func>
+static auto acquire_cl_metric(http_context& ctx, Func&& func) {
+    typedef std::result_of_t<Func(db::commitlog *)> ret_type;
 
-    return ctx.db.map_reduce0([func = std::move(func)](database& db) {
+    return ctx.db.map_reduce0([func = std::forward<Func>(func)](database& db) {
         if (db.commitlog() == nullptr) {
             return make_ready_future<ret_type>();
         }
@@ -64,15 +63,15 @@ void set_commitlog(http_context& ctx, routes& r) {
     });
 
     httpd::commitlog_json::get_completed_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
+        return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
     });
 
     httpd::commitlog_json::get_pending_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
+        return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
     });
 
     httpd::commitlog_json::get_total_commit_log_size.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
+        return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
     });
 }
 

api/compaction_manager.cc

@@ -24,7 +24,6 @@
 #include "api/api-doc/compaction_manager.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
-#include <utility>
 
 namespace api {
 
@@ -39,16 +38,6 @@ static future<json::json_return_type> get_cm_stats(http_context& ctx,
         return make_ready_future<json::json_return_type>(res);
     });
 }
-static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash> sum_pending_tasks(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>&& a,
-        const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& b) {
-    for (auto&& i : b) {
-        if (i.second) {
-            a[i.first] += i.second;
-        }
-    }
-    return std::move(a);
-}
-
 
 void set_compaction_manager(http_context& ctx, routes& r) {
     cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -58,8 +47,8 @@ void set_compaction_manager(http_context& ctx, routes& r) {
 
             for (const auto& c : cm.get_compactions()) {
                 cm::summary s;
-                s.ks = c->ks_name;
-                s.cf = c->cf_name;
+                s.ks = c->ks;
+                s.cf = c->cf;
                 s.unit = "keys";
                 s.task_type = sstables::compaction_name(c->type);
                 s.completed = c->total_keys_written;
@@ -72,32 +61,6 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         });
     });
 
-    cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([&ctx](database& db) {
-            return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&ctx, &db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
-                return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
-                    table& cf = *i.second.get();
-                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
-                    return make_ready_future<>();
-                }).then([&tasks] {
-                    return std::move(tasks);
-                });
-            });
-        }, std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), sum_pending_tasks).then(
-                [](const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& task_map) {
-            std::vector<cm::pending_compaction> res;
-            res.reserve(task_map.size());
-            for (auto i : task_map) {
-                cm::pending_compaction task;
-                task.ks = i.first.first;
-                task.cf = i.first.second;
-                task.task = i.second;
-                res.emplace_back(std::move(task));
-            }
-            return make_ready_future<json::json_return_type>(res);
-        });
-    });
-
     cm::force_user_defined_compaction.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         // FIXME
@@ -140,37 +103,29 @@ void set_compaction_manager(http_context& ctx, routes& r) {
     });
 
     cm::get_compaction_history.set(r, [] (std::unique_ptr<request> req) {
-        std::function<future<>(output_stream<char>&&)> f = [](output_stream<char>&& s) {
-            return do_with(output_stream<char>(std::move(s)), true, [] (output_stream<char>& s, bool& first){
-                return s.write("[").then([&s, &first] {
-                    return db::system_keyspace::get_compaction_history([&s, &first](const db::system_keyspace::compaction_history_entry& entry) mutable {
-                        cm::history h;
-                        h.id = entry.id.to_sstring();
-                        h.ks = std::move(entry.ks);
-                        h.cf = std::move(entry.cf);
-                        h.compacted_at = entry.compacted_at;
-                        h.bytes_in = entry.bytes_in;
-                        h.bytes_out =  entry.bytes_out;
-                        for (auto it : entry.rows_merged) {
-                            httpd::compaction_manager_json::row_merged e;
-                            e.key = it.first;
-                            e.value = it.second;
-                            h.rows_merged.push(std::move(e));
-                        }
-                        auto fut = first ? make_ready_future<>() : s.write(", ");
-                        first = false;
-                        return fut.then([&s, h = std::move(h)] {
-                            return formatter::write(s, h);
-                        });
-                    }).then([&s] {
-                        return s.write("]").then([&s] {
-                            return s.close();
-                        });
-                    });
-                });
-            });
-        };
-        return make_ready_future<json::json_return_type>(std::move(f));
+        return db::system_keyspace::get_compaction_history().then([] (std::vector<db::system_keyspace::compaction_history_entry> history) {
+            std::vector<cm::history> res;
+            res.reserve(history.size());
+
+            for (auto& entry : history) {
+                cm::history h;
+                h.id = entry.id.to_sstring();
+                h.ks = std::move(entry.ks);
+                h.cf = std::move(entry.cf);
+                h.compacted_at = entry.compacted_at;
+                h.bytes_in = entry.bytes_in;
+                h.bytes_out =  entry.bytes_out;
+                for (auto it : entry.rows_merged) {
+                    httpd::compaction_manager_json::row_merged e;
+                    e.key = it.first;
+                    e.value = it.second;
+                    h.rows_merged.push(std::move(e));
+                }
+                res.push_back(std::move(h));
+            }
+
+            return make_ready_future<json::json_return_type>(res);
+        });
     });
 
     cm::get_compaction_info.set(r, [] (std::unique_ptr<request> req) {

api/config.cc

@@ -1,119 +0,0 @@
-/*
- * Copyright 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "api/config.hh"
-#include "api/api-doc/config.json.hh"
-#include "db/config.hh"
-#include "database.hh"
-#include <sstream>
-#include <boost/algorithm/string/replace.hpp>
-
-namespace api {
-
-template<class T>
-json::json_return_type get_json_return_type(const T& val) {
-    return json::json_return_type(val);
-}
-
-/*
- * As commented on db::seed_provider_type is not used
- * and probably never will.
- *
- * Just in case, we will return its name
- */
-template<>
-json::json_return_type get_json_return_type(const db::seed_provider_type& val) {
-    return json::json_return_type(val.class_name);
-}
-
-std::string_view format_type(std::string_view type) {
-    if (type == "int") {
-        return "integer";
-    }
-    return type;
-}
-
-future<> get_config_swagger_entry(std::string_view name, const std::string& description, std::string_view type, bool& first, output_stream<char>& os) {
-    std::stringstream ss;
-    if (first) {
-        first=false;
-    } else {
-        ss <<',';
-    };
-    ss << "\"/config/" << name <<"\": {"
-      "\"get\": {"
-        "\"description\": \"" << boost::replace_all_copy(boost::replace_all_copy(boost::replace_all_copy(description,"\n","\\n"),"\"", "''"), "\t", " ") <<"\","
-        "\"operationId\": \"find_config_"<< name <<"\","
-        "\"produces\": ["
-          "\"application/json\""
-        "],"
-        "\"tags\": [\"config\"],"
-        "\"parameters\": ["
-        "],"
-        "\"responses\": {"
-          "\"200\": {"
-            "\"description\": \"Config value\","
-             "\"schema\": {"
-               "\"type\": \"" << format_type(type) << "\""
-             "}"
-          "},"
-          "\"default\": {"
-            "\"description\": \"unexpected error\","
-            "\"schema\": {"
-              "\"$ref\": \"#/definitions/ErrorModel\""
-            "}"
-          "}"
-        "}"
-      "}"
-    "}";
-    return os.write(ss.str());
-}
-
-namespace cs = httpd::config_json;
-
-void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
-    rb->register_function(r, [&ctx] (output_stream<char>& os) {
-        return do_with(true, [&os, &ctx] (bool& first) {
-            auto f = make_ready_future();
-            for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
-                auto&& cfg = cfg_ref.get();
-                f = f.then([&os, &first, &cfg] {
-                    return get_config_swagger_entry(cfg.name(), std::string(cfg.desc()), cfg.type_name(), first, os);
-                });
-            }
-            return f;
-        });
-    });
-
-    cs::find_config_id.set(r, [&ctx] (const_req r) {
-        auto id = r.param["id"];
-        for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
-            auto&& cfg = cfg_ref.get();
-            if (id == cfg.name()) {
-                return cfg.value_as_json();
-            }
-        }
-        throw bad_param_exception(sstring("No such config entry: ") + id);
-    });
-}
-
-}
-

api/error_injection.cc

@@ -1,69 +0,0 @@
-/*
- * Copyright (C) 2020 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "api/api-doc/error_injection.json.hh"
-#include "api/api.hh"
-
-#include <seastar/http/exception.hh>
-#include "log.hh"
-#include "utils/error_injection.hh"
-#include "seastar/core/future-util.hh"
-
-namespace api {
-
-namespace hf = httpd::error_injection_json;
-
-void set_error_injection(http_context& ctx, routes& r) {
-
-    hf::enable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->param["injection"];
-        bool one_shot = req->get_query_param("one_shot") == "True";
-        auto& errinj = utils::get_local_injector();
-        return errinj.enable_on_all(injection, one_shot).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-    hf::get_enabled_injections_on_all.set(r, [](std::unique_ptr<request> req) {
-        auto& errinj = utils::get_local_injector();
-        auto ret = errinj.enabled_injections_on_all();
-        return make_ready_future<json::json_return_type>(ret);
-    });
-
-    hf::disable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->param["injection"];
-
-        auto& errinj = utils::get_local_injector();
-        return errinj.disable_on_all(injection).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-    hf::disable_on_all.set(r, [](std::unique_ptr<request> req) {
-        auto& errinj = utils::get_local_injector();
-        return errinj.disable_on_all().then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-}
-
-} // namespace api

api/gossiper.cc

@@ -21,7 +21,7 @@
 
 #include "gossiper.hh"
 #include "api/api-doc/gossiper.json.hh"
-#include "gms/gossiper.hh"
+#include <gms/gossiper.hh>
 
 namespace api {
 using namespace json;

api/lsa.cc

@@ -23,7 +23,7 @@
 #include "api/lsa.hh"
 #include "api/api.hh"
 
-#include <seastar/http/exception.hh>
+#include "http/exception.hh"
 #include "utils/logalloc.hh"
 #include "log.hh"
 

api/messaging_service.cc

@@ -21,7 +21,7 @@
 
 #include "messaging_service.hh"
 #include "message/messaging_service.hh"
-#include <seastar/rpc/rpc_types.hh>
+#include "rpc/rpc_types.hh"
 #include "api/api-doc/messaging_service.json.hh"
 #include <iostream>
 #include <sstream>
@@ -53,8 +53,8 @@ std::vector<message_counter> map_to_message_counters(
  * according to a function that it gets as a parameter.
  *
  */
-future_json_function get_client_getter(sharded<netw::messaging_service>& ms, std::function<uint64_t(const shard_info&)> f) {
-    return [&ms, f](std::unique_ptr<request> req) {
+future_json_function get_client_getter(std::function<uint64_t(const shard_info&)> f) {
+    return [f](std::unique_ptr<request> req) {
         using map_type = std::unordered_map<gms::inet_address, uint64_t>;
         auto get_shard_map = [f](messaging_service& ms) {
             std::unordered_map<gms::inet_address, unsigned long> map;
@@ -63,70 +63,70 @@ future_json_function get_client_getter(sharded<netw::messaging_service>& ms, std
             });
             return map;
         };
-        return ms.map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
+        return  get_messaging_service().map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
                 then([](map_type&& map) {
             return make_ready_future<json::json_return_type>(map_to_message_counters(map));
         });
     };
 }
 
-future_json_function get_server_getter(sharded<netw::messaging_service>& ms, std::function<uint64_t(const rpc::stats&)> f) {
-    return [&ms, f](std::unique_ptr<request> req) {
+future_json_function get_server_getter(std::function<uint64_t(const rpc::stats&)> f) {
+    return [f](std::unique_ptr<request> req) {
         using map_type = std::unordered_map<gms::inet_address, uint64_t>;
         auto get_shard_map = [f](messaging_service& ms) {
             std::unordered_map<gms::inet_address, unsigned long> map;
             ms.foreach_server_connection_stats([&map, f] (const rpc::client_info& info, const rpc::stats& stats) mutable {
-                map[gms::inet_address(info.addr.addr())] = f(stats);
+                map[gms::inet_address(net::ipv4_address(info.addr))] = f(stats);
             });
             return map;
         };
-        return ms.map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
+        return  get_messaging_service().map_reduce0(get_shard_map, map_type(), map_sum<map_type>).
                 then([](map_type&& map) {
             return make_ready_future<json::json_return_type>(map_to_message_counters(map));
         });
     };
 }
 
-void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms) {
-    get_timeout_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
+void set_messaging_service(http_context& ctx, routes& r) {
+    get_timeout_messages.set(r, get_client_getter([](const shard_info& c) {
         return c.get_stats().timeout;
     }));
 
-    get_sent_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
+    get_sent_messages.set(r, get_client_getter([](const shard_info& c) {
         return c.get_stats().sent_messages;
     }));
 
-    get_dropped_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
+    get_dropped_messages.set(r, get_client_getter([](const shard_info& c) {
         // We don't have the same drop message mechanism
         // as origin has.
         // hence we can always return 0
         return 0;
     }));
 
-    get_exception_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
+    get_exception_messages.set(r, get_client_getter([](const shard_info& c) {
         return c.get_stats().exception_received;
     }));
 
-    get_pending_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
+    get_pending_messages.set(r, get_client_getter([](const shard_info& c) {
         return c.get_stats().pending;
     }));
 
-    get_respond_pending_messages.set(r, get_server_getter(ms, [](const rpc::stats& c) {
+    get_respond_pending_messages.set(r, get_server_getter([](const rpc::stats& c) {
         return c.pending;
     }));
 
-    get_respond_completed_messages.set(r, get_server_getter(ms, [](const rpc::stats& c) {
+    get_respond_completed_messages.set(r, get_server_getter([](const rpc::stats& c) {
         return c.sent_messages;
     }));
 
-    get_version.set(r, [&ms](const_req req) {
-        return ms.local().get_raw_version(req.get_query_param("addr"));
+    get_version.set(r, [](const_req req) {
+        return netw::get_local_messaging_service().get_raw_version(req.get_query_param("addr"));
     });
 
-    get_dropped_messages_by_ver.set(r, [&ms](std::unique_ptr<request> req) {
+    get_dropped_messages_by_ver.set(r, [](std::unique_ptr<request> req) {
         shared_ptr<std::vector<uint64_t>> map = make_shared<std::vector<uint64_t>>(num_verb);
 
-        return ms.map_reduce([map](const uint64_t* local_map) mutable {
+        return netw::get_messaging_service().map_reduce([map](const uint64_t* local_map) mutable {
             for (auto i = 0; i < num_verb; i++) {
                 (*map)[i]+= local_map[i];
             }
@@ -139,7 +139,7 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
                 messaging_verb v = i; // for type safety we use messaging_verb values
                 auto idx = static_cast<uint32_t>(v);
                 if (idx >= map->size()) {
-                    throw std::runtime_error(format("verb index out of bounds: {:d}, map size: {:d}", idx, map->size()));
+                    throw std::runtime_error(sprint("verb index out of bounds: %lu, map size: %lu", idx, map->size()));
                 }
                 if ((*map)[idx] > 0) {
                     c.count = (*map)[idx];
@@ -151,18 +151,5 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
         });
     });
 }
-
-void unset_messaging_service(http_context& ctx, routes& r) {
-    get_timeout_messages.unset(r);
-    get_sent_messages.unset(r);
-    get_dropped_messages.unset(r);
-    get_exception_messages.unset(r);
-    get_pending_messages.unset(r);
-    get_respond_pending_messages.unset(r);
-    get_respond_completed_messages.unset(r);
-    get_version.unset(r);
-    get_dropped_messages_by_ver.unset(r);
-}
-
 }
 

api/messaging_service.hh

@@ -23,11 +23,8 @@
 
 #include "api.hh"
 
-namespace netw { class messaging_service; }
-
 namespace api {
 
-void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
-void unset_messaging_service(http_context& ctx, routes& r);
+void set_messaging_service(http_context& ctx, routes& r);
 
 }

api/storage_proxy.cc

@@ -26,8 +26,6 @@
 #include "service/storage_service.hh"
 #include "db/config.hh"
 #include "utils/histogram.hh"
-#include "database.hh"
-#include "seastar/core/scheduling_specific.hh"
 
 namespace api {
 
@@ -35,70 +33,12 @@ namespace sp = httpd::storage_proxy_json;
 using proxy = service::storage_proxy;
 using namespace json;
 
-
-/**
- * This function implement a two dimentional map reduce where
- * the first level is a distributed storage_proxy class and the
- * second level is the stats per scheduling group class.
- * @param d -  a reference to the storage_proxy distributed class.
- * @param mapper -  the internal mapper that is used to map the internal
- * stat class into a value of type `V`.
- * @param reducer - the reducer that is used in both outer and inner
- * aggregations.
- * @param initial_value - the initial value to use for both aggregations
- * @return A future that resolves to the result of the aggregation.
- */
-template<typename V, typename Reducer, typename InnerMapper>
-future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
-        InnerMapper mapper, Reducer reducer, V initial_value) {
-    return d.map_reduce0( [mapper, reducer, initial_value] (const service::storage_proxy& sp) {
-        return map_reduce_scheduling_group_specific<service::storage_proxy_stats::stats>(
-                mapper, reducer, initial_value, sp.get_stats_key());
-    }, initial_value, reducer);
+static future<utils::rate_moving_average>  sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
+    return d.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average(),
+            std::plus<utils::rate_moving_average>());
 }
 
-/**
- * This function implement a two dimentional map reduce where
- * the first level is a distributed storage_proxy class and the
- * second level is the stats per scheduling group class.
- * @param d -  a reference to the storage_proxy distributed class.
- * @param f - a field pointer which is the implicit internal reducer.
- * @param reducer - the reducer that is used in both outer and inner
- * aggregations.
- * @param initial_value - the initial value to use for both aggregations* @return
- * @return A future that resolves to the result of the aggregation.
- */
-template<typename V, typename Reducer, typename F>
-future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
-        V F::*f, Reducer reducer, V initial_value) {
-    return two_dimensional_map_reduce(d, [f] (F& stats) {
-        return stats.*f;
-    }, reducer, initial_value);
-}
-
-/**
- * A partial Specialization of sum_stats for the storage proxy
- * case where the get stats function doesn't return a
- * stats object with fields but a per scheduling group
- * stats object, the name was also changed since functions
- * partial specialization is not supported in C++.
- *
- */
-template<typename V, typename F>
-future<json::json_return_type>  sum_stats_storage_proxy(distributed<proxy>& d, V F::*f) {
-    return two_dimensional_map_reduce(d, [f] (F& stats) { return stats.*f; }, std::plus<V>(), V(0)).then([] (V val) {
-        return make_ready_future<json::json_return_type>(val);
-    });
-}
-
-
-static future<utils::rate_moving_average>  sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
-    return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
-        return (stats.*f).rate();
-    }, std::plus<utils::rate_moving_average>(), utils::rate_moving_average());
-}
-
-static future<json::json_return_type>  sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
+static future<json::json_return_type>  sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
     return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
         httpd::utils_json::rate_moving_average m;
         m = val;
@@ -106,93 +46,29 @@ static future<json::json_return_type>  sum_timed_rate_as_obj(distributed<proxy>&
     });
 }
 
-httpd::utils_json::rate_moving_average_and_histogram get_empty_moving_average() {
-    return timer_to_json(utils::rate_moving_average_and_histogram());
-}
-
-static future<json::json_return_type>  sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
+static future<json::json_return_type>  sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
     return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
         return make_ready_future<json::json_return_type>(val.count);
     });
 }
 
-utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val) {
-    utils_json::estimated_histogram res;
-    for (size_t i = 0; i < val.size(); i++) {
-        res.buckets.push(val.get(i));
-        res.bucket_offsets.push(val.get_bucket_lower_limit(i));
-    }
-    return res;
-}
-
-static future<json::json_return_type>  sum_estimated_histogram(http_context& ctx, utils::time_estimated_histogram service::storage_proxy_stats::stats::*f) {
-
-    return two_dimensional_map_reduce(ctx.sp, f, utils::time_estimated_histogram_merge,
-            utils::time_estimated_histogram()).then([](const utils::time_estimated_histogram& val) {
-        return make_ready_future<json::json_return_type>(time_to_json_histogram(val));
-    });
-}
-
-static future<json::json_return_type>  sum_estimated_histogram(http_context& ctx, utils::estimated_histogram service::storage_proxy_stats::stats::*f) {
-
-    return two_dimensional_map_reduce(ctx.sp, f, utils::estimated_histogram_merge,
-            utils::estimated_histogram()).then([](const utils::estimated_histogram& val) {
+static future<json::json_return_type>  sum_estimated_histogram(http_context& ctx, utils::estimated_histogram proxy::stats::*f) {
+    return ctx.sp.map_reduce0([f](const proxy& p) {return p.get_stats().*f;}, utils::estimated_histogram(),
+            utils::estimated_histogram_merge).then([](const utils::estimated_histogram& val) {
         utils_json::estimated_histogram res;
         res = val;
         return make_ready_future<json::json_return_type>(res);
     });
 }
 
-static future<json::json_return_type>  total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram service::storage_proxy_stats::stats::*f) {
-    return two_dimensional_map_reduce(ctx.sp, [f] (service::storage_proxy_stats::stats& stats) {
-            return (stats.*f).hist.mean * (stats.*f).hist.count;
-        }, std::plus<double>(), 0.0).then([](double val) {
+static future<json::json_return_type>  total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram proxy::stats::*f) {
+    return ctx.sp.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).hist.mean * (p.get_stats().*f).hist.count;}, 0.0,
+            std::plus<double>()).then([](double val) {
         int64_t res = val;
         return make_ready_future<json::json_return_type>(res);
     });
 }
 
-/**
- * A partial Specialization of sum_histogram_stats
- * for the storage proxy case where the get stats
- * function doesn't return a stats object with
- * fields but a per scheduling group stats object,
- * the name was also changed since function partial
- * specialization is not supported in C++.
- */
-template<typename F>
-future<json::json_return_type>
-sum_histogram_stats_storage_proxy(distributed<proxy>& d,
-        utils::timed_rate_moving_average_and_histogram F::*f) {
-    return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
-        return (stats.*f).hist;
-    }, std::plus<utils::ihistogram>(), utils::ihistogram()).
-            then([](const utils::ihistogram& val) {
-        return make_ready_future<json::json_return_type>(to_json(val));
-    });
-}
-
-/**
- * A partial Specialization of sum_timer_stats for the
- * storage proxy case where the get stats function
- * doesn't return a stats object with fields but a
- * per scheduling group stats object, the name
- * was also changed since partial function specialization
- * is not supported in C++.
- */
-template<typename F>
-future<json::json_return_type>
-sum_timer_stats_storage_proxy(distributed<proxy>& d,
-        utils::timed_rate_moving_average_and_histogram F::*f) {
-
-    return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
-        return (stats.*f).rate();
-    }, std::plus<utils::rate_moving_average_and_histogram>(),
-            utils::rate_moving_average_and_histogram()).then([](const utils::rate_moving_average_and_histogram& val) {
-        return make_ready_future<json::json_return_type>(timer_to_json(val));
-    });
-}
-
 void set_storage_proxy(http_context& ctx, routes& r) {
     sp::get_total_hints.set(r, [](std::unique_ptr<request> req)  {
         //TBD
@@ -200,9 +76,12 @@ void set_storage_proxy(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_hinted_handoff_enabled.set(r, [&ctx](std::unique_ptr<request> req)  {
-        auto enabled = ctx.db.local().get_config().hinted_handoff_enabled();
-        return make_ready_future<json::json_return_type>(enabled);
+    sp::get_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req)  {
+        //TBD
+        // FIXME
+        // hinted handoff is not supported currently,
+        // so we should return false
+        return make_ready_future<json::json_return_type>(false);
     });
 
     sp::set_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req)  {
@@ -342,15 +221,15 @@ void set_storage_proxy(http_context& ctx, routes& r) {
     });
 
     sp::get_read_repair_attempted.set(r, [&ctx](std::unique_ptr<request> req)  {
-        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_attempts);
+        return sum_stats(ctx.sp, &proxy::stats::read_repair_attempts);
     });
 
     sp::get_read_repair_repaired_blocking.set(r, [&ctx](std::unique_ptr<request> req)  {
-        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_blocking);
+        return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_blocking);
     });
 
     sp::get_read_repair_repaired_background.set(r, [&ctx](std::unique_ptr<request> req)  {
-        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
+        return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_background);
     });
 
     sp::get_schema_versions.set(r, [](std::unique_ptr<request> req)  {
@@ -366,154 +245,163 @@ void set_storage_proxy(http_context& ctx, routes& r) {
         });
     });
 
-    sp::get_cas_read_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_timeouts);
+    sp::get_cas_read_timeouts.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return 0
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_read_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_unavailables);
+    sp::get_cas_read_unavailables.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return 0
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_timeouts);
+    sp::get_cas_write_timeouts.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return 0
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_unavailables);
+    sp::get_cas_write_unavailables.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return 0
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_stats(ctx.sp, &proxy::stats::cas_write_unfinished_commit);
+    sp::get_cas_write_metrics_unfinished_commit.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_estimated_histogram(ctx, &proxy::stats::cas_write_contention);
+    sp::get_cas_write_metrics_contention.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_metrics_condition_not_met.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_stats(ctx.sp, &proxy::stats::cas_write_condition_not_met);
+    sp::get_cas_write_metrics_condition_not_met.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_write_metrics_failed_read_round_optimization.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_stats(ctx.sp, &proxy::stats::cas_failed_read_round_optimization);
+    sp::get_cas_read_metrics_unfinished_commit.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_read_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_stats(ctx.sp, &proxy::stats::cas_read_unfinished_commit);
+    sp::get_cas_read_metrics_contention.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_cas_read_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_estimated_histogram(ctx, &proxy::stats::cas_read_contention);
+    sp::get_cas_read_metrics_condition_not_met.set(r, [](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(0);
     });
 
     sp::get_read_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_timeouts);
     });
 
     sp::get_read_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_unavailables);
     });
 
     sp::get_range_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_timeouts);
     });
 
     sp::get_range_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_unavailables);
     });
 
     sp::get_write_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_timeouts);
     });
 
     sp::get_write_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_unavailables);
     });
 
     sp::get_read_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_timeouts);
     });
 
     sp::get_read_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_unavailables);
     });
 
     sp::get_range_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_timeouts);
     });
 
     sp::get_range_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_unavailables);
     });
 
     sp::get_write_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_timeouts);
     });
 
     sp::get_write_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
+        return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_unavailables);
     });
 
     sp::get_range_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
+        return sum_histogram_stats(ctx.sp, &proxy::stats::range);
     });
 
     sp::get_write_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
+        return sum_histogram_stats(ctx.sp, &proxy::stats::write);
     });
 
     sp::get_read_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
+        return sum_histogram_stats(ctx.sp, &proxy::stats::read);
     });
 
     sp::get_range_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
+        return sum_timer_stats(ctx.sp, &proxy::stats::range);
     });
 
     sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
-    });
-    sp::get_cas_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats(ctx.sp, &proxy::stats::cas_write);
-    });
-
-    sp::get_cas_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats(ctx.sp, &proxy::stats::cas_read);
-    });
-
-    sp::get_view_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        //TBD
-        // FIXME
-        // No View metrics are available, so just return empty moving average
-
-        return make_ready_future<json::json_return_type>(get_empty_moving_average());
+        return sum_timer_stats(ctx.sp, &proxy::stats::write);
     });
 
     sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
+        return sum_timer_stats(ctx.sp, &proxy::stats::read);
     });
 
     sp::get_read_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_read);
+        return sum_estimated_histogram(ctx, &proxy::stats::estimated_read);
     });
 
     sp::get_read_latency.set(r, [&ctx](std::unique_ptr<request> req) {
-        return total_latency(ctx, &service::storage_proxy_stats::stats::read);
+        return total_latency(ctx, &proxy::stats::read);
     });
     sp::get_write_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_write);
+        return sum_estimated_histogram(ctx, &proxy::stats::estimated_write);
     });
 
     sp::get_write_latency.set(r, [&ctx](std::unique_ptr<request> req) {
-        return total_latency(ctx, &service::storage_proxy_stats::stats::write);
+        return total_latency(ctx, &proxy::stats::write);
     });
 
     sp::get_range_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
+        return sum_timer_stats(ctx.sp, &proxy::stats::range);
     });
 
     sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {
-        return total_latency(ctx, &service::storage_proxy_stats::stats::range);
+        return total_latency(ctx, &proxy::stats::range);
     });
 }
 

api/storage_service.cc

@@ -22,28 +22,19 @@
 #include "storage_service.hh"
 #include "api/api-doc/storage_service.json.hh"
 #include "db/config.hh"
-#include <optional>
-#include <time.h>
 #include <boost/range/adaptor/map.hpp>
 #include <boost/range/adaptor/filtered.hpp>
-#include "service/storage_service.hh"
-#include "service/load_meter.hh"
-#include "db/commitlog/commitlog.hh"
-#include "gms/gossiper.hh"
-#include "db/system_keyspace.hh"
-#include "seastar/http/exception.hh"
+#include <service/storage_service.hh>
+#include <db/commitlog/commitlog.hh>
+#include <gms/gossiper.hh>
+#include <db/system_keyspace.hh>
+#include "http/exception.hh"
 #include "repair/repair.hh"
 #include "locator/snitch_base.hh"
 #include "column_family.hh"
 #include "log.hh"
 #include "release.hh"
 #include "sstables/compaction_manager.hh"
-#include "sstables/sstables.hh"
-#include "database.hh"
-#include "db/extensions.hh"
-#include "db/snapshot-ctl.hh"
-#include "transport/controller.hh"
-#include "thrift/controller.hh"
 
 namespace api {
 
@@ -57,195 +48,27 @@ static sstring validate_keyspace(http_context& ctx, const parameters& param) {
     throw bad_param_exception("Keyspace " + param["keyspace"] + " Does not exist");
 }
 
-static ss::token_range token_range_endpoints_to_json(const dht::token_range_endpoints& d) {
-    ss::token_range r;
-    r.start_token = d._start_token;
-    r.end_token = d._end_token;
-    r.endpoints = d._endpoints;
-    r.rpc_endpoints = d._rpc_endpoints;
-    for (auto det : d._endpoint_details) {
-        ss::endpoint_detail ed;
-        ed.host = det._host;
-        ed.datacenter = det._datacenter;
-        if (det._rack != "") {
-            ed.rack = det._rack;
+
+static std::vector<ss::token_range> describe_ring(const sstring& keyspace) {
+    std::vector<ss::token_range> res;
+    for (auto d : service::get_local_storage_service().describe_ring(keyspace)) {
+        ss::token_range r;
+        r.start_token = d._start_token;
+        r.end_token = d._end_token;
+        r.endpoints = d._endpoints;
+        r.rpc_endpoints = d._rpc_endpoints;
+        for (auto det : d._endpoint_details) {
+            ss::endpoint_detail ed;
+            ed.host = det._host;
+            ed.datacenter = det._datacenter;
+            if (det._rack != "") {
+                ed.rack = det._rack;
+            }
+            r.endpoint_details.push(ed);
         }
-        r.endpoint_details.push(ed);
+        res.push_back(r);
     }
-    return r;
-}
-
-using ks_cf_func = std::function<future<json::json_return_type>(http_context&, std::unique_ptr<request>, sstring, std::vector<sstring>)>;
-
-static auto wrap_ks_cf(http_context &ctx, ks_cf_func f) {
-    return [&ctx, f = std::move(f)](std::unique_ptr<request> req) {
-        auto keyspace = validate_keyspace(ctx, req->param);
-        auto column_families = split_cf(req->get_query_param("cf"));
-        if (column_families.empty()) {
-            column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
-        }
-        return f(ctx, std::move(req), std::move(keyspace), std::move(column_families));
-    };
-}
-
-future<json::json_return_type> set_tables_autocompaction(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
-    if (tables.empty()) {
-        tables = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
-    }
-
-    return service::get_local_storage_service().set_tables_autocompaction(keyspace, tables, enabled).then([]{
-        return make_ready_future<json::json_return_type>(json_void());
-    });
-}
-
-void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl) {
-    ss::start_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
-        return ctl.start_server().then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::stop_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
-        return ctl.stop_server().then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::is_native_transport_running.set(r, [&ctl] (std::unique_ptr<request> req) {
-        return ctl.is_server_running().then([] (bool running) {
-            return make_ready_future<json::json_return_type>(running);
-        });
-    });
-}
-
-void unset_transport_controller(http_context& ctx, routes& r) {
-    ss::start_native_transport.unset(r);
-    ss::stop_native_transport.unset(r);
-    ss::is_native_transport_running.unset(r);
-}
-
-void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl) {
-    ss::stop_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
-        return ctl.stop_server().then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::start_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
-        return ctl.start_server().then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::is_rpc_server_running.set(r, [&ctl] (std::unique_ptr<request> req) {
-        return ctl.is_server_running().then([] (bool running) {
-            return make_ready_future<json::json_return_type>(running);
-        });
-    });
-}
-
-void unset_rpc_controller(http_context& ctx, routes& r) {
-    ss::stop_rpc_server.unset(r);
-    ss::start_rpc_server.unset(r);
-    ss::is_rpc_server_running.unset(r);
-}
-
-void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms) {
-    ss::repair_async.set(r, [&ctx, &ms](std::unique_ptr<request> req) {
-        static std::vector<sstring> options = {"primaryRange", "parallelism", "incremental",
-                "jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "trace",
-                "startToken", "endToken" };
-        std::unordered_map<sstring, sstring> options_map;
-        for (auto o : options) {
-            auto s = req->get_query_param(o);
-            if (s != "") {
-                options_map[o] = s;
-            }
-        }
-
-        // The repair process is asynchronous: repair_start only starts it and
-        // returns immediately, not waiting for the repair to finish. The user
-        // then has other mechanisms to track the ongoing repair's progress,
-        // or stop it.
-        return repair_start(ctx.db, ms, validate_keyspace(ctx, req->param),
-                options_map).then([] (int i) {
-                    return make_ready_future<json::json_return_type>(i);
-                });
-    });
-
-    ss::get_active_repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
-        return get_active_repairs(ctx.db).then([] (std::vector<int> res){
-            return make_ready_future<json::json_return_type>(res);
-        });
-    });
-
-    ss::repair_async_status.set(r, [&ctx](std::unique_ptr<request> req) {
-        return repair_get_status(ctx.db, boost::lexical_cast<int>( req->get_query_param("id")))
-                .then_wrapped([] (future<repair_status>&& fut) {
-            ss::ns_repair_async_status::return_type_wrapper res;
-            try {
-                res = fut.get0();
-            } catch(std::runtime_error& e) {
-                throw httpd::bad_param_exception(e.what());
-            }
-            return make_ready_future<json::json_return_type>(json::json_return_type(res));
-        });
-    });
-
-    ss::repair_await_completion.set(r, [&ctx](std::unique_ptr<request> req) {
-        int id;
-        using clock = std::chrono::steady_clock;
-        clock::time_point expire;
-        try {
-            id = boost::lexical_cast<int>(req->get_query_param("id"));
-            // If timeout is not provided, it means no timeout.
-            sstring s = req->get_query_param("timeout");
-            int64_t timeout = s.empty() ? int64_t(-1) : boost::lexical_cast<int64_t>(s);
-            if (timeout < 0 && timeout != -1) {
-                return make_exception_future<json::json_return_type>(
-                        httpd::bad_param_exception("timeout can only be -1 (means no timeout) or non negative integer"));
-            }
-            if (timeout < 0) {
-                expire = clock::time_point::max();
-            } else {
-                expire = clock::now() + std::chrono::seconds(timeout);
-            }
-        } catch (std::exception& e) {
-            return make_exception_future<json::json_return_type>(httpd::bad_param_exception(e.what()));
-        }
-        return repair_await_completion(ctx.db, id, expire)
-                .then_wrapped([] (future<repair_status>&& fut) {
-            ss::ns_repair_async_status::return_type_wrapper res;
-            try {
-                res = fut.get0();
-            } catch (std::exception& e) {
-                return make_exception_future<json::json_return_type>(httpd::server_error_exception(e.what()));
-            }
-            return make_ready_future<json::json_return_type>(json::json_return_type(res));
-        });
-    });
-
-    ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
-        return repair_abort_all(service::get_local_storage_service().db()).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
-        return repair_abort_all(service::get_local_storage_service().db()).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-}
-
-void unset_repair(http_context& ctx, routes& r) {
-    ss::repair_async.unset(r);
-    ss::get_active_repair_async.unset(r);
-    ss::repair_async_status.unset(r);
-    ss::repair_await_completion.unset(r);
-    ss::force_terminate_all_repair_sessions.unset(r);
-    ss::force_terminate_all_repair_sessions_new.unset(r);
+    return res;
 }
 
 void set_storage_service(http_context& ctx, routes& r) {
@@ -255,43 +78,42 @@ void set_storage_service(http_context& ctx, routes& r) {
         });
     });
 
-    ss::get_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().sorted_tokens(), [](const dht::token& i) {
-           return boost::lexical_cast<std::string>(i);
-        }));
+    ss::get_tokens.set(r, [] (const_req req) {
+        auto tokens = service::get_local_storage_service().get_token_metadata().sorted_tokens();
+        return container_to_vec(tokens);
     });
 
-    ss::get_node_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
-        gms::inet_address addr(req->param["endpoint"]);
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().get_tokens(addr), [](const dht::token& i) {
-           return boost::lexical_cast<std::string>(i);
-       }));
+    ss::get_node_tokens.set(r, [] (const_req req) {
+        gms::inet_address addr(req.param["endpoint"]);
+        auto tokens = service::get_local_storage_service().get_token_metadata().get_tokens(addr);
+        return container_to_vec(tokens);
     });
 
     ss::get_commitlog.set(r, [&ctx](const_req req) {
         return ctx.db.local().commitlog()->active_config().commit_log_location;
     });
 
-    ss::get_token_endpoint.set(r, [] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_to_endpoint_map(), [](const auto& i) {
-            storage_service_json::mapper val;
-            val.key = boost::lexical_cast<std::string>(i.first);
-            val.value = boost::lexical_cast<std::string>(i.second);
-            return val;
-        }));
+    ss::get_token_endpoint.set(r, [] (const_req req) {
+        auto token_to_ep = service::get_local_storage_service().get_token_to_endpoint_map();
+        std::vector<storage_service_json::mapper> res;
+        return map_to_key_value(token_to_ep, res);
     });
 
-    ss::get_leaving_nodes.set(r, [&ctx](const_req req) {
-        return container_to_vec(ctx.token_metadata.local().get_leaving_endpoints());
+    ss::get_leaving_nodes.set(r, [](const_req req) {
+        return container_to_vec(service::get_local_storage_service().get_token_metadata().get_leaving_endpoints());
     });
 
     ss::get_moving_nodes.set(r, [](const_req req) {
+        auto points = service::get_local_storage_service().get_token_metadata().get_moving_endpoints();
         std::unordered_set<sstring> addr;
+        for (auto i: points) {
+            addr.insert(boost::lexical_cast<std::string>(i.second));
+        }
         return container_to_vec(addr);
     });
 
-    ss::get_joining_nodes.set(r, [&ctx](const_req req) {
-        auto points = ctx.token_metadata.local().get_bootstrap_tokens();
+    ss::get_joining_nodes.set(r, [](const_req req) {
+        auto points = service::get_local_storage_service().get_token_metadata().get_bootstrap_tokens();
         std::unordered_set<sstring> addr;
         for (auto i: points) {
             addr.insert(boost::lexical_cast<std::string>(i.second));
@@ -319,26 +141,11 @@ void set_storage_service(http_context& ctx, routes& r) {
     });
 
     ss::get_range_to_endpoint_map.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
         auto keyspace = validate_keyspace(ctx, req->param);
         std::vector<ss::maplist_mapper> res;
-        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_range_to_address_map(keyspace),
-                [](const std::pair<dht::token_range, std::vector<gms::inet_address>>& entry){
-            ss::maplist_mapper m;
-            if (entry.first.start()) {
-                m.key.push(entry.first.start().value().value().to_sstring());
-            } else {
-                m.key.push("");
-            }
-            if (entry.first.end()) {
-                m.key.push(entry.first.end().value().value().to_sstring());
-            } else {
-                m.key.push("");
-            }
-            for (const gms::inet_address& address : entry.second) {
-                m.value.push(address.to_sstring());
-            }
-            return m;
-        }));
+        return make_ready_future<json::json_return_type>(res);
     });
 
     ss::get_pending_range_to_endpoint_map.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -349,26 +156,27 @@ void set_storage_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(res);
     });
 
-    ss::describe_any_ring.set(r, [&ctx](std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(""), token_range_endpoints_to_json));
+    ss::describe_any_ring.set(r, [&ctx](const_req req) {
+        return describe_ring("");
     });
 
-    ss::describe_ring.set(r, [&ctx](std::unique_ptr<request> req) {
-        auto keyspace = validate_keyspace(ctx, req->param);
-        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(keyspace), token_range_endpoints_to_json));
+    ss::describe_ring.set(r, [&ctx](const_req req) {
+        auto keyspace = validate_keyspace(ctx, req.param);
+        return describe_ring(keyspace);
     });
 
-    ss::get_host_id_map.set(r, [&ctx](const_req req) {
+    ss::get_host_id_map.set(r, [](const_req req) {
         std::vector<ss::mapper> res;
-        return map_to_key_value(ctx.token_metadata.local().get_endpoint_to_host_id_map_for_reading(), res);
+        return map_to_key_value(service::get_local_storage_service().
+                get_token_metadata().get_endpoint_to_host_id_map_for_reading(), res);
     });
 
     ss::get_load.set(r, [&ctx](std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &column_family_stats::live_disk_space_used);
+        return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
     });
 
-    ss::get_load_map.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.lmeter.get_load_map().then([] (auto&& load_map) {
+    ss::get_load_map.set(r, [] (std::unique_ptr<request> req) {
+        return service::get_local_storage_service().get_load_map().then([] (auto&& load_map) {
             std::vector<ss::map_string_double> res;
             for (auto i : load_map) {
                 ss::map_string_double val;
@@ -393,12 +201,64 @@ void set_storage_service(http_context& ctx, routes& r) {
                 req.get_query_param("key")));
     });
 
-    ss::cdc_streams_check_and_repair.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return service::get_local_storage_service().check_and_repair_cdc_streams().then([] {
+    ss::get_snapshot_details.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().get_snapshot_details().then([] (auto result) {
+            std::vector<ss::snapshots> res;
+            for (auto& map: result) {
+                ss::snapshots all_snapshots;
+                all_snapshots.key = map.first;
+
+                std::vector<ss::snapshot> snapshot;
+                for (auto& cf: map.second) {
+                    ss::snapshot s;
+                    s.ks = cf.ks;
+                    s.cf = cf.cf;
+                    s.live = cf.live;
+                    s.total = cf.total;
+                    snapshot.push_back(std::move(s));
+                }
+                all_snapshots.value = std::move(snapshot);
+                res.push_back(std::move(all_snapshots));
+            }
+            return make_ready_future<json::json_return_type>(std::move(res));
+        });
+    });
+
+    ss::take_snapshot.set(r, [](std::unique_ptr<request> req) {
+        auto tag = req->get_query_param("tag");
+        auto column_family = req->get_query_param("cf");
+
+        std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
+
+        auto resp = make_ready_future<>();
+        if (column_family.empty()) {
+            resp = service::get_local_storage_service().take_snapshot(tag, keynames);
+        } else {
+            if (keynames.size() > 1) {
+                throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
+            }
+            resp = service::get_local_storage_service().take_column_family_snapshot(keynames[0], column_family, tag);
+        }
+        return resp.then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
+    ss::del_snapshot.set(r, [](std::unique_ptr<request> req) {
+        auto tag = req->get_query_param("tag");
+
+        std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
+        return service::get_local_storage_service().clear_snapshot(tag, keynames).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::true_snapshots_size.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().true_snapshots_size().then([] (int64_t size) {
+            return make_ready_future<json::json_return_type>(size);
+        });
+    });
+
     ss::force_keyspace_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
         auto column_families = split_cf(req->get_query_param("cf"));
@@ -424,40 +284,38 @@ void set_storage_service(http_context& ctx, routes& r) {
         if (column_families.empty()) {
             column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
         }
-        return service::get_local_storage_service().is_cleanup_allowed(keyspace).then([&ctx, keyspace,
-                column_families = std::move(column_families)] (bool is_cleanup_allowed) mutable {
-            if (!is_cleanup_allowed) {
-                return make_exception_future<json::json_return_type>(
-                        std::runtime_error("Can not perform cleanup operation when topology changes"));
+        return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
+            std::vector<column_family*> column_families_vec;
+            auto& cm = db.get_compaction_manager();
+            for (auto cf : column_families) {
+                column_families_vec.push_back(&db.find_column_family(keyspace, cf));
             }
-            return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
-                std::vector<column_family*> column_families_vec;
-                auto& cm = db.get_compaction_manager();
-                for (auto cf : column_families) {
-                    column_families_vec.push_back(&db.find_column_family(keyspace, cf));
-                }
-                return parallel_for_each(column_families_vec, [&cm, &db] (column_family* cf) {
-                    return cm.perform_cleanup(db, cf);
-                });
-            }).then([]{
-                return make_ready_future<json::json_return_type>(0);
-            });
-        });
-    });
-
-    ss::upgrade_sstables.set(r, wrap_ks_cf(ctx, [] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
-        bool exclude_current_version = req_param<bool>(*req, "exclude_current_version", false);
-
-        return ctx.db.invoke_on_all([=] (database& db) {
-            return do_for_each(column_families, [=, &db](sstring cfname) {
-                auto& cm = db.get_compaction_manager();
-                auto& cf = db.find_column_family(keyspace, cfname);
-                return cm.perform_sstable_upgrade(db, &cf, exclude_current_version);
+            return parallel_for_each(column_families_vec, [&cm] (column_family* cf) {
+                return cm.perform_cleanup(cf);
             });
         }).then([]{
             return make_ready_future<json::json_return_type>(0);
         });
-    }));
+    });
+
+    ss::scrub.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        auto keyspace = validate_keyspace(ctx, req->param);
+        auto column_family = req->get_query_param("cf");
+        auto disable_snapshot = req->get_query_param("disable_snapshot");
+        auto skip_corrupted = req->get_query_param("skip_corrupted");
+        return make_ready_future<json::json_return_type>(json_void());
+    });
+
+    ss::upgrade_sstables.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
+        auto keyspace = validate_keyspace(ctx, req->param);
+        auto column_family = req->get_query_param("cf");
+        auto exclude_current_version = req->get_query_param("exclude_current_version");
+        return make_ready_future<json::json_return_type>(json_void());
+    });
 
     ss::force_keyspace_flush.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
@@ -475,6 +333,53 @@ void set_storage_service(http_context& ctx, routes& r) {
     });
 
 
+    ss::repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
+        static std::vector<sstring> options = {"primaryRange", "parallelism", "incremental",
+                "jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "trace",
+                "startToken", "endToken" };
+        std::unordered_map<sstring, sstring> options_map;
+        for (auto o : options) {
+            auto s = req->get_query_param(o);
+            if (s != "") {
+                options_map[o] = s;
+            }
+        }
+
+        // The repair process is asynchronous: repair_start only starts it and
+        // returns immediately, not waiting for the repair to finish. The user
+        // then has other mechanisms to track the ongoing repair's progress,
+        // or stop it.
+        return repair_start(ctx.db, validate_keyspace(ctx, req->param),
+                options_map).then([] (int i) {
+                    return make_ready_future<json::json_return_type>(i);
+                });
+    });
+
+    ss::repair_async_status.set(r, [&ctx](std::unique_ptr<request> req) {
+        return repair_get_status(ctx.db, boost::lexical_cast<int>( req->get_query_param("id")))
+                .then_wrapped([] (future<repair_status>&& fut) {
+            ss::ns_repair_async_status::return_type_wrapper res;
+            try {
+                res = fut.get0();
+            } catch(std::runtime_error& e) {
+                throw httpd::bad_param_exception(e.what());
+            }
+            return make_ready_future<json::json_return_type>(json::json_return_type(res));
+        });
+    });
+
+    ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
+        return repair_abort_all(service::get_local_storage_service().db()).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
+        return repair_abort_all(service::get_local_storage_service().db()).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
     ss::decommission.set(r, [](std::unique_ptr<request> req) {
         return service::get_local_storage_service().decommission().then([] {
             return make_ready_future<json::json_return_type>(json_void());
@@ -542,7 +447,7 @@ void set_storage_service(http_context& ctx, routes& r) {
         return service::get_storage_service().map_reduce(adder<service::storage_service::drain_progress>(), [] (auto& ss) {
             return ss.get_drain_progress();
         }).then([] (auto&& progress) {
-            auto progress_str = format("Drained {}/{} ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
+            auto progress_str = sprint("Drained %s/%s ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
             return make_ready_future<json::json_return_type>(std::move(progress_str));
         });
     });
@@ -610,8 +515,46 @@ void set_storage_service(http_context& ctx, routes& r) {
         });
     });
 
+    ss::stop_rpc_server.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().stop_rpc_server().then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::start_rpc_server.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().start_rpc_server().then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::is_rpc_server_running.set(r, [] (std::unique_ptr<request> req) {
+        return service::get_local_storage_service().is_rpc_server_running().then([] (bool running) {
+            return make_ready_future<json::json_return_type>(running);
+        });
+    });
+
+    ss::start_native_transport.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().start_native_transport().then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::stop_native_transport.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().stop_native_transport().then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
+    ss::is_native_transport_running.set(r, [] (std::unique_ptr<request> req) {
+        return service::get_local_storage_service().is_native_transport_running().then([] (bool running) {
+            return make_ready_future<json::json_return_type>(running);
+        });
+    });
+
     ss::join_ring.set(r, [](std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(json_void());
+        return service::get_local_storage_service().join_ring().then([] {
+            return make_ready_future<json::json_return_type>(json_void());
+        });
     });
 
     ss::is_joined.set(r, [] (std::unique_ptr<request> req) {
@@ -715,11 +658,7 @@ void set_storage_service(http_context& ctx, routes& r) {
         auto coordinator = std::hash<sstring>()(cf) % smp::count;
         return service::get_storage_service().invoke_on(coordinator, [ks = std::move(ks), cf = std::move(cf)] (service::storage_service& s) {
             return s.load_new_sstables(ks, cf);
-        }).then_wrapped([] (auto&& f) {
-            if (f.failed()) {
-                auto msg = fmt::format("Failed to load new sstables: {}", f.get_exception());
-                return make_exception_future<json::json_return_type>(httpd::server_error_exception(msg));
-            }
+        }).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -739,7 +678,7 @@ void set_storage_service(http_context& ctx, routes& r) {
 
     ss::set_trace_probability.set(r, [](std::unique_ptr<request> req) {
         auto probability = req->get_query_param("probability");
-        return futurize_invoke([probability] {
+        return futurize<json::json_return_type>::apply([probability] {
             double real_prob = std::stod(probability.c_str());
             return tracing::tracing::tracing_instance().invoke_on_all([real_prob] (auto& local_tracing) {
                 local_tracing.set_trace_probability(real_prob);
@@ -753,7 +692,7 @@ void set_storage_service(http_context& ctx, routes& r) {
             } catch (std::out_of_range& e) {
                 throw httpd::bad_param_exception(e.what());
             } catch (std::invalid_argument&){
-                throw httpd::bad_param_exception(format("Bad format in a probability value: \"{}\"", probability.c_str()));
+                throw httpd::bad_param_exception(sprint("Bad format in a probability value: \"%s\"", probability.c_str()));
             }
         });
     });
@@ -789,22 +728,24 @@ void set_storage_service(http_context& ctx, routes& r) {
                 return make_ready_future<json::json_return_type>(json_void());
             });
         } catch (...) {
-            throw httpd::bad_param_exception(format("Bad format value: "));
+            throw httpd::bad_param_exception(sprint("Bad format value: "));
         }
     });
 
     ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
         auto keyspace = validate_keyspace(ctx, req->param);
-        auto tables = split_cf(req->get_query_param("cf"));
-
-        return set_tables_autocompaction(ctx, keyspace, tables, true);
+        auto column_family = req->get_query_param("cf");
+        return make_ready_future<json::json_return_type>(json_void());
     });
 
     ss::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        unimplemented();
         auto keyspace = validate_keyspace(ctx, req->param);
-        auto tables = split_cf(req->get_query_param("cf"));
-
-        return set_tables_autocompaction(ctx, keyspace, tables, false);
+        auto column_family = req->get_query_param("cf");
+        return make_ready_future<json::json_return_type>(json_void());
     });
 
     ss::deliver_hints.set(r, [](std::unique_ptr<request> req) {
@@ -869,7 +810,7 @@ void set_storage_service(http_context& ctx, routes& r) {
     });
 
     ss::get_metrics_load.set(r, [&ctx](std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &column_family_stats::live_disk_space_used);
+        return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
     });
 
     ss::get_exceptions.set(r, [](const_req req) {
@@ -902,252 +843,6 @@ void set_storage_service(http_context& ctx, routes& r) {
             return make_ready_future<json::json_return_type>(map_to_key_value(ownership, res));
         });
     });
-
-    ss::view_build_statuses.set(r, [&ctx] (std::unique_ptr<request> req) {
-        auto keyspace = validate_keyspace(ctx, req->param);
-        auto view = req->param["view"];
-        return service::get_local_storage_service().view_build_statuses(std::move(keyspace), std::move(view)).then([] (std::unordered_map<sstring, sstring> status) {
-            std::vector<storage_service_json::mapper> res;
-            return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
-        });
-    });
-
-    ss::sstable_info.set(r, [&ctx] (std::unique_ptr<request> req) {
-        auto ks = api::req_param<sstring>(*req, "keyspace", {}).value;
-        auto cf = api::req_param<sstring>(*req, "cf", {}).value;
-
-        // The size of this vector is bound by ks::cf. I.e. it is as most Nks + Ncf long
-        // which is not small, but not huge either. 
-        using table_sstables_list = std::vector<ss::table_sstables>;
-
-        return do_with(table_sstables_list{}, [ks, cf, &ctx](table_sstables_list& dst) {
-            return service::get_local_storage_service().db().map_reduce([&dst](table_sstables_list&& res) {
-                for (auto&& t : res) {
-                    auto i = std::find_if(dst.begin(), dst.end(), [&t](const ss::table_sstables& t2) {
-                        return t.keyspace() == t2.keyspace() && t.table() == t2.table();
-                    });
-                    if (i == dst.end()) {
-                        dst.emplace_back(std::move(t));
-                        continue;
-                    }
-                    auto& ssd = i->sstables; 
-                    for (auto&& sd : t.sstables._elements) {
-                        auto j = std::find_if(ssd._elements.begin(), ssd._elements.end(), [&sd](const ss::sstable& s) {
-                            return s.generation() == sd.generation();
-                        });
-                        if (j == ssd._elements.end()) {
-                            i->sstables.push(std::move(sd));
-                        }
-                    }
-                }
-            }, [ks, cf](const database& db) {
-                // see above
-                table_sstables_list res;
-
-                auto& ext = db.get_config().extensions();
-
-                for (auto& t : db.get_column_families() | boost::adaptors::map_values) {
-                    auto& schema = t->schema();
-                    if ((ks.empty() || ks == schema->ks_name()) && (cf.empty() || cf == schema->cf_name())) {
-                        // at most Nsstables long
-                        ss::table_sstables tst;
-                        tst.keyspace = schema->ks_name();
-                        tst.table = schema->cf_name();
-
-                        for (auto sstable : *t->get_sstables_including_compacted_undeleted()) {
-                            auto ts = db_clock::to_time_t(sstable->data_file_write_time());
-                            ::tm t;
-                            ::gmtime_r(&ts, &t);
-
-                            ss::sstable info;
-
-                            info.timestamp = t;
-                            info.generation = sstable->generation();
-                            info.level = sstable->get_sstable_level();
-                            info.size = sstable->bytes_on_disk();
-                            info.data_size = sstable->ondisk_data_size();
-                            info.index_size = sstable->index_size();
-                            info.filter_size = sstable->filter_size();
-                            info.version = sstable->get_version();
-
-                            if (sstable->has_component(sstables::component_type::CompressionInfo)) {
-                                auto& c = sstable->get_compression();
-                                auto cp = sstables::get_sstable_compressor(c);
-
-                                ss::named_maps nm;
-                                nm.group = "compression_parameters";
-                                for (auto& p : cp->options()) {
-                                    ss::mapper e;
-                                    e.key = p.first;
-                                    e.value = p.second;
-                                    nm.attributes.push(std::move(e));
-                                }
-                                if (!cp->options().contains(compression_parameters::SSTABLE_COMPRESSION)) {
-                                    ss::mapper e;
-                                    e.key = compression_parameters::SSTABLE_COMPRESSION;
-                                    e.value = cp->name();
-                                    nm.attributes.push(std::move(e));
-                                }
-                                info.extended_properties.push(std::move(nm));
-                            }
-
-                            sstables::file_io_extension::attr_value_map map;
-
-                            for (auto* ep : ext.sstable_file_io_extensions()) {
-                                map.merge(ep->get_attributes(*sstable));
-                            }
-
-                            for (auto& p : map) {
-                                struct {
-                                    const sstring& key; 
-                                    ss::sstable& info;
-                                    void operator()(const std::map<sstring, sstring>& map) const {
-                                        ss::named_maps nm;
-                                        nm.group = key;
-                                        for (auto& p : map) {
-                                            ss::mapper e;
-                                            e.key = p.first;
-                                            e.value = p.second;
-                                            nm.attributes.push(std::move(e));
-                                        }
-                                        info.extended_properties.push(std::move(nm));
-                                    }
-                                    void operator()(const sstring& value) const {
-                                        ss::mapper e;
-                                        e.key = key;
-                                        e.value = value;
-                                        info.properties.push(std::move(e));                                        
-                                    }
-                                } v{p.first, info};
-
-                                std::visit(v, p.second);
-                            }
-
-                            tst.sstables.push(std::move(info));
-                        }
-                        res.emplace_back(std::move(tst));
-                    }
-                }
-                std::sort(res.begin(), res.end(), [](const ss::table_sstables& t1, const ss::table_sstables& t2) {
-                    return t1.keyspace() < t2.keyspace() || (t1.keyspace() == t2.keyspace() && t1.table() < t2.table());
-                });
-                return res;
-            }).then([&dst] {
-                return make_ready_future<json::json_return_type>(stream_object(dst));
-            });
-        });
-    });
-
-}
-
-void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl) {
-    ss::get_snapshot_details.set(r, [&snap_ctl](std::unique_ptr<request> req) {
-        return snap_ctl.local().get_snapshot_details().then([] (std::unordered_map<sstring, std::vector<db::snapshot_ctl::snapshot_details>>&& result) {
-            std::function<future<>(output_stream<char>&&)> f = [result = std::move(result)](output_stream<char>&& s) {
-                return do_with(output_stream<char>(std::move(s)), true, [&result] (output_stream<char>& s, bool& first){
-                    return s.write("[").then([&s, &first, &result] {
-                        return do_for_each(result, [&s, &first](std::tuple<sstring, std::vector<db::snapshot_ctl::snapshot_details>>&& map){
-                            return do_with(ss::snapshots(), [&s, &first, &map](ss::snapshots& all_snapshots) {
-                                all_snapshots.key = std::get<0>(map);
-                                future<> f = first ? make_ready_future<>() : s.write(", ");
-                                first = false;
-                                std::vector<ss::snapshot> snapshot;
-                                for (auto& cf: std::get<1>(map)) {
-                                    ss::snapshot snp;
-                                    snp.ks = cf.ks;
-                                    snp.cf = cf.cf;
-                                    snp.live = cf.live;
-                                    snp.total = cf.total;
-                                    snapshot.push_back(std::move(snp));
-                                }
-                                all_snapshots.value = std::move(snapshot);
-                                return f.then([&s, &all_snapshots] {
-                                    return all_snapshots.write(s);
-                                });
-                            });
-                        });
-                    }).then([&s] {
-                        return s.write("]").then([&s] {
-                            return s.close();
-                        });
-                    });
-                });
-            };
-
-            return make_ready_future<json::json_return_type>(std::move(f));
-        });
-    });
-
-    ss::take_snapshot.set(r, [&snap_ctl](std::unique_ptr<request> req) {
-        auto tag = req->get_query_param("tag");
-        auto column_families = split(req->get_query_param("cf"), ",");
-
-        std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
-
-        auto resp = make_ready_future<>();
-        if (column_families.empty()) {
-            resp = snap_ctl.local().take_snapshot(tag, keynames);
-        } else {
-            if (keynames.empty()) {
-                throw httpd::bad_param_exception("The keyspace of column families must be specified");
-            }
-            if (keynames.size() > 1) {
-                throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
-            }
-            resp = snap_ctl.local().take_column_family_snapshot(keynames[0], column_families, tag);
-        }
-        return resp.then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::del_snapshot.set(r, [&snap_ctl](std::unique_ptr<request> req) {
-        auto tag = req->get_query_param("tag");
-        auto column_family = req->get_query_param("cf");
-
-        std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
-        return snap_ctl.local().clear_snapshot(tag, keynames, column_family).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    ss::true_snapshots_size.set(r, [&snap_ctl](std::unique_ptr<request> req) {
-        return snap_ctl.local().true_snapshots_size().then([] (int64_t size) {
-            return make_ready_future<json::json_return_type>(size);
-        });
-    });
-
-    ss::scrub.set(r, wrap_ks_cf(ctx, [&snap_ctl] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
-        const auto skip_corrupted = req_param<bool>(*req, "skip_corrupted", false);
-
-        auto f = make_ready_future<>();
-        if (!req_param<bool>(*req, "disable_snapshot", false)) {
-            auto tag = format("pre-scrub-{:d}", db_clock::now().time_since_epoch().count());
-            f = parallel_for_each(column_families, [&snap_ctl, keyspace, tag](sstring cf) {
-                return snap_ctl.local().take_column_family_snapshot(keyspace, cf, tag);
-            });
-        }
-
-        return f.then([&ctx, keyspace, column_families, skip_corrupted] {
-            return ctx.db.invoke_on_all([=] (database& db) {
-                return do_for_each(column_families, [=, &db](sstring cfname) {
-                    auto& cm = db.get_compaction_manager();
-                    auto& cf = db.find_column_family(keyspace, cfname);
-                    return cm.perform_sstable_scrub(&cf, skip_corrupted);
-                });
-            });
-        }).then([]{
-            return make_ready_future<json::json_return_type>(0);
-        });
-    }));
-}
-
-void unset_snapshot(http_context& ctx, routes& r) {
-    ss::get_snapshot_details.unset(r);
-    ss::take_snapshot.unset(r);
-    ss::del_snapshot.unset(r);
-    ss::true_snapshots_size.unset(r);
-    ss::scrub.unset(r);
 }
 
 }

api/storage_service.hh

@@ -21,24 +21,10 @@
 
 #pragma once
 
-#include <seastar/core/sharded.hh>
 #include "api.hh"
 
-namespace cql_transport { class controller; }
-class thrift_controller;
-namespace db { class snapshot_ctl; }
-namespace netw { class messaging_service; }
-
 namespace api {
 
 void set_storage_service(http_context& ctx, routes& r);
-void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
-void unset_repair(http_context& ctx, routes& r);
-void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl);
-void unset_transport_controller(http_context& ctx, routes& r);
-void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl);
-void unset_rpc_controller(http_context& ctx, routes& r);
-void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl);
-void unset_snapshot(http_context& ctx, routes& r);
 
 }

api/system.cc

@@ -22,8 +22,7 @@
 #include "api/api-doc/system.json.hh"
 #include "api/api.hh"
 
-#include <seastar/core/reactor.hh>
-#include <seastar/http/exception.hh>
+#include "http/exception.hh"
 #include "log.hh"
 
 namespace api {
@@ -31,10 +30,6 @@ namespace api {
 namespace hs = httpd::system_json;
 
 void set_system(http_context& ctx, routes& r) {
-    hs::get_system_uptime.set(r, [](const_req req) {
-        return std::chrono::duration_cast<std::chrono::milliseconds>(engine().uptime()).count();
-    });
-
     hs::get_all_logger_names.set(r, [](const_req req) {
         return logging::logger_registry().get_all_logger_names();
     });

atomic_cell.cc

@@ -1,287 +0,0 @@
-/*
- * Copyright (C) 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "atomic_cell.hh"
-#include "atomic_cell_or_collection.hh"
-#include "counters.hh"
-#include "types.hh"
-
-/// LSA mirator for cells with irrelevant type
-///
-///
-const data::type_imr_descriptor& no_type_imr_descriptor() {
-    static thread_local data::type_imr_descriptor state(data::type_info::make_variable_size());
-    return state;
-}
-
-atomic_cell atomic_cell::make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
-    auto& imr_data = no_type_imr_descriptor();
-    return atomic_cell(
-            imr_data.type_info(),
-            imr_object_type::make(data::cell::make_dead(timestamp, deletion_time), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, atomic_cell::collection_member cm) {
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value, atomic_cell::collection_member cm) {
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value, collection_member cm)
-{
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
-                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
-                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
-                                   gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm)
-{
-    auto& imr_data = type.imr_state();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
-    auto& imr_data = no_type_imr_descriptor();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live_counter_update(timestamp, value), &imr_data.lsa_migrator())
-    );
-}
-
-atomic_cell atomic_cell::make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size) {
-    auto& imr_data = no_type_imr_descriptor();
-    return atomic_cell(
-        imr_data.type_info(),
-        imr_object_type::make(data::cell::make_live_uninitialized(imr_data.type_info(), timestamp, size), &imr_data.lsa_migrator())
-    );
-}
-
-static imr::utils::object<data::cell::structure> copy_cell(const data::type_imr_descriptor& imr_data, const uint8_t* ptr)
-{
-    using imr_object_type = imr::utils::object<data::cell::structure>;
-
-    // If the cell doesn't own any memory it is trivial and can be copied with
-    // memcpy.
-    auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
-    if (!f.template get<data::cell::tags::external_data>()) {
-        data::cell::context ctx(f, imr_data.type_info());
-        // XXX: We may be better off storing the total cell size in memory. Measure!
-        auto size = data::cell::structure::serialized_object_size(ptr, ctx);
-        return imr_object_type::make_raw(size, [&] (uint8_t* dst) noexcept {
-            std::copy_n(ptr, size, dst);
-        }, &imr_data.lsa_migrator());
-    }
-
-    return imr_object_type::make(data::cell::copy_fn(imr_data.type_info(), ptr), &imr_data.lsa_migrator());
-}
-
-atomic_cell::atomic_cell(const abstract_type& type, atomic_cell_view other)
-    : atomic_cell(type.imr_state().type_info(),
-                  copy_cell(type.imr_state(), other._view.raw_pointer()))
-{ }
-
-atomic_cell_or_collection atomic_cell_or_collection::copy(const abstract_type& type) const {
-    if (!_data.get()) {
-        return atomic_cell_or_collection();
-    }
-    auto& imr_data = type.imr_state();
-    return atomic_cell_or_collection(
-        copy_cell(imr_data, _data.get())
-    );
-}
-
-atomic_cell_or_collection::atomic_cell_or_collection(const abstract_type& type, atomic_cell_view acv)
-    : _data(copy_cell(type.imr_state(), acv._view.raw_pointer()))
-{
-}
-
-bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_cell_or_collection& other) const
-{
-    auto ptr_a = _data.get();
-    auto ptr_b = other._data.get();
-
-    if (!ptr_a || !ptr_b) {
-        return !ptr_a && !ptr_b;
-    }
-
-    if (type.is_atomic()) {
-        auto a = atomic_cell_view::from_bytes(type.imr_state().type_info(), _data);
-        auto b = atomic_cell_view::from_bytes(type.imr_state().type_info(), other._data);
-        if (a.timestamp() != b.timestamp()) {
-            return false;
-        }
-        if (a.is_live() != b.is_live()) {
-            return false;
-        }
-        if (a.is_live()) {
-            if (a.is_counter_update() != b.is_counter_update()) {
-                return false;
-            }
-            if (a.is_counter_update()) {
-                return a.counter_update_value() == b.counter_update_value();
-            }
-            if (a.is_live_and_has_ttl() != b.is_live_and_has_ttl()) {
-                return false;
-            }
-            if (a.is_live_and_has_ttl()) {
-                if (a.ttl() != b.ttl() || a.expiry() != b.expiry()) {
-                    return false;
-                }
-            }
-            return a.value() == b.value();
-        }
-        return a.deletion_time() == b.deletion_time();
-    } else {
-        return as_collection_mutation().data == other.as_collection_mutation().data;
-    }
-}
-
-size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t) const
-{
-    if (!_data.get()) {
-        return 0;
-    }
-    auto ctx = data::cell::context(_data.get(), t.imr_state().type_info());
-
-    auto view = data::cell::structure::make_view(_data.get(), ctx);
-    auto flags = view.get<data::cell::tags::flags>();
-
-    size_t external_value_size = 0;
-    if (flags.get<data::cell::tags::external_data>()) {
-        if (flags.get<data::cell::tags::collection>()) {
-            external_value_size = as_collection_mutation().data.size_bytes();
-        } else {
-            auto cell_view = data::cell::atomic_cell_view(t.imr_state().type_info(), view);
-            external_value_size = cell_view.value_size();
-        }
-        // Add overhead of chunk headers. The last one is a special case.
-        external_value_size += (external_value_size - 1) / data::cell::effective_external_chunk_length * data::cell::external_chunk_overhead;
-        external_value_size += data::cell::external_last_chunk_overhead;
-    }
-    return data::cell::structure::serialized_object_size(_data.get(), ctx)
-        + imr_object_type::size_overhead + external_value_size;
-}
-
-std::ostream&
-operator<<(std::ostream& os, const atomic_cell_view& acv) {
-    if (acv.is_live()) {
-        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
-            acv.is_counter_update()
-                    ? "counter_update_value=" + to_sstring(acv.counter_update_value())
-                    : to_hex(acv.value().linearize()),
-            acv.timestamp(),
-            acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
-            acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
-    } else {
-        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
-            acv.timestamp(), acv.deletion_time().time_since_epoch().count());
-    }
-}
-
-std::ostream&
-operator<<(std::ostream& os, const atomic_cell& ac) {
-    return os << atomic_cell_view(ac);
-}
-
-std::ostream&
-operator<<(std::ostream& os, const atomic_cell_view::printer& acvp) {
-    auto& type = acvp._type;
-    auto& acv = acvp._cell;
-    if (acv.is_live()) {
-        std::ostringstream cell_value_string_builder;
-        if (type.is_counter()) {
-            if (acv.is_counter_update()) {
-                cell_value_string_builder << "counter_update_value=" << acv.counter_update_value();
-            } else {
-                cell_value_string_builder << "shards: ";
-                counter_cell_view::with_linearized(acv, [&cell_value_string_builder] (counter_cell_view& ccv) {
-                    cell_value_string_builder << ::join(", ", ccv.shards());
-                });
-            }
-        } else {
-            cell_value_string_builder << type.to_string(acv.value().linearize());
-        }
-        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
-            cell_value_string_builder.str(),
-            acv.timestamp(),
-            acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
-            acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
-    } else {
-        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
-            acv.timestamp(), acv.deletion_time().time_since_epoch().count());
-    }
-}
-
-std::ostream&
-operator<<(std::ostream& os, const atomic_cell::printer& acp) {
-    return operator<<(os, static_cast<const atomic_cell_view::printer&>(acp));
-}
-
-std::ostream& operator<<(std::ostream& os, const atomic_cell_or_collection::printer& p) {
-    if (!p._cell._data.get()) {
-        return os << "{ null atomic_cell_or_collection }";
-    }
-    using dc = data::cell;
-    os << "{ ";
-    if (dc::structure::get_member<dc::tags::flags>(p._cell._data.get()).get<dc::tags::collection>()) {
-        os << "collection ";
-        auto cmv = p._cell.as_collection_mutation();
-        os << collection_mutation_view::printer(*p._cdef.type, cmv);
-    } else {
-        os << atomic_cell_view::printer(*p._cdef.type, p._cell.as_atomic_cell(p._cdef));
-    }
-    return os << " }";
-}

atomic_cell.hh

@@ -26,55 +26,204 @@
 #include "tombstone.hh"
 #include "gc_clock.hh"
 #include "utils/managed_bytes.hh"
-#include <seastar/net//byteorder.hh>
+#include "net/byteorder.hh"
 #include <cstdint>
 #include <iosfwd>
-#include "data/cell.hh"
-#include "data/schema_info.hh"
-#include "imr/utils.hh"
-#include "utils/fragmented_temporary_buffer.hh"
+#include <seastar/util/gcc6-concepts.hh>
 
-#include "serializer.hh"
+template<typename T, typename Input>
+static inline
+void set_field(Input& v, unsigned offset, T val) {
+    reinterpret_cast<net::packed<T>*>(v.begin() + offset)->raw = net::hton(val);
+}
+
+template<typename T>
+static inline
+T get_field(const bytes_view& v, unsigned offset) {
+    return net::ntoh(*reinterpret_cast<const net::packed<T>*>(v.begin() + offset));
+}
 
-class abstract_type;
-class collection_type_impl;
 class atomic_cell_or_collection;
 
-using atomic_cell_value_view = data::value_view;
-using atomic_cell_value_mutable_view = data::value_mutable_view;
-
-/// View of an atomic cell
-template<mutable_view is_mutable>
-class basic_atomic_cell_view {
-protected:
-    data::cell::basic_atomic_cell_view<is_mutable> _view;
-    friend class atomic_cell;
+/*
+ * Represents atomic cell layout. Works on serialized form.
+ *
+ * Layout:
+ *
+ *  <live>  := <int8_t:flags><int64_t:timestamp>(<int32_t:expiry><int32_t:ttl>)?<value>
+ *  <dead>  := <int8_t:    0><int64_t:timestamp><int32_t:deletion_time>
+ */
+class atomic_cell_type final {
+private:
+    static constexpr int8_t LIVE_FLAG = 0x01;
+    static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
+    static constexpr int8_t REVERT_FLAG = 0x04; // transient flag used to efficiently implement ReversiblyMergeable for atomic cells.
+    static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
+    static constexpr int8_t COUNTER_IN_PLACE_REVERT = 0x10;
+    static constexpr unsigned flags_size = 1;
+    static constexpr unsigned timestamp_offset = flags_size;
+    static constexpr unsigned timestamp_size = 8;
+    static constexpr unsigned expiry_offset = timestamp_offset + timestamp_size;
+    static constexpr unsigned expiry_size = 4;
+    static constexpr unsigned deletion_time_offset = timestamp_offset + timestamp_size;
+    static constexpr unsigned deletion_time_size = 4;
+    static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
+    static constexpr unsigned ttl_size = 4;
+    friend class counter_cell_builder;
+private:
+    static bool is_counter_update(bytes_view cell) {
+        return cell[0] & COUNTER_UPDATE_FLAG;
+    }
+    static bool is_revert_set(bytes_view cell) {
+        return cell[0] & REVERT_FLAG;
+    }
+    static bool is_counter_in_place_revert_set(bytes_view cell) {
+        return cell[0] & COUNTER_IN_PLACE_REVERT;
+    }
+    template<typename BytesContainer>
+    static void set_revert(BytesContainer& cell, bool revert) {
+        cell[0] = (cell[0] & ~REVERT_FLAG) | (revert * REVERT_FLAG);
+    }
+    template<typename BytesContainer>
+    static void set_counter_in_place_revert(BytesContainer& cell, bool flag) {
+        cell[0] = (cell[0] & ~COUNTER_IN_PLACE_REVERT) | (flag * COUNTER_IN_PLACE_REVERT);
+    }
+    static bool is_live(const bytes_view& cell) {
+        return cell[0] & LIVE_FLAG;
+    }
+    static bool is_live_and_has_ttl(const bytes_view& cell) {
+        return cell[0] & EXPIRY_FLAG;
+    }
+    static bool is_dead(const bytes_view& cell) {
+        return !is_live(cell);
+    }
+    // Can be called on live and dead cells
+    static api::timestamp_type timestamp(const bytes_view& cell) {
+        return get_field<api::timestamp_type>(cell, timestamp_offset);
+    }
+    template<typename BytesContainer>
+    static void set_timestamp(BytesContainer& cell, api::timestamp_type ts) {
+        set_field(cell, timestamp_offset, ts);
+    }
+    // Can be called on live cells only
+private:
+    template<typename BytesView>
+    static BytesView do_get_value(BytesView cell) {
+        auto expiry_field_size = bool(cell[0] & EXPIRY_FLAG) * (expiry_size + ttl_size);
+        auto value_offset = flags_size + timestamp_size + expiry_field_size;
+        cell.remove_prefix(value_offset);
+        return cell;
+    }
 public:
-    using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
+    static bytes_view value(bytes_view cell) {
+        return do_get_value(cell);
+    }
+    static bytes_mutable_view value(bytes_mutable_view cell) {
+        return do_get_value(cell);
+    }
+    // Can be called on live counter update cells only
+    static int64_t counter_update_value(bytes_view cell) {
+        return get_field<int64_t>(cell, flags_size + timestamp_size);
+    }
+    // Can be called only when is_dead() is true.
+    static gc_clock::time_point deletion_time(const bytes_view& cell) {
+        assert(is_dead(cell));
+        return gc_clock::time_point(gc_clock::duration(
+            get_field<int32_t>(cell, deletion_time_offset)));
+    }
+    // Can be called only when is_live_and_has_ttl() is true.
+    static gc_clock::time_point expiry(const bytes_view& cell) {
+        assert(is_live_and_has_ttl(cell));
+        auto expiry = get_field<int32_t>(cell, expiry_offset);
+        return gc_clock::time_point(gc_clock::duration(expiry));
+    }
+    // Can be called only when is_live_and_has_ttl() is true.
+    static gc_clock::duration ttl(const bytes_view& cell) {
+        assert(is_live_and_has_ttl(cell));
+        return gc_clock::duration(get_field<int32_t>(cell, ttl_offset));
+    }
+    static managed_bytes make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
+        managed_bytes b(managed_bytes::initialized_later(), flags_size + timestamp_size + deletion_time_size);
+        b[0] = 0;
+        set_field(b, timestamp_offset, timestamp);
+        set_field(b, deletion_time_offset, deletion_time.time_since_epoch().count());
+        return b;
+    }
+    static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value) {
+        auto value_offset = flags_size + timestamp_size;
+        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
+        b[0] = LIVE_FLAG;
+        set_field(b, timestamp_offset, timestamp);
+        std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
+        return b;
+    }
+    static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
+        auto value_offset = flags_size + timestamp_size;
+        managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
+        b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
+        set_field(b, timestamp_offset, timestamp);
+        set_field(b, value_offset, value);
+        return b;
+    }
+    static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value, gc_clock::time_point expiry, gc_clock::duration ttl) {
+        auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
+        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
+        b[0] = EXPIRY_FLAG | LIVE_FLAG;
+        set_field(b, timestamp_offset, timestamp);
+        set_field(b, expiry_offset, expiry.time_since_epoch().count());
+        set_field(b, ttl_offset, ttl.count());
+        std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
+        return b;
+    }
+    // make_live_from_serializer() is intended for users that need to serialise
+    // some object or objects to the format used in atomic_cell::value().
+    // With just make_live() the patter would look like follows:
+    // 1. allocate a buffer and write to it serialised objects
+    // 2. pass that buffer to make_live()
+    // 3. make_live() needs to prepend some metadata to the cell value so it
+    //    allocates a new buffer and copies the content of the original one
+    //
+    // The allocation and copy of a buffer can be avoided.
+    // make_live_from_serializer() allows the user code to specify the timestamp
+    // and size of the cell value as well as provide the serialiser function
+    // object, which would write the serialised value of the cell to the buffer
+    // given to it by make_live_from_serializer().
+    template<typename Serializer>
+    GCC6_CONCEPT(requires requires(Serializer serializer, bytes::iterator it) {
+        serializer(it);
+    })
+    static managed_bytes make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
+        auto value_offset = flags_size + timestamp_size;
+        managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
+        b[0] = LIVE_FLAG;
+        set_field(b, timestamp_offset, timestamp);
+        serializer(b.begin() + value_offset);
+        return b;
+    }
+    template<typename ByteContainer>
+    friend class atomic_cell_base;
+    friend class atomic_cell;
+};
+
+template<typename ByteContainer>
+class atomic_cell_base {
 protected:
-    explicit basic_atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> v)
-        : _view(std::move(v)) { }
-
-    basic_atomic_cell_view(const data::type_info& ti, pointer_type ptr)
-        : _view(data::cell::make_atomic_cell_view(ti, ptr))
-    { }
-
+    ByteContainer _data;
+protected:
+    atomic_cell_base(ByteContainer&& data) : _data(std::forward<ByteContainer>(data)) { }
     friend class atomic_cell_or_collection;
 public:
-    operator basic_atomic_cell_view<mutable_view::no>() const noexcept {
-        return basic_atomic_cell_view<mutable_view::no>(_view);
-    }
-
-    void swap(basic_atomic_cell_view& other) noexcept {
-        using std::swap;
-        swap(_view, other._view);
-    }
-
     bool is_counter_update() const {
-        return _view.is_counter_update();
+        return atomic_cell_type::is_counter_update(_data);
+    }
+    bool is_revert_set() const {
+        return atomic_cell_type::is_revert_set(_data);
+    }
+    bool is_counter_in_place_revert_set() const {
+        return atomic_cell_type::is_counter_in_place_revert_set(_data);
     }
     bool is_live() const {
-        return _view.is_live();
+        return atomic_cell_type::is_live(_data);
     }
     bool is_live(tombstone t, bool is_counter) const {
         return is_live() && !is_covered_by(t, is_counter);
@@ -83,161 +232,165 @@ public:
         return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
     }
     bool is_live_and_has_ttl() const {
-        return _view.is_expiring();
+        return atomic_cell_type::is_live_and_has_ttl(_data);
     }
     bool is_dead(gc_clock::time_point now) const {
-        return !is_live() || has_expired(now);
+        return atomic_cell_type::is_dead(_data) || has_expired(now);
     }
     bool is_covered_by(tombstone t, bool is_counter) const {
         return timestamp() <= t.timestamp || (is_counter && t.timestamp != api::missing_timestamp);
     }
     // Can be called on live and dead cells
     api::timestamp_type timestamp() const {
-        return _view.timestamp();
+        return atomic_cell_type::timestamp(_data);
     }
     void set_timestamp(api::timestamp_type ts) {
-        _view.set_timestamp(ts);
+        atomic_cell_type::set_timestamp(_data, ts);
     }
     // Can be called on live cells only
-    data::basic_value_view<is_mutable> value() const {
-        return _view.value();
-    }
-    // Can be called on live cells only
-    size_t value_size() const {
-        return _view.value_size();
-    }
-    bool is_value_fragmented() const {
-        return _view.is_value_fragmented();
+    auto value() const {
+        return atomic_cell_type::value(_data);
     }
     // Can be called on live counter update cells only
     int64_t counter_update_value() const {
-        return _view.counter_update_value();
+        return atomic_cell_type::counter_update_value(_data);
     }
     // Can be called only when is_dead(gc_clock::time_point)
     gc_clock::time_point deletion_time() const {
-        return !is_live() ? _view.deletion_time() : expiry() - ttl();
+        return !is_live() ? atomic_cell_type::deletion_time(_data) : expiry() - ttl();
     }
     // Can be called only when is_live_and_has_ttl()
     gc_clock::time_point expiry() const {
-        return _view.expiry();
+        return atomic_cell_type::expiry(_data);
     }
     // Can be called only when is_live_and_has_ttl()
     gc_clock::duration ttl() const {
-        return _view.ttl();
+        return atomic_cell_type::ttl(_data);
     }
     // Can be called on live and dead cells
     bool has_expired(gc_clock::time_point now) const {
         return is_live_and_has_ttl() && expiry() <= now;
     }
-
     bytes_view serialize() const {
-        return _view.serialize();
+        return _data;
+    }
+    void set_revert(bool revert) {
+        atomic_cell_type::set_revert(_data, revert);
+    }
+    void set_counter_in_place_revert(bool flag) {
+        atomic_cell_type::set_counter_in_place_revert(_data, flag);
     }
 };
 
-class atomic_cell_view final : public basic_atomic_cell_view<mutable_view::no> {
-    atomic_cell_view(const data::type_info& ti, const uint8_t* data)
-        : basic_atomic_cell_view<mutable_view::no>(ti, data) {}
-
-    template<mutable_view is_mutable>
-    atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> view)
-        : basic_atomic_cell_view<mutable_view::no>(view) { }
-    friend class atomic_cell;
+class atomic_cell_view final : public atomic_cell_base<bytes_view> {
+    atomic_cell_view(bytes_view data) : atomic_cell_base(std::move(data)) {}
 public:
-    static atomic_cell_view from_bytes(const data::type_info& ti, const imr::utils::object<data::cell::structure>& data) {
-        return atomic_cell_view(ti, data.get());
-    }
-
-    static atomic_cell_view from_bytes(const data::type_info& ti, bytes_view bv) {
-        return atomic_cell_view(ti, reinterpret_cast<const uint8_t*>(bv.begin()));
-    }
+    static atomic_cell_view from_bytes(bytes_view data) { return atomic_cell_view(data); }
 
+    friend class atomic_cell;
     friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
-
-    class printer {
-        const abstract_type& _type;
-        const atomic_cell_view& _cell;
-    public:
-        printer(const abstract_type& type, const atomic_cell_view& cell) : _type(type), _cell(cell) {}
-        friend std::ostream& operator<<(std::ostream& os, const printer& acvp);
-    };
 };
 
-class atomic_cell_mutable_view final : public basic_atomic_cell_view<mutable_view::yes> {
-    atomic_cell_mutable_view(const data::type_info& ti, uint8_t* data)
-        : basic_atomic_cell_view<mutable_view::yes>(ti, data) {}
+class atomic_cell_mutable_view final : public atomic_cell_base<bytes_mutable_view> {
+    atomic_cell_mutable_view(bytes_mutable_view data) : atomic_cell_base(std::move(data)) {}
 public:
-    static atomic_cell_mutable_view from_bytes(const data::type_info& ti, imr::utils::object<data::cell::structure>& data) {
-        return atomic_cell_mutable_view(ti, data.get());
-    }
+    static atomic_cell_mutable_view from_bytes(bytes_mutable_view data) { return atomic_cell_mutable_view(data); }
 
     friend class atomic_cell;
 };
 
-using atomic_cell_ref = atomic_cell_mutable_view;
-
-class atomic_cell final : public basic_atomic_cell_view<mutable_view::yes> {
-    using imr_object_type =  imr::utils::object<data::cell::structure>;
-    imr_object_type _data;
-    atomic_cell(const data::type_info& ti, imr::utils::object<data::cell::structure>&& data)
-        : basic_atomic_cell_view<mutable_view::yes>(ti, data.get()), _data(std::move(data)) {}
+class atomic_cell_ref final : public atomic_cell_base<managed_bytes&> {
 public:
-    class collection_member_tag;
-    using collection_member = bool_class<collection_member_tag>;
+    atomic_cell_ref(managed_bytes& buf) : atomic_cell_base(buf) {}
+};
 
+class atomic_cell final : public atomic_cell_base<managed_bytes> {
+    atomic_cell(managed_bytes b) : atomic_cell_base(std::move(b)) {}
+public:
+    atomic_cell(const atomic_cell&) = default;
     atomic_cell(atomic_cell&&) = default;
-    atomic_cell& operator=(const atomic_cell&) = delete;
+    atomic_cell& operator=(const atomic_cell&) = default;
     atomic_cell& operator=(atomic_cell&&) = default;
-    void swap(atomic_cell& other) noexcept {
-        basic_atomic_cell_view<mutable_view::yes>::swap(other);
-        _data.swap(other._data);
+    static atomic_cell from_bytes(managed_bytes b) {
+        return atomic_cell(std::move(b));
     }
-    operator atomic_cell_view() const { return atomic_cell_view(_view); }
-    atomic_cell(const abstract_type& t, atomic_cell_view other);
-    static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
-                                 collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
-                                 collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
-                                 collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
-                                 collection_member cm = collection_member::no) {
-        return make_live(type, timestamp, bytes_view(value), cm);
+    atomic_cell(atomic_cell_view other) : atomic_cell_base(managed_bytes{other._data}) {}
+    operator atomic_cell_view() const {
+        return atomic_cell_view(_data);
     }
-    static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value);
-    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, bytes_view value,
-        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
-        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
-        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
-                                 gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm = collection_member::no)
+    static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
+        return atomic_cell_type::make_dead(timestamp, deletion_time);
+    }
+    static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value) {
+        return atomic_cell_type::make_live(timestamp, value);
+    }
+    static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value) {
+        return make_live(timestamp, bytes_view(value));
+    }
+    static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
+        return atomic_cell_type::make_live_counter_update(timestamp, value);
+    }
+    static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value,
+        gc_clock::time_point expiry, gc_clock::duration ttl)
     {
-        return make_live(type, timestamp, bytes_view(value), expiry, ttl, cm);
+        return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
     }
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, ttl_opt ttl, collection_member cm = collection_member::no) {
+    static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value,
+                                 gc_clock::time_point expiry, gc_clock::duration ttl)
+    {
+        return make_live(timestamp, bytes_view(value), expiry, ttl);
+    }
+    static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value, ttl_opt ttl) {
         if (!ttl) {
-            return make_live(type, timestamp, value, cm);
+            return atomic_cell_type::make_live(timestamp, value);
         } else {
-            return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
+            return atomic_cell_type::make_live(timestamp, value, gc_clock::now() + *ttl, *ttl);
         }
     }
-    static atomic_cell make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size);
+    template<typename Serializer>
+    static atomic_cell make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
+        return atomic_cell_type::make_live_from_serializer(timestamp, size, std::forward<Serializer>(serializer));
+    }
     friend class atomic_cell_or_collection;
     friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
-
-    class printer : atomic_cell_view::printer {
-    public:
-        printer(const abstract_type& type, const atomic_cell_view& cell) : atomic_cell_view::printer(type, cell) {}
-        friend std::ostream& operator<<(std::ostream& os, const printer& acvp);
-    };
 };
 
+class collection_mutation_view;
+
+// Represents a mutation of a collection.  Actual format is determined by collection type,
+// and is:
+//   set:  list of atomic_cell
+//   map:  list of pair<atomic_cell, bytes> (for key/value)
+//   list: tbd, probably ugly
+class collection_mutation {
+public:
+    managed_bytes data;
+    collection_mutation() {}
+    collection_mutation(managed_bytes b) : data(std::move(b)) {}
+    collection_mutation(collection_mutation_view v);
+    operator collection_mutation_view() const;
+};
+
+class collection_mutation_view {
+public:
+    bytes_view data;
+    bytes_view serialize() const { return data; }
+    static collection_mutation_view from_bytes(bytes_view v) { return { v }; }
+};
+
+inline
+collection_mutation::collection_mutation(collection_mutation_view v)
+        : data(v.data) {
+}
+
+inline
+collection_mutation::operator collection_mutation_view() const {
+    return { data };
+}
+
 class column_definition;
 
 int compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
-void merge_column(const abstract_type& def,
+void merge_column(const column_definition& def,
         atomic_cell_or_collection& old,
         const atomic_cell_or_collection& neww);

atomic_cell_hash.hh

@@ -24,9 +24,7 @@
 // Not part of atomic_cell.hh to avoid cyclic dependency between types.hh and atomic_cell.hh
 
 #include "types.hh"
-#include "types/collection.hh"
 #include "atomic_cell.hh"
-#include "atomic_cell_or_collection.hh"
 #include "hashing.hh"
 #include "counters.hh"
 
@@ -34,13 +32,12 @@ template<>
 struct appending_hash<collection_mutation_view> {
     template<typename Hasher>
     void operator()(Hasher& h, collection_mutation_view cell, const column_definition& cdef) const {
-        cell.with_deserialized(*cdef.type, [&] (collection_mutation_view_description m_view) {
-            ::feed_hash(h, m_view.tomb);
-            for (auto&& key_and_value : m_view.cells) {
-                ::feed_hash(h, key_and_value.first);
-                ::feed_hash(h, key_and_value.second, cdef);
-            }
-      });
+        auto m_view = collection_type_impl::deserialize_mutation_form(cell);
+        ::feed_hash(h, m_view.tomb);
+        for (auto&& key_and_value : m_view.cells) {
+            ::feed_hash(h, key_and_value.first);
+            ::feed_hash(h, key_and_value.second, cdef);
+        }
     }
 };
 
@@ -52,9 +49,7 @@ struct appending_hash<atomic_cell_view> {
         feed_hash(h, cell.timestamp());
         if (cell.is_live()) {
             if (cdef.is_counter()) {
-                counter_cell_view::with_linearized(cell, [&] (counter_cell_view ccv) {
-                    ::feed_hash(h, ccv);
-                });
+                ::feed_hash(h, counter_cell_view(cell));
                 return;
             }
             if (cell.is_live_and_has_ttl()) {
@@ -83,15 +78,3 @@ struct appending_hash<collection_mutation> {
         feed_hash(h, static_cast<collection_mutation_view>(cm), cdef);
     }
 };
-
-template<>
-struct appending_hash<atomic_cell_or_collection> {
-    template<typename Hasher>
-    void operator()(Hasher& h, const atomic_cell_or_collection& c, const column_definition& cdef) const {
-        if (cdef.is_atomic()) {
-            feed_hash(h, c.as_atomic_cell(cdef), cdef);
-        } else {
-            feed_hash(h, c.as_collection_mutation(), cdef);
-        }
-    }
-};

atomic_cell_or_collection.hh

@@ -22,72 +22,53 @@
 #pragma once
 
 #include "atomic_cell.hh"
-#include "collection_mutation.hh"
 #include "schema.hh"
 #include "hashing.hh"
 
-#include "imr/utils.hh"
-
 // A variant type that can hold either an atomic_cell, or a serialized collection.
 // Which type is stored is determined by the schema.
+// Has an "empty" state.
+// Objects moved-from are left in an empty state.
 class atomic_cell_or_collection final {
-    // FIXME: This has made us lose small-buffer optimisation. Unfortunately,
-    // due to the changed cell format it would be less effective now, anyway.
-    // Measure the actual impact because any attempts to fix this will become
-    // irrelevant once rows are converted to the IMR as well, so maybe we can
-    // live with this like that.
-    using imr_object_type = imr::utils::object<data::cell::structure>;
-    imr_object_type _data;
+    managed_bytes _data;
 private:
-    atomic_cell_or_collection(imr::utils::object<data::cell::structure>&& data) : _data(std::move(data)) {}
+    atomic_cell_or_collection(managed_bytes&& data) : _data(std::move(data)) {}
 public:
     atomic_cell_or_collection() = default;
-    atomic_cell_or_collection(atomic_cell_or_collection&&) = default;
-    atomic_cell_or_collection(const atomic_cell_or_collection&) = delete;
-    atomic_cell_or_collection& operator=(atomic_cell_or_collection&&) = default;
-    atomic_cell_or_collection& operator=(const atomic_cell_or_collection&) = delete;
     atomic_cell_or_collection(atomic_cell ac) : _data(std::move(ac._data)) {}
-    atomic_cell_or_collection(const abstract_type& at, atomic_cell_view acv);
     static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
-    atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
-    atomic_cell_ref as_atomic_cell_ref(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
-    atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
-    atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm._data)) { }
-    atomic_cell_or_collection copy(const abstract_type&) const;
+    atomic_cell_view as_atomic_cell() const { return atomic_cell_view::from_bytes(_data); }
+    atomic_cell_ref as_atomic_cell_ref() { return { _data }; }
+    atomic_cell_mutable_view as_mutable_atomic_cell() { return atomic_cell_mutable_view::from_bytes(_data); }
+    atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm.data)) {}
     explicit operator bool() const {
-        return bool(_data);
+        return !_data.empty();
     }
-    static constexpr bool can_use_mutable_view() {
-        return true;
+    bool can_use_mutable_view() const {
+        return !_data.is_fragmented();
     }
-    void swap(atomic_cell_or_collection& other) noexcept {
-        _data.swap(other._data);
+    static atomic_cell_or_collection from_collection_mutation(collection_mutation data) {
+        return std::move(data.data);
     }
-    static atomic_cell_or_collection from_collection_mutation(collection_mutation data) { return std::move(data._data); }
-    collection_mutation_view as_collection_mutation() const;
-    bytes_view serialize() const;
-    bool equals(const abstract_type& type, const atomic_cell_or_collection& other) const;
-    size_t external_memory_usage(const abstract_type&) const;
-
-    class printer {
-        const column_definition& _cdef;
-        const atomic_cell_or_collection& _cell;
-    public:
-        printer(const column_definition& cdef, const atomic_cell_or_collection& cell)
-            : _cdef(cdef), _cell(cell) { }
-        printer(const printer&) = delete;
-        printer(printer&&) = delete;
-
-        friend std::ostream& operator<<(std::ostream&, const printer&);
-    };
-    friend std::ostream& operator<<(std::ostream&, const printer&);
+    collection_mutation_view as_collection_mutation() const {
+        return collection_mutation_view{_data};
+    }
+    bytes_view serialize() const {
+        return _data;
+    }
+    bool operator==(const atomic_cell_or_collection& other) const {
+        return _data == other._data;
+    }
+    template<typename Hasher>
+    void feed_hash(Hasher& h, const column_definition& def) const {
+        if (def.is_atomic()) {
+            ::feed_hash(h, as_atomic_cell(), def);
+        } else {
+            ::feed_hash(h, as_collection_mutation(), def);
+        }
+    }
+    size_t external_memory_usage() const {
+        return _data.external_memory_usage();
+    }
+    friend std::ostream& operator<<(std::ostream&, const atomic_cell_or_collection&);
 };
-
-namespace std {
-
-inline void swap(atomic_cell_or_collection& a, atomic_cell_or_collection& b) noexcept
-{
-    a.swap(b);
-}
-
-}

auth/allow_all_authenticator.cc

@@ -26,7 +26,10 @@
 
 namespace auth {
 
-constexpr std::string_view allow_all_authenticator_name("org.apache.cassandra.auth.AllowAllAuthenticator");
+const sstring& allow_all_authenticator_name() {
+    static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthenticator";
+    return name;
+}
 
 // To ensure correct initialization order, we unfortunately need to use a string literal.
 static const class_registrator<

auth/allow_all_authenticator.hh

@@ -23,8 +23,8 @@
 
 #include <stdexcept>
 
-#include "auth/authenticated_user.hh"
 #include "auth/authenticator.hh"
+#include "auth/authenticated_user.hh"
 #include "auth/common.hh"
 
 namespace cql3 {
@@ -37,63 +37,59 @@ class migration_manager;
 
 namespace auth {
 
-extern const std::string_view allow_all_authenticator_name;
+const sstring& allow_all_authenticator_name();
 
 class allow_all_authenticator final : public authenticator {
 public:
     allow_all_authenticator(cql3::query_processor&, ::service::migration_manager&) {
     }
 
-    virtual future<> start() override {
+    future<> start() override {
         return make_ready_future<>();
     }
 
-    virtual future<> stop() override {
+    future<> stop() override {
         return make_ready_future<>();
     }
 
-    virtual std::string_view qualified_java_name() const override {
-        return allow_all_authenticator_name;
+    const sstring& qualified_java_name() const override {
+        return allow_all_authenticator_name();
     }
 
-    virtual bool require_authentication() const override {
+    bool require_authentication() const override {
         return false;
     }
 
-    virtual authentication_option_set supported_options() const override {
-        return authentication_option_set();
+    option_set supported_options() const override {
+        return option_set();
     }
 
-    virtual authentication_option_set alterable_options() const override {
-        return authentication_option_set();
+    option_set alterable_options() const override {
+        return option_set();
     }
 
-    future<authenticated_user> authenticate(const credentials_map& credentials) const override {
-        return make_ready_future<authenticated_user>(anonymous_user());
+    future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override {
+        return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>());
     }
 
-    virtual future<> create(std::string_view, const authentication_options& options) const override {
+    future<> create(sstring username, const option_map& options) override {
         return make_ready_future();
     }
 
-    virtual future<> alter(std::string_view, const authentication_options& options) const override {
+    future<> alter(sstring username, const option_map& options) override {
         return make_ready_future();
     }
 
-    virtual future<> drop(std::string_view) const override {
+    future<> drop(sstring username) override {
         return make_ready_future();
     }
 
-    virtual future<custom_options> query_custom_options(std::string_view role_name) const override {
-        return make_ready_future<custom_options>();
+    const resource_ids& protected_resources() const override {
+        static const resource_ids ids;
+        return ids;
     }
 
-    virtual const resource_set& protected_resources() const override {
-        static const resource_set resources;
-        return resources;
-    }
-
-    virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
+    ::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
         throw std::runtime_error("Should not reach");
     }
 };

auth/allow_all_authorizer.cc

@@ -26,7 +26,10 @@
 
 namespace auth {
 
-constexpr std::string_view allow_all_authorizer_name("org.apache.cassandra.auth.AllowAllAuthorizer");
+const sstring& allow_all_authorizer_name() {
+    static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthorizer";
+    return name;
+}
 
 // To ensure correct initialization order, we unfortunately need to use a string literal.
 static const class_registrator<

auth/allow_all_authorizer.hh

@@ -21,8 +21,9 @@
 
 #pragma once
 
-#include "auth/authorizer.hh"
+#include "authorizer.hh"
 #include "exceptions/exceptions.hh"
+#include "stdx.hh"
 
 namespace cql3 {
 class query_processor;
@@ -34,58 +35,63 @@ class migration_manager;
 
 namespace auth {
 
-extern const std::string_view allow_all_authorizer_name;
+class service;
+
+const sstring& allow_all_authorizer_name();
 
 class allow_all_authorizer final  : public authorizer {
 public:
     allow_all_authorizer(cql3::query_processor&, ::service::migration_manager&) {
     }
 
-    virtual future<> start() override {
+    future<> start() override {
         return make_ready_future<>();
     }
 
-    virtual future<> stop() override {
+    future<> stop() override {
         return make_ready_future<>();
     }
 
-    virtual std::string_view qualified_java_name() const override {
-        return allow_all_authorizer_name;
+    const sstring& qualified_java_name() const override {
+        return allow_all_authorizer_name();
     }
 
-    virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override {
+    future<permission_set> authorize(service&, ::shared_ptr<authenticated_user>, data_resource) const override {
         return make_ready_future<permission_set>(permissions::ALL);
     }
 
-    virtual future<> grant(std::string_view, permission_set, const resource&) const override {
-        return make_exception_future<>(
-                unsupported_authorization_operation("GRANT operation is not supported by AllowAllAuthorizer"));
+    future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
+        throw exceptions::invalid_request_exception("GRANT operation is not supported by AllowAllAuthorizer");
     }
 
-    virtual future<> revoke(std::string_view, permission_set, const resource&) const override {
-        return make_exception_future<>(
-                unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
+    future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
+        throw exceptions::invalid_request_exception("REVOKE operation is not supported by AllowAllAuthorizer");
     }
 
-    virtual future<std::vector<permission_details>> list_all() const override {
-        return make_exception_future<std::vector<permission_details>>(
-                unsupported_authorization_operation(
-                        "LIST PERMISSIONS operation is not supported by AllowAllAuthorizer"));
+    future<std::vector<permission_details>> list(
+            service&,
+            ::shared_ptr<authenticated_user> performer,
+            permission_set,
+            stdx::optional<data_resource>,
+            stdx::optional<sstring>) const override {
+        throw exceptions::invalid_request_exception("LIST PERMISSIONS operation is not supported by AllowAllAuthorizer");
     }
 
-    virtual future<> revoke_all(std::string_view) const override {
-        return make_exception_future(
-                unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
+    future<> revoke_all(sstring dropped_user) override {
+        return make_ready_future();
     }
 
-    virtual future<> revoke_all(const resource&) const override {
-        return make_exception_future(
-                unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
+    future<> revoke_all(data_resource) override {
+        return make_ready_future();
     }
 
-    virtual const resource_set& protected_resources() const override {
-        static const resource_set resources;
-        return resources;
+    const resource_ids& protected_resources() override {
+        static const resource_ids ids;
+        return ids;
+    }
+
+    future<> validate_configuration() const override {
+        return make_ready_future();
     }
 };
 

auth/authenticated_user.cc

@@ -39,30 +39,26 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "auth/authenticated_user.hh"
 
-#include <iostream>
+#include "authenticated_user.hh"
 
-namespace auth {
+const sstring auth::authenticated_user::ANONYMOUS_USERNAME("anonymous");
 
-authenticated_user::authenticated_user(std::string_view name)
-        : name(sstring(name)) {
-}
-
-std::ostream& operator<<(std::ostream& os, const authenticated_user& u) {
-    if (!u.name) {
-        os << "anonymous";
-    } else {
-        os << *u.name;
-    }
-
-    return os;
-}
-
-static const authenticated_user the_anonymous_user{};
-
-const authenticated_user& anonymous_user() noexcept {
-    return the_anonymous_user;
+auth::authenticated_user::authenticated_user()
+                : _anon(true)
+{}
+
+auth::authenticated_user::authenticated_user(sstring name)
+                : _name(name), _anon(false)
+{}
+
+auth::authenticated_user::authenticated_user(authenticated_user&&) = default;
+auth::authenticated_user::authenticated_user(const authenticated_user&) = default;
+
+const sstring& auth::authenticated_user::name() const {
+    return _anon ? ANONYMOUS_USERNAME : _name;
 }
 
+bool auth::authenticated_user::operator==(const authenticated_user& v) const {
+    return _anon ? v._anon : _name == v._name;
 }

auth/authenticated_user.hh

@@ -41,62 +41,35 @@
 
 #pragma once
 
-#include <string_view>
-#include <functional>
-#include <iosfwd>
-#include <optional>
-
 #include <seastar/core/sstring.hh>
-
+#include <seastar/core/future.hh>
 #include "seastarx.hh"
 
 namespace auth {
 
-///
-/// A type-safe wrapper for the name of a logged-in user, or a nameless (anonymous) user.
-///
-class authenticated_user final {
+class authenticated_user {
 public:
-    ///
-    /// An anonymous user has no name.
-    ///
-    std::optional<sstring> name{};
+    static const sstring ANONYMOUS_USERNAME;
 
-    ///
-    /// An anonymous user.
-    ///
-    authenticated_user() = default;
-    explicit authenticated_user(std::string_view name);
-};
+    authenticated_user();
+    authenticated_user(sstring name);
+    authenticated_user(authenticated_user&&);
+    authenticated_user(const authenticated_user&);
 
-///
-/// The user name, or "anonymous".
-///
-std::ostream& operator<<(std::ostream&, const authenticated_user&);
+    const sstring& name() const;
 
-inline bool operator==(const authenticated_user& u1, const authenticated_user& u2) noexcept {
-    return u1.name == u2.name;
-}
-
-inline bool operator!=(const authenticated_user& u1, const authenticated_user& u2) noexcept {
-    return !(u1 == u2);
-}
-
-const authenticated_user& anonymous_user() noexcept;
-
-inline bool is_anonymous(const authenticated_user& u) noexcept {
-    return u == anonymous_user();
-}
-
-}
-
-namespace std {
-
-template <>
-struct hash<auth::authenticated_user> final {
-    size_t operator()(const auth::authenticated_user &u) const {
-        return std::hash<std::optional<sstring>>()(u.name);
+    /**
+     * If IAuthenticator doesn't require authentication, this method may return true.
+     */
+    bool is_anonymous() const {
+        return _anon;
     }
+
+    bool operator==(const authenticated_user&) const;
+private:
+    sstring _name;
+    bool _anon;
 };
 
 }
+

auth/authentication_options.cc

@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "auth/authentication_options.hh"
-
-#include <iostream>
-
-namespace auth {
-
-std::ostream& operator<<(std::ostream& os, authentication_option a) {
-    switch (a) {
-        case authentication_option::password: os << "PASSWORD"; break;
-        case authentication_option::options: os << "OPTIONS"; break;
-    }
-
-    return os;
-}
-
-}

auth/authentication_options.hh

@@ -1,64 +0,0 @@
-/*
- * Copyright (C) 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <iosfwd>
-#include <optional>
-#include <stdexcept>
-#include <unordered_map>
-#include <unordered_set>
-
-#include <seastar/core/print.hh>
-#include <seastar/core/sstring.hh>
-
-#include "seastarx.hh"
-
-namespace auth {
-
-enum class authentication_option {
-    password,
-    options
-};
-
-std::ostream& operator<<(std::ostream&, authentication_option);
-
-using authentication_option_set = std::unordered_set<authentication_option>;
-
-using custom_options = std::unordered_map<sstring, sstring>;
-
-struct authentication_options final {
-    std::optional<sstring> password;
-    std::optional<custom_options> options;
-};
-
-inline bool any_authentication_options(const authentication_options& aos) noexcept {
-    return aos.password || aos.options;
-}
-
-class unsupported_authentication_option : public std::invalid_argument {
-public:
-    explicit unsupported_authentication_option(authentication_option k)
-            : std::invalid_argument(format("The {} option is not supported.", k)) {
-    }
-};
-
-}

auth/authenticator.cc

@@ -39,13 +39,29 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "auth/authenticator.hh"
-
-#include "auth/authenticated_user.hh"
-#include "auth/common.hh"
-#include "auth/password_authenticator.hh"
+#include "authenticator.hh"
+#include "authenticated_user.hh"
+#include "common.hh"
+#include "password_authenticator.hh"
 #include "cql3/query_processor.hh"
+#include "db/config.hh"
 #include "utils/class_registrator.hh"
 
 const sstring auth::authenticator::USERNAME_KEY("username");
 const sstring auth::authenticator::PASSWORD_KEY("password");
+
+auth::authenticator::option auth::authenticator::string_to_option(const sstring& name) {
+    if (strcasecmp(name.c_str(), "password") == 0) {
+        return option::PASSWORD;
+    }
+    throw std::invalid_argument(name);
+}
+
+sstring auth::authenticator::option_to_string(option opt) {
+    switch (opt) {
+    case option::PASSWORD:
+        return "PASSWORD";
+    default:
+        throw std::invalid_argument(sprint("Unknown option {}", opt));
+    }
+}

auth/authenticator.hh

@@ -41,22 +41,19 @@
 
 #pragma once
 
-#include <string_view>
 #include <memory>
+#include <unordered_map>
 #include <set>
 #include <stdexcept>
-#include <unordered_map>
-
 #include <boost/any.hpp>
-#include <seastar/core/enum.hh>
-#include <seastar/core/future.hh>
-#include <seastar/core/sstring.hh>
-#include <seastar/core/shared_ptr.hh>
 
-#include "auth/authentication_options.hh"
-#include "auth/resource.hh"
-#include "auth/sasl_challenge.hh"
+#include <seastar/core/sstring.hh>
+#include <seastar/core/future.hh>
+#include <seastar/core/shared_ptr.hh>
+#include <seastar/core/enum.hh>
+
 #include "bytes.hh"
+#include "data_resource.hh"
 #include "enum_set.hh"
 #include "exceptions/exceptions.hh"
 
@@ -68,90 +65,126 @@ namespace auth {
 
 class authenticated_user;
 
-///
-/// Abstract client for authenticating role identity.
-///
-/// All state necessary to authorize a role is stored externally to the client instance.
-///
 class authenticator {
 public:
-    ///
-    /// The name of the key to be used for the user-name part of password authentication with \ref authenticate.
-    ///
     static const sstring USERNAME_KEY;
-
-    ///
-    /// The name of the key to be used for the password part of password authentication with \ref authenticate.
-    ///
     static const sstring PASSWORD_KEY;
 
+    /**
+     * Supported CREATE USER/ALTER USER options.
+     * Currently only PASSWORD is available.
+     */
+    enum class option {
+        PASSWORD
+    };
+
+    static option string_to_option(const sstring&);
+    static sstring option_to_string(option);
+
+    using option_set = enum_set<super_enum<option, option::PASSWORD>>;
+    using option_map = std::unordered_map<option, boost::any, enum_hash<option>>;
     using credentials_map = std::unordered_map<sstring, sstring>;
 
-    virtual ~authenticator() = default;
+    virtual ~authenticator()
+    {}
 
     virtual future<> start() = 0;
 
     virtual future<> stop() = 0;
 
-    ///
-    /// A fully-qualified (class with package) Java-like name for this implementation.
-    ///
-    virtual std::string_view qualified_java_name() const = 0;
+    virtual const sstring& qualified_java_name() const = 0;
 
+    /**
+     * Whether or not the authenticator requires explicit login.
+     * If false will instantiate user with AuthenticatedUser.ANONYMOUS_USER.
+     */
     virtual bool require_authentication() const = 0;
 
-    virtual authentication_option_set supported_options() const = 0;
+    /**
+     * Set of options supported by CREATE USER and ALTER USER queries.
+     * Should never return null - always return an empty set instead.
+     */
+    virtual option_set supported_options() const = 0;
 
-    ///
-    /// A subset of `supported_options()` that users are permitted to alter for themselves.
-    ///
-    virtual authentication_option_set alterable_options() const = 0;
+    /**
+     * Subset of supportedOptions that users are allowed to alter when performing ALTER USER [themselves].
+     * Should never return null - always return an empty set instead.
+     */
+    virtual option_set alterable_options() const = 0;
 
-    ///
-    /// Authenticate a user given implementation-specific credentials.
-    ///
-    /// If this implementation does not require authentication (\ref require_authentication), an anonymous user may
-    /// result.
-    ///
-    /// \returns an exceptional future with \ref exceptions::authentication_exception if given invalid credentials.
-    ///
-    virtual future<authenticated_user> authenticate(const credentials_map& credentials) const = 0;
+    /**
+     * Authenticates a user given a Map<String, String> of credentials.
+     * Should never return null - always throw AuthenticationException instead.
+     * Returning AuthenticatedUser.ANONYMOUS_USER is an option as well if authentication is not required.
+     *
+     * @throws authentication_exception if credentials don't match any known user.
+     */
+    virtual future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const = 0;
 
-    ///
-    /// Create an authentication record for a new user. This is required before the user can log-in.
-    ///
-    /// The options provided must be a subset of `supported_options()`.
-    ///
-    virtual future<> create(std::string_view role_name, const authentication_options& options) const = 0;
+    /**
+     * Called during execution of CREATE USER query (also may be called on startup, see seedSuperuserOptions method).
+     * If authenticator is static then the body of the method should be left blank, but don't throw an exception.
+     * options are guaranteed to be a subset of supportedOptions().
+     *
+     * @param username Username of the user to create.
+     * @param options Options the user will be created with.
+     * @throws exceptions::request_validation_exception
+     * @throws exceptions::request_execution_exception
+     */
+    virtual future<> create(sstring username, const option_map& options) = 0;
 
-    ///
-    /// Alter the authentication record of an existing user.
-    ///
-    /// The options provided must be a subset of `supported_options()`.
-    ///
-    /// Callers must ensure that the specification of `alterable_options()` is adhered to.
-    ///
-    virtual future<> alter(std::string_view role_name, const authentication_options& options) const = 0;
+    /**
+     * Called during execution of ALTER USER query.
+     * options are always guaranteed to be a subset of supportedOptions(). Furthermore, if the user performing the query
+     * is not a superuser and is altering himself, then options are guaranteed to be a subset of alterableOptions().
+     * Keep the body of the method blank if your implementation doesn't support any options.
+     *
+     * @param username Username of the user that will be altered.
+     * @param options Options to alter.
+     * @throws exceptions::request_validation_exception
+     * @throws exceptions::request_execution_exception
+     */
+    virtual future<> alter(sstring username, const option_map& options) = 0;
 
-    ///
-    /// Delete the authentication record for a user. This will disallow the user from logging in.
-    ///
-    virtual future<> drop(std::string_view role_name) const = 0;
 
-    ///
-    /// Query for custom options (those corresponding to \ref authentication_options::options).
-    ///
-    /// If no options are set the result is an empty container.
-    ///
-    virtual future<custom_options> query_custom_options(std::string_view role_name) const = 0;
+    /**
+     * Called during execution of DROP USER query.
+     *
+     * @param username Username of the user that will be dropped.
+     * @throws exceptions::request_validation_exception
+     * @throws exceptions::request_execution_exception
+     */
+    virtual future<> drop(sstring username) = 0;
 
-    ///
-    /// System resources used internally as part of the implementation. These are made inaccessible to users.
-    ///
-    virtual const resource_set& protected_resources() const = 0;
+     /**
+     * Set of resources that should be made inaccessible to users and only accessible internally.
+     *
+     * @return Keyspaces, column families that will be unmodifiable by users; other resources.
+     * @see resource_ids
+     */
+    virtual const resource_ids& protected_resources() const = 0;
 
+    class sasl_challenge {
+    public:
+        virtual ~sasl_challenge() {}
+        virtual bytes evaluate_response(bytes_view client_response) = 0;
+        virtual bool is_complete() const = 0;
+        virtual future<::shared_ptr<authenticated_user>> get_authenticated_user() const = 0;
+    };
+
+    /**
+     * Provide a sasl_challenge to be used by the CQL binary protocol server. If
+     * the configured authenticator requires authentication but does not implement this
+     * interface we refuse to start the binary protocol server as it will have no way
+     * of authenticating clients.
+     * @return sasl_challenge implementation
+     */
     virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const = 0;
 };
 
+inline std::ostream& operator<<(std::ostream& os, authenticator::option opt) {
+    return os << authenticator::option_to_string(opt);
+}
+
 }
 

auth/authorizer.cc

@@ -0,0 +1,118 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/*
+ * Copyright (C) 2016 ScyllaDB
+ *
+ * Modified by ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "authorizer.hh"
+#include "authenticated_user.hh"
+#include "common.hh"
+#include "default_authorizer.hh"
+#include "auth.hh"
+#include "cql3/query_processor.hh"
+#include "db/config.hh"
+#include "utils/class_registrator.hh"
+
+const sstring& auth::allow_all_authorizer_name() {
+    static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthorizer";
+    return name;
+}
+
+/**
+ * Authenticator is assumed to be a fully state-less immutable object (note all the const).
+ * We thus store a single instance globally, since it should be safe/ok.
+ */
+static std::unique_ptr<auth::authorizer> global_authorizer;
+using authorizer_registry = class_registry<auth::authorizer, cql3::query_processor&>;
+
+future<>
+auth::authorizer::setup(const sstring& type) {
+    if (type == allow_all_authorizer_name()) {
+        class allow_all_authorizer : public authorizer {
+        public:
+            future<> start() override {
+                return make_ready_future<>();
+            }
+            future<> stop() override {
+                return make_ready_future<>();
+            }
+            const sstring& qualified_java_name() const override {
+                return allow_all_authorizer_name();
+            }
+            future<permission_set> authorize(::shared_ptr<authenticated_user>, data_resource) const override {
+                return make_ready_future<permission_set>(permissions::ALL);
+            }
+            future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
+                throw exceptions::invalid_request_exception("GRANT operation is not supported by AllowAllAuthorizer");
+            }
+            future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
+                throw exceptions::invalid_request_exception("REVOKE operation is not supported by AllowAllAuthorizer");
+            }
+            future<std::vector<permission_details>> list(::shared_ptr<authenticated_user> performer, permission_set, optional<data_resource>, optional<sstring>) const override {
+                throw exceptions::invalid_request_exception("LIST PERMISSIONS operation is not supported by AllowAllAuthorizer");
+            }
+            future<> revoke_all(sstring dropped_user) override {
+                return make_ready_future();
+            }
+            future<> revoke_all(data_resource) override {
+                return make_ready_future();
+            }
+            const resource_ids& protected_resources() override {
+                static const resource_ids ids;
+                return ids;
+            }
+            future<> validate_configuration() const override {
+                return make_ready_future();
+            }
+        };
+
+        global_authorizer = std::make_unique<allow_all_authorizer>();
+        return make_ready_future();
+    } else {
+        auto a = authorizer_registry::create(type, cql3::get_local_query_processor());
+        auto f = a->start();
+        return f.then([a = std::move(a)]() mutable {
+            global_authorizer = std::move(a);
+        });
+    }
+}
+
+auth::authorizer& auth::authorizer::get() {
+    assert(global_authorizer);
+    return *global_authorizer;
+}

auth/authorizer.hh

@@ -41,115 +41,127 @@
 
 #pragma once
 
-#include <string_view>
-#include <functional>
-#include <optional>
-#include <stdexcept>
-#include <tuple>
 #include <vector>
+#include <tuple>
 
+#include <experimental/optional>
 #include <seastar/core/future.hh>
 #include <seastar/core/shared_ptr.hh>
 
-#include "auth/permission.hh"
-#include "auth/resource.hh"
+#include "permission.hh"
+#include "data_resource.hh"
+
 #include "seastarx.hh"
 
 namespace auth {
 
-class role_or_anonymous;
+class service;
+
+class authenticated_user;
 
 struct permission_details {
-    sstring role_name;
-    ::auth::resource resource;
+    sstring user;
+    data_resource resource;
     permission_set permissions;
+
+    bool operator<(const permission_details& v) const {
+        return std::tie(user, resource, permissions) < std::tie(v.user, v.resource, v.permissions);
+    }
 };
 
-inline bool operator==(const permission_details& pd1, const permission_details& pd2) {
-    return std::forward_as_tuple(pd1.role_name, pd1.resource, pd1.permissions.mask())
-            == std::forward_as_tuple(pd2.role_name, pd2.resource, pd2.permissions.mask());
-}
+using std::experimental::optional;
 
-inline bool operator!=(const permission_details& pd1, const permission_details& pd2) {
-    return !(pd1 == pd2);
-}
-
-inline bool operator<(const permission_details& pd1, const permission_details& pd2) {
-    return std::forward_as_tuple(pd1.role_name, pd1.resource, pd1.permissions)
-            < std::forward_as_tuple(pd2.role_name, pd2.resource, pd2.permissions);
-}
-
-class unsupported_authorization_operation : public std::invalid_argument {
-public:
-    using std::invalid_argument::invalid_argument;
-};
-
-///
-/// Abstract client for authorizing roles to access resources.
-///
-/// All state necessary to authorize a role is stored externally to the client instance.
-///
 class authorizer {
 public:
-    virtual ~authorizer() = default;
+    virtual ~authorizer() {}
 
     virtual future<> start() = 0;
 
     virtual future<> stop() = 0;
 
-    ///
-    /// A fully-qualified (class with package) Java-like name for this implementation.
-    ///
-    virtual std::string_view qualified_java_name() const = 0;
+    virtual const sstring& qualified_java_name() const = 0;
 
-    ///
-    /// Query for the permissions granted directly to a role for a particular \ref resource (and not any of its
-    /// parents).
-    ///
-    /// The optional role name is empty when an anonymous user is authorized. Some implementations may still wish to
-    /// grant default permissions in this case.
-    ///
-    virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const = 0;
+    /**
+     * The primary Authorizer method. Returns a set of permissions of a user on a resource.
+     *
+     * @param user Authenticated user requesting authorization.
+     * @param resource Resource for which the authorization is being requested. @see DataResource.
+     * @return Set of permissions of the user on the resource. Should never return empty. Use permission.NONE instead.
+     */
+    virtual future<permission_set> authorize(service&, ::shared_ptr<authenticated_user>, data_resource) const = 0;
 
-    ///
-    /// Grant a set of permissions to a role for a particular \ref resource.
-    ///
-    /// \throws \ref unsupported_authorization_operation if granting permissions is not supported.
-    ///
-    virtual future<> grant(std::string_view role_name, permission_set, const resource&) const = 0;
+    /**
+     * Grants a set of permissions on a resource to a user.
+     * The opposite of revoke().
+     *
+     * @param performer User who grants the permissions.
+     * @param permissions Set of permissions to grant.
+     * @param to Grantee of the permissions.
+     * @param resource Resource on which to grant the permissions.
+     *
+     * @throws RequestValidationException
+     * @throws RequestExecutionException
+     */
+    virtual future<> grant(::shared_ptr<authenticated_user> performer, permission_set, data_resource, sstring to) = 0;
 
-    ///
-    /// Revoke a set of permissions from a role for a particular \ref resource.
-    ///
-    /// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
-    ///
-    virtual future<> revoke(std::string_view role_name, permission_set, const resource&) const = 0;
+    /**
+     * Revokes a set of permissions on a resource from a user.
+     * The opposite of grant().
+     *
+     * @param performer User who revokes the permissions.
+     * @param permissions Set of permissions to revoke.
+     * @param from Revokee of the permissions.
+     * @param resource Resource on which to revoke the permissions.
+     *
+     * @throws RequestValidationException
+     * @throws RequestExecutionException
+     */
+    virtual future<> revoke(::shared_ptr<authenticated_user> performer, permission_set, data_resource, sstring from) = 0;
 
-    ///
-    /// Query for all directly granted permissions.
-    ///
-    /// \throws \ref unsupported_authorization_operation if listing permissions is not supported.
-    ///
-    virtual future<std::vector<permission_details>> list_all() const = 0;
+    /**
+     * Returns a list of permissions on a resource of a user.
+     *
+     * @param performer User who wants to see the permissions.
+     * @param permissions Set of Permission values the user is interested in. The result should only include the matching ones.
+     * @param resource The resource on which permissions are requested. Can be null, in which case permissions on all resources
+     *                 should be returned.
+     * @param of The user whose permissions are requested. Can be null, in which case permissions of every user should be returned.
+     *
+     * @return All of the matching permission that the requesting user is authorized to know about.
+     *
+     * @throws RequestValidationException
+     * @throws RequestExecutionException
+     */
+    virtual future<std::vector<permission_details>> list(service&, ::shared_ptr<authenticated_user> performer, permission_set, optional<data_resource>, optional<sstring>) const = 0;
 
-    ///
-    /// Revoke all permissions granted directly to a particular role.
-    ///
-    /// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
-    ///
-    virtual future<> revoke_all(std::string_view role_name) const = 0;
+    /**
+     * This method is called before deleting a user with DROP USER query so that a new user with the same
+     * name wouldn't inherit permissions of the deleted user in the future.
+     *
+     * @param droppedUser The user to revoke all permissions from.
+     */
+    virtual future<> revoke_all(sstring dropped_user) = 0;
 
-    ///
-    /// Revoke all permissions granted to any role for a particular resource.
-    ///
-    /// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
-    ///
-    virtual future<> revoke_all(const resource&) const = 0;
+    /**
+     * This method is called after a resource is removed (i.e. keyspace or a table is dropped).
+     *
+     * @param droppedResource The resource to revoke all permissions on.
+     */
+    virtual future<> revoke_all(data_resource) = 0;
 
-    ///
-    /// System resources used internally as part of the implementation. These are made inaccessible to users.
-    ///
-    virtual const resource_set& protected_resources() const = 0;
+    /**
+     * Set of resources that should be made inaccessible to users and only accessible internally.
+     *
+     * @return Keyspaces, column families that will be unmodifiable by users; other resources.
+     */
+    virtual const resource_ids& protected_resources() = 0;
+
+    /**
+     * Validates configuration of IAuthorizer implementation (if configurable).
+     *
+     * @throws ConfigurationException when there is a configuration error.
+     */
+    virtual future<> validate_configuration() const = 0;
 };
 
 }

auth/common.cc

@@ -25,98 +25,46 @@
 
 #include "cql3/query_processor.hh"
 #include "cql3/statements/create_table_statement.hh"
-#include "database.hh"
 #include "schema_builder.hh"
 #include "service/migration_manager.hh"
-#include "timeout_config.hh"
 
 namespace auth {
 
 namespace meta {
 
-constexpr std::string_view AUTH_KS("system_auth");
-constexpr std::string_view USERS_CF("users");
-constexpr std::string_view AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
+const sstring DEFAULT_SUPERUSER_NAME("cassandra");
+const sstring AUTH_KS("system_auth");
+const sstring USERS_CF("users");
+const sstring AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
 
 }
 
-static logging::logger auth_log("auth");
-
-// Func must support being invoked more than once.
-future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func) {
-    struct empty_state { };
-    return delay_until_system_ready(as).then([&as, func = std::move(func)] () mutable {
-        return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
-            return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
-                if (f.failed()) {
-                    auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
-                    return { };
-                }
-                return { empty_state() };
-            });
-        });
-    }).discard_result();
-}
-
-static future<> create_metadata_table_if_missing_impl(
-        std::string_view table_name,
+future<> create_metadata_table_if_missing(
+        const sstring& table_name,
         cql3::query_processor& qp,
-        std::string_view cql,
+        const sstring& cql,
         ::service::migration_manager& mm) {
-    static auto ignore_existing = [] (seastar::noncopyable_function<future<>()> func) {
-        return futurize_invoke(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
-    };
-    auto& db = qp.db();
-    auto parsed_statement = cql3::query_processor::parse_statement(cql);
-    auto& parsed_cf_statement = static_cast<cql3::statements::raw::cf_statement&>(*parsed_statement);
+    auto& db = qp.db().local();
 
-    parsed_cf_statement.prepare_keyspace(meta::AUTH_KS);
+    if (db.has_schema(meta::AUTH_KS, table_name)) {
+        return make_ready_future<>();
+    }
+
+    auto parsed_statement = static_pointer_cast<cql3::statements::raw::cf_statement>(
+            cql3::query_processor::parse_statement(cql));
+
+    parsed_statement->prepare_keyspace(meta::AUTH_KS);
 
     auto statement = static_pointer_cast<cql3::statements::create_table_statement>(
-            parsed_cf_statement.prepare(db, qp.get_cql_stats())->statement);
+            parsed_statement->prepare(db, qp.get_cql_stats())->statement);
 
-    const auto schema = statement->get_cf_meta_data(qp.db());
+    const auto schema = statement->get_cf_meta_data();
     const auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
 
     schema_builder b(schema);
     b.set_uuid(uuid);
-    schema_ptr table = b.build();
-    return ignore_existing([&mm, table = std::move(table)] () {
-        return mm.announce_new_column_family(table, false);
-    });
-}
 
-future<> create_metadata_table_if_missing(
-        std::string_view table_name,
-        cql3::query_processor& qp,
-        std::string_view cql,
-        ::service::migration_manager& mm) noexcept {
-    return futurize_invoke(create_metadata_table_if_missing_impl, table_name, qp, cql, mm);
-}
-
-future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db, seastar::abort_source& as) {
-    static const auto pause = [] { return sleep(std::chrono::milliseconds(500)); };
-
-    return do_until([&db, &as] {
-        as.check();
-        return db.get_version() != database::empty_version;
-    }, pause).then([&mm, &as] {
-        return do_until([&mm, &as] {
-            as.check();
-            return mm.have_schema_agreement();
-        }, pause);
-    });
-}
-
-const timeout_config& internal_distributed_timeout_config() noexcept {
-#ifdef DEBUG
-    // Give the much slower debug tests more headroom for completing auth queries.
-    static const auto t = 30s;
-#else
-    static const auto t = 5s;
-#endif
-    static const timeout_config tc{t, t, t, t, t, t, t};
-    return tc;
+    return mm.announce_new_column_family(b.build(), false);
 }
 
 }

auth/common.hh

@@ -22,24 +22,14 @@
 #pragma once
 
 #include <chrono>
-#include <string_view>
 
 #include <seastar/core/future.hh>
-#include <seastar/core/abort_source.hh>
-#include <seastar/util/noncopyable_function.hh>
-#include <seastar/core/seastar.hh>
+#include <seastar/core/reactor.hh>
 #include <seastar/core/resource.hh>
 #include <seastar/core/sstring.hh>
-#include <seastar/core/smp.hh>
 
-#include "log.hh"
+#include "delayed_tasks.hh"
 #include "seastarx.hh"
-#include "utils/exponential_backoff_retry.hh"
-
-using namespace std::chrono_literals;
-
-class database;
-class timeout_config;
 
 namespace service {
 class migration_manager;
@@ -53,40 +43,32 @@ namespace auth {
 
 namespace meta {
 
-constexpr std::string_view DEFAULT_SUPERUSER_NAME("cassandra");
-extern const std::string_view AUTH_KS;
-extern const std::string_view USERS_CF;
-extern const std::string_view AUTH_PACKAGE_NAME;
+extern const sstring DEFAULT_SUPERUSER_NAME;
+extern const sstring AUTH_KS;
+extern const sstring USERS_CF;
+extern const sstring AUTH_PACKAGE_NAME;
 
 }
 
 template <class Task>
 future<> once_among_shards(Task&& f) {
-    if (this_shard_id() == 0u) {
+    if (engine().cpu_id() == 0u) {
         return f();
     }
 
     return make_ready_future<>();
 }
 
-inline future<> delay_until_system_ready(seastar::abort_source& as) {
-    return sleep_abortable(15s, as);
+template <class Task, class Clock>
+void delay_until_system_ready(delayed_tasks<Clock>& ts, Task&& f) {
+    static const typename std::chrono::milliseconds delay_duration(10000);
+    ts.schedule_after(delay_duration, std::forward<Task>(f));
 }
 
-// Func must support being invoked more than once.
-future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func);
-
 future<> create_metadata_table_if_missing(
-        std::string_view table_name,
+        const sstring& table_name,
         cql3::query_processor&,
-        std::string_view cql,
-        ::service::migration_manager&) noexcept;
-
-future<> wait_for_schema_agreement(::service::migration_manager&, const database&, seastar::abort_source&);
-
-///
-/// Time-outs for internal, non-local CQL queries.
-///
-const timeout_config& internal_distributed_timeout_config() noexcept;
+        const sstring& cql,
+        ::service::migration_manager&);
 
 }

auth/data_resource.cc

@@ -0,0 +1,171 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/*
+ * Copyright (C) 2016 ScyllaDB
+ *
+ * Modified by ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "data_resource.hh"
+
+#include <regex>
+#include "service/storage_proxy.hh"
+
+const sstring auth::data_resource::ROOT_NAME("data");
+
+auth::data_resource::data_resource(level l, const sstring& ks, const sstring& cf)
+    : _level(l), _ks(ks), _cf(cf)
+{
+}
+
+auth::data_resource::data_resource()
+    : data_resource(level::ROOT)
+{}
+
+auth::data_resource::data_resource(const sstring& ks)
+    : data_resource(level::KEYSPACE, ks)
+{}
+
+auth::data_resource::data_resource(const sstring& ks, const sstring& cf)
+    : data_resource(level::COLUMN_FAMILY, ks, cf)
+{}
+
+auth::data_resource::level auth::data_resource::get_level() const {
+    return _level;
+}
+
+auth::data_resource auth::data_resource::from_name(
+                const sstring& s) {
+
+    static std::regex slash_regex("/");
+
+    auto i = std::regex_token_iterator<sstring::const_iterator>(s.begin(),
+                    s.end(), slash_regex, -1);
+    auto e = std::regex_token_iterator<sstring::const_iterator>();
+    auto n = std::distance(i, e);
+
+    if (n > 3 || ROOT_NAME != sstring(*i++)) {
+        throw std::invalid_argument(sprint("%s is not a valid data resource name", s));
+    }
+
+    if (n == 1) {
+        return data_resource();
+    }
+    auto ks = *i++;
+    if (n == 2) {
+        return data_resource(ks.str());
+    }
+    auto cf = *i++;
+    return data_resource(ks.str(), cf.str());
+}
+
+sstring auth::data_resource::name() const {
+    switch (get_level()) {
+        case level::ROOT:
+            return ROOT_NAME;
+        case level::KEYSPACE:
+            return sprint("%s/%s", ROOT_NAME, _ks);
+        case level::COLUMN_FAMILY:
+        default:
+            return sprint("%s/%s/%s", ROOT_NAME, _ks, _cf);
+    }
+}
+
+auth::data_resource auth::data_resource::get_parent() const {
+    switch (get_level()) {
+    case level::KEYSPACE:
+        return data_resource();
+    case level::COLUMN_FAMILY:
+        return data_resource(_ks);
+    default:
+        throw std::invalid_argument("Root-level resource can't have a parent");
+    }
+}
+
+const sstring& auth::data_resource::keyspace() const {
+    if (is_root_level()) {
+        throw std::invalid_argument("ROOT data resource has no keyspace");
+    }
+    return _ks;
+}
+
+const sstring& auth::data_resource::column_family() const {
+    if (!is_column_family_level()) {
+        throw std::invalid_argument(sprint("%s data resource has no column family", name()));
+    }
+    return _cf;
+}
+
+bool auth::data_resource::has_parent() const {
+    return !is_root_level();
+}
+
+bool auth::data_resource::exists() const {
+    switch (get_level()) {
+        case level::ROOT:
+            return true;
+        case level::KEYSPACE:
+            return service::get_local_storage_proxy().get_db().local().has_keyspace(_ks);
+        case level::COLUMN_FAMILY:
+        default:
+            return service::get_local_storage_proxy().get_db().local().has_schema(_ks, _cf);
+    }
+}
+
+sstring auth::data_resource::to_string() const {
+    switch (get_level()) {
+        case level::ROOT:
+            return "<all keyspaces>";
+        case level::KEYSPACE:
+            return sprint("<keyspace %s>", _ks);
+        case level::COLUMN_FAMILY:
+        default:
+            return sprint("<table %s.%s>", _ks, _cf);
+    }
+}
+
+bool auth::data_resource::operator==(const data_resource& v) const {
+    return _ks == v._ks && _cf == v._cf;
+}
+
+bool auth::data_resource::operator<(const data_resource& v) const {
+    return _ks < v._ks ? true : (v._ks < _ks ? false : _cf < v._cf);
+}
+
+std::ostream& auth::operator<<(std::ostream& os, const data_resource& r) {
+    return os << r.to_string();
+}
+

auth/data_resource.hh

@@ -0,0 +1,159 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/*
+ * Copyright (C) 2016 ScyllaDB
+ *
+ * Modified by ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include "utils/hash.hh"
+#include <iosfwd>
+#include <set>
+#include <seastar/core/sstring.hh>
+#include "seastarx.hh"
+
+namespace auth {
+
+class data_resource {
+private:
+    enum class level {
+        ROOT, KEYSPACE, COLUMN_FAMILY
+    };
+
+    static const sstring ROOT_NAME;
+
+    level _level;
+    sstring _ks;
+    sstring _cf;
+
+    data_resource(level, const sstring& ks = {}, const sstring& cf = {});
+
+    level get_level() const;
+public:
+    /**
+     * Creates a DataResource representing the root-level resource.
+     * @return the root-level resource.
+     */
+    data_resource();
+    /**
+     * Creates a DataResource representing a keyspace.
+     *
+     * @param keyspace Name of the keyspace.
+     */
+    data_resource(const sstring& ks);
+    /**
+     * Creates a DataResource instance representing a column family.
+     *
+     * @param keyspace Name of the keyspace.
+     * @param columnFamily Name of the column family.
+     */
+    data_resource(const sstring& ks, const sstring& cf);
+
+    /**
+     * Parses a data resource name into a DataResource instance.
+     *
+     * @param name Name of the data resource.
+     * @return DataResource instance matching the name.
+     */
+    static data_resource from_name(const sstring&);
+
+    /**
+     * @return Printable name of the resource.
+     */
+    sstring name() const;
+
+    /**
+     * @return Parent of the resource, if any. Throws IllegalStateException if it's the root-level resource.
+     */
+    data_resource get_parent() const;
+
+    bool is_root_level() const {
+        return get_level() == level::ROOT;
+    }
+
+    bool is_keyspace_level() const {
+        return get_level() == level::KEYSPACE;
+    }
+
+    bool is_column_family_level() const {
+        return get_level() == level::COLUMN_FAMILY;
+    }
+
+    /**
+     * @return keyspace of the resource.
+     * @throws std::invalid_argument if it's the root-level resource.
+     */
+    const sstring& keyspace() const;
+
+    /**
+     * @return column family of the resource.
+     * @throws std::invalid_argument if it's not a cf-level resource.
+     */
+    const sstring& column_family() const;
+
+    /**
+     * @return Whether or not the resource has a parent in the hierarchy.
+     */
+    bool has_parent() const;
+
+    /**
+     * @return Whether or not the resource exists in scylla.
+     */
+    bool exists() const;
+
+    sstring to_string() const;
+
+    bool operator==(const data_resource&) const;
+    bool operator<(const data_resource&) const;
+
+    size_t hash_value() const {
+        return utils::tuple_hash()(_ks, _cf);
+    }
+};
+
+/**
+ * Resource id mappings, i.e. keyspace and/or column families.
+ */
+using resource_ids = std::set<data_resource>;
+
+std::ostream& operator<<(std::ostream&, const data_resource&);
+
+}
+
+
+

auth/default_authorizer.cc

@@ -39,285 +39,198 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "auth/default_authorizer.hh"
-
-extern "C" {
-#include <crypt.h>
 #include <unistd.h>
-}
-
-#include <chrono>
+#include <crypt.h>
 #include <random>
+#include <chrono>
 
-#include <boost/algorithm/string/join.hpp>
-#include <boost/range.hpp>
-#include <seastar/core/seastar.hh>
+#include <seastar/core/reactor.hh>
 
-#include "auth/authenticated_user.hh"
-#include "auth/common.hh"
-#include "auth/permission.hh"
-#include "auth/role_or_anonymous.hh"
+#include "common.hh"
+#include "default_authorizer.hh"
+#include "authenticated_user.hh"
+#include "permission.hh"
 #include "cql3/query_processor.hh"
 #include "cql3/untyped_result_set.hh"
 #include "exceptions/exceptions.hh"
 #include "log.hh"
-#include "database.hh"
 
-namespace auth {
-
-std::string_view default_authorizer::qualified_java_name() const {
-    return "org.apache.cassandra.auth.CassandraAuthorizer";
+const sstring& auth::default_authorizer_name() {
+    static const sstring name = meta::AUTH_PACKAGE_NAME + "CassandraAuthorizer";
+    return name;
 }
 
-static constexpr std::string_view ROLE_NAME = "role";
-static constexpr std::string_view RESOURCE_NAME = "resource";
-static constexpr std::string_view PERMISSIONS_NAME = "permissions";
-static constexpr std::string_view PERMISSIONS_CF = "role_permissions";
+static const sstring USER_NAME = "username";
+static const sstring RESOURCE_NAME = "resource";
+static const sstring PERMISSIONS_NAME = "permissions";
+static const sstring PERMISSIONS_CF = "permissions";
 
 static logging::logger alogger("default_authorizer");
 
 // To ensure correct initialization order, we unfortunately need to use a string literal.
 static const class_registrator<
-        authorizer,
-        default_authorizer,
+        auth::authorizer,
+        auth::default_authorizer,
         cql3::query_processor&,
         ::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.CassandraAuthorizer");
 
-default_authorizer::default_authorizer(cql3::query_processor& qp, ::service::migration_manager& mm)
+auth::default_authorizer::default_authorizer(cql3::query_processor& qp, ::service::migration_manager& mm)
         : _qp(qp)
         , _migration_manager(mm) {
 }
 
-default_authorizer::~default_authorizer() {
+auth::default_authorizer::~default_authorizer() {
 }
 
-static const sstring legacy_table_name{"permissions"};
+future<> auth::default_authorizer::start() {
+    static const sstring create_table = sprint("CREATE TABLE %s.%s ("
+                    "%s text,"
+                    "%s text,"
+                    "%s set<text>,"
+                    "PRIMARY KEY(%s, %s)"
+                    ") WITH gc_grace_seconds=%d", meta::AUTH_KS,
+                    PERMISSIONS_CF, USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME,
+                    USER_NAME, RESOURCE_NAME, 90 * 24 * 60 * 60); // 3 months.
 
-bool default_authorizer::legacy_metadata_exists() const {
-    return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
-}
-
-future<bool> default_authorizer::any_granted() const {
-    static const sstring query = format("SELECT * FROM {}.{} LIMIT 1", meta::AUTH_KS, PERMISSIONS_CF);
-
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::LOCAL_ONE,
-            infinite_timeout_config,
-            {},
-            true).then([this](::shared_ptr<cql3::untyped_result_set> results) {
-        return !results->empty();
-    });
-}
-
-future<> default_authorizer::migrate_legacy_metadata() const {
-    alogger.info("Starting migration of legacy permissions metadata.");
-    static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
-
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::LOCAL_ONE,
-            infinite_timeout_config).then([this](::shared_ptr<cql3::untyped_result_set> results) {
-        return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
-            return do_with(
-                    row.get_as<sstring>("username"),
-                    parse_resource(row.get_as<sstring>(RESOURCE_NAME)),
-                    [this, &row](const auto& username, const auto& r) {
-                const permission_set perms = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
-                return grant(username, perms, r);
-            });
-        }).finally([results] {});
-    }).then([] {
-        alogger.info("Finished migrating legacy permissions metadata.");
-    }).handle_exception([](std::exception_ptr ep) {
-        alogger.error("Encountered an error during migration!");
-        std::rethrow_exception(ep);
-    });
-}
-
-future<> default_authorizer::start() {
-    static const sstring create_table = sprint(
-            "CREATE TABLE %s.%s ("
-            "%s text,"
-            "%s text,"
-            "%s set<text>,"
-            "PRIMARY KEY(%s, %s)"
-            ") WITH gc_grace_seconds=%d",
-            meta::AUTH_KS,
-            PERMISSIONS_CF,
-            ROLE_NAME,
-            RESOURCE_NAME,
-            PERMISSIONS_NAME,
-            ROLE_NAME,
-            RESOURCE_NAME,
-            90 * 24 * 60 * 60); // 3 months.
-
-    return once_among_shards([this] {
-        return create_metadata_table_if_missing(
+    return auth::once_among_shards([this] {
+        return auth::create_metadata_table_if_missing(
                 PERMISSIONS_CF,
                 _qp,
                 create_table,
-                _migration_manager).then([this] {
-            _finished = do_after_system_ready(_as, [this] {
-                return async([this] {
-                    wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
+                _migration_manager);
+    });
+}
 
-                    if (legacy_metadata_exists()) {
-                        if (!any_granted().get0()) {
-                            migrate_legacy_metadata().get0();
-                            return;
-                        }
+future<> auth::default_authorizer::stop() {
+    return make_ready_future<>();
+}
 
-                        alogger.warn("Ignoring legacy permissions metadata since role permissions exist.");
-                    }
-                });
-            });
+future<auth::permission_set> auth::default_authorizer::authorize(
+                service& ser, ::shared_ptr<authenticated_user> user, data_resource resource) const {
+    return auth::is_super_user(ser, *user).then([this, user, resource = std::move(resource)](bool is_super) {
+        if (is_super) {
+            return make_ready_future<permission_set>(permissions::ALL);
+        }
+
+        /**
+         * TOOD: could create actual data type for permission (translating string<->perm),
+         * but this seems overkill right now. We still must store strings so...
+         */
+        auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? AND %s = ?"
+                        , PERMISSIONS_NAME, meta::AUTH_KS, PERMISSIONS_CF, USER_NAME, RESOURCE_NAME);
+        return _qp.process(query, db::consistency_level::LOCAL_ONE, {user->name(), resource.name() })
+                        .then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
+            try {
+                auto res = f.get0();
+
+                if (res->empty() || !res->one().has(PERMISSIONS_NAME)) {
+                    return make_ready_future<permission_set>(permissions::NONE);
+                }
+                return make_ready_future<permission_set>(permissions::from_strings(res->one().get_set<sstring>(PERMISSIONS_NAME)));
+            } catch (exceptions::request_execution_exception& e) {
+                alogger.warn("CassandraAuthorizer failed to authorize {} for {}", user->name(), resource);
+                return make_ready_future<permission_set>(permissions::NONE);
+            }
         });
     });
 }
 
-future<> default_authorizer::stop() {
-    _as.request_abort();
-    return _finished.handle_exception_type([](const sleep_aborted&) {}).handle_exception_type([](const abort_requested_exception&) {});
+#include <boost/range.hpp>
+
+future<> auth::default_authorizer::modify(
+                ::shared_ptr<authenticated_user> performer, permission_set set,
+                data_resource resource, sstring user, sstring op) {
+    // TODO: why does this not check super user?
+    auto query = sprint("UPDATE %s.%s SET %s = %s %s ? WHERE %s = ? AND %s = ?",
+                    meta::AUTH_KS, PERMISSIONS_CF, PERMISSIONS_NAME,
+                    PERMISSIONS_NAME, op, USER_NAME, RESOURCE_NAME);
+    return _qp.process(query, db::consistency_level::ONE, {
+                    permissions::to_strings(set), user, resource.name() }).discard_result();
 }
 
-future<permission_set>
-default_authorizer::authorize(const role_or_anonymous& maybe_role, const resource& r) const {
-    if (is_anonymous(maybe_role)) {
-        return make_ready_future<permission_set>(permissions::NONE);
-    }
 
-    static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? AND {} = ?",
-            PERMISSIONS_NAME,
-            meta::AUTH_KS,
-            PERMISSIONS_CF,
-            ROLE_NAME,
-            RESOURCE_NAME);
+future<> auth::default_authorizer::grant(
+                ::shared_ptr<authenticated_user> performer, permission_set set,
+                data_resource resource, sstring to) {
+    return modify(std::move(performer), std::move(set), std::move(resource), std::move(to), "+");
+}
 
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::LOCAL_ONE,
-            infinite_timeout_config,
-            {*maybe_role.name, r.name()}).then([](::shared_ptr<cql3::untyped_result_set> results) {
-        if (results->empty()) {
-            return permissions::NONE;
+future<> auth::default_authorizer::revoke(
+                ::shared_ptr<authenticated_user> performer, permission_set set,
+                data_resource resource, sstring from) {
+    return modify(std::move(performer), std::move(set), std::move(resource), std::move(from), "-");
+}
+
+future<std::vector<auth::permission_details>> auth::default_authorizer::list(
+                service& ser, ::shared_ptr<authenticated_user> performer, permission_set set,
+                optional<data_resource> resource, optional<sstring> user) const {
+    return auth::is_super_user(ser, *performer).then([this, performer, set = std::move(set), resource = std::move(resource), user = std::move(user)](bool is_super) {
+        if (!is_super && (!user || performer->name() != *user)) {
+            throw exceptions::unauthorized_exception(sprint("You are not authorized to view %s's permissions", user ? *user : "everyone"));
         }
 
-        return permissions::from_strings(results->one().get_set<sstring>(PERMISSIONS_NAME));
-    });
-}
+        auto query = sprint("SELECT %s, %s, %s FROM %s.%s", USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME, meta::AUTH_KS, PERMISSIONS_CF);
 
-future<>
-default_authorizer::modify(
-        std::string_view role_name,
-        permission_set set,
-        const resource& resource,
-        std::string_view op) const {
-    return do_with(
-            format("UPDATE {}.{} SET {} = {} {} ? WHERE {} = ? AND {} = ?",
-                    meta::AUTH_KS,
-                    PERMISSIONS_CF,
-                    PERMISSIONS_NAME,
-                    PERMISSIONS_NAME,
-                    op,
-                    ROLE_NAME,
-                    RESOURCE_NAME),
-            [this, &role_name, set, &resource](const auto& query) {
-        return _qp.execute_internal(
-                query,
-                db::consistency_level::ONE,
-                internal_distributed_timeout_config(),
-                {permissions::to_strings(set), sstring(role_name), resource.name()}).discard_result();
-    });
-}
+        // Oh, look, it is a case where it does not pay off to have
+        // parameters to process in an initializer list.
+        future<::shared_ptr<cql3::untyped_result_set>> f = make_ready_future<::shared_ptr<cql3::untyped_result_set>>();
 
+        if (resource && user) {
+            query += sprint(" WHERE %s = ? AND %s = ?", USER_NAME, RESOURCE_NAME);
+            f = _qp.process(query, db::consistency_level::ONE, {*user, resource->name()});
+        } else if (resource) {
+            query += sprint(" WHERE %s = ? ALLOW FILTERING", RESOURCE_NAME);
+            f = _qp.process(query, db::consistency_level::ONE, {resource->name()});
+        } else if (user) {
+            query += sprint(" WHERE %s = ?", USER_NAME);
+            f = _qp.process(query, db::consistency_level::ONE, {*user});
+        } else {
+            f = _qp.process(query, db::consistency_level::ONE, {});
+        }
 
-future<> default_authorizer::grant(std::string_view role_name, permission_set set, const resource& resource) const {
-    return modify(role_name, std::move(set), resource, "+");
-}
+        return f.then([set](::shared_ptr<cql3::untyped_result_set> res) {
+            std::vector<permission_details> result;
 
-future<> default_authorizer::revoke(std::string_view role_name, permission_set set, const resource& resource) const {
-    return modify(role_name, std::move(set), resource, "-");
-}
+            for (auto& row : *res) {
+                if (row.has(PERMISSIONS_NAME)) {
+                    auto username = row.get_as<sstring>(USER_NAME);
+                    auto resource = data_resource::from_name(row.get_as<sstring>(RESOURCE_NAME));
+                    auto ps = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
+                    ps = permission_set::from_mask(ps.mask() & set.mask());
 
-future<std::vector<permission_details>> default_authorizer::list_all() const {
-    static const sstring query = format("SELECT {}, {}, {} FROM {}.{}",
-            ROLE_NAME,
-            RESOURCE_NAME,
-            PERMISSIONS_NAME,
-            meta::AUTH_KS,
-            PERMISSIONS_CF);
-
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::ONE,
-            internal_distributed_timeout_config(),
-            {},
-            true).then([](::shared_ptr<cql3::untyped_result_set> results) {
-        std::vector<permission_details> all_details;
-
-        for (const auto& row : *results) {
-            if (row.has(PERMISSIONS_NAME)) {
-                auto role_name = row.get_as<sstring>(ROLE_NAME);
-                auto resource = parse_resource(row.get_as<sstring>(RESOURCE_NAME));
-                auto perms = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
-                all_details.push_back(permission_details{std::move(role_name), std::move(resource), std::move(perms)});
+                    result.emplace_back(permission_details {username, resource, ps});
+                }
             }
-        }
-
-        return all_details;
+            return make_ready_future<std::vector<permission_details>>(std::move(result));
+        });
     });
 }
 
-future<> default_authorizer::revoke_all(std::string_view role_name) const {
-    static const sstring query = format("DELETE FROM {}.{} WHERE {} = ?",
-            meta::AUTH_KS,
-            PERMISSIONS_CF,
-            ROLE_NAME);
-
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::ONE,
-            internal_distributed_timeout_config(),
-            {sstring(role_name)}).discard_result().handle_exception([role_name](auto ep) {
-        try {
-            std::rethrow_exception(ep);
-        } catch (exceptions::request_execution_exception& e) {
-            alogger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", role_name, e);
-        }
-    });
+future<> auth::default_authorizer::revoke_all(sstring dropped_user) {
+    auto query = sprint("DELETE FROM %s.%s WHERE %s = ?", meta::AUTH_KS,
+                    PERMISSIONS_CF, USER_NAME);
+    return _qp.process(query, db::consistency_level::ONE, { dropped_user }).discard_result().handle_exception(
+                    [dropped_user](auto ep) {
+                        try {
+                            std::rethrow_exception(ep);
+                        } catch (exceptions::request_execution_exception& e) {
+                            alogger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", dropped_user, e);
+                        }
+                    });
 }
 
-future<> default_authorizer::revoke_all(const resource& resource) const {
-    static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? ALLOW FILTERING",
-            ROLE_NAME,
-            meta::AUTH_KS,
-            PERMISSIONS_CF,
-            RESOURCE_NAME);
-
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::LOCAL_ONE,
-            infinite_timeout_config,
-            {resource.name()}).then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
+future<> auth::default_authorizer::revoke_all(data_resource resource) {
+    auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? ALLOW FILTERING",
+                    USER_NAME, meta::AUTH_KS, PERMISSIONS_CF, RESOURCE_NAME);
+    return _qp.process(query, db::consistency_level::LOCAL_ONE, { resource.name() })
+                    .then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
         try {
             auto res = f.get0();
-            return parallel_for_each(
-                    res->begin(),
-                    res->end(),
-                    [this, res, resource](const cql3::untyped_result_set::row& r) {
-                static const sstring query = format("DELETE FROM {}.{} WHERE {} = ? AND {} = ?",
-                        meta::AUTH_KS,
-                        PERMISSIONS_CF,
-                        ROLE_NAME,
-                        RESOURCE_NAME);
-
-                return _qp.execute_internal(
-                        query,
-                        db::consistency_level::LOCAL_ONE,
-                        infinite_timeout_config,
-                        {r.get_as<sstring>(ROLE_NAME), resource.name()}).discard_result().handle_exception(
-                                [resource](auto ep) {
+            return parallel_for_each(res->begin(), res->end(), [this, res, resource](const cql3::untyped_result_set::row& r) {
+                auto query = sprint("DELETE FROM %s.%s WHERE %s = ? AND %s = ?"
+                                , meta::AUTH_KS, PERMISSIONS_CF, USER_NAME, RESOURCE_NAME);
+                return _qp.process(query, db::consistency_level::LOCAL_ONE, { r.get_as<sstring>(USER_NAME), resource.name() })
+                                .discard_result().handle_exception([resource](auto ep) {
                     try {
                         std::rethrow_exception(ep);
                     } catch (exceptions::request_execution_exception& e) {
@@ -333,9 +246,12 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
     });
 }
 
-const resource_set& default_authorizer::protected_resources() const {
-    static const resource_set resources({ make_data_resource(meta::AUTH_KS, PERMISSIONS_CF) });
-    return resources;
+
+const auth::resource_ids& auth::default_authorizer::protected_resources() {
+    static const resource_ids ids({ data_resource(meta::AUTH_KS, PERMISSIONS_CF) });
+    return ids;
 }
 
+future<> auth::default_authorizer::validate_configuration() const {
+    return make_ready_future();
 }

auth/default_authorizer.hh

@@ -43,56 +43,49 @@
 
 #include <functional>
 
-#include <seastar/core/abort_source.hh>
-
-#include "auth/authorizer.hh"
+#include "authorizer.hh"
 #include "cql3/query_processor.hh"
 #include "service/migration_manager.hh"
 
 namespace auth {
 
+const sstring& default_authorizer_name();
+
 class default_authorizer : public authorizer {
     cql3::query_processor& _qp;
 
     ::service::migration_manager& _migration_manager;
 
-    abort_source _as{};
-
-    future<> _finished{make_ready_future<>()};
-
 public:
     default_authorizer(cql3::query_processor&, ::service::migration_manager&);
-
     ~default_authorizer();
 
-    virtual future<> start() override;
+    future<> start() override;
 
-    virtual future<> stop() override;
+    future<> stop() override;
 
-    virtual std::string_view qualified_java_name() const override;
+    const sstring& qualified_java_name() const override {
+        return default_authorizer_name();
+    }
 
-    virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override;
+    future<permission_set> authorize(service&, ::shared_ptr<authenticated_user>, data_resource) const override;
 
-    virtual future<> grant(std::string_view, permission_set, const resource&) const override;
+    future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
 
-    virtual future<> revoke( std::string_view, permission_set, const resource&) const override;
+    future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
 
-    virtual future<std::vector<permission_details>> list_all() const override;
+    future<std::vector<permission_details>> list(service&, ::shared_ptr<authenticated_user>, permission_set, optional<data_resource>, optional<sstring>) const override;
 
-    virtual future<> revoke_all(std::string_view) const override;
+    future<> revoke_all(sstring) override;
 
-    virtual future<> revoke_all(const resource&) const override;
+    future<> revoke_all(data_resource) override;
 
-    virtual const resource_set& protected_resources() const override;
+    const resource_ids& protected_resources() override;
+
+    future<> validate_configuration() const override;
 
 private:
-    bool legacy_metadata_exists() const;
-
-    future<bool> any_granted() const;
-
-    future<> migrate_legacy_metadata() const;
-
-    future<> modify(std::string_view, permission_set, const resource&, std::string_view) const;
+    future<> modify(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring, sstring);
 };
 
 } /* namespace auth */

auth/password_authenticator.cc

@@ -39,184 +39,198 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "auth/password_authenticator.hh"
-
-#include <algorithm>
-#include <chrono>
+#include <unistd.h>
+#include <crypt.h>
 #include <random>
-#include <string_view>
-#include <optional>
+#include <chrono>
 
-#include <boost/algorithm/cxx11/all_of.hpp>
-#include <seastar/core/seastar.hh>
+#include <seastar/core/reactor.hh>
 
-#include "auth/authenticated_user.hh"
-#include "auth/common.hh"
-#include "auth/passwords.hh"
-#include "auth/roles-metadata.hh"
+#include "common.hh"
+#include "password_authenticator.hh"
+#include "authenticated_user.hh"
 #include "cql3/untyped_result_set.hh"
 #include "log.hh"
 #include "service/migration_manager.hh"
 #include "utils/class_registrator.hh"
-#include "database.hh"
 
-namespace auth {
-
-constexpr std::string_view password_authenticator_name("org.apache.cassandra.auth.PasswordAuthenticator");
+const sstring& auth::password_authenticator_name() {
+    static const sstring name = meta::AUTH_PACKAGE_NAME + "PasswordAuthenticator";
+    return name;
+}
 
 // name of the hash column.
-static constexpr std::string_view SALTED_HASH = "salted_hash";
-static constexpr std::string_view DEFAULT_USER_NAME = meta::DEFAULT_SUPERUSER_NAME;
-static const sstring DEFAULT_USER_PASSWORD = sstring(meta::DEFAULT_SUPERUSER_NAME);
+static const sstring SALTED_HASH = "salted_hash";
+static const sstring USER_NAME = "username";
+static const sstring DEFAULT_USER_NAME = auth::meta::DEFAULT_SUPERUSER_NAME;
+static const sstring DEFAULT_USER_PASSWORD = auth::meta::DEFAULT_SUPERUSER_NAME;
+static const sstring CREDENTIALS_CF = "credentials";
 
 static logging::logger plogger("password_authenticator");
 
 // To ensure correct initialization order, we unfortunately need to use a string literal.
 static const class_registrator<
-        authenticator,
-        password_authenticator,
+        auth::authenticator,
+        auth::password_authenticator,
         cql3::query_processor&,
         ::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.PasswordAuthenticator");
 
-static thread_local auto rng_for_salt = std::default_random_engine(std::random_device{}());
+auth::password_authenticator::~password_authenticator()
+{}
 
-password_authenticator::~password_authenticator() {
-}
-
-password_authenticator::password_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
+auth::password_authenticator::password_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
     : _qp(qp)
-    , _migration_manager(mm)
-    , _stopped(make_ready_future<>()) {
+    , _migration_manager(mm) {
 }
 
-static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
-    return !row.get_or<sstring>(SALTED_HASH, "").empty();
+// TODO: blowfish
+// Origin uses Java bcrypt library, i.e. blowfish salt
+// generation and hashing, which is arguably a "better"
+// password hash than sha/md5 versions usually available in
+// crypt_r. Otoh, glibc 2.7+ uses a modified sha512 algo
+// which should be the same order of safe, so the only
+// real issue should be salted hash compatibility with
+// origin if importing system tables from there.
+//
+// Since bcrypt/blowfish is _not_ (afaict) not available
+// as a dev package/lib on most linux distros, we'd have to
+// copy and compile for example OWL  crypto
+// (http://cvsweb.openwall.com/cgi/cvsweb.cgi/Owl/packages/glibc/crypt_blowfish/)
+// to be fully bit-compatible.
+//
+// Until we decide this is needed, let's just use crypt_r,
+// and some old-fashioned random salt generation.
+
+static constexpr size_t rand_bytes = 16;
+static thread_local crypt_data tlcrypt = { 0, };
+
+static sstring hashpw(const sstring& pass, const sstring& salt) {
+    auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
+    if (res == nullptr) {
+        throw std::system_error(errno, std::system_category());
+    }
+    return res;
 }
 
-static const sstring& update_row_query() {
-    static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} = ?",
-            meta::roles_table::qualified_name,
-            SALTED_HASH,
-            meta::roles_table::role_col_name);
-    return update_row_query;
+static bool checkpw(const sstring& pass, const sstring& salted_hash) {
+    auto tmp = hashpw(pass, salted_hash);
+    return tmp == salted_hash;
 }
 
-static const sstring legacy_table_name{"credentials"};
+static sstring gensalt() {
+    static sstring prefix;
 
-bool password_authenticator::legacy_metadata_exists() const {
-    return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
-}
+    std::random_device rd;
+    std::default_random_engine e1(rd());
+    std::uniform_int_distribution<char> dist;
 
-future<> password_authenticator::migrate_legacy_metadata() const {
-    plogger.info("Starting migration of legacy authentication metadata.");
-    static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
+    sstring valid_salt = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
+    sstring input(rand_bytes, 0);
 
-    return _qp.execute_internal(
-            query,
-            db::consistency_level::QUORUM,
-            internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
-        return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
-            auto username = row.get_as<sstring>("username");
-            auto salted_hash = row.get_as<sstring>(SALTED_HASH);
+    for (char&c : input) {
+        c = valid_salt[dist(e1) % valid_salt.size()];
+    }
 
-            return _qp.execute_internal(
-                    update_row_query(),
-                    consistency_for_user(username),
-                    internal_distributed_timeout_config(),
-                    {std::move(salted_hash), username}).discard_result();
-        }).finally([results] {});
-    }).then([] {
-       plogger.info("Finished migrating legacy authentication metadata.");
-    }).handle_exception([](std::exception_ptr ep) {
-        plogger.error("Encountered an error during migration!");
-        std::rethrow_exception(ep);
-    });
-}
+    sstring salt;
 
-future<> password_authenticator::create_default_if_missing() const {
-    return default_role_row_satisfies(_qp, &has_salted_hash).then([this](bool exists) {
-        if (!exists) {
-            return _qp.execute_internal(
-                    update_row_query(),
-                    db::consistency_level::QUORUM,
-                    internal_distributed_timeout_config(),
-                    {passwords::hash(DEFAULT_USER_PASSWORD, rng_for_salt), DEFAULT_USER_NAME}).then([](auto&&) {
-                plogger.info("Created default superuser authentication record.");
-            });
+    if (!prefix.empty()) {
+        return prefix + input;
+    }
+
+    // Try in order:
+    // blowfish 2011 fix, blowfish, sha512, sha256, md5
+    for (sstring pfx : { "$2y$", "$2a$", "$6$", "$5$", "$1$" }) {
+        salt = pfx + input;
+        const char* e = crypt_r("fisk", salt.c_str(), &tlcrypt);
+
+        if (e && (e[0] != '*')) {
+            prefix = pfx;
+            return salt;
         }
+    }
+    throw std::runtime_error("Could not initialize hashing algorithm");
+}
 
-        return make_ready_future<>();
+static sstring hashpw(const sstring& pass) {
+    return hashpw(pass, gensalt());
+}
+
+future<> auth::password_authenticator::start() {
+    return auth::once_among_shards([this] {
+        gensalt(); // do this once to determine usable hashing
+
+        static const sstring create_table = sprint(
+                "CREATE TABLE %s.%s ("
+                "%s text,"
+                "%s text," // salt + hash + number of rounds
+                "options map<text,text>,"// for future extensions
+                "PRIMARY KEY(%s)"
+                ") WITH gc_grace_seconds=%d",
+                meta::AUTH_KS,
+                CREDENTIALS_CF, USER_NAME, SALTED_HASH, USER_NAME,
+                90 * 24 * 60 * 60); // 3 months.
+
+        return auth::create_metadata_table_if_missing(
+                CREDENTIALS_CF,
+                _qp,
+                create_table,
+                _migration_manager).then([this] {
+            auth::delay_until_system_ready(_delayed, [this] {
+                return has_existing_users().then([this](bool existing) {
+                    if (!existing) {
+                        return _qp.process(
+                                sprint(
+                                        "INSERT INTO %s.%s (%s, %s) VALUES (?, ?) USING TIMESTAMP 0",
+                                        meta::AUTH_KS,
+                                        CREDENTIALS_CF,
+                                        USER_NAME, SALTED_HASH),
+                                db::consistency_level::ONE,
+                                { DEFAULT_USER_NAME, hashpw(DEFAULT_USER_PASSWORD) }).then([](auto) {
+                            plogger.info("Created default user '{}'", DEFAULT_USER_NAME);
+                        });
+                    }
+
+                    return make_ready_future<>();
+                });
+            });
+        });
     });
 }
 
-future<> password_authenticator::start() {
-     return once_among_shards([this] {
-         auto f = create_metadata_table_if_missing(
-                 meta::roles_table::name,
-                 _qp,
-                 meta::roles_table::creation_query(),
-                 _migration_manager);
-
-         _stopped = do_after_system_ready(_as, [this] {
-             return async([this] {
-                 wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
-
-                 if (any_nondefault_role_row_satisfies(_qp, &has_salted_hash).get0()) {
-                     if (legacy_metadata_exists()) {
-                         plogger.warn("Ignoring legacy authentication metadata since nondefault data already exist.");
-                     }
-
-                     return;
-                 }
-
-                 if (legacy_metadata_exists()) {
-                     migrate_legacy_metadata().get0();
-                     return;
-                 }
-
-                 create_default_if_missing().get0();
-             });
-         });
-
-         return f;
-     });
- }
-
-future<> password_authenticator::stop() {
-    _as.request_abort();
-    return _stopped.handle_exception_type([] (const sleep_aborted&) { }).handle_exception_type([](const abort_requested_exception&) {});
+future<> auth::password_authenticator::stop() {
+    return make_ready_future<>();
 }
 
-db::consistency_level password_authenticator::consistency_for_user(std::string_view role_name) {
-    if (role_name == DEFAULT_USER_NAME) {
+db::consistency_level auth::password_authenticator::consistency_for_user(const sstring& username) {
+    if (username == DEFAULT_USER_NAME) {
         return db::consistency_level::QUORUM;
     }
     return db::consistency_level::LOCAL_ONE;
 }
 
-std::string_view password_authenticator::qualified_java_name() const {
-    return password_authenticator_name;
+const sstring& auth::password_authenticator::qualified_java_name() const {
+    return password_authenticator_name();
 }
 
-bool password_authenticator::require_authentication() const {
+bool auth::password_authenticator::require_authentication() const {
     return true;
 }
 
-authentication_option_set password_authenticator::supported_options() const {
-    return authentication_option_set{authentication_option::password};
+auth::authenticator::option_set auth::password_authenticator::supported_options() const {
+    return option_set::of<option::PASSWORD>();
 }
 
-authentication_option_set password_authenticator::alterable_options() const {
-    return authentication_option_set{authentication_option::password};
+auth::authenticator::option_set auth::password_authenticator::alterable_options() const {
+    return option_set::of<option::PASSWORD>();
 }
 
-future<authenticated_user> password_authenticator::authenticate(
+future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::authenticate(
                 const credentials_map& credentials) const {
-    if (!credentials.contains(USERNAME_KEY)) {
-        throw exceptions::authentication_exception(format("Required key '{}' is missing", USERNAME_KEY));
+    if (!credentials.count(USERNAME_KEY)) {
+        throw exceptions::authentication_exception(sprint("Required key '%s' is missing", USERNAME_KEY));
     }
-    if (!credentials.contains(PASSWORD_KEY)) {
-        throw exceptions::authentication_exception(format("Required key '{}' is missing", PASSWORD_KEY));
+    if (!credentials.count(PASSWORD_KEY)) {
+        throw exceptions::authentication_exception(sprint("Required key '%s' is missing", PASSWORD_KEY));
     }
 
     auto& username = credentials.at(USERNAME_KEY);
@@ -227,98 +241,178 @@ future<authenticated_user> password_authenticator::authenticate(
     // obsolete prepared statements pretty quickly.
     // Rely on query processing caching statements instead, and lets assume
     // that a map lookup string->statement is not gonna kill us much.
-    return futurize_invoke([this, username, password] {
-        static const sstring query = format("SELECT {} FROM {} WHERE {} = ?",
-                SALTED_HASH,
-                meta::roles_table::qualified_name,
-                meta::roles_table::role_col_name);
-
-        return _qp.execute_internal(
-                query,
-                consistency_for_user(username),
-                internal_distributed_timeout_config(),
-                {username},
-                true);
+    return futurize_apply([this, username, password] {
+        return _qp.process(sprint("SELECT %s FROM %s.%s WHERE %s = ?", SALTED_HASH,
+                                        meta::AUTH_KS, CREDENTIALS_CF, USER_NAME),
+                        consistency_for_user(username), {username}, true);
     }).then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
         try {
             auto res = f.get0();
-            auto salted_hash = std::optional<sstring>();
-            if (!res->empty()) {
-                salted_hash = res->one().get_opt<sstring>(SALTED_HASH);
-            }
-            if (!salted_hash || !passwords::check(password, *salted_hash)) {
+            if (res->empty() || !checkpw(password, res->one().get_as<sstring>(SALTED_HASH))) {
                 throw exceptions::authentication_exception("Username and/or password are incorrect");
             }
-            return make_ready_future<authenticated_user>(username);
+            return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>(username));
         } catch (std::system_error &) {
             std::throw_with_nested(exceptions::authentication_exception("Could not verify password"));
         } catch (exceptions::request_execution_exception& e) {
             std::throw_with_nested(exceptions::authentication_exception(e.what()));
-        } catch (exceptions::authentication_exception& e) {
-            std::throw_with_nested(e);
         } catch (...) {
             std::throw_with_nested(exceptions::authentication_exception("authentication failed"));
         }
     });
 }
 
-future<> password_authenticator::create(std::string_view role_name, const authentication_options& options) const {
-    if (!options.password) {
-        return make_ready_future<>();
+future<> auth::password_authenticator::create(sstring username,
+                const option_map& options) {
+    try {
+        auto password = boost::any_cast<sstring>(options.at(option::PASSWORD));
+        auto query = sprint("INSERT INTO %s.%s (%s, %s) VALUES (?, ?)",
+                        meta::AUTH_KS, CREDENTIALS_CF, USER_NAME, SALTED_HASH);
+        return _qp.process(query, consistency_for_user(username), { username, hashpw(password) }).discard_result();
+    } catch (std::out_of_range&) {
+        throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
     }
-
-    return _qp.execute_internal(
-            update_row_query(),
-            consistency_for_user(role_name),
-            internal_distributed_timeout_config(),
-            {passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
 }
 
-future<> password_authenticator::alter(std::string_view role_name, const authentication_options& options) const {
-    if (!options.password) {
-        return make_ready_future<>();
+future<> auth::password_authenticator::alter(sstring username,
+                const option_map& options) {
+    try {
+        auto password = boost::any_cast<sstring>(options.at(option::PASSWORD));
+        auto query = sprint("UPDATE %s.%s SET %s = ? WHERE %s = ?",
+                        meta::AUTH_KS, CREDENTIALS_CF, SALTED_HASH, USER_NAME);
+        return _qp.process(query, consistency_for_user(username), { hashpw(password), username }).discard_result();
+    } catch (std::out_of_range&) {
+        throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
     }
-
-    static const sstring query = format("UPDATE {} SET {} = ? WHERE {} = ?",
-            meta::roles_table::qualified_name,
-            SALTED_HASH,
-            meta::roles_table::role_col_name);
-
-    return _qp.execute_internal(
-            query,
-            consistency_for_user(role_name),
-            internal_distributed_timeout_config(),
-            {passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
 }
 
-future<> password_authenticator::drop(std::string_view name) const {
-    static const sstring query = format("DELETE {} FROM {} WHERE {} = ?",
-            SALTED_HASH,
-            meta::roles_table::qualified_name,
-            meta::roles_table::role_col_name);
-
-    return _qp.execute_internal(
-            query, consistency_for_user(name),
-            internal_distributed_timeout_config(),
-            {sstring(name)}).discard_result();
+future<> auth::password_authenticator::drop(sstring username) {
+    try {
+        auto query = sprint("DELETE FROM %s.%s WHERE %s = ?",
+                        meta::AUTH_KS, CREDENTIALS_CF, USER_NAME);
+        return _qp.process(query, consistency_for_user(username), { username }).discard_result();
+    } catch (std::out_of_range&) {
+        throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
+    }
 }
 
-future<custom_options> password_authenticator::query_custom_options(std::string_view role_name) const {
-    return make_ready_future<custom_options>();
+const auth::resource_ids& auth::password_authenticator::protected_resources() const {
+    static const resource_ids ids({ data_resource(meta::AUTH_KS, CREDENTIALS_CF) });
+    return ids;
 }
 
-const resource_set& password_authenticator::protected_resources() const {
-    static const resource_set resources({make_data_resource(meta::AUTH_KS, meta::roles_table::name)});
-    return resources;
+::shared_ptr<auth::authenticator::sasl_challenge> auth::password_authenticator::new_sasl_challenge() const {
+    class plain_text_password_challenge: public sasl_challenge {
+        const password_authenticator& _self;
+
+    public:
+        plain_text_password_challenge(const password_authenticator& self) : _self(self)
+        {}
+
+        /**
+         * SASL PLAIN mechanism specifies that credentials are encoded in a
+         * sequence of UTF-8 bytes, delimited by 0 (US-ASCII NUL).
+         * The form is : {code}authzId<NUL>authnId<NUL>password<NUL>{code}
+         * authzId is optional, and in fact we don't care about it here as we'll
+         * set the authzId to match the authnId (that is, there is no concept of
+         * a user being authorized to act on behalf of another).
+         *
+         * @param bytes encoded credentials string sent by the client
+         * @return map containing the username/password pairs in the form an IAuthenticator
+         * would expect
+         * @throws javax.security.sasl.SaslException
+         */
+        bytes evaluate_response(bytes_view client_response) override {
+            plogger.debug("Decoding credentials from client token");
+
+            sstring username, password;
+
+            auto b = client_response.crbegin();
+            auto e = client_response.crend();
+            auto i = b;
+
+            while (i != e) {
+                if (*i == 0) {
+                    sstring tmp(i.base(), b.base());
+                    if (password.empty()) {
+                        password = std::move(tmp);
+                    } else if (username.empty()) {
+                        username = std::move(tmp);
+                    }
+                    b = ++i;
+                    continue;
+                }
+                ++i;
+            }
+
+            if (username.empty()) {
+                throw exceptions::authentication_exception("Authentication ID must not be null");
+            }
+            if (password.empty()) {
+                throw exceptions::authentication_exception("Password must not be null");
+            }
+
+            _credentials[USERNAME_KEY] = std::move(username);
+            _credentials[PASSWORD_KEY] = std::move(password);
+            _complete = true;
+            return {};
+        }
+        bool is_complete() const override {
+            return _complete;
+        }
+        future<::shared_ptr<authenticated_user>> get_authenticated_user() const override {
+            return _self.authenticate(_credentials);
+        }
+    private:
+        credentials_map _credentials;
+        bool _complete = false;
+    };
+    return ::make_shared<plain_text_password_challenge>(*this);
 }
 
-::shared_ptr<sasl_challenge> password_authenticator::new_sasl_challenge() const {
-    return ::make_shared<plain_sasl_challenge>([this](std::string_view username, std::string_view password) {
-        credentials_map credentials{};
-        credentials[USERNAME_KEY] = sstring(username);
-        credentials[PASSWORD_KEY] = sstring(password);
-        return this->authenticate(credentials);
+
+//
+// Similar in structure to `auth::service::has_existing_users()`, but trying to generalize the pattern breaks all kinds
+// of module boundaries and leaks implementation details.
+//
+future<bool> auth::password_authenticator::has_existing_users() const {
+    static const sstring default_user_query = sprint(
+            "SELECT * FROM %s.%s WHERE %s = ?",
+            meta::AUTH_KS,
+            CREDENTIALS_CF,
+            USER_NAME);
+
+    static const sstring all_users_query = sprint(
+            "SELECT * FROM %s.%s LIMIT 1",
+            meta::AUTH_KS,
+            CREDENTIALS_CF);
+
+    // This logic is borrowed directly from Apache Cassandra. By first checking for the presence of the default user, we
+    // can potentially avoid doing a range query with a high consistency level.
+
+    return _qp.process(
+            default_user_query,
+            db::consistency_level::ONE,
+            { meta::DEFAULT_SUPERUSER_NAME },
+            true).then([this](auto results) {
+        if (!results->empty()) {
+            return make_ready_future<bool>(true);
+        }
+
+        return _qp.process(
+                default_user_query,
+                db::consistency_level::QUORUM,
+                { meta::DEFAULT_SUPERUSER_NAME },
+                true).then([this](auto results) {
+            if (!results->empty()) {
+                return make_ready_future<bool>(true);
+            }
+
+            return _qp.process(
+                    all_users_query,
+                    db::consistency_level::QUORUM).then([](auto results) {
+                return make_ready_future<bool>(!results->empty());
+            });
+        });
     });
 }
-
-}

auth/password_authenticator.hh

@@ -41,10 +41,9 @@
 
 #pragma once
 
-#include <seastar/core/abort_source.hh>
-
-#include "auth/authenticator.hh"
+#include "authenticator.hh"
 #include "cql3/query_processor.hh"
+#include "delayed_tasks.hh"
 
 namespace service {
 class migration_manager;
@@ -52,53 +51,39 @@ class migration_manager;
 
 namespace auth {
 
-extern const std::string_view password_authenticator_name;
+const sstring& password_authenticator_name();
 
 class password_authenticator : public authenticator {
     cql3::query_processor& _qp;
+
     ::service::migration_manager& _migration_manager;
-    future<> _stopped;
-    seastar::abort_source _as;
+
+    delayed_tasks<> _delayed{};
 
 public:
-    static db::consistency_level consistency_for_user(std::string_view role_name);
-
     password_authenticator(cql3::query_processor&, ::service::migration_manager&);
-
     ~password_authenticator();
 
-    virtual future<> start() override;
+    future<> start() override;
 
-    virtual future<> stop() override;
+    future<> stop() override;
 
-    virtual std::string_view qualified_java_name() const override;
+    const sstring& qualified_java_name() const override;
+    bool require_authentication() const override;
+    option_set supported_options() const override;
+    option_set alterable_options() const override;
+    future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override;
+    future<> create(sstring username, const option_map& options) override;
+    future<> alter(sstring username, const option_map& options) override;
+    future<> drop(sstring username) override;
+    const resource_ids& protected_resources() const override;
+    ::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
 
-    virtual bool require_authentication() const override;
 
-    virtual authentication_option_set supported_options() const override;
-
-    virtual authentication_option_set alterable_options() const override;
-
-    virtual future<authenticated_user> authenticate(const credentials_map& credentials) const override;
-
-    virtual future<> create(std::string_view role_name, const authentication_options& options) const override;
-
-    virtual future<> alter(std::string_view role_name, const authentication_options& options) const override;
-
-    virtual future<> drop(std::string_view role_name) const override;
-
-    virtual future<custom_options> query_custom_options(std::string_view role_name) const override;
-
-    virtual const resource_set& protected_resources() const override;
-
-    virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
+    static db::consistency_level consistency_for_user(const sstring& username);
 
 private:
-    bool legacy_metadata_exists() const;
-
-    future<> migrate_legacy_metadata() const;
-
-    future<> create_default_if_missing() const;
+    future<bool> has_existing_users() const;
 };
 
 }

auth/passwords.cc

@@ -1,84 +0,0 @@
-/*
- * Copyright (C) 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "auth/passwords.hh"
-
-#include <cerrno>
-#include <optional>
-
-extern "C" {
-#include <crypt.h>
-#include <unistd.h>
-}
-
-namespace auth::passwords {
-
-static thread_local crypt_data tlcrypt = { 0, };
-
-namespace detail {
-
-scheme identify_best_supported_scheme() {
-    const auto all_schemes = { scheme::bcrypt_y, scheme::bcrypt_a, scheme::sha_512, scheme::sha_256, scheme::md5 };
-    // "Random", for testing schemes.
-    const sstring random_part_of_salt = "aaaabbbbccccdddd";
-
-    for (scheme c : all_schemes) {
-        const sstring salt = sstring(prefix_for_scheme(c)) + random_part_of_salt;
-        const char* e = crypt_r("fisk", salt.c_str(), &tlcrypt);
-
-        if (e && (e[0] != '*')) {
-            return c;
-        }
-    }
-
-    throw no_supported_schemes();
-}
-
-sstring hash_with_salt(const sstring& pass, const sstring& salt) {
-    auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
-    if (!res || (res[0] == '*')) {
-        throw std::system_error(errno, std::system_category());
-    }
-    return res;
-}
-
-const char* prefix_for_scheme(scheme c) noexcept {
-    switch (c) {
-    case scheme::bcrypt_y: return "$2y$";
-    case scheme::bcrypt_a: return "$2a$";
-    case scheme::sha_512: return "$6$";
-    case scheme::sha_256: return "$5$";
-    case scheme::md5: return "$1$";
-    default: return nullptr;
-    }
-}
-
-} // namespace detail
-
-no_supported_schemes::no_supported_schemes()
-        : std::runtime_error("No allowed hashing schemes are supported on this system") {
-}
-
-bool check(const sstring& pass, const sstring& salted_hash) {
-    return detail::hash_with_salt(pass, salted_hash) == salted_hash;
-}
-
-} // namespace auth::paswords

auth/passwords.hh

@@ -1,125 +0,0 @@
-/*
- * Copyright (C) 2018 ScyllaDB
- */
-
-/*
- * This file is part of Scylla.
- *
- * Scylla is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Affero General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Scylla is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <random>
-#include <stdexcept>
-
-#include <seastar/core/sstring.hh>
-
-#include "seastarx.hh"
-
-namespace auth::passwords {
-
-class no_supported_schemes : public std::runtime_error {
-public:
-    no_supported_schemes();
-};
-
-///
-/// Apache Cassandra uses a library to provide the bcrypt scheme. Many Linux implementations do not support bcrypt, so
-/// we support alternatives. The cost is loss of direct compatibility with Apache Cassandra system tables.
-///
-enum class scheme {
-    bcrypt_y,
-    bcrypt_a,
-    sha_512,
-    sha_256,
-    md5
-};
-
-namespace detail {
-
-template <typename RandomNumberEngine>
-sstring generate_random_salt_bytes(RandomNumberEngine& g) {
-    static const sstring valid_bytes = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
-    static constexpr std::size_t num_bytes = 16;
-    std::uniform_int_distribution<std::size_t> dist(0, valid_bytes.size() - 1);
-    sstring result(num_bytes, 0);
-
-    for (char& c : result) {
-        c = valid_bytes[dist(g)];
-    }
-
-    return result;
-}
-
-///
-/// Test each allowed hashing scheme and report the best supported one on the current system.
-///
-/// \throws \ref no_supported_schemes when none of the known schemes is supported.
-///
-scheme identify_best_supported_scheme();
-
-const char* prefix_for_scheme(scheme) noexcept;
-
-///
-/// Generate a implementation-specific salt string for hashing passwords.
-///
-/// The `RandomNumberEngine` is used to generate the string, which is an implementation-specific length.
-///
-/// \throws \ref no_supported_schemes when no known hashing schemes are supported on the system.
-///
-template <typename RandomNumberEngine>
-sstring generate_salt(RandomNumberEngine& g) {
-    static const scheme scheme = identify_best_supported_scheme();
-    static const sstring prefix = sstring(prefix_for_scheme(scheme));
-    return prefix + generate_random_salt_bytes(g);
-}
-
-///
-/// Hash a password combined with an implementation-specific salt string.
-///
-/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
-///
-sstring hash_with_salt(const sstring& pass, const sstring& salt);
-
-} // namespace detail
-
-///
-/// Run a one-way hashing function on cleartext to produce encrypted text.
-///
-/// Prior to applying the hashing function, random salt is amended to the cleartext. The random salt bytes are generated
-/// according to the random number engine `g`.
-///
-/// The result is the encrypted cyphertext, and also the salt used but in a implementation-specific format.
-///
-/// \throws \ref std::system_error when the implementation-specific implementation fails to hash the cleartext.
-///
-template <typename RandomNumberEngine>
-sstring hash(const sstring& pass, RandomNumberEngine& g) {
-    return detail::hash_with_salt(pass, detail::generate_salt(g));
-}
-
-///
-/// Check that cleartext matches previously hashed cleartext with salt.
-///
-/// \ref salted_hash is the result of invoking \ref hash, which is the implementation-specific combination of the hashed
-/// password and the salt that was generated for it.
-///
-/// \returns `true` if the cleartext matches the salted hash.
-///
-/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
-///
-bool check(const sstring& pass, const sstring& salted_hash);
-
-} // namespace auth::passwords

auth/permission.cc

@@ -39,33 +39,32 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "auth/permission.hh"
-
-#include <boost/algorithm/string.hpp>
-
 #include <unordered_map>
+#include <boost/algorithm/string.hpp>
+#include "permission.hh"
 
-const auth::permission_set auth::permissions::ALL = auth::permission_set::of<
-        auth::permission::CREATE,
-        auth::permission::ALTER,
-        auth::permission::DROP,
-        auth::permission::SELECT,
-        auth::permission::MODIFY,
-        auth::permission::AUTHORIZE,
-        auth::permission::DESCRIBE>();
-
+const auth::permission_set auth::permissions::ALL_DATA =
+                auth::permission_set::of<auth::permission::CREATE,
+                                auth::permission::ALTER, auth::permission::DROP,
+                                auth::permission::SELECT,
+                                auth::permission::MODIFY,
+                                auth::permission::AUTHORIZE>();
+const auth::permission_set auth::permissions::ALL = auth::permissions::ALL_DATA;
 const auth::permission_set auth::permissions::NONE;
+const auth::permission_set auth::permissions::ALTERATIONS =
+                auth::permission_set::of<auth::permission::CREATE,
+                                auth::permission::ALTER, auth::permission::DROP>();
 
 static const std::unordered_map<sstring, auth::permission> permission_names({
-        {"READ", auth::permission::READ},
-        {"WRITE", auth::permission::WRITE},
-        {"CREATE", auth::permission::CREATE},
-        {"ALTER", auth::permission::ALTER},
-        {"DROP", auth::permission::DROP},
-        {"SELECT", auth::permission::SELECT},
-        {"MODIFY", auth::permission::MODIFY},
-        {"AUTHORIZE", auth::permission::AUTHORIZE},
-        {"DESCRIBE", auth::permission::DESCRIBE}});
+    { "READ", auth::permission::READ },
+    { "WRITE", auth::permission::WRITE  },
+    { "CREATE", auth::permission::CREATE },
+    { "ALTER", auth::permission::ALTER },
+    { "DROP", auth::permission::DROP },
+    { "SELECT", auth::permission::SELECT  },
+    { "MODIFY", auth::permission::MODIFY   },
+    { "AUTHORIZE", auth::permission::AUTHORIZE },
+});
 
 const sstring& auth::permissions::to_string(permission p) {
     for (auto& v : permission_names) {

auth/permission.hh

@@ -42,11 +42,10 @@
 #pragma once
 
 #include <unordered_set>
-
 #include <seastar/core/sstring.hh>
 
-#include "enum_set.hh"
 #include "seastarx.hh"
+#include "enum_set.hh"
 
 namespace auth {
 
@@ -67,13 +66,9 @@ enum class permission {
 
     // permission management
     AUTHORIZE, // required for GRANT and REVOKE.
-    DESCRIBE, // required on the root-level role resource to list all roles.
-
 };
 
-typedef enum_set<
-        super_enum<
-                permission,
+typedef enum_set<super_enum<permission,
                 permission::READ,
                 permission::WRITE,
                 permission::CREATE,
@@ -81,15 +76,16 @@ typedef enum_set<
                 permission::DROP,
                 permission::SELECT,
                 permission::MODIFY,
-                permission::AUTHORIZE,
-                permission::DESCRIBE>> permission_set;
+                permission::AUTHORIZE>> permission_set;
 
 bool operator<(const permission_set&, const permission_set&);
 
 namespace permissions {
 
+extern const permission_set ALL_DATA;
 extern const permission_set ALL;
 extern const permission_set NONE;
+extern const permission_set ALTERATIONS;
 
 const sstring& to_string(permission);
 permission from_string(const sstring&);
@@ -97,6 +93,7 @@ permission from_string(const sstring&);
 std::unordered_set<sstring> to_strings(const permission_set&);
 permission_set from_strings(const std::unordered_set<sstring>&);
 
+
 }
 
 }

auth/permissions_cache.cc

@@ -24,20 +24,28 @@
 #include "auth/authorizer.hh"
 #include "auth/common.hh"
 #include "auth/service.hh"
+#include "db/config.hh"
 
 namespace auth {
 
+permissions_cache_config permissions_cache_config::from_db_config(const db::config& dc) {
+    permissions_cache_config c;
+    c.max_entries = dc.permissions_cache_max_entries();
+    c.validity_period = std::chrono::milliseconds(dc.permissions_validity_in_ms());
+    c.update_period = std::chrono::milliseconds(dc.permissions_update_interval_in_ms());
+
+    return c;
+}
+
 permissions_cache::permissions_cache(const permissions_cache_config& c, service& ser, logging::logger& log)
         : _cache(c.max_entries, c.validity_period, c.update_period, log, [&ser, &log](const key_type& k) {
-              log.debug("Refreshing permissions for {}", k.first);
-              return ser.get_uncached_permissions(k.first, k.second);
+              log.debug("Refreshing permissions for {}", k.first.name());
+              return ser.underlying_authorizer().authorize(ser, ::make_shared<authenticated_user>(k.first), k.second);
           }) {
 }
 
-future<permission_set> permissions_cache::get(const role_or_anonymous& maybe_role, const resource& r) {
-    return do_with(key_type(maybe_role, r), [this](const auto& k) {
-        return _cache.get(k);
-    });
+future<permission_set> permissions_cache::get(::shared_ptr<authenticated_user> user, data_resource r) {
+    return _cache.get(key_type(*user, r));
 }
 
 }