mutation_partition: correctly measure static row size when doing digest calculation

The code uses incorrect output stream in case only digest is requested
and thus getting incorrect data size. Failing to correctly account
for static row size while calculating digest may cause digest mismatch
between digest and data query.

Fixes #3753.

Message-Id: <20180905131219.GD2326@scylladb.com>
(cherry picked from commit 98092353df)

.clang-format

@@ -1,209 +0,0 @@
----
-Language: Cpp
-AccessModifierOffset: -4
-AlignAfterOpenBracket: DontAlign
-AlignArrayOfStructures: None
-AlignConsecutiveAssignments:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: true
-AlignConsecutiveBitFields:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveDeclarations:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveMacros:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveShortCaseStatements:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCaseColons: false
-AlignEscapedNewlines: Right
-AlignOperands: Align
-AlignTrailingComments:
-  Kind: Always
-  OverEmptyLines: 0
-AllowAllArgumentsOnNextLine: true
-AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortBlocksOnASingleLine: Never
-AllowShortCaseLabelsOnASingleLine: false
-AllowShortEnumsOnASingleLine: true
-AllowShortFunctionsOnASingleLine: None
-AllowShortIfStatementsOnASingleLine: Never
-AllowShortLambdasOnASingleLine: Empty
-AllowShortLoopsOnASingleLine: false
-AlwaysBreakAfterDefinitionReturnType: None
-AlwaysBreakAfterReturnType: None
-AlwaysBreakBeforeMultilineStrings: false
-AlwaysBreakTemplateDeclarations: Yes
-AttributeMacros:
-  - __capability
-BinPackArguments: true
-BinPackParameters: true
-BitFieldColonSpacing: Both
-BraceWrapping:
-  AfterCaseLabel: false
-  AfterClass: false
-  AfterControlStatement: Never
-  AfterEnum: false
-  AfterExternBlock: false
-  AfterFunction: false
-  AfterNamespace: false
-  AfterObjCDeclaration: false
-  AfterStruct: false
-  AfterUnion: false
-  BeforeCatch: false
-  BeforeElse: false
-  BeforeLambdaBody: false
-  BeforeWhile: false
-  IndentBraces: false
-  SplitEmptyFunction: true
-  SplitEmptyRecord: true
-  SplitEmptyNamespace: true
-BreakAfterAttributes: Never
-BreakAfterJavaFieldAnnotations: false
-BreakArrays: true
-BreakBeforeBinaryOperators: None
-BreakBeforeConceptDeclarations: Always
-BreakBeforeBraces: Attach
-BreakBeforeInlineASMColon: OnlyMultiline
-BreakBeforeTernaryOperators: true
-BreakConstructorInitializers: BeforeComma
-BreakInheritanceList: BeforeColon
-BreakStringLiterals: true
-ColumnLimit: 160
-CommentPragmas: '^ IWYU pragma:'
-CompactNamespaces: false
-ConstructorInitializerIndentWidth: 4
-ContinuationIndentWidth: 8
-Cpp11BracedListStyle: true
-DerivePointerAlignment: false
-DisableFormat: false
-EmptyLineAfterAccessModifier: Never
-EmptyLineBeforeAccessModifier: LogicalBlock
-ExperimentalAutoDetectBinPacking: false
-FixNamespaceComments: true
-ForEachMacros:
-  - foreach
-  - Q_FOREACH
-  - BOOST_FOREACH
-IfMacros:
-  - KJ_IF_MAYBE
-IndentAccessModifiers: false
-IndentCaseBlocks: false
-IndentCaseLabels: false
-IndentExternBlock: AfterExternBlock
-IndentGotoLabels: true
-IndentPPDirectives: None
-IndentRequiresClause: true
-IndentWidth: 4
-IndentWrappedFunctionNames: false
-InsertBraces: false
-InsertNewlineAtEOF: true
-InsertTrailingCommas: None
-IntegerLiteralSeparator:
-  Binary: 0
-  BinaryMinDigits: 0
-  Decimal: 0
-  DecimalMinDigits: 0
-  Hex: 0
-  HexMinDigits: 0
-JavaScriptQuotes: Leave
-JavaScriptWrapImports: true
-KeepEmptyLinesAtTheStartOfBlocks: true
-KeepEmptyLinesAtEOF: false
-LambdaBodyIndentation: Signature
-LineEnding: DeriveLF
-MacroBlockBegin: ''
-MacroBlockEnd: ''
-MaxEmptyLinesToKeep: 2
-NamespaceIndentation: None
-PackConstructorInitializers: BinPack
-PenaltyBreakAssignment: 2
-PenaltyBreakBeforeFirstCallParameter: 19
-PenaltyBreakComment: 300
-PenaltyBreakFirstLessLess: 120
-PenaltyBreakOpenParenthesis: 0
-PenaltyBreakString: 1000
-PenaltyBreakTemplateDeclaration: 10
-PenaltyExcessCharacter: 1000000
-PenaltyIndentedWhitespace: 0
-PenaltyReturnTypeOnItsOwnLine: 60
-PointerAlignment: Left
-PPIndentWidth: -1
-QualifierAlignment: Leave
-ReferenceAlignment: Pointer
-ReflowComments: true
-RemoveBracesLLVM: false
-RemoveParentheses: Leave
-RemoveSemicolon: false
-RequiresClausePosition: OwnLine
-RequiresExpressionIndentation: OuterScope
-SeparateDefinitionBlocks: Leave
-ShortNamespaceLines: 1
-SortIncludes: Never
-SortJavaStaticImport: Before
-SortUsingDeclarations: Never
-SpaceAfterCStyleCast: false
-SpaceAfterLogicalNot: false
-SpaceAfterTemplateKeyword: true
-SpaceAroundPointerQualifiers: Default
-SpaceBeforeAssignmentOperators: true
-SpaceBeforeCaseColon: false
-SpaceBeforeCpp11BracedList: false
-SpaceBeforeCtorInitializerColon: true
-SpaceBeforeInheritanceColon: true
-SpaceBeforeJsonColon: false
-SpaceBeforeParens: ControlStatements
-SpaceBeforeParensOptions:
-  AfterControlStatements: true
-  AfterForeachMacros: true
-  AfterFunctionDefinitionName: false
-  AfterFunctionDeclarationName: false
-  AfterIfMacros: true
-  AfterOverloadedOperator: false
-  AfterRequiresInClause: false
-  AfterRequiresInExpression: false
-  BeforeNonEmptyParentheses: false
-SpaceBeforeRangeBasedForLoopColon: true
-SpaceBeforeSquareBrackets: false
-SpaceInEmptyBlock: false
-SpacesBeforeTrailingComments: 1
-SpacesInAngles: Never
-SpacesInContainerLiterals: true
-SpacesInLineCommentPrefix:
-  Minimum: 1
-  Maximum: -1
-SpacesInParens: Never
-SpacesInParensOptions:
-  InCStyleCasts: false
-  InConditionalStatements: false
-  InEmptyParentheses: false
-  Other: false
-SpacesInSquareBrackets: false
-Standard: Latest
-TabWidth: 8
-UseTab: Never
-VerilogBreakBetweenInstancePorts: true
-WhitespaceSensitiveMacros:
-  - BOOST_PP_STRINGIZE
-  - CF_SWIFT_NAME
-  - NS_SWIFT_NAME
-  - PP_STRINGIZE
-  - STRINGIZE
-...
-

.dockerignore

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

.gitattributes

@@ -1,5 +1,2 @@
 *.cc diff=cpp
 *.hh diff=cpp
-*.svg binary
-docs/_static/api/js/* binary
-pgo/profiles/** filter=lfs diff=lfs merge=lfs -text

.github/CODEOWNERS

@@ -1,103 +0,0 @@
-# AUTH
-auth/* @nuivall
-
-# CACHE
-row_cache* @tgrabiec
-*mutation* @tgrabiec
-test/boost/mvcc* @tgrabiec
-
-# CDC
-cdc/* @kbr-scylla @elcallio @piodul
-test/cql/cdc_* @kbr-scylla @elcallio @piodul
-test/boost/cdc_* @kbr-scylla @elcallio @piodul
-
-# COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio @eliransin
-db/batch* @elcallio
-
-# COORDINATOR
-service/storage_proxy* @gleb-cloudius
-
-# COMPACTION
-compaction/* @raphaelsc
-
-# CQL TRANSPORT LAYER
-transport/*
-
-# CQL QUERY LANGUAGE
-cql3/* @tgrabiec @nuivall
-
-# COUNTERS
-counters* @nuivall
-tests/counter_test* @nuivall
-
-# DOCS
-docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh
-
-# GOSSIP
-gms/* @tgrabiec @asias @kbr-scylla
-
-# DOCKER
-dist/docker/*
-
-# LSA
-utils/logalloc* @tgrabiec
-
-# MATERIALIZED VIEWS
-db/view/* @nyh @piodul
-cql3/statements/*view* @nyh @piodul
-test/boost/view_* @nyh @piodul
-
-# PACKAGING
-dist/* @syuu1228
-
-# REPAIR
-repair/* @tgrabiec @asias
-
-# SCHEMA MANAGEMENT
-db/schema_tables* @tgrabiec
-service/migration* @tgrabiec
-schema* @tgrabiec
-
-# SECONDARY INDEXES
-index/* @nyh @piodul
-cql3/statements/*index* @nyh @piodul
-test/boost/*index* @nyh @piodul
-
-# SSTABLES
-sstables/* @tgrabiec @raphaelsc
-
-# STREAMING
-streaming/* @tgrabiec @asias
-service/storage_service.* @tgrabiec @asias
-
-# ALTERNATOR
-alternator/* @nyh
-test/alternator/* @nyh
-
-# HINTED HANDOFF
-db/hints/* @piodul @vladzcloudius @eliransin
-
-# REDIS
-redis/* @syuu1228
-test/redis/* @syuu1228
-
-# READERS
-reader_* @denesb
-querier* @denesb
-test/boost/mutation_reader_test.cc @denesb
-test/boost/querier_cache_test.cc @denesb
-
-# PYTEST-BASED CQL TESTS
-test/cqlpy/* @nyh
-
-# RAFT
-raft/* @kbr-scylla @gleb-cloudius @kostja
-test/raft/* @kbr-scylla @gleb-cloudius @kostja
-
-# HEAT-WEIGHTED LOAD BALANCING
-db/heat_load_balance.* @nyh @gleb-cloudius
-
-# Tools
-tools/* @denesb

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,9 @@
+*Installation details*
+Scylla version (or git commit hash):
+Cluster size:
+OS (RHEL/CentOS/Ubuntu/AWS AMI):
+
+*Hardware details (for performance issues)*          Delete if unneeded
+Platform (physical/VM/cloud instance type/docker):
+Hardware: sockets= cores= hyperthreading= memory=
+Disks: (SSD/HDD, count)

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,86 +0,0 @@
-name: "Report a bug"
-description: "File a bug report."
-title: "[Bug]: "
-type: "bug"
-labels: bug
-body:
-  - type: checkboxes
-    id: terms
-    attributes:
-      label: Code of Conduct
-      description: "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 forum at https://forum.scylladb.com/ or in our slack channel https://slack.scylladb.com/ "
-      options:
-        - label: I have read the disclaimer above and am reporting a suspected malfunction in Scylla.
-          required: true
-
-  - type: input
-    id: product-version
-    attributes:
-      label: product version
-      description: Scylla version (or git commit hash)
-      placeholder: ex. scylla-6.1.1
-    validations:
-      required: true
-      
-  - type: input
-    id: cluster-size
-    attributes:
-      label: Cluster Size
-    validations:
-      required: true  
-      
-  - type: input
-    id: os
-    attributes:
-      label: OS
-      placeholder: RHEL/CentOS/Ubuntu/AWS AMI
-    validations:
-      required: true
-      
-  - type: textarea
-    id: additional-data
-    attributes:
-      label: Additional Environmental Data
-      #description: 
-      placeholder: Add additional data
-      value: "Platform (physical/VM/cloud instance type/docker):\n
-Hardware: sockets=   cores=   hyperthreading=   memory=\n
-Disks: (SSD/HDD, count)"
-    validations:
-      required: false
-      
-  - type: textarea
-    id: reproducer-steps
-    attributes:
-      label: Reproduction Steps
-      placeholder: Describe how to reproduce the problem
-      value: "The steps to reproduce the problem are:"
-    validations:
-      required: true
-      
-  - type: textarea
-    id: the-problem
-    attributes:
-      label: What is the problem?
-      placeholder: Describe the problem you found
-      value: "The problem is that"
-    validations:
-      required: true
-      
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: Expected behavior?
-      placeholder: Describe what should have happened
-      value: "I expected that "
-    validations:
-      required: true
-      
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output
-      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
-      render: shell

.github/clang-include-cleaner.json

@@ -1,20 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "clang-include-cleaner",
-            "severity": "error",
-            "pattern": [
-                {
-                    "regexp": "^([^\\-\\+].*)$",
-                    "file": 1
-                },
-                {
-                    "regexp": "^(-\\s+[^\\s]+)\\s+@Line:(\\d+)$",
-                    "line": 2,
-                    "message": 1,
-                    "loop": true
-                }
-            ]
-        }
-    ]
-}

.github/clang-matcher.json

@@ -1,18 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "clang",
-            "pattern": [
-                {
-                    "regexp": "^([^:]+):(\\d+):(\\d+):\\s+(warning|error):\\s+(.*?)\\s+\\[(.*?)\\]$",
-                    "file": 1,
-                    "line": 2,
-                    "column": 3,
-                    "severity": 4,
-                    "message": 5,
-                    "code": 6
-                }
-            ]
-        }
-    ]
-}

.github/copilot-instructions.md

@@ -1,86 +0,0 @@
-# ScyllaDB Development Instructions
-
-## Project Context
-High-performance distributed NoSQL database. Core values: performance, correctness, readability.
-
-## Build System
-
-### Modern Build (configure.py + ninja)
-```bash
-# Configure (run once per mode, or when switching modes)
-./configure.py --mode=<mode>  # mode: dev, debug, release, sanitize
-
-# Build everything
-ninja <mode>-build  # e.g., ninja dev-build
-
-# Build Scylla binary only (sufficient for Python integration tests)
-ninja build/<mode>/scylla
-
-# Build specific test
-ninja build/<mode>/test/boost/<test_name>
-```
-
-## Running Tests
-
-### C++ Unit Tests
-```bash
-# Run all tests in a file
-./test.py --mode=<mode> test/<suite>/<test_name>.cc
-
-# Run a single test case from a file
-./test.py --mode=<mode> test/<suite>/<test_name>.cc::<test_case_name>
-
-# Examples
-./test.py --mode=dev test/boost/memtable_test.cc
-./test.py --mode=dev test/raft/raft_server_test.cc::test_check_abort_on_client_api
-```
-
-**Important:** 
-- Use full path with `.cc` extension (e.g., `test/boost/test_name.cc`, not `boost/test_name`)
-- To run a single test case, append `::<test_case_name>` to the file path
-- If you encounter permission issues with cgroup metric gathering, add `--no-gather-metrics` flag
-
-**Rebuilding Tests:**
-- test.py does NOT automatically rebuild when test source files are modified
-- Many tests are part of composite binaries (e.g., `combined_tests` in test/boost contains multiple test files)
-- To find which binary contains a test, check `configure.py` in the repository root (primary source) or `test/<suite>/CMakeLists.txt`
-- To rebuild a specific test binary: `ninja build/<mode>/test/<suite>/<binary_name>`
-- Examples: 
-  - `ninja build/dev/test/boost/combined_tests` (contains group0_voter_calculator_test.cc and others)
-  - `ninja build/dev/test/raft/replication_test` (standalone Raft test)
-
-### Python Integration Tests
-```bash
-# Only requires Scylla binary (full build usually not needed)
-ninja build/<mode>/scylla
-
-# Run all tests in a file
-./test.py --mode=<mode> <test_path>
-
-# Run a single test case from a file
-./test.py --mode=<mode> <test_path>::<test_function_name>
-
-# Examples
-./test.py --mode=dev alternator/
-./test.py --mode=dev cluster/test_raft_voters::test_raft_limited_voters_retain_coordinator
-
-# Optional flags
-./test.py --mode=dev cluster/test_raft_no_quorum -v  # Verbose output
-./test.py --mode=dev cluster/test_raft_no_quorum --repeat 5  # Repeat test 5 times
-```
-
-**Important:**
-- Use path without `.py` extension (e.g., `cluster/test_raft_no_quorum`, not `cluster/test_raft_no_quorum.py`)
-- To run a single test case, append `::<test_function_name>` to the file path
-- Add `-v` for verbose output
-- Add `--repeat <num>` to repeat a test multiple times
-- After modifying C++ source files, only rebuild the Scylla binary for Python tests - building the entire repository is unnecessary
-
-## Code Philosophy
-- Performance matters in hot paths (data read/write, inner loops)
-- Self-documenting code through clear naming
-- Comments explain "why", not "what"
-- Prefer standard library over custom implementations
-- Strive for simplicity and clarity, add complexity only when clearly justified
-- Question requests: don't blindly implement requests - evaluate trade-offs, identify issues, and suggest better alternatives when appropriate
-- Consider different approaches, weigh pros and cons, and recommend the best fit for the specific context

.github/dependabot.yml

@@ -1,9 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: "pip"
-  directory: "/docs"
-  schedule:
-    interval: "daily"
-  allow:
-  - dependency-name: "sphinx-scylladb-theme"
-  - dependency-name: "sphinx-multiversion-scylla"

.github/instructions/cpp.instructions.md

@@ -1,115 +0,0 @@
----
-applyTo: "**/*.{cc,hh}"
----
-
-# C++ Guidelines
-
-**Important:** Always match the style and conventions of existing code in the file and directory.
-
-## Memory Management
-- Prefer stack allocation whenever possible
-- Use `std::unique_ptr` by default for dynamic allocations
-- `new`/`delete` are forbidden (use RAII)
-- Use `seastar::lw_shared_ptr` or `seastar::shared_ptr` for shared ownership within same shard
-- Use `seastar::foreign_ptr` for cross-shard sharing
-- Avoid `std::shared_ptr` except when interfacing with external C++ APIs
-- Avoid raw pointers except for non-owning references or C API interop
-
-## Seastar Asynchronous Programming
-- Use `seastar::future<T>` for all async operations
-- Prefer coroutines (`co_await`, `co_return`) over `.then()` chains for readability
-- Coroutines are preferred over `seastar::do_with()` for managing temporary state
-- In hot paths where futures are ready, continuations may be more efficient than coroutines
-- Chain futures with `.then()`, don't block with `.get()` (unless in `seastar::thread` context)
-- All I/O must be asynchronous (no blocking calls)
-- Use `seastar::gate` for shutdown coordination
-- Use `seastar::semaphore` for resource limiting (not `std::mutex`)
-- Break long loops with `maybe_yield()` to avoid reactor stalls
-
-## Coroutines
-```cpp
-seastar::future<T> func() {
-    auto result = co_await async_operation();
-    co_return result;
-}
-```
-
-## Error Handling
-- Throw exceptions for errors (futures propagate them automatically)
-- In data path: avoid exceptions, use `std::expected` (or `boost::outcome`) instead
-- Use standard exceptions (`std::runtime_error`, `std::invalid_argument`)
-- Database-specific: throw appropriate schema/query exceptions
-
-## Performance
-- Pass large objects by `const&` or `&&` (move semantics)
-- Use `std::string_view` for non-owning string references
-- Avoid copies: prefer move semantics
-- Use `utils::chunked_vector` instead of `std::vector` for large allocations (>128KB)
-- Minimize dynamic allocations in hot paths
-
-## Database-Specific Types
-- Use `schema_ptr` for schema references
-- Use `mutation` and `mutation_partition` for data modifications
-- Use `partition_key` and `clustering_key` for keys
-- Use `api::timestamp_type` for database timestamps
-- Use `gc_clock` for garbage collection timing
-
-## Style
-- C++23 standard (prefer modern features, especially coroutines)
-- Use `auto` when type is obvious from RHS
-- Avoid `auto` when it obscures the type
-- Use range-based for loops: `for (const auto& item : container)`
-- Use standard algorithms when they clearly simplify code (e.g., replacing 10-line loops)
-- Avoid chaining multiple algorithms if a straightforward loop is clearer
-- Mark functions and variables `const` whenever possible
-- Use scoped enums: `enum class` (not unscoped `enum`)
-
-## Headers
-- Use `#pragma once`
-- Include order: own header, C++ std, Seastar, Boost, project headers
-- Forward declare when possible
-- Never `using namespace` in headers (exception: `using namespace seastar` is globally available via `seastarx.hh`)
-
-## Documentation
-- Public APIs require clear documentation
-- Implementation details should be self-evident from code
-- Use `///` or Doxygen `/** */` for public documentation, `//` for implementation notes - follow the existing style
-
-## Naming
-- `snake_case` for most identifiers (classes, functions, variables, namespaces)
-- Template parameters: `CamelCase` (e.g., `template<typename ValueType>`)
-- Member variables: prefix with `_` (e.g., `int _count;`)
-- Structs (value-only): no `_` prefix on members
-- Constants and `constexpr`: `snake_case` (e.g., `static constexpr int max_size = 100;`)
-- Files: `.hh` for headers, `.cc` for source
-
-## Formatting
-- 4 spaces indentation, never tabs
-- Opening braces on same line as control structure (except namespaces)
-- Space after keywords: `if (`, `while (`, `return `
-- Whitespace around operators matches precedence: `*a + *b` not `* a+* b`
-- Line length: keep reasonable (<160 chars), use continuation lines with double indent if needed
-- Brace all nested scopes, even single statements
-- Minimal patches: only format code you modify, never reformat entire files
-
-## Logging
-- Use structured logging with appropriate levels: DEBUG, INFO, WARN, ERROR
-- Include context in log messages (e.g., request IDs)
-- Never log sensitive data (credentials, PII)
-
-## Forbidden
-- `malloc`/`free`
-- `printf` family (use logging or fmt)
-- Raw pointers for ownership
-- `using namespace` in headers
-- Blocking operations: `std::sleep`, `std::read`, `std::mutex` (use Seastar equivalents)
-- `std::atomic` (reserved for very special circumstances only)
-- Macros (use `inline`, `constexpr`, or templates instead)
-
-## Testing
-When modifying existing code, follow TDD: create/update test first, then implement.
-- Examine existing tests for style and structure
-- Use Boost.Test framework
-- Use `SEASTAR_THREAD_TEST_CASE` for Seastar asynchronous tests
-- Aim for high code coverage, especially for new features and bug fixes
-- Maintain bisectability: all tests must pass in every commit. Mark failing tests with `BOOST_FAIL()` or similar, then fix in subsequent commit

.github/instructions/python.instructions.md

@@ -1,51 +0,0 @@
----
-applyTo: "**/*.py"
----
-
-# Python Guidelines
-
-**Important:** Match existing code style. Some directories (like `test/cqlpy` and `test/alternator`) prefer simplicity over type hints and docstrings.
-
-## Style
-- Follow PEP 8
-- Use type hints for function signatures (unless directory style omits them)
-- Use f-strings for formatting
-- Line length: 160 characters max
-- 4 spaces for indentation
-
-## Imports
-Order: standard library, third-party, local imports
-```python
-import os
-import sys
-
-import pytest
-from cassandra.cluster import Cluster
-
-from test.utils import setup_keyspace
-```
-
-Never use `from module import *`
-
-## Documentation
-All public functions/classes need docstrings (unless the current directory conventions omit them):
-```python
-def my_function(arg1: str, arg2: int) -> bool:
-    """
-    Brief summary of function purpose.
-
-    Args:
-        arg1: Description of first argument.
-        arg2: Description of second argument.
-
-    Returns:
-        Description of return value.
-    """
-    pass
-```
-
-## Testing Best Practices
-- Maintain bisectability: all tests must pass in every commit
-- Mark currently-failing tests with `@pytest.mark.xfail`, unmark when fixed
-- Use descriptive names that convey intent
-- Docstrings/comments should explain what the test verifies and why, and if it reproduces a specific issue or how it fits into the larger test suite

.github/mergify.yml

@@ -1,92 +0,0 @@
-pull_request_rules:
-  - name: put PR in draft if conflicts
-    conditions:
-      - label = conflicts
-      - author = mergify[bot]
-      - head ~= ^mergify/
-    actions:
-      edit:
-         draft: true
-  - name: Delete mergify backport branch
-    conditions:
-      - base~=branch-
-      - or:
-        - merged
-        - closed
-    actions:
-      delete_head_branch:
-  - name: Automate backport pull request 6.2
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.2 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.2] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-          Refs #{{number}}
-        branches:
-          - branch-6.2
-        assignees:
-          - "{{ author }}"
-  - name: Automate backport pull request 6.1
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.1 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.1] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-           Refs #{{number}}
-        branches:
-          - branch-6.1
-        assignees:
-          - "{{ author }}"
-  - name: Automate backport pull request 6.0
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.0 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.0] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-           Refs #{{number}}
-        branches:
-          - branch-6.0
-        assignees:
-          - "{{ author }}"

.github/pull_request_template.md

@@ -1 +0,0 @@
-**Please replace this line with justification for the backport/\* labels added to this PR**

.github/scripts/auto-backport.py

@@ -1,245 +0,0 @@
-#!/usr/bin/env python3
-
-import argparse
-import os
-import re
-import sys
-import tempfile
-import logging
-
-from github import Github, GithubException
-from git import Repo, GitCommandError
-
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def is_pull_request():
-    return '--pull-request' in sys.argv[1:]
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--repo', type=str, required=True, help='Github repository name')
-    parser.add_argument('--base-branch', type=str, default='refs/heads/master', help='Base branch')
-    parser.add_argument('--commits', default=None, type=str, help='Range of promoted commits.')
-    parser.add_argument('--pull-request', type=int, help='Pull request number to be backported')
-    parser.add_argument('--head-commit', type=str, required=is_pull_request(), help='The HEAD of target branch after the pull request specified by --pull-request is merged')
-    parser.add_argument('--github-event', type=str, help='Get GitHub event type')
-    return parser.parse_args()
-
-
-def create_pull_request(repo, new_branch_name, base_branch_name, pr, backport_pr_title, commits, is_draft, is_collaborator):
-    pr_body = f'{pr.body}\n\n'
-    for commit in commits:
-        pr_body += f'- (cherry picked from commit {commit})\n\n'
-    pr_body += f'Parent PR: #{pr.number}'
-    try:
-        backport_pr = repo.create_pull(
-            title=backport_pr_title,
-            body=pr_body,
-            head=f'scylladbbot:{new_branch_name}',
-            base=base_branch_name,
-            draft=is_draft
-        )
-        logging.info(f"Pull request created: {backport_pr.html_url}")
-        labels_to_add = []
-        priority_labels = {"P0", "P1"}
-        parent_pr_labels = [label.name for label in pr.labels]
-        for label in priority_labels:
-            if label in parent_pr_labels:
-                labels_to_add.append(label)
-                labels_to_add.append("force_on_cloud")
-                logging.info(f"Adding {label} and force_on_cloud labels from parent PR to backport PR")
-                break  # Only apply the highest priority label
-        
-        if is_collaborator:
-            backport_pr.add_to_assignees(pr.user)
-        if is_draft:
-            labels_to_add.append("conflicts")
-            pr_comment = f"@{pr.user.login} - This PR was marked as draft because it has conflicts\n"
-            pr_comment += "Please resolve them and remove the 'conflicts' label. The PR will be made ready for review automatically."
-            backport_pr.create_issue_comment(pr_comment)
-        
-        # Apply all labels at once if we have any
-        if labels_to_add:
-            backport_pr.add_to_labels(*labels_to_add)
-            logging.info(f"Added labels to backport PR: {labels_to_add}")
-
-        logging.info(f"Assigned PR to original author: {pr.user}")
-        return backport_pr
-    except GithubException as e:
-        if 'A pull request already exists' in str(e):
-            logging.warning(f'A pull request already exists for {pr.user}:{new_branch_name}')
-        else:
-            logging.error(f'Failed to create PR: {e}')
-
-
-def get_pr_commits(repo, pr, stable_branch, start_commit=None):
-    commits = []
-    if pr.merged:
-        merge_commit = repo.get_commit(pr.merge_commit_sha)
-        if len(merge_commit.parents) > 1:  # Check if this merge commit includes multiple commits
-            for commit in pr.get_commits():
-                commits.append(commit.sha)
-        else:
-            if start_commit:
-                promoted_commits = repo.compare(start_commit, stable_branch).commits
-            else:
-                promoted_commits = repo.get_commits(sha=stable_branch)
-            for commit in pr.get_commits():
-                for promoted_commit in promoted_commits:
-                    commit_title = commit.commit.message.splitlines()[0]
-                    # In Scylla-pkg and scylla-dtest, for example,
-                    # we don't create a merge commit for a PR with multiple commits,
-                    # according to the GitHub API, the last commit will be the merge commit,
-                    # which is not what we need when backporting (we need all the commits).
-                    # So here, we are validating the correct SHA for each commit so we can cherry-pick
-                    if promoted_commit.commit.message.startswith(commit_title):
-                        commits.append(promoted_commit.sha)
-
-    elif pr.state == 'closed':
-        events = pr.get_issue_events()
-        for event in events:
-            if event.event == 'closed':
-                commits.append(event.commit_id)
-    return commits
-
-
-def backport(repo, pr, version, commits, backport_base_branch, is_collaborator):
-    new_branch_name = f'backport/{pr.number}/to-{version}'
-    backport_pr_title = f'[Backport {version}] {pr.title}'
-    repo_url = f'https://scylladbbot:{github_token}@github.com/{repo.full_name}.git'
-    fork_repo = f'https://scylladbbot:{github_token}@github.com/scylladbbot/{repo.name}.git'
-    with (tempfile.TemporaryDirectory() as local_repo_path):
-        try:
-            repo_local = Repo.clone_from(repo_url, local_repo_path, branch=backport_base_branch)
-            repo_local.git.checkout(b=new_branch_name)
-            is_draft = False
-            for commit in commits:
-                try:
-                    repo_local.git.cherry_pick(commit, '-x')
-                except GitCommandError as e:
-                    logging.warning(f'Cherry-pick conflict on commit {commit}: {e}')
-                    is_draft = True
-                    repo_local.git.add(A=True)
-                    repo_local.git.cherry_pick('--continue')
-            # Check if the branch already exists in the remote fork
-            remote_refs = repo_local.git.ls_remote('--heads', fork_repo, new_branch_name)
-            if not remote_refs:
-                # Branch does not exist, create it with a regular push
-                repo_local.git.push(fork_repo, new_branch_name)
-                create_pull_request(repo, new_branch_name, backport_base_branch, pr, backport_pr_title, commits,
-                                    is_draft, is_collaborator)
-            else:
-                logging.info(f"Remote branch {new_branch_name} already exists in fork. Skipping push.")
-        except GitCommandError as e:
-            logging.warning(f"GitCommandError: {e}")
-
-
-def with_github_keyword_prefix(repo, pr):
-    # GitHub issue pattern: #123, scylladb/scylladb#123, or full GitHub URLs
-    github_pattern = rf"(?:fix(?:|es|ed))\s*:?\s*(?:(?:(?:{repo.full_name})?#)|https://github\.com/{repo.full_name}/issues/)(\d+)"
-    
-    # JIRA issue pattern: PKG-92 or https://scylladb.atlassian.net/browse/PKG-92
-    jira_pattern = r"(?:fix(?:|es|ed))\s*:?\s*(?:(?:https://scylladb\.atlassian\.net/browse/)?([A-Z]+-\d+))"
-    
-    # Check PR body for GitHub issues
-    github_match = re.findall(github_pattern, pr.body, re.IGNORECASE)
-    # Check PR body for JIRA issues
-    jira_match = re.findall(jira_pattern, pr.body, re.IGNORECASE)
-    
-    match = github_match or jira_match
-
-    if match:
-        return True
-
-    for commit in pr.get_commits():
-        github_match = re.findall(github_pattern, commit.commit.message, re.IGNORECASE)
-        jira_match = re.findall(jira_pattern, commit.commit.message, re.IGNORECASE)
-        if github_match or jira_match:
-            print(f'{pr.number} has a valid close reference in commit message {commit.sha}')
-            return True
-
-    print(f'No valid close reference for {pr.number}')
-    return False
-
-def main():
-    args = parse_args()
-    base_branch = args.base_branch.split('/')[2]
-    promoted_label = 'promoted-to-master'
-    repo_name = args.repo
-    fork_repo_name = 'scylladbbot/scylladb'
-    if 'scylla-enterprise' in args.repo:
-        promoted_label = 'promoted-to-enterprise'
-        fork_repo_name = 'scylladbbot/scylla-enterprise'
-    stable_branch = base_branch
-    backport_branch = 'branch-'
-
-    backport_label_pattern = re.compile(r'backport/\d+\.\d+$')
-
-    g = Github(github_token)
-    repo = g.get_repo(repo_name)
-    scylladbbot_repo = g.get_repo(fork_repo_name)
-    closed_prs = []
-    start_commit = None
-    is_collaborator = True
-
-    if args.commits:
-        start_commit, end_commit = args.commits.split('..')
-        commits = repo.compare(start_commit, end_commit).commits
-        for commit in commits:
-            match = re.search(rf"Closes .*#([0-9]+)", commit.commit.message, re.IGNORECASE)
-            if match:
-                pr_number = int(match.group(1))
-                pr = repo.get_pull(pr_number)
-                closed_prs.append(pr)
-    if args.pull_request:
-        start_commit = args.head_commit
-        pr = repo.get_pull(args.pull_request)
-        closed_prs = [pr]
-
-    for pr in closed_prs:
-        labels = [label.name for label in pr.labels]
-        backport_labels = [label for label in labels if backport_label_pattern.match(label)]
-        if promoted_label not in labels:
-            print(f'no {promoted_label} label: {pr.number}')
-            continue
-        if not backport_labels:
-            print(f'no backport label: {pr.number}')
-            continue
-        if not with_github_keyword_prefix(repo, pr) and args.github_event != 'unlabeled':
-            comment = f''':warning:  @{pr.user.login} PR body or PR commits do not contain a Fixes reference to an issue and can not be backported
-            please update PR body with a valid ref to an issue. Then remove `scylladbbot/backport_error` label to re-trigger the backport process
-            '''
-            pr.create_issue_comment(comment)
-            pr.add_to_labels("scylladbbot/backport_error")
-            continue
-        if not repo.private and not scylladbbot_repo.has_in_collaborators(pr.user.login):
-            logging.info(f"Sending an invite to {pr.user.login} to become a collaborator to {scylladbbot_repo.full_name} ")
-            scylladbbot_repo.add_to_collaborators(pr.user.login)
-            comment = f''':warning:  @{pr.user.login} you have been added as collaborator to scylladbbot fork
-            Please check your inbox and approve the invitation, otherwise you will not be able to edit PR branch when needed
-            '''
-            # When a pull request is pending for backport but its author is not yet a collaborator of "scylladbbot",
-            # we attach a "scylladbbot/backport_error" label to the PR.
-            # This prevents the workflow from proceeding with the backport process
-            # until the author has been granted proper permissions
-            # the author should remove the label manually to re-trigger the backport workflow.
-            pr.add_to_labels("scylladbbot/backport_error")
-            pr.create_issue_comment(comment)
-            is_collaborator = False
-        commits = get_pr_commits(repo, pr, stable_branch, start_commit)
-        logging.info(f"Found PR #{pr.number} with commit {commits} and the following labels: {backport_labels}")
-        for backport_label in backport_labels:
-            version = backport_label.replace('backport/', '')
-            backport_base_branch = backport_label.replace('backport/', backport_branch)
-            backport(repo, pr, version, commits, backport_base_branch, is_collaborator)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/check-license.py

@@ -1,81 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# Copyright (C) 2024-present ScyllaDB
-#
-#
-# SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
-#
-
-import argparse
-import sys
-from pathlib import Path
-from typing import Set
-
-
-def parse_args() -> argparse.Namespace:
-    """Parses command-line arguments."""
-    parser = argparse.ArgumentParser(description='Check license headers in files')
-    parser.add_argument('--files', required=True, nargs="+", type=Path,
-                        help='List of files to check')
-    parser.add_argument('--license', required=True,
-                        help='License to check for')
-    parser.add_argument('--check-lines', type=int, default=10,
-                        help='Number of lines to check (default: %(default)s)')
-    parser.add_argument('--extensions', required=True, nargs="+",
-                        help='List of file extensions to check')
-    parser.add_argument('--verbose', action='store_true',
-                        help='Print verbose output (default: %(default)s)')
-    return parser.parse_args()
-
-
-def should_check_file(file_path: Path, allowed_extensions: Set[str]) -> bool:
-    return file_path.suffix in allowed_extensions
-
-
-def check_license_header(file_path: Path, license_header: str, check_lines: int) -> bool:
-    try:
-        with open(file_path, 'r', encoding='utf-8') as f:
-            for _ in range(check_lines):
-                line = f.readline()
-                if license_header in line:
-                    return True
-        return False
-    except (UnicodeDecodeError, StopIteration):
-        # Handle files that can't be read as text or have fewer lines
-        return False
-
-
-def main() -> int:
-    args = parse_args()
-
-    if not args.files:
-        print("No files to check")
-        return 0
-
-    num_errors = 0
-
-    for file_path in args.files:
-        # Skip non-existent files
-        if not file_path.exists():
-            continue
-
-        # Skip files with non-matching extensions
-        if not should_check_file(file_path, args.extensions):
-            print(f"ℹ️ Skipping file with unchecked extension: {file_path}")
-            continue
-
-        # Check license header
-        if check_license_header(file_path, args.license, args.check_lines):
-            if args.verbose:
-                print(f"✅ License header found in: {file_path}")
-        else:
-            print(f"❌ Missing license header in: {file_path}")
-            num_errors += 1
-
-    if num_errors > 0:
-        sys.exit(1)
-
-
-if __name__ == '__main__':
-    main()

.github/scripts/label_promoted_commits.py

@@ -1,89 +0,0 @@
-import argparse
-import re
-import sys
-import os
-from github import Github
-from github.GithubException import UnknownObjectException
-
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def parser():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--repository', type=str, required=True,
-                        help='Github repository name (e.g., scylladb/scylladb)')
-    parser.add_argument('--commits', type=str, required=True, help='Range of promoted commits.')
-    parser.add_argument('--label', type=str, default='promoted-to-master', help='Label to use')
-    parser.add_argument('--ref', type=str, required=True, help='PR target branch')
-    return parser.parse_args()
-
-
-def add_comment_and_close_pr(pr, comment):
-    if pr.state == 'open':
-        pr.create_issue_comment(comment)
-        pr.edit(state="closed")
-
-
-def mark_backport_done(repo, ref_pr_number, branch):
-    pr = repo.get_pull(int(ref_pr_number))
-    label_to_remove = f'backport/{branch}'
-    label_to_add = f'{label_to_remove}-done'
-    current_labels = [label.name for label in pr.get_labels()]
-    if label_to_remove in current_labels:
-        pr.remove_from_labels(label_to_remove)
-    if label_to_add not in current_labels:
-        pr.add_to_labels(label_to_add)
-
-
-def main():
-    # This script is triggered by a push event to either the master branch or a branch named branch-x.y (where x and y represent version numbers). Based on the pushed branch, the script performs the following actions:
-    # - When ref branch is `master`, it will add the `promoted-to-master` label, which we need later for the auto backport process
-    # - When ref branch is `branch-x.y` (which means we backported a patch), it will replace in the original PR the `backport/x.y` label with `backport/x.y-done` and will close the backport PR (Since GitHub close only the one referring to default branch)
-    args = parser()
-    pr_pattern = re.compile(r'Closes .*#([0-9]+)')
-    target_branch = re.search(r'branch-(\d+\.\d+)', args.ref)
-    g = Github(github_token)
-    repo = g.get_repo(args.repository, lazy=False)
-    start_commit, end_commit = args.commits.split('..')
-    commits = repo.compare(start_commit, end_commit).commits
-    processed_prs = set()
-    # Print commit information
-    for commit in commits:
-        print(f'Commit sha is: {commit.sha}')
-        pr_last_line = commit.commit.message.splitlines()
-        for line in reversed(pr_last_line):
-            match = pr_pattern.search(line)
-            if match:
-                pr_number = int(match.group(1))
-                if pr_number in processed_prs:
-                    continue
-                if target_branch:
-                    pr = repo.get_pull(pr_number)
-                    branch_name = target_branch[1]
-                    refs_pr = re.findall(r'Parent PR: (?:#|https.*?)(\d+)', pr.body)
-                    if refs_pr:
-                        print(f'branch-{target_branch.group(1)}, pr number is: {pr_number}')
-                        # 1. change the backport label of the parent PR to note that
-                        #    we've merged the corresponding backport PR
-                        # 2. close the backport PR and leave a comment on it to note
-                        #    that it has been merged with a certain git commit.
-                        ref_pr_number = refs_pr[0]
-                        mark_backport_done(repo, ref_pr_number, branch_name)
-                        comment = f'Closed via {commit.sha}'
-                        add_comment_and_close_pr(pr, comment)
-                else:
-                    try:
-                        pr = repo.get_pull(pr_number)
-                        pr.add_to_labels('promoted-to-master')
-                        print(f'master branch, pr number is: {pr_number}')
-                    except UnknownObjectException:
-                        print(f'{pr_number} is not a PR but an issue, no need to add label')
-                processed_prs.add(pr_number)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/sync_labels.py

@@ -1,113 +0,0 @@
-#!/usr/bin/env python3
-import argparse
-import os
-import sys
-from github import Github
-import re
-
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def parser():
-    parse = argparse.ArgumentParser()
-    parse.add_argument('--repo', type=str, required=True, help='Github repository name (e.g., scylladb/scylladb)')
-    parse.add_argument('--number', type=int, required=True, help='Pull request or issue number to sync labels from')
-    parse.add_argument('--label', type=str, default=None, help='Label to add/remove from an issue or PR')
-    parse.add_argument('--is_issue', action='store_true', help='Determined if label change is in Issue or not')
-    parse.add_argument('--action', type=str, choices=['opened', 'labeled', 'unlabeled'], required=True, help='Sync labels action')
-    return parse.parse_args()
-
-
-def copy_labels_from_linked_issues(repo, pr_number):
-    pr = repo.get_pull(pr_number)
-    if pr.body:
-        linked_issue_numbers = set(re.findall(r'Fixes:? (?:#|https.*?/issues/)(\d+)', pr.body))
-        for issue_number in linked_issue_numbers:
-            try:
-                issue = repo.get_issue(int(issue_number))
-                for label in issue.labels:
-                    # Copy ALL labels from issues to PR when PR is opened
-                    pr.add_to_labels(label.name)
-                    print(f"Copied label '{label.name}' from issue #{issue_number} to PR #{pr_number}")
-                    if label.name in ['P0', 'P1']:
-                        pr.add_to_labels('force_on_cloud')
-                        print(f"Added force_on_cloud label to PR #{pr_number} due to {label.name} label")
-                print(f"All labels from issue #{issue_number} copied to PR #{pr_number}")
-            except Exception as e:
-                print(f"Error processing issue #{issue_number}: {e}")
-
-
-def get_linked_pr_from_issue_number(repo, number):
-    linked_prs = []
-    for pr in repo.get_pulls(state='all', base='master'):
-        if pr.body and f'{number}' in pr.body:
-            linked_prs.append(pr.number)
-            break
-        else:
-            continue
-    return linked_prs
-
-
-def get_linked_issues_based_on_pr_body(repo, number):
-    pr = repo.get_pull(number)
-    repo_name = repo.full_name
-    pattern = rf"(?:fix(?:|es|ed)|resolve(?:|d|s))\s*:?\s*(?:(?:(?:{repo_name})?#)|https://github\.com/{repo_name}/issues/)(\d+)"
-    issue_number_from_pr_body = []
-    if pr.body is None:
-        return issue_number_from_pr_body
-    matches = re.findall(pattern, pr.body, re.IGNORECASE)
-    if matches:
-        for match in matches:
-            issue_number_from_pr_body.append(match)
-            print(f"Found issue number: {match}")
-    return issue_number_from_pr_body
-
-
-def sync_labels(repo, number, label, action, is_issue=False):
-    if is_issue:
-        linked_prs_or_issues = get_linked_pr_from_issue_number(repo, number)
-    else:
-        linked_prs_or_issues = get_linked_issues_based_on_pr_body(repo, number)
-    for pr_or_issue_number in linked_prs_or_issues:
-        if is_issue:
-            target = repo.get_issue(pr_or_issue_number)
-        else:
-            target = repo.get_issue(int(pr_or_issue_number))
-        if action == 'labeled':
-            target.add_to_labels(label)
-            if label in ['P0', 'P1'] and is_issue:
-                # Only add force_on_cloud to PRs when P0/P1 is added to an issue
-                target.add_to_labels('force_on_cloud')
-                print(f"Added 'force_on_cloud' label to PR #{pr_or_issue_number} due to {label} label")
-            print(f"Label '{label}' successfully added.")
-        elif action == 'unlabeled':
-            target.remove_from_labels(label)
-            if label in ['P0', 'P1'] and is_issue:
-                # Check if any other P0/P1 labels remain before removing force_on_cloud
-                remaining_priority_labels = [l.name for l in target.labels if l.name in ['P0', 'P1']]
-                if not remaining_priority_labels:
-                    try:
-                        target.remove_from_labels('force_on_cloud')
-                        print(f"Removed 'force_on_cloud' label from PR #{pr_or_issue_number} as no P0/P1 labels remain")
-                    except Exception as e:
-                        print(f"Warning: Could not remove force_on_cloud label: {e}")
-            print(f"Label '{label}' successfully removed.")
-        elif action == 'opened':
-            copy_labels_from_linked_issues(repo, number)
-        else:
-            print("Invalid action. Use 'labeled', 'unlabeled' or 'opened'.")
-
-
-def main():
-    args = parser()
-    github = Github(github_token)
-    repo = github.get_repo(args.repo)
-    sync_labels(repo, args.number, args.label, args.action, args.is_issue)
-
-
-if __name__ == "__main__":
-    main()

.github/seastar-bad-include.json

@@ -1,16 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "seastar-bad-include",
-            "severity": "error",
-            "pattern": [
-                {
-                    "regexp": "^(.+):(\\d+):(.+)$",
-                    "file": 1,
-                    "line": 2,
-                    "message": 3
-                }
-            ]
-        }
-    ]
-}

.github/workflows/add-label-when-promoted.yaml

@@ -1,83 +0,0 @@
-name: Check if commits are promoted
-
-on:
-  push:
-    branches:
-      - master
-      - branch-*.*
-      - enterprise
-  pull_request_target:
-    types: [labeled, unlabeled]
-    branches: [master, next, enterprise]
-
-jobs:
-  check-commit:
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Set Default Branch
-        id: set_branch
-        run: |
-          if [[ "${{ github.repository }}" == *enterprise* ]]; then
-            echo "DEFAULT_BRANCH=enterprise" >> $GITHUB_ENV
-          else
-            echo "DEFAULT_BRANCH=master" >> $GITHUB_ENV
-          fi
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          repository: ${{ github.repository }}
-          ref: ${{ env.DEFAULT_BRANCH }}
-          token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-          fetch-depth: 0  # Fetch all history for all tags and branches
-      - name: Set up Git identity
-        run: |
-          git config --global user.name "GitHub Action"
-          git config --global user.email "action@github.com"
-          git config --global merge.conflictstyle diff3
-      - name: Install dependencies
-        run: sudo apt-get install -y python3-github python3-git
-      - name: Run python script
-        if: github.event_name == 'push'
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/label_promoted_commits.py  --commits ${{ github.event.before }}..${{ github.sha }} --repository ${{ github.repository }} --ref ${{ github.ref }}
-      - name: Run auto-backport.py when promotion completed
-        if: ${{ github.event_name == 'push' && github.ref == format('refs/heads/{0}', env.DEFAULT_BRANCH) }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/auto-backport.py --repo ${{ github.repository }} --base-branch ${{ github.ref }} --commits ${{ github.event.before }}..${{ github.sha }}
-      - name: Check if a valid backport label exists and no backport_error
-        env:
-          LABELS_JSON: ${{ toJson(github.event.pull_request.labels) }}
-        id: check_label
-        run: |
-          labels_json="$LABELS_JSON"
-          echo "Checking labels:"
-          echo "$labels_json" | jq -r '.[].name'
-
-          # Check if a valid backport label exists
-          if echo "$labels_json" | jq -e 'any(.[] | .name; test("backport/[0-9]+\\.[0-9]+$"))' > /dev/null; then
-            # Ensure scylladbbot/backport_error is NOT present
-            if ! echo "$labels_json" | jq -e '.[] | select(.name == "scylladbbot/backport_error")' > /dev/null; then
-              echo "A matching backport label was found and no backport_error label exists."
-              echo "ready_for_backport=true" >> "$GITHUB_OUTPUT"
-              exit 0
-            else
-              echo "The label 'scylladbbot/backport_error' is present, invalidating backport."
-            fi
-          else
-            echo "No matching backport label found."
-          fi
-          echo "ready_for_backport=false" >> "$GITHUB_OUTPUT"
-      - name: Run auto-backport.py when PR is closed
-        if: ${{ github.event_name == 'pull_request_target' && steps.check_label.outputs.ready_for_backport == 'true' && github.event.pull_request.state == 'closed' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/auto-backport.py --repo ${{ github.repository }} --base-branch ${{ github.ref }} --pull-request ${{ github.event.pull_request.number }} --head-commit ${{ github.event.pull_request.base.sha }} --github-event ${{ github.event.action }}

.github/workflows/backport-pr-fixes-validation.yaml

@@ -1,33 +0,0 @@
-name: Fixes validation for backport PR
-
-on:
-  pull_request:
-    types: [opened, reopened, edited]
-    branches: [branch-*]
-
-jobs:
-  check-fixes-prefix:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check PR body for "Fixes" prefix patterns
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const body = context.payload.pull_request.body;
-            const repo = context.payload.repository.full_name;
-            
-            // Regular expression pattern to check for "Fixes" prefix
-            // Adjusted to dynamically insert the repository full name
-            const pattern = `Fixes:? ((?:#|${repo.replace('/', '\\/')}#|https://github\\.com/${repo.replace('/', '\\/')}/issues/)(\\d+)|([A-Z]+-\\d+))`;
-            const regex = new RegExp(pattern);
-            
-            if (!regex.test(body)) {
-              const error = "PR body does not contain a valid 'Fixes' reference.";
-              core.setFailed(error);
-              await github.rest.issues.createComment({
-                issue_number: context.issue.number,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `:warning: ${error}`
-              });
-            }

.github/workflows/build-scylla.yaml

@@ -1,39 +0,0 @@
-name: Build Scylla
-
-on:
-  workflow_call:
-    inputs:
-      build_mode:
-        description: 'the build mode'
-        type: string
-        required: true
-    outputs:
-      md5sum:
-        description: 'the md5sum for scylla executable'
-        value: ${{ jobs.build.outputs.md5sum }}
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  build:
-    if: github.repository == 'scylladb/scylladb'
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    outputs:
-      md5sum: ${{ steps.checksum.outputs.md5sum }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: Generate the building system
-        run: |
-          git config --global --add safe.directory $GITHUB_WORKSPACE
-          ./configure.py --mode ${{ inputs.build_mode }} --with scylla
-      - run: |
-          ninja build/${{ inputs.build_mode }}/scylla
-      - id: checksum
-        run: |
-          checksum=$(md5sum build/${{ inputs.build_mode }}/scylla | cut -c -32)
-          echo "md5sum=$checksum" >> $GITHUB_OUTPUT

.github/workflows/call_jira_status_in_progress.yml

@@ -1,12 +0,0 @@
-name: Call Jira Status In Progress
-
-on:
-  pull_request_target:
-    types: [opened]
-
-jobs:
-  call-jira-status-in-progress:
-    uses: scylladb/github-automation/.github/workflows/main_update_jira_status_to_in_progress.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-

.github/workflows/call_jira_status_in_review.yml

@@ -1,12 +0,0 @@
-name: Call Jira Status In Review
-
-on:
-  pull_request_target:
-    types: [ready_for_review, review_requested]
-
-jobs:
-  call-jira-status-in-review:
-    uses: scylladb/github-automation/.github/workflows/main_update_jira_status_to_in_review.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-

.github/workflows/call_jira_status_ready_for_merge.yml

@@ -1,12 +0,0 @@
-name: Call Jira Status Ready For Merge
-
-on:
-  pull_request_target:
-    types: [labeled]
-
-jobs:
-  call-jira-status-update:
-    uses: scylladb/github-automation/.github/workflows/main_update_jira_status_to_ready_for_merge.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-

.github/workflows/call_sync_milestone_to_jira.yml

@@ -1,14 +0,0 @@
-name: Call Jira release creation for new milestone
-
-on:
-  milestone:
-    types: [created]
-
-jobs:
-  sync-milestone-to-jira:
-    uses: scylladb/github-automation/.github/workflows/main_sync_milestone_to_jira_release.yml@main
-    with:
-      # Comma-separated list of Jira project keys
-      jira_project_keys: "SCYLLADB,CUSTOMER"
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/check-license-header.yaml

@@ -1,52 +0,0 @@
-name: License Header Check
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened]
-    branches: [master]
-
-env:
-  HEADER_CHECK_LINES: 10
-  LICENSE: "LicenseRef-ScyllaDB-Source-Available-1.0"
-  CHECKED_EXTENSIONS: ".cc .hh .py"
-
-jobs:
-  check-license-headers:
-    name: Check License Headers
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Get changed files
-        id: changed-files
-        run: |
-          # Get list of added files comparing with base branch
-          echo "files=$(git diff --name-only --diff-filter=A ${{ github.event.pull_request.base.sha }} ${{ github.sha }} | tr '\n' ' ')" >> $GITHUB_OUTPUT
-
-      - name: Check license headers
-        if: steps.changed-files.outputs.files != ''
-        run: |
-          .github/scripts/check-license.py \
-            --files ${{ steps.changed-files.outputs.files }} \
-            --license "${{ env.LICENSE }}" \
-            --check-lines "${{ env.HEADER_CHECK_LINES }}" \
-            --extensions ${{ env.CHECKED_EXTENSIONS }}
-
-      - name: Comment on PR if check fails
-        if: failure()
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const license = '${{ env.LICENSE }}';
-            await github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `❌ License header check failed. Please ensure all new files include the header within the first ${{ env.HEADER_CHECK_LINES }} lines:\n\`\`\`\n${license}\n\`\`\`\nSee action logs for details.`
-            });

.github/workflows/clang-nightly.yaml

@@ -1,66 +0,0 @@
-name: clang-nightly
-
-on:
-  schedule:
-    # only at 5AM Saturday
-    - cron: '0 5 * * SAT'
-
-env:
-  # use the development branch explicitly
-  CLANG_VERSION: 21
-  BUILD_DIR: build
-
-permissions: {}
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  clang-dev:
-    name: Build with clang nightly
-    if: github.repository == 'scylladb/scylladb'
-    runs-on: ubuntu-latest
-    container: fedora:40
-    strategy:
-      matrix:
-        build_type:
-          - Debug
-          - RelWithDebInfo
-          - Dev
-    steps:
-      - run: |
-          sudo dnf -y install git
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Install build dependencies
-        run: |
-          # use the copr repo for llvm snapshot builds, see
-          # https://copr.fedorainfracloud.org/coprs/g/fedora-llvm-team/llvm-snapshots/
-          sudo dnf -y install 'dnf-command(copr)'
-          sudo dnf copr enable -y @fedora-llvm-team/llvm-snapshots
-          # do not install java dependencies, which is not only not used here
-          sed -i.orig \
-            -e '/tools\/.*\/install-dependencies.sh/d' \
-            -e 's/(minio_download_jobs)/(true)/' \
-            ./install-dependencies.sh
-          sudo ./install-dependencies.sh
-          sudo dnf -y install lld
-      - name: Generate the building system
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DCMAKE_C_COMPILER=clang-$CLANG_VERSION     \
-            -DCMAKE_CXX_COMPILER=clang++-$CLANG_VERSION \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      # see https://github.com/actions/toolkit/blob/main/docs/problem-matchers.md
-      - run: |
-          echo "::add-matcher::.github/clang-matcher.json"
-      - run: |
-          cmake --build $BUILD_DIR --target scylla
-      - run: |
-          echo "::remove-matcher owner=clang::"

.github/workflows/clang-tidy.yaml

@@ -1,69 +0,0 @@
-name: clang-tidy
-
-on:
-  pull_request:
-    branches:
-      - master
-    paths-ignore:
-      - '**/*.rst'
-      - '**/*.md'
-      - 'docs/**'
-      - '.github/**'
-  workflow_dispatch:
-  issue_comment:
-    types:
-      - created
-
-env:
-  BUILD_TYPE: RelWithDebInfo
-  BUILD_DIR: build
-  CLANG_TIDY_CHECKS: '-*,bugprone-use-after-move'
-
-permissions: {}
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  read-toolchain:
-    if: github.event_name == 'pull_request' || (github.event.issue.pull_request && startsWith(github.event.comment.body, '/clang-tidy'))
-    uses: ./.github/workflows/read-toolchain.yaml
-  clang-tidy:
-    name: Run clang-tidy
-    needs:
-      - read-toolchain
-    if: "${{ needs.read-toolchain.result == 'success' }}"
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    steps:
-      - env:
-          IMAGE: ${{ needs.read-toolchain.image }}
-        run: |
-          echo ${{ needs.read-toolchain.image }}
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - run: |
-          sudo dnf -y install clang-tools-extra
-      - name: Generate the building system
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=$BUILD_TYPE              \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DScylla_USE_LINKER=ld.lld                  \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -DCMAKE_EXPORT_COMPILE_COMMANDS=ON          \
-            -DCMAKE_CXX_CLANG_TIDY="clang-tidy;--checks=$CLANG_TIDY_CHECKS" \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      # see https://github.com/actions/toolkit/blob/main/docs/problem-matchers.md
-      - run: |
-          echo "::add-matcher::.github/clang-matcher.json"
-      - name: Build with clang-tidy enabled
-        run: |
-          cmake --build $BUILD_DIR --target scylla
-      - run: |
-          echo "::remove-matcher owner=clang::"

.github/workflows/codespell.yaml

@@ -1,17 +0,0 @@
-name: codespell
-on:
-  pull_request:
-    branches:
-      - master
-permissions: {}
-jobs:
-  codespell:
-    name: Check for spelling errors
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: codespell-project/actions-codespell@master
-        with:
-          only_warn: 1
-          ignore_words_list: "ans,datas,fo,ser,ue,crate,nd,reenable,strat,stap,te,raison"
-          skip: "./.git,./build,./tools,*.js,*.lock,./test,./licenses,./redis/lolwut.cc,*.svg"

.github/workflows/conflict_reminder.yaml

@@ -1,154 +0,0 @@
-name: Notify PR Authors of Conflicts
-
-permissions:
-  issues: write
-  pull-requests: write
-
-on:
-  push:
-    branches:
-      - 'master'
-      - 'branch-*'
-  schedule:
-    - cron: '0 10 * * 1'  # Runs every Monday at 10:00am
-
-jobs:
-  notify_conflict_prs:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Notify PR Authors of Conflicts
-        uses: actions/github-script@v7
-        with:
-          script: |
-            console.log("Starting conflict reminder script...");
-            // Print trigger event
-            if (process.env.GITHUB_EVENT_NAME) {
-              console.log(`Workflow triggered by: ${process.env.GITHUB_EVENT_NAME}`);
-            } else {
-              console.log("Could not determine workflow trigger event.");
-            }
-            const isPushEvent = process.env.GITHUB_EVENT_NAME === 'push';
-            console.log(`isPushEvent: ${isPushEvent}`);
-            const twoMonthsAgo = new Date();
-            twoMonthsAgo.setMonth(twoMonthsAgo.getMonth() - 2);
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              state: 'open',
-              per_page: 100
-            });
-            console.log(`Fetched ${prs.length} open PRs`);
-            const recentPrs = prs.filter(pr => new Date(pr.created_at) >= twoMonthsAgo);
-            const validBaseBranches = ['master'];
-            const branchPrefix = 'branch-';
-            const oneWeekAgo = new Date();
-            const conflictLabel = 'conflicts';
-            oneWeekAgo.setDate(oneWeekAgo.getDate() - 7);
-            console.log(`One week ago: ${oneWeekAgo.toISOString()}`);
-
-            for (const pr of recentPrs) {
-              console.log(`Checking PR #${pr.number} on base branch '${pr.base.ref}'`);
-              const isBranchX = pr.base.ref.startsWith(branchPrefix);
-              const isMaster = validBaseBranches.includes(pr.base.ref);
-              if (!(isBranchX || isMaster)) {
-                console.log(`PR #${pr.number} skipped: base branch is not 'master' or does not start with '${branchPrefix}'`);
-                continue;
-              }
-              const updatedDate = new Date(pr.updated_at);
-              console.log(`PR #${pr.number} last updated at: ${updatedDate.toISOString()}`);
-              if (!isPushEvent && updatedDate >= oneWeekAgo) {
-                console.log(`PR #${pr.number} skipped: updated within last week`);
-                continue;
-              }
-              if (pr.assignee === null) {
-                console.log(`PR #${pr.number} skipped: no assignee`);
-                continue;
-              }
-
-              // Fetch PR details to check mergeability
-              let { data: prDetails } = await github.rest.pulls.get({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: pr.number,
-              });
-              console.log(`PR #${pr.number} mergeable: ${prDetails.mergeable}`);
-
-              // Wait and re-fetch if mergeable is null
-              if (prDetails.mergeable === null) {
-                console.log(`PR #${pr.number} mergeable is null, waiting 2 seconds and retrying...`);
-                await new Promise(resolve => setTimeout(resolve, 2000)); // wait 2 seconds
-                prDetails = (await github.rest.pulls.get({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  pull_number: pr.number,
-                })).data;
-                console.log(`PR #${pr.number} mergeable after retry: ${prDetails.mergeable}`);
-              }
-
-              if (prDetails.mergeable === false) {
-                const hasConflictLabel = pr.labels.some(label => label.name === conflictLabel);
-                console.log(`PR #${pr.number} has conflict label: ${hasConflictLabel}`);
-
-                // Fetch comments to check for existing notifications
-                const comments = await github.paginate(github.rest.issues.listComments, {
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: pr.number,
-                  per_page: 100,
-                });
-                
-                // Find last notification comment from the bot
-                const notificationPrefix = `@${pr.assignee.login}, this PR has merge conflicts with the base branch.`;
-                const lastNotification = comments
-                  .filter(c =>
-                    c.user.type === "Bot" &&
-                    c.body.startsWith(notificationPrefix)
-                  )
-                  .sort((a, b) => new Date(b.created_at) - new Date(a.created_at))[0];
-
-                // Check if we should skip notification based on recent notification
-                let shouldSkipNotification = false;
-                if (lastNotification) {
-                  const lastNotified = new Date(lastNotification.created_at);
-                  if (lastNotified >= oneWeekAgo) {
-                    console.log(`PR #${pr.number} skipped: last notification was less than 1 week ago`);
-                    shouldSkipNotification = true;
-                  }
-                }
-
-                // Additional check for push events on draft PRs with conflict labels
-                if (
-                  isPushEvent &&
-                  pr.draft === true &&
-                  hasConflictLabel &&
-                  shouldSkipNotification
-                ) {
-                  continue;
-                }
-
-                if (!hasConflictLabel) {
-                  await github.rest.issues.addLabels({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number,
-                    labels: [conflictLabel],
-                  });
-                  console.log(`Added 'conflicts' label to PR #${pr.number}`);
-                }
-                
-                const assignee = pr.assignee.login;
-                if (assignee && !shouldSkipNotification) {
-                  await github.rest.issues.createComment({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number,
-                    body: `@${assignee}, this PR has merge conflicts with the base branch. Please resolve the conflicts so we can merge it.`,
-                  });
-                  console.log(`Notified @${assignee} for PR #${pr.number}`);
-                }
-              } else {
-                console.log(`PR #${pr.number} is mergeable, no action needed.`);
-              }
-            }
-            console.log(`Total PRs checked: ${prs.length}`);

.github/workflows/differential-shellcheck.yaml

@@ -1,32 +0,0 @@
----
-# https://github.com/redhat-plumbers-in-action/differential-shellcheck#readme
-
-name: Differential ShellCheck
-on:
-  push:
-    branches:
-      - master
-  pull_request:
-    branches:
-      - master
-
-permissions:
-  contents: read
-
-jobs:
-  lint:
-    runs-on: ubuntu-latest
-
-    permissions:
-      security-events: write
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Differential ShellCheck
-        uses: redhat-plumbers-in-action/differential-shellcheck@v5
-        with:
-          severity: warning
-          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pages.yaml

@@ -1,43 +0,0 @@
-name: "Docs / Publish"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-  DEFAULT_BRANCH: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'master' }}
-
-on:
-  push:
-    branches:
-      - 'master'
-      - 'enterprise'
-      - 'branch-**'
-    paths:
-      - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ env.DEFAULT_BRANCH }}
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" multiversion
-      - name: Build redirects
-        run: make -C docs FLAG="${{ env.FLAG }}" redirects
-      - name: Deploy docs to GitHub Pages
-        run: ./docs/_utils/deploy.sh
-        if: (github.ref_name == 'master' && env.FLAG == 'opensource') || (github.ref_name == 'enterprise' && env.FLAG == 'enterprise')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pr.yaml

@@ -1,33 +0,0 @@
-name: "Docs / Build PR"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-
-on:
-  pull_request:
-    branches:
-      - master
-      - enterprise
-    paths:
-      - "docs/**"
-      - "db/config.hh"
-      - "db/config.cc"
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" test

.github/workflows/docs-validate-metrics.yml

@@ -1,34 +0,0 @@
-name: Docs / Validate metrics
-
-on:
-  pull_request:
-    branches:
-      - master
-      - enterprise
-    paths:
-      - '**/*.cc'
-      - 'scripts/metrics-config.yml'
-      - 'scripts/get_description.py'
-      - 'docs/_ext/scylladb_metrics.py'
-
-jobs:
-  validate-metrics:
-    runs-on: ubuntu-latest
-    name: Check metrics documentation coverage
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        submodules: true
-
-    - name: Set up Python
-      uses: actions/setup-python@v6
-      with:
-        python-version: '3.10'
-
-    - name: Install dependencies
-      run: pip install PyYAML
-
-    - name: Validate metrics
-      run: python3 scripts/get_description.py --validate -c scripts/metrics-config.yml

.github/workflows/iwyu.yaml

@@ -1,104 +0,0 @@
-name: iwyu
-
-on:
-  pull_request:
-    branches:
-      - master
-
-env:
-  BUILD_TYPE: RelWithDebInfo
-  BUILD_DIR: build
-  CLEANER_OUTPUT_PATH: build/clang-include-cleaner.log
-  # the "idl" subdirectory does not contain C++ source code. the .hh files in it are
-  # supposed to be processed by idl-compiler.py, so we don't check them using the cleaner
-  CLEANER_DIRS: test/unit exceptions alternator api auth cdc compaction db dht gms index lang message mutation mutation_writer node_ops raft redis replica service
-  SEASTAR_BAD_INCLUDE_OUTPUT_PATH: build/seastar-bad-include.log
-
-permissions: {}
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  clang-include-cleaner:
-    name: "Analyze #includes in source files"
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - run: |
-          sudo dnf -y install clang-tools-extra
-      - name: Generate compilation database
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=$BUILD_TYPE              \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -DCMAKE_EXPORT_COMPILE_COMMANDS=ON          \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      - run: |
-          cmake                       \
-          --build $BUILD_DIR          \
-          --target wasmtime_bindings
-      - name: Build headers
-        run: |
-          swagger_targets=''
-          for f in api/api-doc/*.json; do
-            if test "${f#*.}" = json; then
-              name=$(basename "$f" .json)
-              if test $name != swagger20_header; then
-                swagger_targets+=" scylla_swagger_gen_$name"
-              fi
-            fi
-          done
-          cmake                                         \
-            --build build                               \
-             --target seastar_http_request_parser       \
-             --target idl-sources                       \
-             --target $swagger_targets
-      - run: |
-          echo "::add-matcher::.github/clang-include-cleaner.json"
-      - name: clang-include-cleaner
-        run: |
-          for d in $CLEANER_DIRS; do
-            find $d -name '*.cc' -o -name '*.hh'          \
-              -exec echo {} \;                            \
-              -exec clang-include-cleaner                 \
-                --ignore-headers=seastarx.hh              \
-                --print=changes                           \
-                -p $BUILD_DIR                             \
-                {} \; | tee --append $CLEANER_OUTPUT_PATH
-          done
-      - run: |
-          echo "::remove-matcher owner=clang-include-cleaner::"
-      - run: |
-          echo "::add-matcher::.github/seastar-bad-include.json"
-      - name: check for seastar includes
-        run: |
-          git -c safe.directory="$PWD"    \
-            grep -nE '#include +"seastar/' \
-            | tee "$SEASTAR_BAD_INCLUDE_OUTPUT_PATH"
-      - run: |
-          echo "::remove-matcher owner=seastar-bad-include::"
-      - uses: actions/upload-artifact@v4
-        with:
-          name: Logs
-          path: |
-            ${{ env.CLEANER_OUTPUT_PATH }}
-            ${{ env.SEASTAR_BAD_INCLUDE_OUTPUT_PATH }}
-      - name: fail if seastar headers are included as an internal library
-        run: |
-          if [ -s "$SEASTAR_BAD_INCLUDE_OUTPUT_PATH" ]; then
-            echo "::error::Found #include \"seastar/ in the source code. Use angle brackets instead."
-            exit 1
-          fi

.github/workflows/make-pr-ready-for-review.yaml

@@ -1,29 +0,0 @@
-name: Mark PR as Ready When Conflicts Label is Removed
-
-on:
-  pull_request_target:
-    types:
-      - unlabeled
-
-env:
-  DEFAULT_BRANCH: 'master'
-
-jobs:
-  mark-ready:
-    if: github.event.label.name == 'conflicts'
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          repository: ${{ github.repository }}
-          ref: ${{ env.DEFAULT_BRANCH }}
-          token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-          fetch-depth: 1
-      - name: Mark pull request as ready for review
-        run:  gh pr ready "${{ github.event.pull_request.number }}"
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}

.github/workflows/pr-require-backport-label.yaml

@@ -1,24 +0,0 @@
-name: PR require backport label
-on:
-  pull_request:
-    types: [opened, labeled, unlabeled, synchronize]
-    branches:
-      - master
-      - next
-jobs:
-  label:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-    steps:
-      - name: Wait for label to be added
-        run: sleep 1m
-      - uses: mheap/github-action-required-labels@v5
-        with:
-          mode: minimum
-          count: 1
-          labels: "backport/none\nbackport/\\d{4}\\.\\d+\nbackport/\\d+\\.\\d+"
-          use_regex: true
-          add_comment: false

.github/workflows/read-toolchain.yaml

@@ -1,23 +0,0 @@
-name: Read Toolchain
-
-on:
-  workflow_call:
-    outputs:
-      image:
-        description: "the toolchain docker image"
-        value: ${{ jobs.read-toolchain.outputs.image }}
-
-jobs:
-  read-toolchain:
-    runs-on: ubuntu-latest
-    outputs:
-      image: ${{ steps.read.outputs.image }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          sparse-checkout: tools/toolchain/image
-          sparse-checkout-cone-mode: false
-      - id: read
-        run: |
-          image=$(cat tools/toolchain/image)
-          echo "image=$image" >> $GITHUB_OUTPUT

.github/workflows/reproducible-build.yaml

@@ -1,35 +0,0 @@
-name: Check Reproducible Build
-
-on:
-  schedule:
-    # 5AM every friday
-    - cron: '0 5 * * FRI'
-
-permissions: {}
-
-env:
-  BUILD_MODE: release
-jobs:
-  build-a:
-    uses: ./.github/workflows/build-scylla.yaml
-    with:
-      build_mode: release
-  build-b:
-    uses: ./.github/workflows/build-scylla.yaml
-    with:
-      build_mode: release
-  compare-checksum:
-    if: github.repository == 'scylladb/scylladb'
-    runs-on: ubuntu-latest
-    needs:
-      - build-a
-      - build-b
-    steps:
-      - env:
-          CHECKSUM_A: ${{needs.build-a.outputs.md5sum}}
-          CHECKSUM_B: ${{needs.build-b.outputs.md5sum}}
-        run: |
-          if [ $CHECKSUM_A != $CHECKSUM_B ]; then                             \
-            echo "::error::mismatched checksums: $CHECKSUM_A != $CHECKSUM_B"; \
-            exit 1;                                                           \
-          fi

.github/workflows/seastar.yaml

@@ -1,53 +0,0 @@
-name: Build with the latest Seastar
-
-on:
-  schedule:
-    # 5AM everyday
-    - cron: '0 5 * * *'
-
-permissions: {}
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  BUILD_DIR: build
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  build-with-the-latest-seastar:
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    strategy:
-      matrix:
-        build_type:
-          - Debug
-          - RelWithDebInfo
-          - Dev
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - run: |
-          rm -rf seastar
-      - uses: actions/checkout@v4
-        with:
-          repository: scylladb/seastar
-          submodules: true
-          path: seastar
-      - name: Generate the building system
-        run: |
-          git config --global --add safe.directory $GITHUB_WORKSPACE
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      - run: |
-          cmake --build $BUILD_DIR --target scylla

.github/workflows/sync-labels.yaml

@@ -1,49 +0,0 @@
-name: Sync labels
-
-on:
-  pull_request_target:
-    types: [opened, labeled, unlabeled]
-    branches: [master, next]
-  issues:
-    types: [labeled, unlabeled]
-
-jobs:
-  label-sync:
-    if: ${{ github.repository == 'scylladb/scylladb' }}
-    name:  Synchronize labels between PR and the issue(s) fixed by it
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          sparse-checkout: |
-            .github/scripts/sync_labels.py
-          sparse-checkout-cone-mode: false
-
-      - name: Install dependencies
-        run: sudo apt-get install -y python3-github
-
-      - name: Pull request opened event
-        if: ${{ github.event.action == 'opened' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.number }} --action ${{ github.event.action }}
-
-      - name: Pull request labeled or unlabeled event
-        if: github.event_name == 'pull_request_target' && (startsWith(github.event.label.name, 'backport/') || github.event.label.name == 'P0' || github.event.label.name == 'P1')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.number }} --action ${{ github.event.action }} --label ${{ github.event.label.name }}
-
-      - name: Issue labeled or unlabeled event
-        if: github.event_name == 'issues' && (startsWith(github.event.label.name, 'backport/') || github.event.label.name == 'P0' || github.event.label.name == 'P1')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.issue.number }} --action ${{ github.event.action }} --is_issue --label ${{ github.event.label.name }}

.github/workflows/trigger-scylla-ci.yaml

@@ -1,24 +0,0 @@
-name: Trigger Scylla CI Route
-
-on:
-  issue_comment:
-    types: [created]
-  pull_request_target:
-    types:
-      - unlabeled
-
-jobs:
-  trigger-jenkins:
-    if: (github.event.comment.user.login != 'scylladbbot' && contains(github.event.comment.body, '@scylladbbot') && contains(github.event.comment.body, 'trigger-ci')) || github.event.label.name == 'conflicts'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger Scylla-CI-Route Jenkins Job
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-        run: |
-          PR_NUMBER=${{ github.event.issue.number }}
-          PR_REPO_NAME=${{ github.event.repository.full_name }}
-          curl -X POST "$JENKINS_URL/job/releng/job/Scylla-CI-Route/buildWithParameters?PR_NUMBER=$PR_NUMBER&PR_REPO_NAME=$PR_REPO_NAME" \
-          --user "$JENKINS_USER:$JENKINS_API_TOKEN" --fail -i -v

.github/workflows/trigger_ci.yaml

@@ -1,242 +0,0 @@
-name: Trigger next gating
-
-on:
-  pull_request_target:
-    types: [opened, reopened, synchronize]
-  issue_comment:
-    types: [created]
-    
-jobs:
-  trigger-ci:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Checkout PR code
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0  # Needed to access full history
-          ref: ${{ github.event.pull_request.head.ref }}
-
-      - name: Fetch before commit if needed
-        run: |
-          if ! git cat-file -e ${{ github.event.before }} 2>/dev/null; then
-            echo "Fetching before commit ${{ github.event.before }}"
-            git fetch --depth=1 origin ${{ github.event.before }}
-          fi
-
-      - name: Compare commits for file changes
-        if: github.action == 'synchronize'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          echo "Base: ${{ github.event.before }}"
-          echo "Head: ${{ github.event.after }}"
-
-          TREE_BEFORE=$(git show -s --format=%T ${{ github.event.before }})
-          TREE_AFTER=$(git show -s --format=%T ${{ github.event.after }})
-          
-          echo "TREE_BEFORE=$TREE_BEFORE" >> $GITHUB_ENV
-          echo "TREE_AFTER=$TREE_AFTER" >> $GITHUB_ENV
-
-      - name: Check if last push has file changes
-        run: |
-          if [[ "${{ env.TREE_BEFORE }}" == "${{ env.TREE_AFTER }}" ]]; then
-            echo "No file changes detected in the last push, only commit message edit."
-            echo "has_file_changes=false" >> $GITHUB_ENV
-          else
-            echo "File changes detected in the last push."
-            echo "has_file_changes=true" >> $GITHUB_ENV
-          fi
-
-      - name: Rule 1 - Check PR draft or conflict status
-        run: |
-          # Check if PR is in draft mode
-          IS_DRAFT="${{ github.event.pull_request.draft }}"
-          
-          # Check if PR has 'conflict' label
-          HAS_CONFLICT_LABEL="false"
-          LABELS='${{ toJson(github.event.pull_request.labels) }}'
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^conflict$"; then
-            HAS_CONFLICT_LABEL="true"
-          fi
-          
-          # Set draft_or_conflict variable
-          if [[ "$IS_DRAFT" == "true" || "$HAS_CONFLICT_LABEL" == "true" ]]; then
-            echo "draft_or_conflict=true" >> $GITHUB_ENV
-            echo "✅ Rule 1: PR is in draft mode or has conflict label - setting draft_or_conflict=true"
-          else
-            echo "draft_or_conflict=false" >> $GITHUB_ENV
-            echo "✅ Rule 1: PR is ready and has no conflict label - setting draft_or_conflict=false"
-          fi
-          
-          echo "Draft status: $IS_DRAFT"
-          echo "Has conflict label: $HAS_CONFLICT_LABEL"
-          echo "Result: draft_or_conflict = $draft_or_conflict"
-
-      - name: Rule 2 - Check labels
-        run: |
-          # Check if PR has P0 or P1 labels
-          HAS_P0_P1_LABEL="false"
-          LABELS='${{ toJson(github.event.pull_request.labels) }}'
-          if echo "$LABELS" | jq -r '.[].name' | grep -E "^(P0|P1)$" > /dev/null; then
-            HAS_P0_P1_LABEL="true"
-          fi
-          
-          # Check if PR already has force_on_cloud label
-          echo "HAS_FORCE_ON_CLOUD_LABEL=false" >> $GITHUB_ENV
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^force_on_cloud$"; then
-            HAS_FORCE_ON_CLOUD_LABEL="true"
-            echo "HAS_FORCE_ON_CLOUD_LABEL=true" >> $GITHUB_ENV
-          fi
-          
-          echo "Has P0/P1 label: $HAS_P0_P1_LABEL"
-          echo "Has force_on_cloud label: $HAS_FORCE_ON_CLOUD_LABEL"
-          
-          # Add force_on_cloud label if PR has P0/P1 and doesn't already have force_on_cloud
-          if [[ "$HAS_P0_P1_LABEL" == "true" && "$HAS_FORCE_ON_CLOUD_LABEL" == "false" ]]; then
-            echo "✅ Rule 2: PR has P0 or P1 label - adding force_on_cloud label"
-            curl -X POST \
-              -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
-              -H "Accept: application/vnd.github.v3+json" \
-              "https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/labels" \
-              -d '{"labels":["force_on_cloud"]}'
-          elif [[ "$HAS_P0_P1_LABEL" == "true" && "$HAS_FORCE_ON_CLOUD_LABEL" == "true" ]]; then
-            echo "✅ Rule 2: PR has P0 or P1 label and already has force_on_cloud label - no action needed"
-          else
-            echo "✅ Rule 2: PR does not have P0 or P1 label - no force_on_cloud label needed"
-          fi
-
-          SKIP_UNIT_TEST_CUSTOM="false"
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^ci/skip_unit-tests_custom$"; then
-            SKIP_UNIT_TEST_CUSTOM="true"
-          fi
-          echo "SKIP_UNIT_TEST_CUSTOM=$SKIP_UNIT_TEST_CUSTOM" >> $GITHUB_ENV
-
-      - name: Rule 3 - Analyze changed files and set build requirements
-        run: |
-          # Get list of changed files
-          CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }})
-          echo "Changed files:"
-          echo "$CHANGED_FILES"
-          echo ""
-          
-          # Initialize all requirements to false
-          REQUIRE_BUILD="false"
-          REQUIRE_DTEST="false"
-          REQUIRE_UNITTEST="false"
-          REQUIRE_ARTIFACTS="false"
-          REQUIRE_SCYLLA_GDB="false"
-          
-          # Check each file against patterns
-          while IFS= read -r file; do
-            if [[ -n "$file" ]]; then
-              echo "Checking file: $file"
-              
-              # Build pattern: ^(?!scripts\/pull_github_pr.sh).*$
-              # Everything except scripts/pull_github_pr.sh
-              if [[ "$file" != "scripts/pull_github_pr.sh" ]]; then
-                REQUIRE_BUILD="true"
-                echo "  ✓ Matches build pattern"
-              fi
-              
-              # Dtest pattern: ^(?!test(.py|\/)|dist\/docker\/|dist\/common\/scripts\/).*$
-              # Everything except test files, dist/docker/, dist/common/scripts/
-              if [[ ! "$file" =~ ^test\.(py|/).*$ ]] && [[ ! "$file" =~ ^dist/docker/.*$ ]] && [[ ! "$file" =~ ^dist/common/scripts/.*$ ]]; then
-                REQUIRE_DTEST="true"
-                echo "  ✓ Matches dtest pattern"
-              fi
-              
-              # Unittest pattern: ^(?!dist\/docker\/|dist\/common\/scripts).*$
-              # Everything except dist/docker/, dist/common/scripts/
-              if [[ ! "$file" =~ ^dist/docker/.*$ ]] && [[ ! "$file" =~ ^dist/common/scripts.*$ ]]; then
-                REQUIRE_UNITTEST="true"
-                echo "  ✓ Matches unittest pattern"
-              fi
-              
-              # Artifacts pattern: ^(?:dist|tools\/toolchain).*$
-              # Files starting with dist or tools/toolchain
-              if [[ "$file" =~ ^dist.*$ ]] || [[ "$file" =~ ^tools/toolchain.*$ ]]; then
-                REQUIRE_ARTIFACTS="true"
-                echo "  ✓ Matches artifacts pattern"
-              fi
-              
-              # Scylla GDB pattern: ^(scylla-gdb.py).*$
-              # Files starting with scylla-gdb.py
-              if [[ "$file" =~ ^scylla-gdb\.py.*$ ]]; then
-                REQUIRE_SCYLLA_GDB="true"
-                echo "  ✓ Matches scylla_gdb pattern"
-              fi
-            fi
-          done <<< "$CHANGED_FILES"
-          
-          # Set environment variables
-          echo "requireBuild=$REQUIRE_BUILD" >> $GITHUB_ENV
-          echo "requireDtest=$REQUIRE_DTEST" >> $GITHUB_ENV
-          echo "requireUnittest=$REQUIRE_UNITTEST" >> $GITHUB_ENV
-          echo "requireArtifacts=$REQUIRE_ARTIFACTS" >> $GITHUB_ENV
-          echo "requireScyllaGdb=$REQUIRE_SCYLLA_GDB" >> $GITHUB_ENV
-          
-          echo ""
-          echo "✅ Rule 3: File analysis complete"
-          echo "Build required: $REQUIRE_BUILD"
-          echo "Dtest required: $REQUIRE_DTEST"
-          echo "Unittest required: $REQUIRE_UNITTEST"
-          echo "Artifacts required: $REQUIRE_ARTIFACTS"
-          echo "Scylla GDB required: $REQUIRE_SCYLLA_GDB"
-
-      - name: Determine Jenkins Job Name
-        run: |
-          if [[ "${{ github.ref_name }}" == "next" ]]; then
-            FOLDER_NAME="scylla-master"
-          elif [[ "${{ github.ref_name }}" == "next-enterprise" ]]; then
-            FOLDER_NAME="scylla-enterprise"
-          else
-            VERSION=$(echo "${{ github.ref_name }}" | awk -F'-' '{print $2}')
-            if [[ "$VERSION" =~ ^202[0-4]\.[0-9]+$ ]]; then
-              FOLDER_NAME="enterprise-$VERSION"
-            elif [[ "$VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
-              FOLDER_NAME="scylla-$VERSION"
-            fi
-          fi
-          echo "JOB_NAME=${FOLDER_NAME}/job/scylla-ci" >> $GITHUB_ENV
-
-      - name: Trigger Jenkins Job
-        if: env.draft_or_conflict == 'false' && env.has_file_changes == 'true' && github.action == 'opened' || github.action == 'reopened'
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-        run: |
-          PR_NUMBER=${{ github.event.issue.number }}
-          PR_REPO_NAME=${{ github.event.repository.full_name }}
-          echo "Triggering Jenkins Job: $JOB_NAME"
-          curl -X POST \
-            "$JENKINS_URL/job/$JOB_NAME/buildWithParameters? \
-            PR_NUMBER=$PR_NUMBER& \
-            RUN_DTEST=$REQUIRE_DTEST& \
-            RUN_ONLY_SCYLLA_GDB=$REQUIRE_SCYLLA_GDB& \
-            RUN_UNIT_TEST=$REQUIRE_UNITTEST& \
-            FORCE_ON_CLOUD=$HAS_FORCE_ON_CLOUD_LABEL& \
-            SKIP_UNIT_TEST_CUSTOM=$SKIP_UNIT_TEST_CUSTOM& \
-            RUN_ARTIFACT_TESTS=$REQUIRE_ARTIFACTS" \
-            --fail \
-            --user "$JENKINS_USER:$JENKINS_API_TOKEN" \
-            -i -v
-  trigger-ci-via-comment:
-    if: github.event.comment.user.login != 'scylladbbot' && contains(github.event.comment.body, '@scylladbbot') && contains(github.event.comment.body, 'trigger-ci')
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger Scylla-CI Jenkins Job
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-        run: |
-          PR_NUMBER=${{ github.event.issue.number }}
-          PR_REPO_NAME=${{ github.event.repository.full_name }}
-          curl -X POST "$JENKINS_URL/job/$JOB_NAME/buildWithParameters?PR_NUMBER=$PR_NUMBER" \
-          --user "$JENKINS_USER:$JENKINS_API_TOKEN" --fail -i -v

.github/workflows/trigger_jenkins.yaml

@@ -1,50 +0,0 @@
-name: Trigger next gating
-
-on:
-  push:
-    branches:
-      - next**
-
-jobs:
-  trigger-jenkins:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Determine Jenkins Job Name
-        run: |
-          if [[ "${{ github.ref_name }}" == "next" ]]; then
-            FOLDER_NAME="scylla-master"
-          elif [[ "${{ github.ref_name }}" == "next-enterprise" ]]; then
-            FOLDER_NAME="scylla-enterprise"
-          else
-            VERSION=$(echo "${{ github.ref_name }}" | awk -F'-' '{print $2}')
-            if [[ "$VERSION" =~ ^202[0-4]\.[0-9]+$ ]]; then
-              FOLDER_NAME="enterprise-$VERSION"
-            elif [[ "$VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
-              FOLDER_NAME="scylla-$VERSION"
-            fi
-          fi
-          echo "JOB_NAME=${FOLDER_NAME}/job/next" >> $GITHUB_ENV
-
-      - name: Trigger Jenkins Job
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-        run: |
-          echo "Triggering Jenkins Job: $JOB_NAME"
-          if ! curl -X POST "$JENKINS_URL/job/$JOB_NAME/buildWithParameters" --fail --user "$JENKINS_USER:$JENKINS_API_TOKEN" -i -v; then
-            echo "Error: Jenkins job trigger failed"
-
-            # Send Slack message
-            curl -X POST -H 'Content-type: application/json' \
-              -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
-              --data '{
-                "channel": "#releng-team",
-                "text": "🚨 @here '$JOB_NAME' failed to be triggered, please check https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }} for more details",
-                "icon_emoji": ":warning:"
-              }' \
-              https://slack.com/api/chat.postMessage
-
-            exit 1
-          fi

.github/workflows/urgent_issue_reminder.yml

@@ -1,58 +0,0 @@
-name: Urgent Issue Reminder
-
-on:
-  schedule:
-    - cron: '10 8 * * *' # Runs daily at 8 AM
-
-jobs:
-  reminder:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Send reminders
-      uses: actions/github-script@v7
-      with:
-        script: |
-          const labelFilters = ['P0', 'P1', 'Field-Tier1','status/release blocker', 'status/regression']; 
-          const excludingLabelFilters = ['documentation'];
-          const daysInactive = 7;
-          const now = new Date();
-
-          // Fetch open issues
-          const issues = await github.rest.issues.listForRepo({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            state: 'open'
-          });
-          console.log("Looking for issues with labels:"+labelFilters+", excluding labels:"+excludingLabelFilters+ ", inactive for more than "+daysInactive+" days.");
-          for (const issue of issues.data) {
-            // Check if issue has any of the specified labels
-            const hasFilteredLabel = issue.labels.some(label => labelFilters.includes(label.name));
-            const hasExcludingLabel = issue.labels.some(label => excludingLabelFilters.includes(label.name));
-            if (hasExcludingLabel) continue;
-            if (!hasFilteredLabel) continue;
-
-            // Check for inactivity
-            const lastUpdated = new Date(issue.updated_at);
-            const diffInDays = (now - lastUpdated) / (1000 * 60 * 60 * 24);
-            console.log("Issue #"+issue.number+"; Days inactive:"+diffInDays);
-            if (diffInDays > daysInactive) {
-              if (issue.assignees.length > 0) {
-                console.log("==>> Alert about issue #"+issue.number);
-                const assigneesLogins = issue.assignees.map(assignee => `@${assignee.login}`).join(', ');
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issue.number,
-                  body: `${assigneesLogins}, This urgent issue had no activity for more than ${daysInactive} days. Please check its status.\n CC @mykaul @dani-tweig`
-                });
-              } else {
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issue.number,
-                  body: `This urgent issue had no activity for more than ${daysInactive} days. Please check its status.\n CC @mykaul @dani-tweig`
-                });
-              }
-            }
-          }

.gitignore

@@ -3,8 +3,6 @@
 .settings
 build
 build.ninja
-cmake-build-*
-build.ninja.new
 cscope.*
 /debian/
 dist/ami/files/*.rpm
@@ -14,26 +12,9 @@ dist/ami/scylla_deploy.sh
 Cql.tokens
 .kdev4
 *.kdev4
-.idea
 CMakeLists.txt.user
 .cache
 .tox
 *.egg-info
 __pycache__CMakeLists.txt.user
 .gdbinit
-/resources
-.pytest_cache
-/expressions.tokens
-tags
-!db/tags/
-testlog
-test/*/*.reject
-.vscode
-compile_commands.json
-.ccls-cache/
-.mypy_cache
-.envrc
-clang_build
-.idea/
-nuke
-rust/target

.gitmodules

@@ -1,17 +1,11 @@
 [submodule "seastar"]
 	path = seastar
-	url = ../seastar
+	url = ../scylla-seastar
 	ignore = dirty
 [submodule "swagger-ui"]
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
-[submodule "abseil"]
-	path = abseil
-	url = ../abseil-cpp
-[submodule "scylla-python3"]
-	path = tools/python3
-	url = ../scylla-python3
-[submodule "tools/cqlsh"]
-	path = tools/cqlsh
-	url = ../scylla-cqlsh
+[submodule "dist/ami/files/scylla-ami"]
+	path = dist/ami/files/scylla-ami
+	url = ../scylla-ami

.mailmap

@@ -1,3 +0,0 @@
-Avi Kivity <avi@scylladb.com> Avi Kivity' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Raphael S. Carvalho <raphaelsc@scylladb.com> Raphael S. Carvalho' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Pavel Emelyanov <xemul@scylladb.com> Pavel Emelyanov' via ScyllaDB development <scylladb-dev@googlegroups.com>

CMakeLists.txt

@@ -1,398 +1,140 @@
-cmake_minimum_required(VERSION 3.27)
+##
+## For best results, first compile the project using the Ninja build-system.
+##
 
+cmake_minimum_required(VERSION 3.7)
 project(scylla)
 
-list(APPEND CMAKE_MODULE_PATH
-  ${CMAKE_CURRENT_SOURCE_DIR}/cmake
-  ${CMAKE_CURRENT_SOURCE_DIR}/seastar/cmake)
+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()
 
-# Set the possible values of build type for cmake-gui
-set(scylla_build_types
-    "Debug" "RelWithDebInfo" "Dev" "Sanitize" "Coverage")
-if(DEFINED CMAKE_BUILD_TYPE)
-    set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
-     ${scylla_build_types})
-    if(NOT CMAKE_BUILD_TYPE)
-        set(CMAKE_BUILD_TYPE "RelWithDebInfo" CACHE
-            STRING "Choose the type of build." FORCE)
-        message(WARNING "CMAKE_BUILD_TYPE not specified, Using 'RelWithDebInfo'")
-    elseif(NOT CMAKE_BUILD_TYPE IN_LIST scylla_build_types)
-        message(FATAL_ERROR "Unknown CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}. "
-            "Following types are supported: ${scylla_build_types}")
-    endif()
-endif(DEFINED CMAKE_BUILD_TYPE)
+# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
+set(SEASTAR_INCLUDE_DIRS "seastar")
 
-option(Scylla_ENABLE_LTO "Turn on link-time optimization for the 'release' mode." ON)
+# 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
+        seastar/dpdk/lib/librte_eal/common/include
+        seastar/dpdk/lib/librte_eal/common/include/generic
+        seastar/dpdk/lib/librte_eal/common/include/x86
+        seastar/dpdk/lib/librte_ether)
 
-include(mode.common)
-get_property(is_multi_config GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
-if(is_multi_config)
-    foreach(config ${CMAKE_CONFIGURATION_TYPES})
-        include(mode.${config})
-        list(APPEND scylla_build_modes ${scylla_build_mode_${config}})
+find_package(PkgConfig REQUIRED)
+
+set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
+pkg_check_modules(SEASTAR seastar)
+
+find_package(Boost COMPONENTS filesystem program_options system thread)
+
+##
+## Populate the names of all source and header files in the indicated paths in a designated variable.
+##
+## When RECURSIVE is specified, directories are traversed recursively.
+##
+## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
+##
+function (scan_scylla_source_directories)
+    set(options RECURSIVE)
+    set(oneValueArgs VAR)
+    set(multiValueArgs PATHS)
+    cmake_parse_arguments(args "${options}" "${oneValueArgs}" "${multiValueArgs}" "${ARGN}")
+
+    set(globs "")
+
+    foreach (dir ${args_PATHS})
+        list(APPEND globs "${dir}/*.cc" "${dir}/*.hh")
     endforeach()
-    add_custom_target(mode_list
-        COMMAND ${CMAKE_COMMAND} -E echo "$<JOIN:${scylla_build_modes}, >"
-        COMMENT "List configured modes"
-        BYPRODUCTS mode-list.phony.stamp
-        COMMAND_EXPAND_LISTS)
-else()
-    include(mode.${CMAKE_BUILD_TYPE})
-    add_custom_target(mode_list
-        ${CMAKE_COMMAND} -E echo "${scylla_build_mode}"
-        COMMENT "List configured modes")
-endif()
 
-include(limit_jobs)
-
-# Configure Seastar compile options to align with Scylla
-set(CMAKE_CXX_STANDARD "23" CACHE INTERNAL "")
-set(CMAKE_CXX_EXTENSIONS ON CACHE INTERNAL "")
-set(CMAKE_CXX_SCAN_FOR_MODULES OFF CACHE INTERNAL "")
-set(CMAKE_VISIBILITY_INLINES_HIDDEN ON)
-
-if(is_multi_config)
-    find_package(Seastar)
-    # this is atypical compared to standard ExternalProject usage:
-    # - Seastar's build system should already be configured at this point.
-    # - We maintain separate project variants for each configuration type.
-    #
-    # Benefits of this approach:
-    # - Allows the parent project to consume the compile options exposed by
-    #   .pc file. as the compile options vary from one config to another.
-    # - Allows application of config-specific settings
-    # - Enables building Seastar within the parent project's build system
-    # - Facilitates linking of artifacts with the external project target,
-    #   establishing proper dependencies between them
-    include(ExternalProject)
-
-    # should be consistent with configure_seastar() in configure.py
-    set(seastar_build_dir "${CMAKE_BINARY_DIR}/$<CONFIG>/seastar")
-    ExternalProject_Add(Seastar
-        SOURCE_DIR "${PROJECT_SOURCE_DIR}/seastar"
-        CONFIGURE_COMMAND ""
-        BUILD_COMMAND ${CMAKE_COMMAND} --build "${seastar_build_dir}"
-          --target seastar
-          --target seastar_testing
-          --target seastar_perf_testing
-          --target app_iotune
-        BUILD_ALWAYS ON
-        BUILD_BYPRODUCTS
-          ${seastar_build_dir}/libseastar.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/libseastar_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/libseastar_perf_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/apps/iotune/iotune
-          ${seastar_build_dir}/gen/include/seastar/http/chunk_parsers.hh
-          ${seastar_build_dir}/gen/include/seastar/http/request_parser.hh
-          ${seastar_build_dir}/gen/include/seastar/http/response_parser.hh
-        INSTALL_COMMAND "")
-    add_dependencies(Seastar::seastar Seastar)
-    add_dependencies(Seastar::seastar_testing Seastar)
-else()
-    set(Seastar_TESTING ON CACHE BOOL "" FORCE)
-    set(Seastar_API_LEVEL 9 CACHE STRING "" FORCE)
-    set(Seastar_DEPRECATED_OSTREAM_FORMATTERS OFF CACHE BOOL "" FORCE)
-    set(Seastar_APPS ON CACHE BOOL "" FORCE)
-    set(Seastar_EXCLUDE_APPS_FROM_ALL ON CACHE BOOL "" FORCE)
-    set(Seastar_EXCLUDE_TESTS_FROM_ALL ON CACHE BOOL "" FORCE)
-    set(Seastar_IO_URING ON CACHE BOOL "" FORCE)
-    set(Seastar_SCHEDULING_GROUPS_COUNT 21 CACHE STRING "" FORCE)
-    set(Seastar_UNUSED_RESULT_ERROR ON CACHE BOOL "" FORCE)
-    add_subdirectory(seastar)
-    target_compile_definitions (seastar
-      PRIVATE
-        SEASTAR_NO_EXCEPTION_HACK)
-endif()
-
-set(ABSL_PROPAGATE_CXX_STD ON CACHE BOOL "" FORCE)
-
-if(Scylla_ENABLE_LTO)
-    list(APPEND absl_cxx_flags $<$<CONFIG:RelWithDebInfo>:${CMAKE_CXX_COMPILE_OPTIONS_IPO};-ffat-lto-objects>)
-endif()
-
-find_package(Sanitizers QUIET)
-list(APPEND absl_cxx_flags
-    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_COMPILE_OPTIONS>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_COMPILE_OPTIONS>>)
-if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-    list(APPEND ABSL_GCC_FLAGS ${absl_cxx_flags})
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
-    list(APPEND absl_cxx_flags "-Wno-deprecated-builtins")
-    list(APPEND ABSL_LLVM_FLAGS ${absl_cxx_flags})
-endif()
-set(ABSL_DEFAULT_LINKOPTS
-    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_LINK_LIBRARIES>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_LINK_LIBRARIES>>)
-add_subdirectory(abseil)
-add_library(absl-headers INTERFACE)
-target_include_directories(absl-headers SYSTEM INTERFACE
-    "${PROJECT_SOURCE_DIR}/abseil")
-add_library(absl::headers ALIAS absl-headers)
-
-# Exclude absl::strerror from the default "all" target since it's not
-# used in Scylla build and, moreover, makes use of deprecated glibc APIs,
-# such as sys_nerr, which are not exposed from "stdio.h" since glibc 2.32,
-# which happens to be the case for recent Fedora distribution versions.
-#
-# Need to use the internal "absl_strerror" target name instead of namespaced
-# variant because `set_target_properties` does not understand the latter form,
-# unfortunately.
-set_target_properties(absl_strerror PROPERTIES EXCLUDE_FROM_ALL TRUE)
-
-# System libraries dependencies
-find_package(Boost REQUIRED
-    COMPONENTS filesystem program_options system thread regex unit_test_framework)
-target_link_libraries(Boost::regex
-  INTERFACE
-    ICU::i18n
-    ICU::uc)
-find_package(Lua REQUIRED)
-find_package(ZLIB REQUIRED)
-find_package(ICU COMPONENTS uc i18n REQUIRED)
-find_package(fmt 10.0.0 REQUIRED)
-find_package(libdeflate REQUIRED)
-find_package(libxcrypt REQUIRED)
-find_package(p11-kit REQUIRED)
-find_package(Snappy REQUIRED)
-find_package(RapidJSON REQUIRED)
-find_package(xxHash REQUIRED)
-find_package(yaml-cpp REQUIRED)
-find_package(zstd REQUIRED)
-find_package(lz4 REQUIRED)
-
-set(scylla_gen_build_dir "${CMAKE_BINARY_DIR}/gen")
-file(MAKE_DIRECTORY "${scylla_gen_build_dir}")
-
-include(add_version_library)
-generate_scylla_version()
-
-option(Scylla_USE_PRECOMPILED_HEADER "Use precompiled header for Scylla" ON)
-add_library(scylla-precompiled-header STATIC exported_templates.cc)
-target_link_libraries(scylla-precompiled-header PRIVATE
-    absl::headers
-    absl::btree
-    absl::hash
-    absl::raw_hash_set
-    Seastar::seastar
-    Snappy::snappy
-    systemd
-    ZLIB::ZLIB
-    lz4::lz4_static
-    zstd::zstd_static)
-if (Scylla_USE_PRECOMPILED_HEADER)
-  set(Scylla_USE_PRECOMPILED_HEADER_USE ON)
-  find_program(DISTCC_EXEC NAMES distcc OPTIONAL)
-  if (DISTCC_EXEC)
-    if(DEFINED ENV{DISTCC_HOSTS})
-      set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-      message(STATUS "Disabling precompiled header usage because distcc exists and DISTCC_HOSTS is set, assuming you're using distributed compilation.")
+    if (args_RECURSIVE)
+        set(glob_kind GLOB_RECURSE)
     else()
-      file(REAL_PATH "~/.distcc/hosts" DIST_CC_HOSTS_PATH EXPAND_TILDE)
-      if (EXISTS ${DIST_CC_HOSTS_PATH})
-        set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-        message(STATUS "Disabling precompiled header usage because distcc and ~/.distcc/hosts exists, assuming you're using distributed compilation.")
-      endif()
+        set(glob_kind GLOB)
     endif()
-  endif()
-  if (Scylla_USE_PRECOMPILED_HEADER_USE)
-    message(STATUS "Using precompiled header for Scylla - remember to add `sloppiness = pch_defines,time_macros` to ccache.conf, if you're using ccache.")
-    target_precompile_headers(scylla-precompiled-header PRIVATE "stdafx.hh")
-    target_compile_definitions(scylla-precompiled-header PRIVATE SCYLLA_USE_PRECOMPILED_HEADER)
-  endif()
-else()
-  set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-endif()
 
-add_library(scylla-main STATIC)
+    file(${glob_kind} var
+            ${globs})
 
-target_sources(scylla-main
-  PRIVATE
-    absl-flat_hash_map.cc
-    bytes.cc
-    client_data.cc
-    clocks-impl.cc
-    sstable_dict_autotrainer.cc
-    exceptions/exceptions.cc
-    debug.cc
-    init.cc
-    keys/keys.cc
-    mutation_query.cc
-    node_ops/task_manager_module.cc
-    partition_slice_builder.cc
-    query/query.cc
-    query_ranges_to_vnodes.cc
-    query/query-result-set.cc
-    tombstone_gc_options.cc
-    tombstone_gc.cc
-    reader_concurrency_semaphore.cc
-    reader_concurrency_semaphore_group.cc
-    serializer.cc
-    service/direct_failure_detector/failure_detector.cc
-    sstables_loader.cc
-    table_helper.cc
-    tasks/task_handler.cc
-    tasks/task_manager.cc
-    timeout_config.cc
-    unimplemented.cc
-    validation.cc
-    vint-serialization.cc)
-target_link_libraries(scylla-main
-  PRIVATE
-    db
-    absl::headers
-    absl::btree
-    absl::hash
-    absl::raw_hash_set
-    Seastar::seastar
-    Snappy::snappy
-    systemd
-    ZLIB::ZLIB
-    lz4::lz4_static
-    zstd::zstd_static
-    scylla-precompiled-header
-)
+    set(${args_VAR} ${var} PARENT_SCOPE)
+endfunction()
 
-option(Scylla_CHECK_HEADERS
-  "Add check-headers target for checking the self-containness of headers")
-if(Scylla_CHECK_HEADERS)
-    add_custom_target(check-headers)
-    # compatibility target used by CI, which builds "check-headers" only for
-    # the "Dev" mode.
-    # our CI currently builds "dev-headers" using ninja without specify a build
-    # mode. where "dev" is actually a prefix encoded in the target name for the
-    # underlying "headers" target. while we don't have this convention in CMake
-    # targets. in contrast, the "check-headers" which is built for all
-    # configurations defined by "CMAKE_DEFAULT_CONFIGS". however, we only need
-    # to build "check-headers" for the "Dev" configuration. Therefore, before
-    # updating the CI to use build "check-headers:Dev", let's add a new target
-    # that specifically builds "check-headers" only for Dev configuration. The
-    # new target will do nothing for other configurations.
-    add_custom_target(dev-headers
-        COMMAND ${CMAKE_COMMAND}
-          "$<IF:$<CONFIG:Dev>,--build;${CMAKE_BINARY_DIR};--config;$<CONFIG>;--target;check-headers,-E;echo;skipping;dev-headers;in;$<CONFIG>>"
-        COMMAND_EXPAND_LISTS)
-endif()
+## Although Seastar is an external project, it is common enough to explore the sources while doing
+## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
+scan_scylla_source_directories(
+        VAR SEASTAR_SOURCE_FILES
+        RECURSIVE
 
-include(check_headers)
-check_headers(check-headers scylla-main
-  GLOB ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)
+        PATHS
+          seastar/core
+          seastar/http
+          seastar/json
+          seastar/net
+          seastar/rpc
+          seastar/tests
+          seastar/util)
 
-option(Scylla_DIST
-  "Build dist targets"
-  ON)
+scan_scylla_source_directories(
+        VAR SCYLLA_ROOT_SOURCE_FILES
+        PATHS .)
 
-add_custom_target(compiler-training)
+scan_scylla_source_directories(
+        VAR SCYLLA_SUB_SOURCE_FILES
+        RECURSIVE
 
-add_subdirectory(api)
-add_subdirectory(alternator)
-add_subdirectory(audit)
-add_subdirectory(db)
-add_subdirectory(auth)
-add_subdirectory(cdc)
-add_subdirectory(compaction)
-add_subdirectory(cql3)
-add_subdirectory(data_dictionary)
-add_subdirectory(dht)
-add_subdirectory(ent)
-add_subdirectory(gms)
-add_subdirectory(idl)
-add_subdirectory(index)
-add_subdirectory(lang)
-add_subdirectory(locator)
-add_subdirectory(message)
-add_subdirectory(mutation)
-add_subdirectory(mutation_writer)
-add_subdirectory(node_ops)
-add_subdirectory(readers)
-add_subdirectory(replica)
-add_subdirectory(raft)
-add_subdirectory(repair)
-add_subdirectory(rust)
-add_subdirectory(schema)
-add_subdirectory(service)
-add_subdirectory(sstables)
-add_subdirectory(streaming)
-add_subdirectory(test)
-add_subdirectory(tools)
-add_subdirectory(tracing)
-add_subdirectory(transport)
-add_subdirectory(types)
-add_subdirectory(utils)
-add_subdirectory(vector_search)
-add_version_library(scylla_version
-    release.cc)
+        PATHS
+          api
+          auth
+          cql3
+          db
+          dht
+          exceptions
+          gms
+          index
+          io
+          locator
+          message
+          repair
+          service
+          sstables
+          streaming
+          tests
+          thrift
+          tracing
+          transport
+          utils)
+
+scan_scylla_source_directories(
+        VAR SCYLLA_GEN_SOURCE_FILES
+        RECURSIVE
+        PATHS build/release/gen)
+
+set(SCYLLA_SOURCE_FILES
+        ${SCYLLA_ROOT_SOURCE_FILES}
+        ${SCYLLA_GEN_SOURCE_FILES}
+        ${SCYLLA_SUB_SOURCE_FILES})
 
 add_executable(scylla
-  main.cc)
-set(scylla_libs
-    audit
-    scylla-main
-    api
-    auth
-    alternator
-    db
-    cdc
-    compaction
-    cql3
-    data_dictionary
-    dht
-    encryption
-    gms
-    idl
-    index
-    lang
-    ldap
-    locator
-    message
-    mutation
-    mutation_writer
-    raft
-    readers
-    repair
-    replica
-    schema
-    scylla_version
-    service
-    sstables
-    streaming
-    test-perf
-    tools
-    tracing
-    transport
-    types
-    utils
-    vector_search)
-target_link_libraries(scylla PRIVATE
-    ${scylla_libs})
+        ${SEASTAR_SOURCE_FILES}
+        ${SCYLLA_SOURCE_FILES})
 
-if(Scylla_ENABLE_LTO)
-  include(enable_lto)
-  foreach(target scylla ${scylla_libs})
-    enable_lto(${target})
-  endforeach()
-endif()
+# 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")
 
-target_link_libraries(scylla PRIVATE
-    p11-kit::p11-kit
-    Seastar::seastar
-    absl::headers
-    yaml-cpp::yaml-cpp
-    Boost::program_options)
+# 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++14
+        -DHAVE_DPDK
+        -DHAVE_HWLOC
+        "${SEASTAR_CFLAGS}")
 
-target_include_directories(scylla PRIVATE
-    "${CMAKE_CURRENT_SOURCE_DIR}"
-    "${scylla_gen_build_dir}")
-
-add_custom_target(maybe-scylla
-  DEPENDS $<$<CONFIG:Dev>:$<TARGET_FILE:scylla>>)
-add_dependencies(compiler-training
-  maybe-scylla)
-
-if(Scylla_DIST)
-  add_subdirectory(dist)
-endif()
-
-if(Scylla_BUILD_INSTRUMENTED)
-  add_subdirectory(pgo)
-endif()
-
-add_executable(patchelf
-  tools/patchelf.cc)
+# The order matters here: prefer the "static" DPDK directories to any dynamic paths from pkg-config. Some files are only
+# available dynamically, though.
+target_include_directories(scylla PUBLIC
+        .
+        ${SEASTAR_DPDK_INCLUDE_DIRS}
+        ${SEASTAR_INCLUDE_DIRS}
+        ${Boost_INCLUDE_DIRS}
+        build/release/gen)

CONTRIBUTING.md

@@ -1,22 +1,11 @@
-# Contributing to Scylla
+# Asking questions or requesting help
 
-## Asking questions or requesting help
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) for general questions and help.
 
-Use the [ScyllaDB Community Forum](https://forum.scylladb.com) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+# Reporting an issue
 
-Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
+Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues.  Fill in as much information as you can in the issue template, especially for performance problems.
 
-## Reporting an issue
+# Contributing Code to Scylla
 
-Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to report issues or to suggest features. Fill in as much information as you can in the issue template, especially for performance problems.
-
-## Contributing code to Scylla
-
-Before you can contribute code to Scylla for the first time, you should sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send the signed form to cla@scylladb.com. You can then submit your changes as patches to the [scylladb-dev mailing list](https://groups.google.com/forum/#!forum/scylladb-dev) or as a pull request to the [Scylla project on github](https://github.com/scylladb/scylla).
-If you need help formatting or sending patches, [check out these instructions](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches).
-
-The Scylla C++ source code uses the [Seastar coding style](https://github.com/scylladb/seastar/blob/master/coding-style.md) so please adhere to that in your patches. Note that Scylla code is written with `using namespace seastar`, so should not explicitly add the `seastar::` prefix to Seastar symbols. You will usually not need to add `using namespace seastar` to new source files, because most Scylla header files have `#include "seastarx.hh"`, which does this.
-
-Header files in Scylla must be self-contained, i.e., each can be included without having to include specific other headers first. To verify that your change did not break this property, run `ninja dev-headers`. If you added or removed header files, you must `touch configure.py` first - this will cause `configure.py` to be automatically re-run to generate a fresh list of header files.
-
-For more criteria on what reviewers consider good code, see the [review checklist](https://github.com/scylladb/scylla/blob/master/docs/dev/review-checklist.md).
+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

@@ -18,42 +18,13 @@ $ git submodule update --init --recursive
 
 ### Dependencies
 
-Scylla is fairly fussy about its build environment, requiring a very recent
-version of the C++23 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++23 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 container 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
-```
-
-Note: do not mix environments - either perform all your work with dbuild, or natively on the host.
-Note2: you can get to an interactive shell within dbuild by running it without any parameters:
-```bash
-$ ./tools/toolchain/dbuild
-```
+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.
 
@@ -72,9 +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.
 
@@ -82,30 +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 everything 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
@@ -122,13 +71,6 @@ Run all tests through the test execution wrapper with
 $ ./test.py --mode={debug,release}
 ```
 
-or, if you are using `dbuild`, you need to build the code and the tests and then you can run them at will:
-
-```bash
-$ ./tools/toolchain/dbuild ninja {debug,release,dev}-build
-$ ./tools/toolchain/dbuild ./test.py --mode {debug,release,dev}
-```
-
 The `--name` argument can be specified to run a particular test.
 
 Alternatively, you can execute the test executable directly. For example,
@@ -141,53 +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]
-MATERIALIZED VIEWS
-  Nadav Har'El <nyh@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
 
@@ -208,11 +106,11 @@ $ # Edit configuration options as appropriate
 $ SCYLLA_HOME=$HOME/scylla build/release/scylla
 ```
 
-The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories`, `commitlog_directory` and `schema_commitlog_directory` fields as appropriate.
+The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories` and `commitlog_directory` fields as appropriate.
 
 Scylla has a number of requirements for the file-system and operating system to operate ideally and at peak performance. However, during development, these requirements can be relaxed with the `--developer-mode` flag.
 
-Additionally, when running on under-powered platforms like portable laptops, the `--overprovisioned` flag is useful.
+Additionally, when running on under-powered platforms like portable laptops, the `--overprovisined` flag is useful.
 
 On a development machine, one might run Scylla as
 
@@ -220,10 +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 version of
-cqlsh. It is available at
-https://github.com/scylladb/scylla-cqlsh and is available as a submodule.
-
 ### 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.
@@ -261,45 +155,21 @@ Once the patch set is ready to be reviewed, push the branch to the public remote
 
 ### Development environment and source code navigation
 
-Scylla includes a [CMake](https://cmake.org/) file, `CMakeLists.txt` that can be used with development environments so
-that they can properly analyze the source code. However, building with CMake is not yet officially supported.
+Scylla includes a [CMake](https://cmake.org/) file, `CMakeLists.txt`, for use only with development environments (not for building) so that they can properly analyze the source code.
 
-Good IDEs that have support for CMake build toolchain are [CLion](https://www.jetbrains.com/clion/),
-[KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
+[CLion](https://www.jetbrains.com/clion/) is a commercial IDE offers reasonably good source code navigation and advice for code hygiene, though its C++ parser sometimes makes errors and flags false issues.
 
-[Eclipse](https://eclipse.org/cdt/) is another open-source option. It doesn't natively work with CMake projects and its
-C++ parser has many issues.
+Other good options that directly parse CMake files are [KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
 
-#### CLion
+To use the `CMakeLists.txt` file with these programs, define the `FOR_IDE` CMake variable or shell environmental variable.
 
-[CLion](https://www.jetbrains.com/clion/) is a commercial IDE offers reasonably good source code navigation and advice
-for code hygiene, though its C++ parser sometimes makes errors and flags false issues. In order to enable proper code
-analysis in CLion, the following steps are needed:
-
-1. Get the ScyllaDB source code by following the [Getting the source code](#getting-the-source-code).
-2. Follow the steps in [Dependencies](#dependencies) in order to install the required tools natively into your system.
-   **Don't** follow the *frozen toolchain* part described there, since CMake checks for the build dependencies installed
-   in the system, not in the container image provided by the toolchain.
-3. In CLion, select `File`→`Open` and select the main ScyllaDB directory in order to open the CMake project there. The
-   project should open and fail to process the `CMakeLists.txt`. That's expected.
-4. In CLion, open `File`→`Settings`.
-5. Find and click on `Toolchains` (type *toolchains* into search box).
-6. Select the toolchain you will use, for instance the `Default` one.
-7. Type in the following system-installed tools to be used:
-    - `CMake`: *cmake*
-    - `Build Tool`: *ninja*
-    - `C Compiler`: *clang*
-    - `C++ Compiler`: *clang*
-8. On the `CMake` panel/tab, click on `Reload CMake Project`
-
-After that, CLion should successfully initialize the CMake project (marked by `[Finished]` in the console) and the
-source code editor should provide code analysis support normally from now on.
+[Eclipse](https://eclipse.org/cdt/) is another open-source option. It doesn't natively work with CMake projects, and its C++ parser has many similar issues as CLion.
 
 ### Distributed compilation: `distcc` and `ccache`
 
 Scylla's compilations times can be long. Two tools help somewhat:
 
-- [ccache](https://ccache.samba.org/) caches compiled object files on disk and reuses them when possible
+- [ccache](https://ccache.samba.org/) caches compiled object files on disk and re-uses them when possible
 - [distcc](https://github.com/distcc/distcc) distributes compilation jobs to remote machines
 
 A reasonably-powered laptop acts as the coordinator for compilation. A second, more powerful, machine acts as a passive compilation server.
@@ -338,7 +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
 
@@ -348,29 +218,11 @@ 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 enabled 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.
 
-One way to do this is to create a local remote for the Seastar submodule in the Scylla repository:
+One way to do this it to create a local remote for the Seastar submodule in the Scylla repository:
 
 ```bash
 $ cd $HOME/src/scylla
@@ -379,62 +231,3 @@ $ git remote add local /home/tsmith/src/seastar
 $ git remote update
 $ git checkout -t local/my_local_seastar_branch
 ```
-
-### Generating code coverage report
-
-Install dependencies:
-
-    $ dnf install llvm # for llvm-profdata and llvm-cov
-    $ dnf install lcov # for genhtml
-
-Instruct `configure.py` to generate build files for `coverage` mode:
-
-    $ ./configure.py --mode=coverage
-
-Build the tests you want to run, then run them via `test.py` (important!):
-
-    $ ./test.py --mode=coverage [...]
-
-Alternatively, you can run individual tests via `./scripts/coverage.py --run`.
-
-Open the link printed at the end. Be horrified. Go and write more tests.
-
-For more details see `./scripts/coverage.py --help`.
-
-### Resolving stack backtraces
-
-Scylla may print stack backtraces to the log for several reasons.
-For example:
-- When aborting (e.g. due to assertion failure, internal error, or segfault)
-- When detecting seastar reactor stalls (where a seastar task runs for a long time without yielding the cpu to other tasks on that shard)
-
-The backtraces contain code pointers so they are not very helpful without resolving into code locations.
-To resolve the backtraces, one needs the scylla relocatable package that contains the scylla binary (with debug information),
-as well as the dynamic libraries it is linked against.
-
-Builds from our automated build system are uploaded to the cloud
-and can be searched on http://backtrace.scylladb.com/
-
-Make sure you have the scylla server exact `build-id` to locate
-its respective relocatable package, required for decoding backtraces it prints.
-
-The build-id is printed to the system log when scylla starts.
-It can also be found by executing `scylla --build-id`, or
-by using the `file` utility, for example:
-```
-$ scylla --build-id
-4cba12e6eb290a406bfa4930918db23941fd4be3
-
-$ file scylla
-scylla: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked, interpreter /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////lib64/ld-linux-x86-64.so.2, for GNU/Linux 3.2.0, BuildID[sha1]=4cba12e6eb290a406bfa4930918db23941fd4be3, with debug_info, not stripped, too many notes (256)
-```
-
-To find the build-id of a coredump, use the `eu-unstrip` utility as follows:
-```
-$ eu-unstrip -n --core <coredump> | awk '/scylla$/ { s=$2; sub(/@.*$/, "", s); print s; exit(0); }'
-4cba12e6eb290a406bfa4930918db23941fd4be3
-```
-
-### Core dump debugging
-
-See [debugging.md](docs/dev/debugging.md).

IDL.md

@@ -0,0 +1,103 @@
+#IDL definition
+The schema we use similar to c++ schema.
+Use class or struct similar to the object you need the serializer for.
+Use namespace when applicable.
+
+##keywords
+* class/struct - a class or a struct like C++
+  class/struct can have final or stub marker
+* namespace - has the same C++ meaning
+* enum class - has the same C++ meaning
+* final modifier for class - when a class mark as final it will not contain a size parameter. Note that final class cannot be extended by future version, so use with care
+* stub class - when a class is mark as stub, it means that no code will be generated for this class and it is only there as a documentation.
+* version attributes - mark with [[version id ]] mark that a field is available from a specific version
+* template - A template class definition like C++
+##Syntax
+
+###Namespace
+```
+namespace ns_name { namespace-body }
+```
+* ns_name: either a previously unused identifier, in which case this is original-namespace-definition or the name of a namespace, in which case this is extension-namespace-definition
+* namespace-body: possibly empty sequence of declarations of any kind (including class and struct definitions as well as nested namespaces)
+
+###class/struct
+`
+class-key  class-name final(optional) stub(optional) { member-specification } ;(optional)
+`
+* class-key: one of class or struct.
+* class-name: the name of the class that's being defined. optionally followed by keyword final, optionally followed by keyword stub
+* final: when a class mark as final, it means it can not be extended and there is no need to serialize its size, use with care.
+* stub: when a class is mark as stub, it means no code will generate for it and it is added for documentation only.
+* member-specification: list of access specifiers, and public member accessor see class member below.
+* to be compatible with C++ a class definition can be followed by a semicolon.
+###enum
+`enum-key identifier enum-base { enumerator-list(optional) }`
+* enum-key: only enum class is supported
+* identifier: the name of the enumeration that's being declared.
+* enum-base: colon (:), followed by a type-specifier-seq that names an integral type (see the C++ standard for the full list of all possible integral types).
+* enumerator-list: comma-separated list of enumerator definitions, each of which is either simply an identifier, which becomes the name of the enumerator, or an identifier with an initializer: identifier = integral value.
+Note that though C++ allows constexpr as an initialize value, it makes the documentation less readable, hence is not permitted.
+
+###class member
+`type member-access attributes(optional) default-value(optional);`
+* type: Any valid C++ type, following the C++ notation. note that there should be a serializer for the type, but deceleration order is not mandatory
+* member-access: is the way the member can be access. If the member is public it can be the name itself. if not it could be a getter function that should be followed by braces. Note that getter can (and probably should) be const methods.
+* attributes: Attributes define by square brackets. Currently are use to mark a version in which a specific member was added [ [ version version-number] ] would mark that the specific member was added in the given version number.
+
+###template
+`template < parameter-list > class-declaration`
+* parameter-list - a non-empty comma-separated list of the template parameters. 
+* class-decleration - (See class section) The class name declared become a template name.
+
+##IDL example
+Forward slashes comments are ignored until the end of the line.
+```
+namespace utils {
+// An example of a stub class
+class UUID stub {
+    int64_t most_sig_bits;
+    int64_t least_sig_bits;
+}
+}
+
+namespace gms {
+//an enum example
+enum class application_state:int {STATUS = 0,
+        LOAD,
+        SCHEMA,
+        DC};
+
+// example of final class
+class versioned_value final {
+// getter and setter as public member
+    int version;
+    sstring value;
+}
+
+class heart_beat_state {
+//getter as function
+    int32_t get_generation();
+//default value example
+    int32_t get_heart_beat_version() = 1;
+}
+
+class endpoint_state {
+    heart_beat_state get_heart_beat_state();
+    std::map<application_state, versioned_value> get_application_state_map();
+}
+
+class gossip_digest {
+    inet_address get_endpoint();
+    int32_t get_generation();
+//mark that a field was added on a specific version
+    int32_t get_max_version() [ [version 0.14.2] ];
+}
+
+class gossip_digest_ack {
+    std::vector<gossip_digest> digests();
+    std::map<inet_address, gms::endpoint_state> get_endpoint_state_map();
+}
+}
+```
+

LICENSE-ScyllaDB-Source-Available.md

@@ -1,62 +0,0 @@
-## **SCYLLADB SOFTWARE LICENSE AGREEMENT**
-
-| Version: | 1.0 |
-| :---- | :---- |
-| Last updated: | December 18, 2024 |
-
-**Your Acceptance**
-
-By utilizing or accessing the Software in any manner, You hereby confirm and agree to be bound by this ScyllaDB Software License Agreement (the "**Agreement**"), which sets forth the terms and conditions on which ScyllaDB Ltd. ("**Licensor**") makes the Software available to You, as the Licensee. If Licensee does not agree to the terms of this Agreement or cannot otherwise comply with the Agreement, Licensee shall not utilize or access the Software.
-
-The terms "**You**" or "**Licensee**" refer to any individual accessing or using the Software under this Agreement ("**Use**"). In case that such individual is Using the Software on behalf of a legal entity, You hereby irrevocably represents and warrants that You have full legal capacity and authority to enter into this Agreement on behalf of such entity as well as bind such entity to this Agreement, and in such case, the term "You" or "Licensee" in this Agreement will refer to such entity.
-
-**Grant of License**
-
-* **Software Definitions:** Software means the ScyllaDB software provided by Licensor, including the source code, object code, and any accompanying documentation or tools, or any part thereof, as made available under this Agreement.
-* **Grant of License:** Subject to the terms and conditions of this Agreement, Licensor grants You a limited, non-exclusive, revocable, non-sublicensable, non-transferable, royalty free license to Use the Software, in each case solely for the purposes of:
-  1) Copying, distributing, evaluating (including performing benchmarking or comparative tests or evaluations , subject to the limitations below) and improving the Software and ScyllaDB; and
-  2) create a modified version of the Software (each, a "**Licensed Work**"); provided however, that each such Licensed Work keeps all or substantially all of the functions and features of the Software, and/or using all or substantially all of the source code of the Software. You hereby agree that all the Licensed Work are, upon creation, considered Licensed Work of the Licensor, shall be the sole property of the Licensor and its assignees, and the Licensor and its assignees shall be the sole owner of all rights of any kind or nature, in connection with such Licensed Work. You hereby irrevocably and unconditionally assign to the Licensor all the Licensed Work and any part thereof.  This License applies separately for each version of the Licensed Work, which shall be considered "Software" for the purpose of this Agreement.
-
-
-**License Limitations, Restrictions and Obligations:** The license grant above is subject to the following limitations, restrictions, and obligations. If Licensee’s Use of the Software does not comply with the above license grant or the terms of this section (including exceeding the Usage Limit set forth below), Licensee must: (i) refrain from any Use of the Software; and (ii) purchase a [commercial paid license](https://www.scylladb.com/scylladb-proprietary-software-license-agreement/) from the Licensor.
-
-* **Updates:** You shall be solely responsible for providing all equipment, systems, assets, access, and ancillary goods and services needed to access and Use the Software.  Licensor may modify or update the Software at any time, without notification, in its sole and absolute discretion.  After the effective date of each such update, Licensor shall bear no obligation to run, provide or support legacy versions of the Software.
-* **"Usage Limit":** Licensee's total overall available storage across all deployments and clusters of the Software and the Licensed Work under this License shall not exceed 10TB and/or an upper limit of 50 VCPUs (hyper threads).
-* **IP Markings:** Licensee must retain all copyright, trademark, and other proprietary notices contained in the Software. You will not modify, delete, alter, remove, or obscure any intellectual property, including without limitations licensing, copyright, trademark, or any other notices of Licensor in the Software.
-* **License Reproduction:** You must conspicuously display this Agreement on each copy of the Software. If You receive the Software from a third party, this Agreement still applies to Your Use of the Software. You will be responsible for any breach of this Agreement by any such third-party.
-* Distribution of any Licensed Works is permitted, provided that: (i) You must include in any Licensed Work prominent notices stating that You have modified the Software, (ii) You include a copy of this Agreement with the Licensed Work, and (iii) You clearly identify all modifications made in the Licensed Work and provides attribution to the Licensor as the original author(s) of the Software.
-* **Commercial Use Restrictions:** Licensee may not offer the Software as a software-as-a-service (SaaS) or commercial database-as-as-service (dBaaS) offering.  Licensee may not use the Software to compete with Licensor's existing or future products or services. If your Use of the Software does not comply with the requirements currently in effect as described in this License, you must purchase a commercial license from the Licensor, its affiliated entities, or you must refrain from using the Software and all Licensed Work. Furthermore, if You make any written claim of patent infringement relating to the Software, Your patent license for the Software granted under this Agreement terminates immediately.
-* Notwithstanding anything to the contrary, under the License granted hereunder, You shall not and shall not permit others to: (i) transfer the Software or any portions thereof to any other party except as expressly permitted herein; (ii) attempt to circumvent or overcome any technological protection measures incorporated into the Software; (iii) incorporate the Software into the structure, machinery or controls of any aircraft, other aerial device, military vehicle, hovercraft, waterborne craft or any medical equipment of any kind; or (iv) use the Software or any part thereof in any unlawful, harmful or illegal manner, or in a manner which infringes third parties’ rights in any way, including intellectual property rights.
-
-**Monitoring; Audit**
-
-* **License Key:** Licensor may implement a method of authentication, e.g., a unique license token ("License Key") as a condition of accessing or using the Software. Upon the implementation of such License Key, Licensee agrees to comply with Licensor terms and requirements with regards to such License Key
-* **Monitoring & Data Sharing:** Licensor do not collect customer data from its database. Notwithstanding, Licensee acknowledges and agrees that the License Key and Software may share telemetry metrics and information regarding the execution volume and statistics with Licensor regarding Licensee’s use of the same. Any disclosure or use of such information shall be subject to, and in accordance with, Licensor’s Privacy Policy and Data Processing Agreement, which can be found at [https://www.scylladb.com/policies-agreements](https://www.scylladb.com/policies-agreements).
-* **Information Requests; Audits:**  Licensee shall keep accurate records of its access to and use of any Software, and shall promptly respond to any Licensor requests for information regarding the same.  To ensure compliance with the terms of this Agreement, during the term of this Agreement and for a period of one (1) year thereafter, Licensor (or an agent bound by customary confidentiality undertakings on its behalf) may audit Licensee’s records which are related to its access to or use of the Software. The cost of such audit shall be borne by Licensor unless it is determined that Licensee has materially breached this Agreement.
-
-**Termination**
-
-* **Termination:** Licensor may immediately terminate this Agreement will automatically terminate if You for any reason, including without limitation for (i) Licensee’s breach of any term, condition, or restriction of this Agreement, unless such breach was cured to Licensor’s satisfaction within no more than 15 days from the date of the breach. Notwithstanding the foregoing, intentional; or (ii) if Licensee brings any claim, demand or repeated breaches lawsuit against Licensor.
-* **Obligations on Termination:**  Upon termination of this Agreement by You will cause Your licenses to terminate automatically and permanently, at Licensor’s sole discretion, Licensee must (i) immediately stop using any Software, (ii) return all copies of any tools or documentation provided by Licensor; and (iii) pay amount due to Licensor hereunder (e.g., audit costs).  All obligations which by their nature must survive the termination of this Agreement shall so survive.
-
-**Indemnity; Disclaimer; Limitation of Liability**
-
-* **Indemnity:** Licensee hereby agrees to indemnify, defend and hold harmless Licensor and its affiliates from any losses or damages incurred due to a third party claim arising out of: (i) Licensee’s breach of this Agreement; (ii) Licensee’s negligence, willful misconduct or violation of law, or (iii) Licensee’s products or services.
-* DISCLAIMER OF WARRANTIES:  LICENSEE AGREES THAT LICENSOR HAS MADE NO EXPRESS WARRANTIES REGARDING THE SOFTWARE AND THAT THE SOFTWARE IS BEING PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND. LICENSOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THE SOFTWARE, EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION, ANY IMPLIED WARRANTIES OF FITNESS FOR A PARTICULAR PURPOSE; TITLE; MERCHANTABILITY;  OR NON-INFRINGEMENT OF THIRD PARTY RIGHTS. LICENSOR DOES NOT WARRANT THAT THE SOFTWARE WILL OPERATE UNINTERRUPTED OR ERROR FREE, OR THAT ALL ERRORS WILL BE CORRECTED.  LICENSOR DOES NOT GUARANTEE ANY PARTICULAR RESULTS FROM THE USE OF THE SOFTWARE, AND DOES NOT WARRANT THAT THE SOFTWARE IS FIT FOR ANY PARTICULAR PURPOSE.
-* LIMITATION OF LIABILITY:  TO THE FULLEST EXTENT PERMISSIBLE UNDER APPLICABLE LAW, IN NO EVENT WILL LICENSOR AND/OR ITS AFFILIATES, EMPLOYEES, OFFICERS AND DIRECTORS BE LIABLE TO LICENSEE FOR (I) ANY LOSS OF USE OR DATA; INTERRUPTION OF BUSINESS; OR ANY INDIRECT; SPECIAL; INCIDENTAL; OR CONSEQUENTIAL DAMAGES OF ANY KIND (INCLUDING LOST PROFITS); AND (II) ANY DIRECT DAMAGES EXCEEDING THE TOTAL AMOUNT OF ONE THOUSAND US DOLLARS ($1,000).  THE FOREGOING PROVISIONS LIMITING THE LIABILITY OF LICENSOR SHALL APPLY REGARDLESS OF THE FORM OR CAUSE OF ACTION, WHETHER IN STRICT LIABILITY, CONTRACT OR TORT.
-
-**Proprietary Rights; No Other Rights**
-
-* **Ownership:** Licensor retains sole and exclusive ownership of all rights, interests and title in the Software and any scripts, processes, techniques, methodologies, inventions, know-how, concepts, formatting, arrangements, visual attributes, ideas, database rights, copyrights, patents, trade secrets, and other intellectual property related thereto, and all derivatives, enhancements, modifications and improvements thereof. Except for the limited license rights granted herein, Licensee has no rights in or to the Software and/ or Licensor’s trademarks, logo, or branding and You acknowledge that such Software, trademarks, logo, or branding is the sole property of Licensor.
-* **Feedback:** Licensee is not required to provide any suggestions, enhancement requests, recommendations or other feedback regarding the Software ("Feedback").  If, notwithstanding this policy, Licensee submits Feedback, Licensee understands and acknowledges that such Feedback is not submitted in confidence and Licensor assumes no obligation, expressed or implied, by considering it.  All right in any trademark or logo of Licensor or its affiliates and You shall make no claim of right to the Software or any part thereof to be supplied by Licensor hereunder and acknowledges that as between Licensor and You, such Software is the sole proprietary, title and interest in and to Licensor.such Feedback shall be assigned to, and shall become the sole and exclusive property of, Licensor upon its creation.
-* Except for the rights expressly granted to You under this Agreement, You are not granted any other licenses or rights in the Software or otherwise. This Agreement constitutes the entire agreement between You and the Licensor with respect to the subject matter hereof and supersedes all prior or contemporaneous communications, representations, or agreements, whether oral or written.
-* **Third-Party Software:** Customer acknowledges that the Software may contain open and closed source components (“OSS Components”) that are governed separately by certain licenses, in each case as further provided by Company upon request. Any applicable OSS Component license is solely between Licensee and the applicable licensor of the OSS Component and Licensee shall comply with the applicable OSS Component license.
-* If any provision of this Agreement is held to be invalid or unenforceable, such provision shall be struck and the remaining provisions shall remain in full force and effect.
-
-**Miscellaneous**
-
-* **Miscellaneous:** This Agreement may be modified at any time by Licensor, and constitutes the entire agreement between the parties with respect to the subject matter hereof. Licensee may not assign or subcontract its rights or obligations under this Agreement.  This Agreement does not, and shall not be construed to create any relationship, partnership, joint venture, employer-employee, agency, or franchisor-franchisee relationship between the parties.
-* **Governing Law & Jurisdiction:** This Agreement shall be governed and construed in accordance with the laws of Israel, without giving effect to their respective conflicts of laws provisions, and the competent courts situated in Tel Aviv, Israel, shall have sole and exclusive jurisdiction over the parties and any conflict and/or dispute arising out of, or in connection to, this Agreement
-
-\[*End of ScyllaDB Software License Agreement*\]
-

LICENSE.AGPL

@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program 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.
+
+    This program 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 Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<http://www.gnu.org/licenses/>.

NOTICE.txt

@@ -1,8 +1,2 @@
 This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
 especially Apache Cassandra.
-
-It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)
-
-It includes modified tests from https://github.com/etcd-io/etcd.git (owned by The etcd Authors)
-
-It includes files from https://github.com/bytecodealliance/wasmtime-cpp (owned by Bytecode Alliance), licensed with Apache License 2.0.

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

@@ -1,112 +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++23 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/dev/building.md
-[docker image build documentation]: dist/docker/debian/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
+```
 
-[![Build with the latest Seastar](https://github.com/scylladb/scylladb/actions/workflows/seastar.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/seastar.yaml) [![Check Reproducible Build](https://github.com/scylladb/scylladb/actions/workflows/reproducible-build.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/reproducible-build.yaml) [![clang-nightly](https://github.com/scylladb/scylladb/actions/workflows/clang-nightly.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/clang-nightly.yaml)
+## Building Fedora RPM
 
-See [test.py manual](docs/dev/testing.md).
+As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
 
-## Scylla APIs and compatibility
-By default, Scylla is compatible with Apache Cassandra and its API - CQL.
-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).
+```
+# Install mock:
+sudo yum install mock
 
-## Documentation
+# Add user to the "mock" group:
+usermod -a -G mock $USER && newgrp mock
+```
 
-Documentation can be found [here](docs/dev/README.md).
-Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
-User documentation can be found [here](https://docs.scylladb.com/).
+Then, to build an RPM, run:
 
-## Training
+```
+./dist/redhat/build_rpm.sh
+```
 
-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.
+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 [community forum] and [Slack channel] are for users to discuss configuration, management, and operations of ScyllaDB.
-* The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
-
-[Community forum]: https://forum.scylladb.com/
-
-[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

@@ -1,119 +1,24 @@
 #!/bin/sh
 
-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] [--date-stamp DATE] -- generate Scylla version and build information files.
-
-Options:
-  -h|--help show this help message.
-  -o|--output-dir PATH specify destination path at which the version files are to be created.
-  -d|--date-stamp DATE manually set date for release parameter
-  -v|--verbose also print out the version number
-
-By default, the script will attempt to parse 'version' file
-in the current directory, which should contain a string of
-'\$version-\$release' form.
-
-Otherwise, it will call 'git log' on the source tree (the
-directory, which contains the script) to obtain current
-commit hash and use it for building the version and release
-strings.
-
-The script assumes that it's called from the Scylla source
-tree.
-
-The files created are:
-  SCYLLA-VERSION-FILE
-  SCYLLA-RELEASE-FILE
-  SCYLLA-PRODUCT-FILE
-
-By default, these files are created in the 'build'
-subdirectory under the directory containing the script.
-The destination directory can be overridden by
-using '-o PATH' option.
-END
-)
-
-DATE=""
-PRINT_VERSION=false
-
-while [ $# -gt 0 ]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$2"
-			shift
-			shift
-			;;
-		--date-stamp)
-			DATE="$2"
-			shift
-			shift
-			;;
-		-v|--verbose)
-			PRINT_VERSION=true
-			shift
-			;;
-		*)
-			echo "Unexpected argument found: $1"
-			echo
-			echo "$USAGE"
-			exit 1
-			;;
-	esac
-done
-
-SCRIPT_DIR="$(dirname "$0")"
-
-if [ -z "$OUTPUT_DIR" ]; then
-	OUTPUT_DIR="$SCRIPT_DIR/build"
-fi
-
-if [ -z "$DATE" ]; then
-  DATE=$(date --utc +%Y%m%d)
-fi
-
-# Default scylla product/version tags
-PRODUCT=scylla
-VERSION=2026.1.0-dev
+VERSION=2.1.6
 
 if test -f version
 then
 	SCYLLA_VERSION=$(cat version | awk -F'-' '{print $1}')
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
+	DATE=$(date +%Y%m%d)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
-	if [ -z "$SCYLLA_RELEASE" ]; then
-		GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1 --abbrev=12)
-		# For custom package builds, replace "0" with "counter.yourname",
-		# where counter starts at 1 and increments for successive versions.
-		# This ensures that the package manager will select your custom
-		# package over the standard release.
-		# Do not use any special characters like - or _ in the name above!
-		# These characters either have special meaning or are illegal in
-		# version strings.
-		SCYLLA_BUILD=0
-		SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
-	elif [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-		echo "setting SCYLLA_RELEASE only makes sense in clean builds" 1>&2
-		exit 1
-	fi
+	# For custom package builds, replace "0" with "counter.your_name",
+	# where counter starts at 1 and increments for successive versions.
+	# This ensures that the package manager will select your custom
+	# package over the standard release.
+	SCYLLA_BUILD=0
+	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
-if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" | rev | cut -d . -f 1 | rev)
-	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
-		exit 0
-	fi
-fi
-
-if $PRINT_VERSION; then
-	echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-fi
-mkdir -p "$OUTPUT_DIR"
-echo "$SCYLLA_VERSION" > "$OUTPUT_DIR/SCYLLA-VERSION-FILE"
-echo "$SCYLLA_RELEASE" > "$OUTPUT_DIR/SCYLLA-RELEASE-FILE"
-echo "$PRODUCT" > "$OUTPUT_DIR/SCYLLA-PRODUCT-FILE"
+echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
+mkdir -p build
+echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
+echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE

absl-flat_hash_map.cc

@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#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

@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#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/CMakeLists.txt

@@ -1,41 +0,0 @@
-include(generate_cql_grammar)
-generate_cql_grammar(
-  GRAMMAR expressions.g
-  SOURCES cql_grammar_srcs)
-
-add_library(alternator STATIC)
-target_sources(alternator
-  PRIVATE
-    controller.cc
-    server.cc
-    executor.cc
-    stats.cc
-    serialization.cc
-    expressions.cc
-    conditions.cc
-    auth.cc
-    streams.cc
-    consumed_capacity.cc
-    ttl.cc
-    parsed_expression_cache.cc
-    ${cql_grammar_srcs})
-target_include_directories(alternator
-  PUBLIC
-    ${CMAKE_SOURCE_DIR}
-    ${CMAKE_BINARY_DIR}
-  PRIVATE
-    ${RAPIDJSON_INCLUDE_DIRS})
-target_link_libraries(alternator
-  PUBLIC
-    Seastar::seastar
-    xxHash::xxhash
-  PRIVATE
-    cql3
-    idl
-    absl::headers)
-
-if (Scylla_USE_PRECOMPILED_HEADER_USE)
-  target_precompile_headers(alternator REUSE_FROM scylla-precompiled-header)
-endif()
-check_headers(check-headers alternator
-  GLOB_RECURSE ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)

alternator/auth.cc

@@ -1,69 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "alternator/error.hh"
-#include "auth/common.hh"
-#include "utils/log.hh"
-#include <string>
-#include <string_view>
-#include "alternator/auth.hh"
-#include <fmt/format.h>
-#include "auth/password_authenticator.hh"
-#include "service/storage_proxy.hh"
-#include "alternator/executor.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/result_set.hh"
-#include "types/types.hh"
-#include <seastar/core/coroutine.hh>
-
-namespace alternator {
-
-static logging::logger alogger("alternator-auth");
-
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, auth::service& as, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema(auth::get_auth_ks_name(as.query_processor()), "roles");
-    partition_key pk = partition_key::from_single_value(*schema, utf8_type->decompose(username));
-    dht::partition_range_vector partition_ranges{dht::partition_range(dht::decorate_key(*schema, pk))};
-    std::vector<query::clustering_range> bounds{query::clustering_range::make_open_ended_both_sides()};
-    const column_definition* salted_hash_col = schema->get_column_definition(bytes("salted_hash"));
-    const column_definition* can_login_col = schema->get_column_definition(bytes("can_login"));
-    if (!salted_hash_col || !can_login_col) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Credentials cannot be fetched for: {}", username)));
-    }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col, can_login_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id, can_login_col->id}, selection->get_query_options());
-    auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice,
-            proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
-    auto cl = auth::password_authenticator::consistency_for_user(username);
-
-    service::client_state client_state{service::client_state::internal_tag()};
-    service::storage_proxy::coordinator_query_result qr = co_await proxy.query(schema, std::move(command), std::move(partition_ranges), cl,
-            service::storage_proxy::coordinator_query_options(executor::default_timeout(), empty_service_permit(), client_state));
-
-    cql3::selection::result_set_builder builder(*selection, gc_clock::now());
-    query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
-
-    auto result_set = builder.build();
-    if (result_set->empty()) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("User not found: {}", username)));
-    }
-    const auto& result = result_set->rows().front();
-    bool can_login = result[1] && value_cast<bool>(boolean_type->deserialize(*result[1]));
-    if (!can_login) {
-        // This is a valid role name, but has "login=False" so should not be
-        // usable for authentication (see #19735).
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Role {} has login=false so cannot be used for login", username)));
-    }
-    const managed_bytes_opt& salted_hash = result.front();
-    if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("No password found for user: {}", username)));
-    }
-    co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
-}
-
-}

alternator/auth.hh

@@ -1,25 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <string>
-#include "utils/loading_cache.hh"
-#include "auth/service.hh"
-
-namespace service {
-class storage_proxy;
-}
-
-namespace alternator {
-
-using key_cache = utils::loading_cache<std::string, std::string, 1>;
-
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, auth::service& as, std::string username);
-
-}

alternator/conditions.cc

@@ -1,756 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include <string_view>
-#include "alternator/conditions.hh"
-#include "alternator/error.hh"
-#include <unordered_map>
-#include "utils/rjson.hh"
-#include "serialization.hh"
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
-#include <stdexcept>
-#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(fmt::format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
-    }
-    std::string op = rjson::to_string(comparison_operator);
-    auto it = ops.find(op);
-    if (it == ops.end()) {
-        throw api_error::validation(fmt::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" */ {
-        try {
-            return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
-        } catch(std::invalid_argument&) {
-            // determine if any of the malformed values is from query and raise an exception if so
-            unwrap_bytes(it1->value, v1_from_query);
-            unwrap_bytes(it2->value, v2_from_query);
-            return false;
-        }
-    }
-}
-
-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, bool v1_from_query, bool v2_from_query) {
-    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") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if (!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return d_kv1->find(*d_kv2) != 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, bool v1_from_query, bool v2_from_query) {
-    if (!v1) {
-        return false;
-    }
-    return !check_CONTAINS(v1, v2, v1_from_query, v2_from_query);
-}
-
-// 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 comparison 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(rjson::to_string_view(kv1.value),
-                   rjson::to_string_view(kv2.value));
-    }
-    if (kv1.name == "B") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if(!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return cmp(*d_kv1, *d_kv2);
-    }
-    // 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(
-                fmt::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(rjson::to_string_view(kv_v.value),
-                             rjson::to_string_view(kv_lb.value),
-                             rjson::to_string_view(kv_ub.value),
-                             bounds_from_query);
-    }
-    if (kv_v.name == "B") {
-        auto d_kv_v = unwrap_bytes(kv_v.value, v_from_query);
-        auto d_kv_lb = unwrap_bytes(kv_lb.value, lb_from_query);
-        auto d_kv_ub = unwrap_bytes(kv_ub.value, ub_from_query);
-        if(!d_kv_v || !d_kv_lb || !d_kv_ub) {
-            return false;
-        }
-        return check_BETWEEN(*d_kv_v, *d_kv_lb, *d_kv_ub, 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, false, true);
-            }
-        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, false, true);
-            }
-        }
-        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(
-                fmt::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 std::ranges::all_of(list.conditions, verify_condition);
-            case '|':
-                return std::ranges::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

@@ -1,46 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-/*
- * 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 "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 v1_from_query, bool v2_from_query);
-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/consumed_capacity.cc

@@ -1,96 +0,0 @@
-/*
- * Copyright 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "consumed_capacity.hh"
-#include "error.hh"
-#include "utils/rjson.hh"
-#include <fmt/format.h>
-
-namespace alternator {
-
-/*
- * \brief DynamoDB counts read capacity in half-integers - a short
- * eventually-consistent read is counted as 0.5 unit.
- * Because we want our counter to be an integer, it counts half units.
- * Both read and write counters count in these half-units, and should be
- * multiply by 0.5 (HALF_UNIT_MULTIPLIER) to get the DynamoDB-compatible RCU or WCU numbers.
- */
-static constexpr double HALF_UNIT_MULTIPLIER = 0.5;
-
-static constexpr uint64_t KB = 1024ULL;
-static constexpr uint64_t RCU_BLOCK_SIZE_LENGTH = 4*KB;
-static constexpr uint64_t WCU_BLOCK_SIZE_LENGTH = 1*KB;
-
-bool consumed_capacity_counter::should_add_capacity(const rjson::value& request) {
-    const rjson::value* return_consumed = rjson::find(request, "ReturnConsumedCapacity");
-    if (!return_consumed) {
-        return false;
-    }
-    if (!return_consumed->IsString()) {
-        throw api_error::validation("Non-string ReturnConsumedCapacity field in request");
-    }
-    std::string_view consumed = rjson::to_string_view(*return_consumed);
-    if (consumed == "INDEXES") {
-        throw api_error::validation("INDEXES consumed capacity is not supported");
-    }
-    if (consumed != "TOTAL") {
-        throw api_error::validation(fmt::format("Unknown consumed capacity {}", consumed));
-    }
-    return true;
-}
-
-void consumed_capacity_counter::add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept {
-    if (_should_add_to_reponse) {
-        auto consumption = rjson::empty_object();
-        rjson::add(consumption, "CapacityUnits", get_consumed_capacity_units());
-        rjson::add(response, "ConsumedCapacity", std::move(consumption));
-    }
-}
-
-static uint64_t calculate_half_units(uint64_t unit_block_size, uint64_t total_bytes, bool is_quorum) {
-    uint64_t half_units = (total_bytes + unit_block_size -1) / unit_block_size; //divide by unit_block_size and round up
-
-    if (is_quorum) {
-        half_units *= 2;
-    }
-    return half_units;
-}
-
-rcu_consumed_capacity_counter::rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum) :
-        consumed_capacity_counter(should_add_capacity(request)),_is_quorum(is_quorum) {
-}
-uint64_t rcu_consumed_capacity_counter::get_half_units(uint64_t total_bytes, bool is_quorum) noexcept {
-    return calculate_half_units(RCU_BLOCK_SIZE_LENGTH, total_bytes, is_quorum);
-}
-
-uint64_t rcu_consumed_capacity_counter::get_half_units() const noexcept {
-    return get_half_units(_total_bytes, _is_quorum);
-}
-
-uint64_t wcu_consumed_capacity_counter::get_half_units() const noexcept {
-    return calculate_half_units(WCU_BLOCK_SIZE_LENGTH, _total_bytes, true);
-}
-
-uint64_t wcu_consumed_capacity_counter::get_units(uint64_t total_bytes) noexcept {
-    return calculate_half_units(WCU_BLOCK_SIZE_LENGTH, total_bytes, true) * HALF_UNIT_MULTIPLIER;
-}
-
-wcu_consumed_capacity_counter::wcu_consumed_capacity_counter(const rjson::value& request) :
-        consumed_capacity_counter(should_add_capacity(request)) {
-}
-
-consumed_capacity_counter& consumed_capacity_counter::operator +=(uint64_t units) {
-    _total_bytes += units;
-    return *this;
-}
-
-double consumed_capacity_counter::get_consumed_capacity_units() const noexcept {
-    return get_half_units() * HALF_UNIT_MULTIPLIER;
-}
-
-}

alternator/consumed_capacity.hh

@@ -1,66 +0,0 @@
-/*
- * Copyright 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "utils/rjson.hh"
-
-namespace alternator {
-
-/**
- * \brief consumed_capacity_counter is a base class that holds the bookkeeping
- *  to calculate RCU and WCU
- *
- * DynamoDB counts read capacity in half-integers - a short
- * eventually-consistent read is counted as 0.5 unit.
- * Because we want our counter to be an integer, we counts half units in
- * our internal calculations.
- *
- * We use consumed_capacity_counter for calculation of a specific action
- *
- * It is also used to update the response if needed.
- */
-class consumed_capacity_counter {
-public:
-    consumed_capacity_counter() = default;
-    consumed_capacity_counter(bool should_add_to_reponse) : _should_add_to_reponse(should_add_to_reponse){}
-    bool operator()() const noexcept {
-        return _should_add_to_reponse;
-    }
-
-    consumed_capacity_counter& operator +=(uint64_t bytes);
-    double get_consumed_capacity_units() const noexcept;
-    void add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept;
-    virtual ~consumed_capacity_counter() = default;
-    /**
-     * \brief get_half_units calculate the half units from the total bytes based on the type of the request
-     */
-    virtual uint64_t get_half_units() const noexcept = 0;
-    uint64_t _total_bytes = 0;
-    static bool should_add_capacity(const rjson::value& request);
-protected:
-    bool _should_add_to_reponse = false;
-};
-
-class rcu_consumed_capacity_counter : public consumed_capacity_counter {
-    bool _is_quorum = false;
-public:
-    rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum);
-    rcu_consumed_capacity_counter(): consumed_capacity_counter(false), _is_quorum(false){}
-    virtual uint64_t get_half_units() const noexcept;
-    static uint64_t get_half_units(uint64_t total_bytes, bool is_quorum) noexcept;
-};
-
-class wcu_consumed_capacity_counter : public consumed_capacity_counter {
-    virtual uint64_t get_half_units() const noexcept;
-public:
-    wcu_consumed_capacity_counter(const rjson::value& request);
-    static uint64_t get_units(uint64_t total_bytes) noexcept;
-};
-
-}

alternator/controller.cc

@@ -1,176 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include <seastar/core/with_scheduling_group.hh>
-#include <seastar/net/dns.hh>
-
-#include "controller.hh"
-#include "server.hh"
-#include "executor.hh"
-#include "rmw_operation.hh"
-#include "db/config.hh"
-#include "cdc/generation_service.hh"
-#include "service/memory_limiter.hh"
-#include "auth/service.hh"
-#include "service/qos/service_level_controller.hh"
-
-using namespace seastar;
-
-namespace alternator {
-
-static logging::logger logger("alternator_controller");
-
-controller::controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config,
-        seastar::scheduling_group sg)
-    : protocol_server(sg)
-    , _gossiper(gossiper)
-    , _proxy(proxy)
-    , _mm(mm)
-    , _sys_dist_ks(sys_dist_ks)
-    , _cdc_gen_svc(cdc_gen_svc)
-    , _memory_limiter(memory_limiter)
-    , _auth_service(auth_service)
-    , _sl_controller(sl_controller)
-    , _config(config)
-{
-}
-
-sstring controller::name() const {
-    return "alternator";
-}
-
-sstring controller::protocol() const {
-    return "dynamodb";
-}
-
-sstring controller::protocol_version() const {
-    return version;
-}
-
-std::vector<socket_address> controller::listen_addresses() const {
-    return _listen_addresses;
-}
-
-future<> controller::start_server() {
-    seastar::thread_attributes attr;
-    attr.sched_group = _sched_group;
-    return seastar::async(std::move(attr), [this] {
-        _listen_addresses.clear();
-
-        auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
-        auto family = _config.enable_ipv6_dns_lookup() || preferred ? std::nullopt : std::make_optional(net::inet_address::family::INET);
-
-        // Create an smp_service_group to be used for limiting the
-        // concurrency when forwarding Alternator request between
-        // shards - if necessary for LWT.
-        smp_service_group_config c;
-        c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get();
-
-        rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
-
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get();
-
-        auto get_cdc_metadata = [] (cdc::generation_service& svc) { return std::ref(svc.get_cdc_metadata()); };
-        auto get_timeout_in_ms = [] (const db::config& cfg) -> utils::updateable_value<uint32_t> {
-            return cfg.alternator_timeout_in_ms;
-        };
-        _executor.start(std::ref(_gossiper), std::ref(_proxy), std::ref(_mm), std::ref(_sys_dist_ks),
-                        sharded_parameter(get_cdc_metadata, std::ref(_cdc_gen_svc)), _ssg.value(),
-                        sharded_parameter(get_timeout_in_ms, std::ref(_config))).get();
-        _server.start(std::ref(_executor), std::ref(_proxy), std::ref(_gossiper), std::ref(_auth_service), std::ref(_sl_controller)).get();
-        // Note: from this point on, if start_server() throws for any reason,
-        // it must first call stop_server() to stop the executor and server
-        // services we just started - or Scylla will cause an assertion
-        // failure when the controller object is destroyed in the exception
-        // unwinding.
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.alternator_port();
-            _listen_addresses.push_back({addr, *alternator_port});
-        }
-        std::optional<uint16_t> alternator_https_port;
-        std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port()) {
-            alternator_https_port = _config.alternator_https_port();
-            _listen_addresses.push_back({addr, *alternator_https_port});
-            creds.emplace();
-            auto opts = _config.alternator_encryption_options();
-            if (opts.empty()) {
-                // Earlier versions mistakenly configured Alternator's
-                // HTTPS parameters via the "server_encryption_option"
-                // configuration parameter. We *temporarily* continue
-                // to allow this, for backward compatibility.
-                opts = _config.server_encryption_options();
-                if (!opts.empty()) {
-                logger.warn("Setting server_encryption_options to configure "
-                        "Alternator's HTTPS encryption is deprecated. Please "
-                        "switch to setting alternator_encryption_options instead.");
-                }
-            }
-            opts.erase("require_client_auth");
-            opts.erase("truststore");
-            try {
-                utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-            } catch(...) {
-                logger.error("Failed to set up Alternator TLS credentials: {}", std::current_exception());
-                stop_server().get();
-                std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
-            }
-        }
-        _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds)] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, creds,
-                    _config.alternator_enforce_authorization,
-                    _config.alternator_warn_authorization,
-                    _config.alternator_max_users_query_size_in_trace_output,
-                    &_memory_limiter.local().get_semaphore(),
-                    _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF", ep);
-            return stop_server().then([ep = std::move(ep)] { return make_exception_future<>(ep); });
-        }).then([addr, alternator_port, alternator_https_port] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF");
-        }).get();
-    });
-}
-
-future<> controller::stop_server() {
-    return seastar::async([this] {
-        if (!_ssg) {
-            return;
-        }
-        _server.stop().get();
-        _executor.stop().get();
-        _listen_addresses.clear();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-future<> controller::request_stop_server() {
-    return with_scheduling_group(_sched_group, [this] {
-        return stop_server();
-    });
-}
-
-future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> controller::get_client_data() {
-    return _server.local().get_client_data();
-}
-
-}

alternator/controller.hh

@@ -1,99 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <seastar/core/sharded.hh>
-#include <seastar/core/smp.hh>
-
-#include "transport/protocol_server.hh"
-
-namespace service {
-class storage_proxy;
-class migration_manager;
-class memory_limiter;
-}
-
-namespace db {
-class system_distributed_keyspace;
-class config;
-}
-
-namespace cdc {
-class generation_service;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace auth {
-class service;
-}
-
-namespace qos {
-class service_level_controller;
-}
-
-namespace alternator {
-
-// This is the official DynamoDB API version.
-// It represents the last major reorganization of that API, and all the features
-// that were added since did NOT increment this version string.
-constexpr const char* version = "2012-08-10";
-
-using namespace seastar;
-
-class executor;
-class server;
-
-class controller : public protocol_server {
-    sharded<gms::gossiper>& _gossiper;
-    sharded<service::storage_proxy>& _proxy;
-    sharded<service::migration_manager>& _mm;
-    sharded<db::system_distributed_keyspace>& _sys_dist_ks;
-    sharded<cdc::generation_service>& _cdc_gen_svc;
-    sharded<service::memory_limiter>& _memory_limiter;
-    sharded<auth::service>& _auth_service;
-    sharded<qos::service_level_controller>& _sl_controller;
-    const db::config& _config;
-
-    std::vector<socket_address> _listen_addresses;
-    sharded<executor> _executor;
-    sharded<server> _server;
-    std::optional<smp_service_group> _ssg;
-
-public:
-    controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config,
-        seastar::scheduling_group sg);
-
-    virtual sstring name() const override;
-    virtual sstring protocol() const override;
-    virtual sstring protocol_version() const override;
-    virtual std::vector<socket_address> listen_addresses() const override;
-    virtual future<> start_server() override;
-    virtual future<> stop_server() override;
-    virtual future<> request_stop_server() override;
-    // This virtual function is called (on each shard separately) when the
-    // virtual table "system.clients" is read. It is expected to generate a
-    // list of clients connected to this server (on this shard).
-    virtual future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> get_client_data() override;
-};
-
-}

alternator/error.hh

@@ -1,111 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <seastar/http/httpd.hh>
-#include "seastarx.hh"
-#include "utils/rjson.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 std::exception {
-public:
-    using status_type = http::reply::status_type;
-    status_type _http_code;
-    std::string _type;
-    std::string _msg;
-    // Additional data attached to the error, null value if not set. It's wrapped in copyable_value
-    // class because copy constructor is required for exception classes otherwise it won't compile
-    // (despite that its use may be optimized away).
-    rjson::copyable_value _extra_fields; 
-    api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request,
-    rjson::value extra_fields = rjson::null_value())
-        : _http_code(std::move(http_code))
-        , _type(std::move(type))
-        , _msg(std::move(msg))
-        , _extra_fields(std::move(extra_fields))
-    { }
-
-    // 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 missing_authentication_token(std::string msg) {
-        return api_error("MissingAuthenticationTokenException", 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, rjson::value&& item) {
-        if (!item.IsNull()) {
-            auto tmp = rjson::empty_object();
-            rjson::add(tmp, "Item", std::move(item));
-            item = std::move(tmp);
-        }
-        return api_error("ConditionalCheckFailedException", std::move(msg), status_type::bad_request, std::move(item));
-    }
-    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 request_limit_exceeded(std::string msg) {
-        return api_error("RequestLimitExceeded", std::move(msg));
-    }
-    static api_error serialization(std::string msg) {
-        return api_error("SerializationException", std::move(msg));
-    }
-    static api_error table_not_found(std::string msg) {
-        return api_error("TableNotFoundException", std::move(msg));
-    }
-    static api_error limit_exceeded(std::string msg) {
-        return api_error("LimitExceededException", std::move(msg));
-    }
-    static api_error internal(std::string msg) {
-        return api_error("InternalServerError", std::move(msg), http::reply::status_type::internal_server_error);
-    }
-    static api_error payload_too_large(std::string msg) {
-        return api_error("PayloadTooLarge", std::move(msg), status_type::payload_too_large);
-    }
-
-    // Provide the "std::exception" interface, to make it easier to print this
-    // exception in log messages. Note that this function is *not* used to
-    // format the error to send it back to the client - server.cc has
-    // generate_error_reply() to format an api_error as the DynamoDB protocol
-    // requires.
-    virtual const char* what() const noexcept override;
-    mutable std::string _what_string;
-};
-
-}
-

alternator/executor.hh

@@ -1,291 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <seastar/core/future.hh>
-#include "seastarx.hh"
-#include <seastar/core/sharded.hh>
-#include <seastar/util/noncopyable_function.hh>
-
-#include "service/migration_manager.hh"
-#include "service/client_state.hh"
-#include "service_permit.hh"
-#include "db/timeout_clock.hh"
-
-#include "alternator/error.hh"
-#include "stats.hh"
-#include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
-
-#include "tracing/trace_state.hh"
-
-namespace db {
-    class system_distributed_keyspace;
-}
-
-namespace query {
-class partition_slice;
-class result;
-}
-
-namespace cql3::selection {
-    class selection;
-}
-
-namespace service {
-    class storage_proxy;
-    class cas_shard;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-class schema_builder;
-
-namespace alternator {
-
-class rmw_operation;
-class put_or_delete_item;
-
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-bool is_alternator_keyspace(const sstring& ks_name);
-// Wraps the db::get_tags_of_table and throws if the table is missing the tags extension.
-const std::map<sstring, sstring>& get_tags_of_table_or_throw(schema_ptr schema);
-
-// An attribute_path_map object is used to hold data for various attributes
-// paths (parsed::path) in a hierarchy of attribute paths. Each attribute path
-// has a root attribute, and then modified by member and index operators -
-// for example in "a.b[2].c" we have "a" as the root, then ".b" member, then
-// "[2]" index, and finally ".c" member.
-// Data can be added to an attribute_path_map using the add() function, but
-// requires that attributes with data not be *overlapping* or *conflicting*:
-//
-// 1. Two attribute paths which are identical or an ancestor of one another
-//    are considered *overlapping* and not allowed. If a.b.c has data,
-//    we can't add more data in a.b.c or any of its descendants like a.b.c.d.
-//
-// 2. Two attribute paths which need the same parent to have both a member and
-//    an index are considered *conflicting* and not allowed. E.g., if a.b has
-//    data, you can't add a[1]. The meaning of adding both would be that the
-//    attribute a is both a map and an array, which isn't sensible.
-//
-// These two requirements are common to the two places where Alternator uses
-// this abstraction to describe how a hierarchical item is to be transformed:
-//
-// 1. In ProjectExpression: for filtering from a full top-level attribute
-//    only the parts for which user asked in ProjectionExpression.
-//
-// 2. In UpdateExpression: for taking the previous value of a top-level
-//    attribute, and modifying it based on the instructions in the user
-//    wrote in UpdateExpression.
-
-template<typename T>
-class attribute_path_map_node {
-public:
-    using data_t = T;
-    // We need the extra unique_ptr<> here because libstdc++ unordered_map
-    // doesn't work with incomplete types :-(
-    using members_t =  std::unordered_map<std::string, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The indexes list is sorted because DynamoDB requires handling writes
-    // beyond the end of a list in index order.
-    using indexes_t = std::map<unsigned, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The prohibition on "overlap" and "conflict" explained above means
-    // That only one of data, members or indexes is non-empty.
-    std::optional<std::variant<data_t, members_t, indexes_t>> _content;
-
-    bool is_empty() const { return !_content; }
-    bool has_value() const { return _content && std::holds_alternative<data_t>(*_content); }
-    bool has_members() const { return _content && std::holds_alternative<members_t>(*_content); }
-    bool has_indexes() const { return _content && std::holds_alternative<indexes_t>(*_content); }
-    // get_members() assumes that has_members() is true
-    members_t& get_members() { return std::get<members_t>(*_content); }
-    const members_t& get_members() const { return std::get<members_t>(*_content); }
-    indexes_t& get_indexes() { return std::get<indexes_t>(*_content); }
-    const indexes_t& get_indexes() const { return std::get<indexes_t>(*_content); }
-    T& get_value() { return std::get<T>(*_content); }
-    const T& get_value() const { return std::get<T>(*_content); }
-};
-
-template<typename T>
-using attribute_path_map = std::unordered_map<std::string, attribute_path_map_node<T>>;
-
-using attrs_to_get_node = attribute_path_map_node<std::monostate>;
-// attrs_to_get lists which top-level attribute are needed, and possibly also
-// which part of the top-level attribute is really needed (when nested
-// attribute paths appeared in the query).
-// Most code actually uses optional<attrs_to_get>. There, a disengaged
-// optional means we should get all attributes, not specific ones.
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-namespace parsed {
-class expression_cache;
-}
-
-class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
-    service::storage_proxy& _proxy;
-    service::migration_manager& _mm;
-    db::system_distributed_keyspace& _sdks;
-    cdc::metadata& _cdc_metadata;
-    utils::updateable_value<bool> _enforce_authorization;
-    utils::updateable_value<bool> _warn_authorization;
-    // 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;
-
-    std::unique_ptr<parsed::expression_cache> _parsed_expression_cache;
-
-public:
-    using client_state = service::client_state;
-    // request_return_type is the return type of the executor methods, which
-    // can be one of:
-    // 1. A string, which is the response body for the request.
-    // 2. A body_writer, an asynchronous function (returning future<>) that
-    //    takes an output_stream and writes the response body into it.
-    // 3. An api_error, which is an error response that should be returned to
-    //    the client.
-    // The body_writer is used for streaming responses, where the response body
-    // is written in chunks to the output_stream. This allows for efficient
-    // handling of large responses without needing to allocate a large buffer
-    // in memory.
-    using body_writer = noncopyable_function<future<>(output_stream<char>&&)>;
-    using request_return_type = std::variant<std::string, body_writer, api_error>;
-    stats _stats;
-    // The metric_groups object holds this stat object's metrics registered
-    // as long as the stats object is alive.
-    seastar::metrics::metric_groups _metrics;
-    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(gms::gossiper& gossiper,
-             service::storage_proxy& proxy,
-             service::migration_manager& mm,
-             db::system_distributed_keyspace& sdks,
-             cdc::metadata& cdc_metadata,
-             smp_service_group ssg,
-             utils::updateable_value<uint32_t> default_timeout_in_ms);
-    ~executor();
-
-    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> update_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_time_to_live(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<request_return_type> describe_continuous_backups(client_state& client_state, service_permit permit, rjson::value request);
-
-    future<> start();
-    future<> stop();
-
-    static sstring table_name(const schema&);
-    static db::timeout_clock::time_point default_timeout();
-private:
-    static thread_local utils::updateable_value<uint32_t> s_default_timeout_in_ms;
-public:
-    static schema_ptr find_table(service::storage_proxy&, std::string_view table_name);
-    static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
-
-private:
-    friend class rmw_operation;
-
-    static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr, const std::map<sstring, sstring> *tags = nullptr);
-
-    future<> do_batch_write(
-        std::vector<std::pair<schema_ptr, put_or_delete_item>> mutation_builders,
-        service::client_state& client_state,
-        tracing::trace_state_ptr trace_state,
-        service_permit permit);
-
-    future<> cas_write(schema_ptr schema, service::cas_shard cas_shard, const dht::decorated_key& dk,
-        const std::vector<put_or_delete_item>& mutation_builders, service::client_state& client_state,
-        tracing::trace_state_ptr trace_state, service_permit permit);
-
-public:
-    static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&, const std::map<sstring, sstring> *tags = nullptr);
-
-    static std::optional<rjson::value> describe_single_item(schema_ptr,
-        const query::partition_slice&,
-        const cql3::selection::selection&,
-        const query::result&,
-        const std::optional<attrs_to_get>&,
-        uint64_t* = nullptr);
-
-    // Converts a multi-row selection result to JSON compatible with DynamoDB.
-    // For each row, this method calls item_callback, which takes the size of
-    // the item as the parameter.
-    static future<std::vector<rjson::value>> describe_multi_item(schema_ptr schema,
-        const query::partition_slice&& slice,
-        shared_ptr<cql3::selection::selection> selection,
-        foreign_ptr<lw_shared_ptr<query::result>> query_result,
-        shared_ptr<const std::optional<attrs_to_get>> attrs_to_get,
-        noncopyable_function<void(uint64_t)> item_callback = {});
-
-    static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<managed_bytes_opt>&,
-        const std::optional<attrs_to_get>&,
-        rjson::value&,
-        uint64_t* item_length_in_bytes = nullptr,
-        bool = false);
-
-    static bool add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
-    static void supplement_table_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
-    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, const service::storage_proxy& sp);
-};
-
-// is_big() checks approximately if the given JSON value is "bigger" than
-// the given big_size number of bytes. The goal is to *quickly* detect
-// oversized JSON that, for example, is too large to be serialized to a
-// contiguous string - we don't need an accurate size for that. Moreover,
-// as soon as we detect that the JSON is indeed "big", we can return true
-// and don't need to continue calculating its exact size.
-// For simplicity, we use a recursive implementation. This is fine because
-// Alternator limits the depth of JSONs it reads from inputs, and doesn't
-// add more than a couple of levels in its own output construction.
-bool is_big(const rjson::value& val, int big_size = 100'000);
-
-// Check CQL's Role-Based Access Control (RBAC) permission (MODIFY,
-// SELECT, DROP, etc.) on the given table. When permission is denied an
-// appropriate user-readable api_error::access_denied is thrown.
-future<> verify_permission(bool enforce_authorization, bool warn_authorization, const service::client_state&, const schema_ptr&, auth::permission, alternator::stats& stats);
-
-/**
- * Make return type for serializing the object "streamed",
- * i.e. direct to HTTP output stream. Note: only useful for
- * (very) large objects as there are overhead issues with this
- * as well, but for massive lists of return objects this can
- * help avoid large allocations/many re-allocs
- */
-executor::body_writer make_streamed(rjson::value&&);
-
-}

alternator/expressions.cc

@@ -1,779 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "expressions.hh"
-#include "serialization.hh"
-#include "utils/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/format.hh>
-#include <seastar/util/log.hh>
-
-#include <functional>
-#include <unordered_map>
-
-namespace alternator {
-
-template <typename Func, typename Result = std::invoke_result_t<Func, expressionsParser&>>
-static Result do_with_parser(std::string_view 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;
-}
-
-template <typename Func, typename Result = std::invoke_result_t<Func, expressionsParser&>>
-static Result parse(const char* input_name, std::string_view input, Func&& f) {
-    if (input.length() > 4096) {
-        throw expressions_syntax_error(format("{} expression size {} exceeds allowed maximum 4096.",
-            input_name, input.length()));
-    }
-    try {
-        return do_with_parser(input, f);
-    } catch (expressions_syntax_error& e) {
-        // If already an expressions_syntax_error, don't print the type's
-        // name (it's just ugly), just the message.
-        // TODO: displayRecognitionError could set a position inside the
-        // expressions_syntax_error in throws, and we could use it here to
-        // mark the broken position in 'input'.
-        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
-            input_name, input, e.what()));
-    } catch (...) {
-        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
-            input_name, input, std::current_exception()));
-    }
-}
-
-parsed::update_expression
-parse_update_expression(std::string_view query) {
-    return parse("UpdateExpression", query,  std::mem_fn(&expressionsParser::update_expression));
-}
-
-std::vector<parsed::path>
-parse_projection_expression(std::string_view query) {
-    return parse ("ProjectionExpression", query,  std::mem_fn(&expressionsParser::projection_expression));
-}
-
-parsed::condition_expression
-parse_condition_expression(std::string_view query, const char* caller) {
-    return parse(caller, query,  std::mem_fn(&expressionsParser::condition_expression));
-}
-
-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);
-}
-
-void path::check_depth_limit() {
-    if (1 + _operators.size() > depth_limit) {
-        throw expressions_syntax_error(format("Document path exceeded {} nesting levels", depth_limit));
-    }
-}
-
-} // 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 std::optional<std::string> resolve_path_component(const std::string& column_name,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    if (column_name.size() > 0 && column_name.front() == '#') {
-        if (!expression_attribute_names) {
-            throw api_error::validation(
-                    fmt::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(
-                    fmt::format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
-        }
-        used_attribute_names.emplace(column_name);
-        auto result = std::string(rjson::to_string_view(*value));
-        validate_attr_name_length("", result.size(), false, "ExpressionAttributeNames contains invalid value: ");
-        return result;
-    }
-    return std::nullopt;
-}
-
-static void resolve_path(parsed::path& p,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    std::optional<std::string> r = resolve_path_component(p.root(), expression_attribute_names, used_attribute_names);
-    if (r) {
-        p.set_root(std::move(*r));
-    }
-    for (auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (std::string& s) {
-                r = resolve_path_component(s, expression_attribute_names, used_attribute_names);
-                if (r) {
-                    s = std::move(*r);
-                }
-            },
-            [&] (unsigned index) {
-                // nothing to resolve
-            }
-        }, op);
-    }
-}
-
-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(
-                        fmt::format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
-            }
-            const rjson::value* value = rjson::find(*expression_attribute_values, valref);
-            if (!value) {
-                throw api_error::validation(
-                        fmt::format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
-            }
-            if (value->IsNull()) {
-                throw api_error::validation(
-                        fmt::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.
-
-// 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.
-// If the value's type (e.g. number) has no size defined, there are two cases:
-// 1. If from_data (the value came directly from an attribute of the data),
-//    It returns a JSON-encoded "null" value. Comparisons against this
-//    non-numeric value will later fail, so eventually the application will
-//    get a ConditionalCheckFailedException.
-// 2. Otherwise (the value came from a constant in the query or some other
-//    calculation), throw a ValidationException.
-static rjson::value calculate_size(const rjson::value& v, bool from_data) {
-    // 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 if (from_data) {
-        rjson::value json_ret = rjson::empty_object();
-        rjson::add(json_ret, "null", rjson::value(true));
-        return json_ret;
-    } else {
-        throw api_error::validation(format("Unsupported operand type {} for function size()", it->name));
-    }
-    rjson::value json_ret = rjson::empty_object();
-    rjson::add(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::add(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);
-            rjson::value ret = list_concatenate(v1, v2);
-            if (ret.IsNull()) {
-                throw api_error::validation("UpdateExpression: list_append() given a non-list");
-            }
-            return ret;
-        }
-    },
-    {"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, f._parameters[0].is_path());
-        }
-    },
-    {"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,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
-        }
-    },
-};
-
-// Given a parsed::path and an item read from the table, extract the value
-// of a certain attribute path, such as "a" or "a.b.c[3]". Returns a null
-// value if the item or the requested attribute does not exist.
-// Note that the item is assumed to be encoded in JSON using DynamoDB
-// conventions - each level of a nested document is a map with one key -
-// a type (e.g., "M" for map) - and its value is the representation of
-// that value.
-static rjson::value extract_path(const rjson::value* item,
-        const parsed::path& p, calculate_value_caller caller) {
-    if (!item) {
-        return rjson::null_value();
-    }
-    const rjson::value* v = rjson::find(*item, p.root());
-    if (!v) {
-        return rjson::null_value();
-    }
-    for (const auto& op : p.operators()) {
-        if (!v->IsObject() || v->MemberCount() != 1) {
-            // This shouldn't happen. We shouldn't have stored malformed
-            // objects. But today Alternator does not validate the structure
-            // of nested documents before storing them, so this can happen on
-            // read.
-            throw api_error::validation(format("{}: malformed item read: {}", caller, *item));
-        }
-        const char* type = v->MemberBegin()->name.GetString();
-        v = &(v->MemberBegin()->value);
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                if (type[0] == 'M' && v->IsObject()) {
-                    v = rjson::find(*v, member);
-                } else {
-                    v = nullptr;
-                }
-            },
-            [&] (unsigned index) {
-                if (type[0] == 'L' && v->IsArray() && index < v->Size()) {
-                    v = &(v->GetArray()[index]);
-                } else {
-                    v = nullptr;
-                }
-            }
-        }, op);
-        if (!v) {
-            return rjson::null_value();
-        }
-    }
-    return rjson::copy(*v);
-}
-
-// 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(
-                        fmt::format("{}: unknown function '{}' called.", caller, f._function_name));
-            }
-            return function_it->second(caller, previous_item, f);
-        },
-        [&] (const parsed::path& p) -> rjson::value {
-            return extract_path(previous_item, p, caller);
-        }
-    }, 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();
-}
-
-void validate_attr_name_length(std::string_view supplementary_context, size_t attr_name_length, bool is_key, std::string_view error_msg_prefix) {
-    constexpr const size_t DYNAMODB_KEY_ATTR_NAME_SIZE_MAX = 255;
-    constexpr const size_t DYNAMODB_NONKEY_ATTR_NAME_SIZE_MAX = 65535;
-
-    const size_t max_length = is_key ? DYNAMODB_KEY_ATTR_NAME_SIZE_MAX : DYNAMODB_NONKEY_ATTR_NAME_SIZE_MAX;
-    if (attr_name_length > max_length) {
-        std::string error_msg;
-        if (!error_msg_prefix.empty()) {
-            error_msg += error_msg_prefix;
-        }
-        if (!supplementary_context.empty()) {
-            error_msg += "in ";
-            error_msg += supplementary_context;
-            error_msg += " - ";
-        }
-        error_msg += fmt::format("Attribute name is too large, must be less than {} bytes", std::to_string(max_length + 1));
-        throw api_error::validation(error_msg);
-    }
-}
-
-} // namespace alternator
-
-auto fmt::formatter<alternator::parsed::path>::format(const alternator::parsed::path& p, fmt::format_context& ctx) const
-        -> decltype(ctx.out()) {
-    auto out = ctx.out();
-    out = fmt::format_to(out, "{}", p.root());
-    for (const auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                out = fmt::format_to(out, ".{}", member);
-            },
-            [&] (unsigned index) {
-                out = fmt::format_to(out, "[{}]", index);
-            }
-        }, op);
-    }
-    return out;
-}

alternator/expressions.g

@@ -1,308 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-/*
- * 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) {
-        const char* err;
-        switch (ex->getType()) {
-        case antlr3::ExceptionType::FAILED_PREDICATE_EXCEPTION:
-            err = "expression nested too deeply";
-            break;
-        default:
-            err = "syntax error";
-            break;
-        }
-        // Alternator expressions are always single line so ex->get_line()
-        // is always 1, no sense to print it.
-        // TODO: return the position as part of the exception, so the
-        // caller in expressions.cc that knows the expression string can
-        // mark the error position in the final error message.
-        throw expressions_syntax_error(format("{} at char {}", err,
-            ex->get_charPositionInLine()));
-    }
-
-    // ANTLR3 tries to recover missing tokens - it tries to finish parsing
-    // and create valid objects, as if the missing token was there.
-    // But it has a bug and leaks these tokens.
-    // We override offending method and handle abandoned pointers.
-    std::vector<std::unique_ptr<TokenType>> _missing_tokens;
-    TokenType* getMissingSymbol(IntStreamType* istream, ExceptionBaseType* e,
-                                ANTLR_UINT32 expectedTokenType, BitsetListType* follow) {
-        auto token = BaseType::getMissingSymbol(istream, e, expectedTokenType, follow);
-        _missing_tokens.emplace_back(token);
-        return token;
-    }
-}
-@lexer::context {
-    void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
-        throw expressions_syntax_error("syntax error");
-    }
-}
-
-/* Unfortunately, ANTLR uses recursion - not the heap - to parse recursive
- * expressions. To make things even worse, ANTLR has no way to limit the
- * depth of this recursion (unlike Yacc which has YYMAXDEPTH). So deeply-
- * nested expression like "(((((((((((((..." can easily crash Scylla on a
- * stack overflow (see issue #14477).
- *
- * We are lucky that in the grammar for DynamoDB expressions (below),
- * only a few specific rules can recurse, so it was fairly easy to add a
- * "depth" counter to a few specific rules, and then use a predicate
- * "{depth<MAX_DEPTH}?" to avoid parsing if the depth exceeds this limit,
- * and throw a FAILED_PREDICATE_EXCEPTION in that case, which we will
- * report to the user as a "expression nested too deeply" error.
- */
-@parser::members {
-    static constexpr int MAX_DEPTH = 400;
-}
-
-/*
- * 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 ']'           {
-                try {
-                    $p.add_index(std::stoi($INTEGER.text));
-                } catch(std::out_of_range&) {
-                    throw expressions_syntax_error("list index out of integer range");
-                }
-            }
-    )*;
-
-/* See comment above why the "depth" counter was needed here */
-value[int depth] returns [parsed::value v]:
-      VALREF       { $v.set_valref($VALREF.text); }
-    | path         { $v.set_path($path.p); }
-    | {depth<MAX_DEPTH}? NAME { $v.set_func_name($NAME.text); }
-     '(' x=value[depth+1]    { $v.add_func_parameter($x.v); }
-     (',' x=value[depth+1]   { $v.add_func_parameter($x.v); })*
-     ')'
-    ;
-
-update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value[0]  { $rhs.set_value(std::move($v.v)); }
-    (   '+' v=value[0]  { $rhs.set_plus(std::move($v.v)); }
-      | '-' v=value[0]  { $rhs.set_minus(std::move($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[0]      { $c.add_value(std::move($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[0]   { $c.add_value(std::move($v.v)); }
-       | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-         AND
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-       | IN '('       { $c.set_operator(parsed::primitive_condition::type::IN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-         (',' v=value[0] { $c.add_value(std::move($v.v)); })*
-         ')'
-      )?
-      {
-          // Post-parse check to reject non-function single values
-          if ($c._op == parsed::primitive_condition::type::VALUE &&
-              !$c._values.front().is_func()) {
-              throw expressions_syntax_error("Single value must be a function");
-          }
-      }
-    ;
-
-// 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.
-// See comment above why the "depth" counter was needed here.
-boolean_expression[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_1[depth]       { $e.append(std::move($b.e), '|'); }
-	  (OR b=boolean_expression_1[depth]   { $e.append(std::move($b.e), '|'); } )*
-	;
-boolean_expression_1[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_2[depth]       { $e.append(std::move($b.e), '&'); }
-	  (AND b=boolean_expression_2[depth]  { $e.append(std::move($b.e), '&'); } )*
-	;
-boolean_expression_2[int depth] returns [parsed::condition_expression e]:
-	  p=primitive_condition        { $e.set_primitive(std::move($p.c)); }
-	| {depth<MAX_DEPTH}? NOT b=boolean_expression_2[depth+1]   { $e = std::move($b.e); $e.apply_not(); }
-	| {depth<MAX_DEPTH}? '(' b=boolean_expression[depth+1] ')' { $e = std::move($b.e); }
-    ;
-
-condition_expression returns [parsed::condition_expression e]:
-    boolean_expression[0] { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -1,119 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#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"
-#include "utils/updateable_value.hh"
-#include "stats.hh"
-
-namespace alternator {
-
-class expressions_syntax_error : public std::runtime_error {
-public:
-    using runtime_error::runtime_error;
-};
-
-namespace parsed {
-class expression_cache_impl;
-class expression_cache {
-    std::unique_ptr<expression_cache_impl> _impl;
-public:
-    struct config {
-        utils::updateable_value<uint32_t> max_cache_entries;
-    };
-    expression_cache(config cfg, stats& stats);
-    ~expression_cache();
-    // stop background tasks, if any
-    future<> stop();
-
-    update_expression parse_update_expression(std::string_view query);
-    std::vector<path> parse_projection_expression(std::string_view query);
-    condition_expression parse_condition_expression(std::string_view query, const char* caller);
-};
-} // namespace parsed
-
-// Preferably use parsed::expression_cache instance instead of this free functions.
-parsed::update_expression parse_update_expression(std::string_view query);
-std::vector<parsed::path> parse_projection_expression(std::string_view query);
-parsed::condition_expression parse_condition_expression(std::string_view query, const char* caller);
-
-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
-};
-
-}
-
-template <> struct fmt::formatter<alternator::calculate_value_caller> {
-    constexpr auto parse(format_parse_context& ctx) { return ctx.begin(); }
-    auto format(alternator::calculate_value_caller caller, fmt::format_context& ctx) const {
-        std::string_view name = "unknown type of expression";
-        switch (caller) {
-            using enum alternator::calculate_value_caller;
-            case UpdateExpression:
-                name = "UpdateExpression";
-                break;
-            case ConditionExpression:
-                name = "ConditionExpression";
-                break;
-            case ConditionExpressionAlone:
-                name = "ConditionExpression";
-                break;
-        }
-        return fmt::format_to(ctx.out(), "{}", name);
-    }
-};
-
-namespace alternator {
-
-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);
-
-void validate_attr_name_length(std::string_view supplementary_context, size_t attr_name_length, bool is_key, std::string_view error_msg_prefix = {});
-
-
-} /* namespace alternator */

alternator/expressions_types.hh

@@ -1,258 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#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::parsed 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;
-    // It is useful to limit the depth of a user-specified path, because is
-    // allows us to use recursive algorithms without worrying about recursion
-    // depth. DynamoDB officially limits the length of paths to 32 components
-    // (including the root) so let's use the same limit.
-    static constexpr unsigned depth_limit = 32;
-    void check_depth_limit();
-public:
-    void set_root(std::string root) {
-        _root = std::move(root);
-    }
-    void add_index(unsigned i) {
-        _operators.emplace_back(i);
-        check_depth_limit();
-    }
-    void add_dot(std::string(name)) {
-        _operators.emplace_back(std::move(name));
-        check_depth_limit();
-    }
-    const std::string& root() const {
-        return _root;
-    }
-    bool has_operators() const {
-        return !_operators.empty();
-    }
-    const std::vector<std::variant<std::string, unsigned>>& operators() const {
-        return _operators;
-    }
-    std::vector<std::variant<std::string, unsigned>>& operators() {
-        return _operators;
-    }
-};
-
-// 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.).
-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
-
-template <> struct fmt::formatter<alternator::parsed::path> : fmt::formatter<string_view> {
-    auto format(const alternator::parsed::path&, fmt::format_context& ctx) const -> decltype(ctx.out());
-};

alternator/extract_from_attrs.hh

@@ -1,73 +0,0 @@
-/*
- * Copyright 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <string>
-#include <string_view>
-
-#include "utils/rjson.hh"
-#include "serialization.hh"
-#include "schema/column_computation.hh"
-#include "db/view/regular_column_transformation.hh"
-
-namespace alternator {
-
-// An implementation of a "column_computation" which extracts a specific
-// non-key attribute from the big map (":attrs") of all non-key attributes,
-// and deserializes it if it has the desired type. GSI will use this computed
-// column as a materialized-view key when the view key attribute isn't a
-// full-fledged CQL column but rather stored in ":attrs".
-class extract_from_attrs_column_computation : public regular_column_transformation {
-    // The name of the CQL column name holding the attribute map. It is a
-    // constant defined in executor.cc (as ":attrs"), so doesn't need
-    // to be specified when constructing the column computation.
-    static const bytes MAP_NAME;
-    // The top-level attribute name to extract from the ":attrs" map.
-    bytes _attr_name;
-    // The type we expect for the value stored in the attribute. If the type
-    // matches the expected type, it is decoded from the serialized format
-    // we store in the map's values) into the raw CQL type value that we use
-    // for keys, and returned by compute_value(). Only the types "S" (string),
-    // "B" (bytes) and "N" (number) are allowed as keys in DynamoDB, and
-    // therefore in desired_type.
-    alternator_type _desired_type;
-public:
-    virtual column_computation_ptr clone() const override;
-    // TYPE_NAME is a unique string that distinguishes this class from other
-    // column_computation subclasses. column_computation::deserialize() will
-    // construct an object of this subclass if it sees a "type" TYPE_NAME.
-    static inline const std::string TYPE_NAME = "alternator_extract_from_attrs";
-    // Serialize the *definition* of this column computation into a JSON
-    // string with a unique "type" string - TYPE_NAME - which then causes
-    // column_computation::deserialize() to create an object from this class.
-    virtual bytes serialize() const override;
-    // Construct this object based on the previous output of serialize().
-    // Calls on_internal_error() if the string doesn't match the output format
-    // of serialize(). "type" is not checked column_computation::deserialize()
-    // won't call this constructor if "type" doesn't match.
-    extract_from_attrs_column_computation(const rjson::value &v);
-    extract_from_attrs_column_computation(bytes_view attr_name, alternator_type desired_type)
-        : _attr_name(attr_name), _desired_type(desired_type)
-        {}
-    // Implement regular_column_transformation's compute_value() that
-    // accepts the full row:
-    result compute_value(const schema& schema, const partition_key& key,
-        const db::view::clustering_or_static_row& row) const override;
-    // But do not implement column_computation's compute_value() that
-    // accepts only a partition key - that's not enough so our implementation
-    // of this function does on_internal_error().
-    bytes compute_value(const schema& schema, const partition_key& key) const override;
-    // This computed column does depend on a non-primary key column, so
-    // its result may change in the update and we need to compute it
-    // before and after the update.
-    virtual bool depends_on_non_primary_key_column() const override {
-        return true;
-    }
-};
-} // namespace alternator

alternator/parsed_expression_cache.cc

@@ -1,109 +0,0 @@
-/*
- * Copyright 2025-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "expressions.hh"
-#include "utils/log.hh"
-
-#include "utils/lru_string_map.hh"
-#include <variant>
-
-static logging::logger logger_("parsed-expression-cache");
-
-namespace alternator::parsed {
-
-struct expression_cache_impl {
-    stats& _stats;
-
-    using cached_expressions_types = std::variant<
-        update_expression,
-        condition_expression,
-        std::vector<path>
-    >;
-    sized_lru_string_map<cached_expressions_types> _cached_entries;
-    utils::observable<uint32_t>::observer _max_cache_entries_observer;
-
-    expression_cache_impl(expression_cache::config cfg, stats& stats);
-
-    // to define the specialized return type of `get_or_create()`
-    template <typename Func, typename... Args>
-    using ParseResult = std::invoke_result_t<Func, std::string_view, Args...>;
-
-    // Caching layer for parsed expressions
-    // The expression type is determined by the type of the parsing function passed as a parameter,
-    // and the return type is exactly the same as the return type of this parsing function.
-    // StatsType is used only to update appropriate statistics - currently it is aligned with the expression type,
-    // but it could be extended in the future if needed, e.g. split per operation.
-    template <stats::expression_types StatsType, typename Func, typename... Args>
-    ParseResult<Func, Args...> get_or_create(std::string_view query, Func&& parse_func, Args&&... other_args) {
-        if (_cached_entries.disabled()) {
-            return parse_func(query, std::forward<Args>(other_args)...);
-        }
-        if (!_cached_entries.sanity_check()) {
-            _stats.expression_cache.requests[StatsType].misses++;
-            return parse_func(query, std::forward<Args>(other_args)...);
-        }
-        auto value = _cached_entries.find(query);
-        if (value) {
-            logger_.trace("Cache hit for query: {}", query);
-            _stats.expression_cache.requests[StatsType].hits++;
-            try {
-                return std::get<ParseResult<Func, Args...>>(value->get());
-            } catch (const std::bad_variant_access&) {
-                // User can reach this code, by sending the same query string as a different expression type.
-                // In practice valid queries are different enough to not collide.
-                // Entries in cache are only valid queries.
-                // This request will fail at parsing below.
-                // If, by any chance this is a valid query, it will be updated below with the new value.
-                logger_.trace("Cache hit for '{}', but type mismatch.", query);
-                _stats.expression_cache.requests[StatsType].hits--;
-            }
-        } else {
-            logger_.trace("Cache miss for query: {}", query);
-        }
-        ParseResult<Func, Args...> expr = parse_func(query, std::forward<Args>(other_args)...);
-        // Invalid query will throw here ^
-
-        _stats.expression_cache.requests[StatsType].misses++;
-        if (value) [[unlikely]] {
-            value->get() = cached_expressions_types{expr};
-        } else {
-            _cached_entries.insert(query, cached_expressions_types{expr});
-        }
-        return expr;
-    }
-};
-
-expression_cache_impl::expression_cache_impl(expression_cache::config cfg, stats& stats) : 
-    _stats(stats), _cached_entries(logger_, _stats.expression_cache.evictions),
-    _max_cache_entries_observer(cfg.max_cache_entries.observe([this] (uint32_t max_value) {
-        _cached_entries.set_max_size(max_value);
-    })) {
-    _cached_entries.set_max_size(cfg.max_cache_entries());
-}
-
-expression_cache::expression_cache(expression_cache::config cfg, stats& stats) : 
-    _impl(std::make_unique<expression_cache_impl>(std::move(cfg), stats)) {
-}
-expression_cache::~expression_cache() = default;
-future<> expression_cache::stop() {
-    return _impl->_cached_entries.stop();
-}
-
-update_expression expression_cache::parse_update_expression(std::string_view query) {
-    return _impl->get_or_create<stats::expression_types::UPDATE_EXPRESSION>(query, alternator::parse_update_expression);
-}
-
-std::vector<path> expression_cache::parse_projection_expression(std::string_view query) {
-    return _impl->get_or_create<stats::expression_types::PROJECTION_EXPRESSION>(query, alternator::parse_projection_expression);
-}
-
-condition_expression expression_cache::parse_condition_expression(std::string_view query, const char* caller) {
-    return _impl->get_or_create<stats::expression_types::CONDITION_EXPRESSION>(query, alternator::parse_condition_expression, caller);
-}
-
-} // namespace alternator::parsed

alternator/rmw_operation.hh

@@ -1,135 +0,0 @@
-/*
- * Copyright 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "cdc/cdc_options.hh"
-#include "cdc/log.hh"
-#include "seastarx.hh"
-#include "service/paxos/cas_request.hh"
-#include "service/cas_shard.hh"
-#include "utils/rjson.hh"
-#include "consumed_capacity.hh"
-#include "executor.hh"
-#include "tracing/trace_state.hh"
-#include "keys/keys.hh"
-
-namespace alternator {
-
-class consumed_capacity;
-
-// 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 require 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;
-
-    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;
-    mutable wcu_consumed_capacity_counter _consumed_capacity;
-    // 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;
-    enum class returnvalues_on_condition_check_failure {
-        NONE, ALL_OLD
-    } _returnvalues_on_condition_check_failure;
-    static returnvalues parse_returnvalues(const rjson::value& request);
-    static returnvalues_on_condition_check_failure parse_returnvalues_on_condition_check_failure(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.
-    // Additionally when _returnvalues_on_condition_check_failure is ALL_OLD
-    // then condition check failure will also result in storing values here.
-    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, cdc::per_request_options& cdc_opts) 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, cdc::per_request_options& cdc_opts) override;
-    virtual ~rmw_operation() = default;
-    const wcu_consumed_capacity_counter& consumed_capacity() const noexcept { return _consumed_capacity; }
-    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,
-            std::optional<service::cas_shard> cas_shard,
-            service::client_state& client_state,
-            tracing::trace_state_ptr trace_state,
-            service_permit permit,
-            bool needs_read_before_write,
-            stats& global_stats,
-            stats& per_table_stats,
-            uint64_t& wcu_total);
-    std::optional<service::cas_shard> shard_for_execute(bool needs_read_before_write);
-
-private:
-    inline bool should_fill_preimage() const { return _schema->cdc_options().enabled(); }
-};
-
-} // namespace alternator

alternator/serialization.cc

@@ -1,614 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
-#include "utils/log.hh"
-#include "serialization.hh"
-#include "error.hh"
-#include "types/concrete_types.hh"
-#include "types/json_utils.hh"
-#include "mutation/position_in_partition.hh"
-
-static logging::logger slogger("alternator-serialization");
-
-namespace alternator {
-
-bool is_alternator_keyspace(const sstring& ks_name);
-
-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;
-}
-
-// Get the magnitude and precision of a big_decimal - as these concepts are
-// defined by DynamoDB - to allow us to enforce limits on those as explained
-// in ssue #6794. The "magnitude" of 9e123 is 123 and of -9e-123 is -123,
-// the "precision" of 12.34e56 is the number of significant digits - 4.
-//
-// Unfortunately it turned out to be quite difficult to take a big_decimal and
-// calculate its magnitude and precision from its scale() and unscaled_value().
-// So in the following ugly implementation we calculate them from the string
-// representation instead. We assume the number was already parsed
-// successfully to a big_decimal to it follows its syntax rules.
-//
-// FIXME: rewrite this function to take a big_decimal, not a string.
-// Maybe a snippet like this can help:
-// boost::multiprecision::cpp_int digits = boost::multiprecision::log10(num.unscaled_value().convert_to<boost::multiprecision::mpf_float_50>()).convert_to<boost::multiprecision::cpp_int>() + 1;
-
-
-internal::magnitude_and_precision internal::get_magnitude_and_precision(std::string_view s) {
-    size_t e_or_end = s.find_first_of("eE");
-    std::string_view base = s.substr(0, e_or_end);
-    if (s[0]=='-' || s[0]=='+') {
-        base = base.substr(1);
-    }
-    int magnitude = 0;
-    int precision = 0;
-    size_t dot_or_end = base.find_first_of(".");
-    size_t nonzero = base.find_first_not_of("0");
-    if (dot_or_end != std::string_view::npos) {
-        if (nonzero == dot_or_end) {
-            // 0.000031 => magnitude = -5 (like 3.1e-5), precision = 2.
-            std::string_view fraction = base.substr(dot_or_end + 1);
-            size_t nonzero2 = fraction.find_first_not_of("0");
-            if (nonzero2 != std::string_view::npos) {
-                magnitude = -nonzero2 - 1;
-                precision = fraction.size() - nonzero2;
-            }
-        } else {
-            // 000123.45678 => magnitude = 2, precision = 8.
-            magnitude = dot_or_end - nonzero - 1;
-            precision = base.size() - nonzero - 1;
-        }
-        // trailing zeros don't count to precision, e.g., precision
-        // of 1000.0, 1.0 or 1.0000 are just 1.
-        size_t last_significant = base.find_last_not_of(".0");
-        if (last_significant == std::string_view::npos) {
-            precision = 0;
-        } else if (last_significant < dot_or_end) {
-            // e.g., 1000.00 reduce 5 = 7 - (0+1) - 1 from precision
-            precision -= base.size() - last_significant - 2;
-        } else {
-            // e.g., 1235.60 reduce 5 = 7 - (5+1) from precision
-            precision -= base.size() - last_significant - 1;
-        }
-    } else if (nonzero == std::string_view::npos) {
-        // all-zero integer 000000
-        magnitude = 0;
-        precision = 0;
-    } else {
-        magnitude = base.size() - 1 - nonzero;
-        precision = base.size() - nonzero;
-        // trailing zeros don't count to precision, e.g., precision
-        // of 1000 is just 1.
-        size_t last_significant = base.find_last_not_of("0");
-        if (last_significant == std::string_view::npos) {
-            precision = 0;
-        } else {
-            // e.g., 1000 reduce 3 = 4 - (0+1)
-            precision -= base.size() - last_significant - 1;
-        }
-    }
-    if (precision && e_or_end != std::string_view::npos) {
-        std::string_view exponent = s.substr(e_or_end + 1);
-        if (exponent.size() > 4) {
-            // don't even bother atoi(), exponent is too large
-            magnitude = exponent[0]=='-' ? -9999 : 9999;
-        } else {
-            try {
-                magnitude += boost::lexical_cast<int32_t>(exponent);
-            } catch (...) {
-                magnitude = 9999;
-            }
-        }
-    }
-    return magnitude_and_precision {magnitude, precision};
-}
-
-// Parse a number read from user input, validating that it has a valid
-// numeric format and also in the allowed magnitude and precision ranges
-// (see issue #6794). Throws an api_error::validation if the validation
-// failed.
-static big_decimal parse_and_validate_number(std::string_view s) {
-    try {
-        big_decimal ret(s);
-        auto [magnitude, precision] = internal::get_magnitude_and_precision(s);
-        if (magnitude > 125) {
-            throw api_error::validation(fmt::format("Number overflow: {}. Attempting to store a number with magnitude larger than supported range.", s));
-        }
-        if (magnitude < -130) {
-            throw api_error::validation(fmt::format("Number underflow: {}. Attempting to store a number with magnitude lower than supported range.", s));
-        }
-        if (precision > 38) {
-            throw api_error::validation(fmt::format("Number too precise: {}. Attempting to store a number with more significant digits than supported.", s));
-        }
-        return ret;
-    } catch (const marshal_exception& e) {
-        throw api_error::validation(fmt::format("The parameter cannot be converted to a numeric value: {}", s));
-    }
-
-}
-
-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 {
-        // FIXME: it's difficult at this point to get information if value was provided
-        // in request or comes from the storage, for now we assume it's user's fault.
-        bo.write(*unwrap_bytes(v, true));
-    }
-    void operator()(const boolean_type_impl& t) const {
-        bo.write(boolean_type->decompose(v.GetBool()));
-    }
-    void operator()(const decimal_type_impl& t) const {
-        bo.write(decimal_type->decompose(parse_and_validate_number(rjson::to_string_view(v))));
-    }
-    // default
-    void operator()(const abstract_type& t) const {
-        bo.write(from_json_object(t, v));
-    }
-};
-
-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::add_with_string_name(deserialized, type_ident, rjson::from_string(s));
-    }
-    void operator()(const string_type_impl& t) {
-        rjson::add_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::add_with_string_name(deserialized, type_ident, rjson::from_string(b64));
-    }
-    // default
-    void operator()(const abstract_type& t) const {
-        rjson::add_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;
-}
-
-// This function takes a bytes_view created earlier by serialize_item(), and
-// if has the type "expected_type", the function returns the value as a
-// raw Scylla type. If the type doesn't match, returns an unset optional.
-// This function only supports the key types S (string), B (bytes) and N
-// (number) - serialize_item() serializes those types as a single-byte type
-// followed by the serialized raw Scylla type, so all this function needs to
-// do is to remove the first byte. This makes this function much more
-// efficient than deserialize_item() above because it avoids transformation
-// to/from JSON.
-std::optional<bytes> serialized_value_if_type(bytes_view bv, alternator_type expected_type) {
-    if (bv.empty() || alternator_type(bv[0]) != expected_type) {
-        return std::nullopt;
-    }
-    // Currently, serialize_item() for types in alternator_type (notably S, B
-    // and N) are nothing more than Scylla's raw format for these types
-    // preceded by a type byte. So we just need to skip that byte and we are
-    // left by exactly what we need to return.
-    bv.remove_prefix(1);
-    return bytes(bv);
-}
-
-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;
-}
-
-std::optional<bytes> try_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) {
-        return std::nullopt;
-    }
-    return get_key_from_typed_value(*key_typed_value, column);
-}
-
-bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
-    auto value = try_get_key_column_value(item, column);
-    if (!value) {
-        throw api_error::validation(fmt::format("Key column {} not found", column.name_as_text()));
-    }
-    return std::move(*value);
-}
-
-// Parses the JSON encoding for a key value, which is a map with a single
-// entry whose key is the type and the value is the encoded value.
-// If this type does not match the desired "type_str", an api_error::validation
-// error is thrown (the "name" parameter is the name of the column which will
-// mentioned in the exception message).
-// If the type does match, a reference to the encoded value is returned.
-static const rjson::value& get_typed_value(const rjson::value& key_typed_value, std::string_view type_str, std::string_view name, std::string_view value_name) {
-    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1) {
-        throw api_error::validation(
-                fmt::format("Malformed value object for {} {}: {}",
-                        value_name, name, key_typed_value));
-    }
-
-    auto it = key_typed_value.MemberBegin();
-    if (rjson::to_string_view(it->name) != type_str) {
-        throw api_error::validation(
-                fmt::format("Type mismatch: expected type {} for {} {}, got type {}",
-                        type_str, value_name, name, it->name));
-    }
-    // We assume this function is called just for key types (S, B, N), and
-    // all of those always have a string value in the JSON.
-    if (!it->value.IsString()) {
-        throw api_error::validation(
-            fmt::format("Malformed value object for {} {}: {}",
-                    value_name, name, key_typed_value));
-
-    }
-    return it->value;
-}
-
-// 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) {
-    auto& value = get_typed_value(key_typed_value, type_to_string(column.type), column.name_as_text(), "key column");
-    std::string_view value_view = rjson::to_string_view(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) {
-        // FIXME: it's difficult at this point to get information if value was provided
-        // in request or comes from the storage, for now we assume it's user's fault.
-        return *unwrap_bytes(value, true);
-    } else if (column.type == decimal_type) {
-        return decimal_type->decompose(parse_and_validate_number(rjson::to_string_view(value)));
-    } else {
-        return column.type->from_string(value_view);
-    }
-
-}
-
-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(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;
-    // Note: it's possible to get more than one clustering column here, as
-    // Alternator can be used to read scylla internal tables.
-    for (const column_definition& cdef : schema->clustering_key_columns()) {
-        auto raw_value = get_key_column_value(item,  cdef);
-        raw_ck.push_back(std::move(raw_value));
-    }
-
-    return clustering_key::from_exploded(raw_ck);
-}
-
-clustering_key_prefix ck_prefix_from_json(const rjson::value& item, schema_ptr schema) {
-    if (schema->clustering_key_size() == 0) {
-        return clustering_key_prefix::make_empty();
-    }
-    std::vector<bytes> raw_ck;
-    for (const column_definition& cdef : schema->clustering_key_columns()) {
-        auto raw_value = try_get_key_column_value(item,  cdef);
-        if (!raw_value) {
-            break;
-        }
-        raw_ck.push_back(std::move(*raw_value));
-    }
-
-    return clustering_key_prefix::from_exploded(raw_ck);
-}
-
-position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema) {
-    const bool is_alternator_ks = is_alternator_keyspace(schema->ks_name());
-    if (is_alternator_ks) {
-        return position_in_partition::for_key(ck_from_json(item, schema));
-    }
-    
-    const auto region_item = rjson::find(item, scylla_paging_region);
-    const auto weight_item = rjson::find(item, scylla_paging_weight);
-    if (bool(region_item) != bool(weight_item)) {
-        throw api_error::validation("Malformed value object: region and weight has to be either both missing or both present");
-    }
-    bound_weight weight;
-    if (region_item) {
-        auto region_view = rjson::to_string_view(get_typed_value(*region_item, "S", scylla_paging_region, "key region"));
-        auto weight_view = rjson::to_string_view(get_typed_value(*weight_item, "N", scylla_paging_weight, "key weight"));
-        auto region = parse_partition_region(region_view);
-        if (weight_view == "-1") {
-            weight = bound_weight::before_all_prefixed;
-        } else if (weight_view == "0") {
-            weight = bound_weight::equal;
-        } else if (weight_view == "1") {
-            weight = bound_weight::after_all_prefixed;
-        } else {
-            throw std::runtime_error(fmt::format("Invalid value for weight: {}", weight_view));
-        }
-        return position_in_partition(region, weight, region == partition_region::clustered ? std::optional(ck_prefix_from_json(item, schema)) : std::nullopt);
-    }
-    auto ck = ck_from_json(item, schema);
-    if (ck.is_empty()) {
-        return position_in_partition::for_partition_start();
-    }
-    return position_in_partition::for_key(std::move(ck));
-}
-
-big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(fmt::format("{}: invalid number object", diagnostic));
-    }
-    auto it = v.MemberBegin();
-    if (it->name != "N") {
-        throw api_error::validation(fmt::format("{}: expected number, found type '{}'", diagnostic, it->name));
-    }
-    if (!it->value.IsString()) {
-        // We shouldn't reach here. Callers normally validate their input
-        // earlier with validate_value().
-        throw api_error::validation(fmt::format("{}: improperly formatted number constant", diagnostic));
-    }
-    big_decimal ret = parse_and_validate_number(rjson::to_string_view(it->value));
-    return ret;
-}
-
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return std::nullopt;
-    }
-    auto it = v.MemberBegin();
-    if (it->name != "N" || !it->value.IsString()) {
-        return std::nullopt;
-    }
-    try {
-        return parse_and_validate_number(rjson::to_string_view(it->value));
-    } catch (api_error&) {
-        return std::nullopt;
-    }
-}
-
-std::optional<bytes> unwrap_bytes(const rjson::value& value, bool from_query) {
-    try {
-        return rjson::base64_decode(value);
-    } catch (...) {
-        if (from_query) {
-            throw api_error::serialization(format("Invalid base64 data"));
-        }
-        return std::nullopt;
-    }
-}
-
-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 = rjson::to_string(it->name);
-    if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
-        return {std::move(it_key), 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();
-    sstring str_ret = (n1 + n2).to_string();
-    rjson::add(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();
-    sstring str_ret = (n1 - n2).to_string();
-    rjson::add(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(fmt::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::add_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(fmt::format("Set DELETE type mismatch: {} 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::add_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;
-}
-
-// 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.
-// Returns a null value if one of the arguments is not actually a list.
-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) {
-        return rjson::null_value();
-    }
-    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::add(ret, "L", std::move(cat));
-    return ret;
-}
-
-}

alternator/serialization.hh

@@ -1,106 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <string>
-#include <string_view>
-#include <optional>
-#include "types/types.hh"
-#include "schema/schema_fwd.hh"
-#include "keys/keys.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-
-class position_in_partition;
-
-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;
-};
-
-inline constexpr std::string_view scylla_paging_region(":scylla:paging:region");
-inline constexpr std::string_view scylla_paging_weight(":scylla:paging:weight");
-
-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::optional<bytes> serialized_value_if_type(bytes_view bv, alternator_type expected_type);
-
-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);
-position_in_partition pos_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);
-
-// try_unwrap_number is like unwrap_number, but returns an unset optional
-// when the given v does not encode a number.
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v);
-
-// unwrap_bytes decodes byte value, on decoding failure it either raises api_error::serialization
-// iff from_query is true or returns unset optional iff from_query is false.
-// Therefore it's safe to dereference returned optional when called with from_query equal true.
-std::optional<bytes> unwrap_bytes(const rjson::value& value, bool from_query);
-
-// 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);
-// 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.
-// Returns a null value if one of the arguments is not actually a list.
-rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2);
-
-namespace internal {
-struct magnitude_and_precision {
-    int magnitude;
-    int precision;
-};
-magnitude_and_precision get_magnitude_and_precision(std::string_view);
-}
-
-}

alternator/server.hh

@@ -1,120 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "alternator/executor.hh"
-#include "utils/scoped_item_list.hh"
-#include <seastar/core/future.hh>
-#include <seastar/core/condition-variable.hh>
-#include <seastar/http/httpd.hh>
-#include <seastar/net/tls.hh>
-#include <optional>
-#include "alternator/auth.hh"
-#include "service/qos/service_level_controller.hh"
-#include "utils/small_vector.hh"
-#include "utils/updateable_value.hh"
-#include <seastar/core/units.hh>
-
-struct client_data;
-
-namespace alternator {
-
-using chunked_content = rjson::chunked_content;
-
-class server : public peering_sharded_service<server> {
-    // The maximum size of a request body that Alternator will accept,
-    // in bytes. This is a safety measure to prevent Alternator from
-    // running out of memory when a client sends a very large request.
-    // DynamoDB also has the same limit set to 16 MB.
-    static constexpr size_t request_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<http::request>)>;
-    using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
-
-    httpd::http_server _http_server;
-    httpd::http_server _https_server;
-    executor& _executor;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-    auth::service& _auth_service;
-    qos::service_level_controller& _sl_controller;
-
-    key_cache _key_cache;
-    utils::updateable_value<bool> _enforce_authorization;
-    utils::updateable_value<bool> _warn_authorization;
-    utils::updateable_value<uint64_t> _max_users_query_size_in_trace_output;
-    utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
-    named_gate _pending_requests;
-    // In some places we will need a CQL updateable_timeout_config object even
-    // though it isn't really relevant for Alternator which defines its own
-    // timeouts separately. We can create this object only once.
-    updateable_timeout_config _timeout_config;
-    client_options_cache_type _connection_options_keys_and_values;
-
-    alternator_callbacks_map _callbacks;
-
-    semaphore* _memory_limiter;
-    utils::updateable_value<uint32_t> _max_concurrent_requests;
-
-    ::shared_ptr<seastar::tls::server_credentials> _credentials;
-
-    class json_parser {
-        static constexpr size_t yieldable_parsing_threshold = 16*KB;
-        chunked_content _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();
-        // Moving a chunked_content into parse() allows parse() to free each
-        // chunk as soon as it is parsed, so when chunks are relatively small,
-        // we don't need to store the sum of unparsed and parsed sizes.
-        future<rjson::value> parse(chunked_content&& content);
-        future<> stop();
-    };
-    json_parser _json_parser;
-
-    // The server maintains a list of ongoing requests, that are being handled
-    // by handle_api_request(). It uses this list in get_client_data(), which
-    // is called when reading the "system.clients" virtual table.
-    struct ongoing_request {
-        socket_address _client_address;
-        client_options_cache_entry_type _user_agent;
-        sstring _username;
-        scheduling_group _scheduling_group;
-        bool _is_https;
-        client_data make_client_data() const;
-    };
-    utils::scoped_item_list<ongoing_request> _ongoing_requests;
-
-public:
-    server(executor& executor, service::storage_proxy& proxy, gms::gossiper& gossiper, auth::service& service, qos::service_level_controller& sl_controller);
-
-    future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-            utils::updateable_value<bool> enforce_authorization, utils::updateable_value<bool> warn_authorization, utils::updateable_value<uint64_t> max_users_query_size_in_trace_output,
-            semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests);
-    future<> stop();
-    // get_client_data() is called (on each shard separately) when the virtual
-    // table "system.clients" is read. It is expected to generate a list of
-    // clients connected to this server (on this shard). This function is
-    // called by alternator::controller::get_client_data().
-    future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> get_client_data();
-private:
-    void set_routes(seastar::httpd::routes& r);
-    // If verification succeeds, returns the authenticated user's username
-    future<std::string> verify_signature(const seastar::http::request&, const chunked_content&);
-    future<executor::request_return_type> handle_api_request(std::unique_ptr<http::request> req);
-};
-
-}
-

alternator/stats.cc

@@ -1,210 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "stats.hh"
-#include "utils/histogram_metrics_helper.hh"
-#include <seastar/core/metrics.hh>
-#include "utils/labels.hh"
-
-namespace alternator {
-
-const char* ALTERNATOR_METRICS = "alternator";
-static seastar::metrics::histogram estimated_histogram_to_metrics(const utils::estimated_histogram& histogram) {
-    seastar::metrics::histogram res;
-    res.buckets.resize(histogram.bucket_offsets.size());
-    uint64_t cumulative_count = 0;
-    res.sample_count = histogram._count;
-    res.sample_sum = histogram._sample_sum;
-    for (size_t i = 0; i < res.buckets.size(); i++) {
-        auto& v = res.buckets[i];
-        v.upper_bound = histogram.bucket_offsets[i];
-        cumulative_count += histogram.buckets[i];
-        v.count = cumulative_count;
-    }
-    return res;
-}
-
-static seastar::metrics::label column_family_label("cf");
-static seastar::metrics::label keyspace_label("ks");
-
-
-static void register_metrics_with_optional_table(seastar::metrics::metric_groups& metrics, const stats& stats, const sstring& ks, const sstring& table) {
-
-    // Register the
-    seastar::metrics::label op("op");
-    bool has_table = table.length();
-    std::vector<seastar::metrics::label> aggregate_labels;
-    std::vector<seastar::metrics::label_instance> labels = {alternator_label};
-    sstring group_name = (has_table)? "alternator_table" : "alternator";
-    if (has_table) {
-        labels.push_back(column_family_label(table));
-        labels.push_back(keyspace_label(ks));
-        aggregate_labels.push_back(seastar::metrics::shard_label);
-    }
-    metrics.add_group(group_name, {
-#define OPERATION(name, CamelCaseName) \
-                seastar::metrics::make_total_operations("operation", stats.api_operations.name, \
-                        seastar::metrics::description("number of operations via Alternator API"), labels)(basic_level)(op(CamelCaseName)).aggregate(aggregate_labels).set_skip_when_empty(),
-#define OPERATION_LATENCY(name, CamelCaseName) \
-		metrics.add_group(group_name, { \
-                seastar::metrics::make_histogram("op_latency", \
-                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), labels, [&stats]{return to_metrics_histogram(stats.api_operations.name.histogram());})(op(CamelCaseName))(basic_level).aggregate({seastar::metrics::shard_label}).set_skip_when_empty()}); \
-            if (!has_table) {\
-            	metrics.add_group("alternator", { \
-				seastar::metrics::make_summary("op_latency_summary", \
-						                        seastar::metrics::description("Latency summary of an operation via Alternator API"), [&stats]{return to_metrics_summary(stats.api_operations.name.summary());})(op(CamelCaseName))(basic_level)(alternator_label).set_skip_when_empty()}); \
-            }
-
-            OPERATION(batch_get_item, "BatchGetItem")
-            OPERATION(batch_write_item, "BatchWriteItem")
-            OPERATION(create_backup, "CreateBackup")
-            OPERATION(create_global_table, "CreateGlobalTable")
-            OPERATION(delete_backup, "DeleteBackup")
-            OPERATION(delete_item, "DeleteItem")
-            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(list_streams, "ListStreams")
-            OPERATION(describe_stream, "DescribeStream")
-            OPERATION(get_shard_iterator, "GetShardIterator")
-            OPERATION(get_records, "GetRecords")
-    });
-    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_LATENCY(batch_write_item_latency, "BatchWriteItem")
-    OPERATION_LATENCY(batch_get_item_latency, "BatchGetItem")
-    OPERATION_LATENCY(get_records_latency, "GetRecords")
-    if (!has_table) {
-        // Create and delete operations are not applicable to a per-table metrics
-        // only register it for the global metrics
-        metrics.add_group("alternator", {
-            OPERATION(create_table, "CreateTable")
-            OPERATION(delete_table, "DeleteTable")
-
-        });
-    }
-    metrics.add_group(group_name, {
-            seastar::metrics::make_total_operations("unsupported_operations", stats.unsupported_operations,
-                    seastar::metrics::description("number of unsupported operations via Alternator API"), labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("total_operations", stats.total_operations,
-                    seastar::metrics::description("number of total operations via Alternator API"), labels)(basic_level).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("reads_before_write", stats.reads_before_write,
-                    seastar::metrics::description("number of performed read-before-write operations"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("write_using_lwt", stats.write_using_lwt,
-                    seastar::metrics::description("number of writes that used LWT"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("shard_bounce_for_lwt", stats.shard_bounce_for_lwt,
-                    seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("requests_blocked_memory", stats.requests_blocked_memory,
-                    seastar::metrics::description("Counts a number of requests blocked due to memory pressure."), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("requests_shed", stats.requests_shed,
-                    seastar::metrics::description("Counts a number of requests shed due to overload."), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("filtered_rows_read_total", stats.cql_stats.filtered_rows_read_total,
-                    seastar::metrics::description("number of rows read during filtering operations"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("filtered_rows_matched_total", stats.cql_stats.filtered_rows_matched_total,
-                    seastar::metrics::description("number of rows read and matched during filtering operations"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("rcu_total", [&stats]{return 0.5 * stats.rcu_half_units_total;},
-                    seastar::metrics::description("total number of consumed read units"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("wcu_total", stats.wcu_total[stats::wcu_types::PUT_ITEM],
-                    seastar::metrics::description("total number of consumed write units"), labels)(op("PutItem")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("wcu_total", stats.wcu_total[stats::wcu_types::DELETE_ITEM],
-                    seastar::metrics::description("total number of consumed write units"), labels)(op("DeleteItem")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("wcu_total", stats.wcu_total[stats::wcu_types::UPDATE_ITEM],
-                    seastar::metrics::description("total number of consumed write units"), labels)(op("UpdateItem")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("wcu_total", stats.wcu_total[stats::wcu_types::INDEX],
-                    seastar::metrics::description("total number of consumed write units"), labels)(op("Index")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("filtered_rows_dropped_total", [&stats] { return stats.cql_stats.filtered_rows_read_total - stats.cql_stats.filtered_rows_matched_total; },
-                    seastar::metrics::description("number of rows read and dropped during filtering operations"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("batch_item_count", seastar::metrics::description("The total number of items processed across all batches"), labels,
-                    stats.api_operations.batch_write_item_batch_total)(op("BatchWriteItem")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_counter("batch_item_count", seastar::metrics::description("The total number of items processed across all batches"), labels,
-                    stats.api_operations.batch_get_item_batch_total)(op("BatchGetItem")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_histogram("batch_item_count_histogram", seastar::metrics::description("Histogram of the number of items in a batch request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.api_operations.batch_get_item_histogram);})(op("BatchGetItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("batch_item_count_histogram", seastar::metrics::description("Histogram of the number of items in a batch request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.api_operations.batch_write_item_histogram);})(op("BatchWriteItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.get_item_op_size_kb);})(op("GetItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.put_item_op_size_kb);})(op("PutItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.delete_item_op_size_kb);})(op("DeleteItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.update_item_op_size_kb);})(op("UpdateItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.batch_get_item_op_size_kb);})(op("BatchGetItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_histogram("operation_size_kb", seastar::metrics::description("Histogram of item sizes involved in a request"), labels,
-                    [&stats]{ return estimated_histogram_to_metrics(stats.operation_sizes.batch_write_item_op_size_kb);})(op("BatchWriteItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-    });
-
-    seastar::metrics::label expression_label("expression");
-    metrics.add_group(group_name, {
-            seastar::metrics::make_total_operations("expression_cache_evictions", stats.expression_cache.evictions,
-                    seastar::metrics::description("Counts number of entries evicted from expressions cache"), labels).aggregate(aggregate_labels).set_skip_when_empty(),
-
-            seastar::metrics::make_total_operations("expression_cache_hits", stats.expression_cache.requests[stats::expression_types::UPDATE_EXPRESSION].hits,
-                    seastar::metrics::description("Counts number of hits of cached expressions"), labels)(expression_label("UpdateExpression")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("expression_cache_misses", stats.expression_cache.requests[stats::expression_types::UPDATE_EXPRESSION].misses,
-                    seastar::metrics::description("Counts number of misses of cached expressions"), labels)(expression_label("UpdateExpression")).aggregate(aggregate_labels).set_skip_when_empty(),
-            
-            seastar::metrics::make_total_operations("expression_cache_hits", stats.expression_cache.requests[stats::expression_types::CONDITION_EXPRESSION].hits,
-                    seastar::metrics::description("Counts number of hits of cached expressions"), labels)(expression_label("ConditionExpression")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("expression_cache_misses", stats.expression_cache.requests[stats::expression_types::CONDITION_EXPRESSION].misses,
-                    seastar::metrics::description("Counts number of misses of cached expressions"), labels)(expression_label("ConditionExpression")).aggregate(aggregate_labels).set_skip_when_empty(),
-
-            seastar::metrics::make_total_operations("expression_cache_hits", stats.expression_cache.requests[stats::expression_types::PROJECTION_EXPRESSION].hits,
-                    seastar::metrics::description("Counts number of hits of cached expressions"), labels)(expression_label("ProjectionExpression")).aggregate(aggregate_labels).set_skip_when_empty(),
-            seastar::metrics::make_total_operations("expression_cache_misses", stats.expression_cache.requests[stats::expression_types::PROJECTION_EXPRESSION].misses,
-                    seastar::metrics::description("Counts number of misses of cached expressions"), labels)(expression_label("ProjectionExpression")).aggregate(aggregate_labels).set_skip_when_empty()
-    });
-
-    // Only register the following metrics for the global metrics, not per-table
-    if (!has_table) {
-        metrics.add_group("alternator", {
-            seastar::metrics::make_counter("authentication_failures", stats.authentication_failures,
-                seastar::metrics::description("total number of authentication failures"), labels).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-            seastar::metrics::make_counter("authorization_failures", stats.authorization_failures,
-                seastar::metrics::description("total number of authorization failures"), labels).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
-        });
-    }
-}
-
-void register_metrics(seastar::metrics::metric_groups& metrics, const stats& stats) {
-    register_metrics_with_optional_table(metrics, stats, "", "");
-}
-table_stats::table_stats(const sstring& ks, const sstring& table) {
-    _stats = make_lw_shared<stats>();
-    register_metrics_with_optional_table(_metrics, *_stats, ks, table);
-}
-}

alternator/stats.hh

@@ -1,170 +0,0 @@
-/*
- * Copyright 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <cstdint>
-
-#include <seastar/core/metrics_registration.hh>
-#include "utils/histogram.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:
-    // Count of DynamoDB API operations by types
-    struct {
-        uint64_t batch_get_item = 0;
-        uint64_t batch_write_item = 0;
-        uint64_t batch_get_item_batch_total = 0;
-        uint64_t batch_write_item_batch_total = 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::timed_rate_moving_average_summary_and_histogram put_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram get_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram delete_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram update_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram batch_write_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram batch_get_item_latency;
-        utils::timed_rate_moving_average_summary_and_histogram get_records_latency;
-
-        utils::estimated_histogram batch_get_item_histogram{22}; // a histogram that covers the range 1 - 100
-        utils::estimated_histogram batch_write_item_histogram{22}; // a histogram that covers the range 1 - 100
-    } api_operations;
-    // Operation size metrics
-    struct {
-        // Item size statistics collected per table and aggregated per node.
-        // Each histogram covers the range 0 - 446. Resolves #25143.
-        // A size is the retrieved item's size.
-        utils::estimated_histogram get_item_op_size_kb{30};
-        // A size is the maximum of the new item's size and the old item's size.
-        utils::estimated_histogram put_item_op_size_kb{30};
-        // A size is the deleted item's size. If the deleted item's size is
-        // unknown (i.e. read-before-write wasn't necessary and it wasn't
-        // forced by a configuration option), it won't be recorded on the
-        // histogram.
-        utils::estimated_histogram delete_item_op_size_kb{30};
-        // A size is the maximum of existing item's size and the estimated size
-        // of the update. This will be changed to the maximum of the existing item's
-        // size and the new item's size in a subsequent PR.
-        utils::estimated_histogram update_item_op_size_kb{30};
-
-        // A size is the sum of the sizes of all items per table. This means
-        // that a single BatchGetItem / BatchWriteItem updates the histogram
-        // for each table that it has items in.
-        // The sizes are the retrieved items' sizes grouped per table.
-        utils::estimated_histogram batch_get_item_op_size_kb{30};
-        // The sizes are the the written items' sizes grouped per table.
-        utils::estimated_histogram batch_write_item_op_size_kb{30};
-    } operation_sizes;
-    // Count of authentication and authorization failures, counted if either
-    // alternator_enforce_authorization or alternator_warn_authorization are
-    // set to true. If both are false, no authentication or authorization
-    // checks are performed, so failures are not recognized or counted.
-    // "authentication" failure means the request was not signed with a valid
-    // user and key combination. "authorization" failure means the request was
-    // authenticated to a valid user - but this user did not have permissions
-    // to perform the operation (considering RBAC settings and the user's
-    // superuser status).
-    uint64_t authentication_failures = 0;
-    uint64_t authorization_failures = 0;
-    // 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;
-    uint64_t requests_shed = 0;
-    uint64_t rcu_half_units_total = 0;
-    // wcu can results from put, update, delete and index
-    // Index related will be done on top of the operation it comes with
-    enum wcu_types {
-        PUT_ITEM,
-        UPDATE_ITEM,
-        DELETE_ITEM,
-        INDEX,
-        NUM_TYPES
-    };
-
-    uint64_t wcu_total[NUM_TYPES] = {0};
-    // CQL-derived stats
-    cql3::cql_stats cql_stats;
-
-    // Enumeration of expression types only for stats
-    // if needed it can be extended e.g. per operation 
-    enum expression_types {
-        UPDATE_EXPRESSION,
-        CONDITION_EXPRESSION,
-        PROJECTION_EXPRESSION,
-        NUM_EXPRESSION_TYPES
-    };
-    struct {
-        struct {
-            uint64_t hits = 0;
-            uint64_t misses = 0;
-        } requests[NUM_EXPRESSION_TYPES];
-        uint64_t evictions = 0;
-    } expression_cache;
-};
-
-struct table_stats {
-    table_stats(const sstring& ks, const sstring& table);
-    seastar::metrics::metric_groups _metrics;
-    lw_shared_ptr<stats> _stats;
-};
-void register_metrics(seastar::metrics::metric_groups& metrics, const stats& stats);
-
-inline uint64_t bytes_to_kb_ceil(uint64_t bytes) {
-    return (bytes + 1023) / 1024;
-}
-
-}

alternator/ttl.cc

@@ -1,917 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include <chrono>
-#include <cstdint>
-#include <exception>
-#include <optional>
-#include <seastar/core/sstring.hh>
-#include <seastar/core/coroutine.hh>
-#include <seastar/core/sleep.hh>
-#include <seastar/core/future.hh>
-#include <seastar/core/lowres_clock.hh>
-#include <seastar/coroutine/maybe_yield.hh>
-
-#include "cdc/log.hh"
-#include "exceptions/exceptions.hh"
-#include "gms/gossiper.hh"
-#include "gms/inet_address.hh"
-#include "inet_address_vectors.hh"
-#include "locator/abstract_replication_strategy.hh"
-#include "utils/log.hh"
-#include "gc_clock.hh"
-#include "replica/database.hh"
-#include "service/client_state.hh"
-#include "service_permit.hh"
-#include "mutation/timestamp.hh"
-#include "service/storage_proxy.hh"
-#include "service/pager/paging_state.hh"
-#include "service/pager/query_pagers.hh"
-#include "gms/feature_service.hh"
-#include "mutation/mutation.hh"
-#include "types/types.hh"
-#include "types/map.hh"
-#include "utils/assert.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/values.hh"
-#include "cql3/query_options.hh"
-#include "cql3/column_identifier.hh"
-#include "alternator/executor.hh"
-#include "alternator/controller.hh"
-#include "alternator/serialization.hh"
-#include "dht/sharder.hh"
-#include "db/config.hh"
-#include "db/tags/utils.hh"
-#include "utils/labels.hh"
-
-#include "ttl.hh"
-
-static logging::logger tlogger("alternator_ttl");
-
-namespace alternator {
-
-// We write the expiration-time attribute enabled on a table in a
-// tag TTL_TAG_KEY.
-// Currently, the *value* of this tag is simply the name of the attribute,
-// and the expiration scanner interprets it as an Alternator attribute name -
-// It can refer to a real column or if that doesn't exist, to a member of
-// the ":attrs" map column. Although this is designed for Alternator, it may
-// be good enough for CQL as well (there, the ":attrs" column won't exist).
-extern const sstring TTL_TAG_KEY;
-
-future<executor::request_return_type> executor::update_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.update_time_to_live++;
-    if (!_proxy.features().alternator_ttl) {
-        co_return api_error::unknown_operation("UpdateTimeToLive not yet supported. Experimental support is available if the 'alternator-ttl' experimental feature is enabled on all nodes.");
-    }
-
-    schema_ptr schema = get_table(_proxy, request);
-    rjson::value* spec = rjson::find(request, "TimeToLiveSpecification");
-    if (!spec || !spec->IsObject()) {
-        co_return api_error::validation("UpdateTimeToLive missing mandatory TimeToLiveSpecification");
-    }
-    const rjson::value* v = rjson::find(*spec, "Enabled");
-    if (!v || !v->IsBool()) {
-        co_return api_error::validation("UpdateTimeToLive requires boolean Enabled");
-    }
-    bool enabled = v->GetBool();
-    v = rjson::find(*spec, "AttributeName");
-    if (!v || !v->IsString()) {
-        co_return api_error::validation("UpdateTimeToLive requires string AttributeName");
-    }
-    // Although the DynamoDB documentation specifies that attribute names
-    // should be between 1 and 64K bytes, in practice, it only allows
-    // between 1 and 255 bytes. There are no other limitations on which
-    // characters are allowed in the name.
-    if (v->GetStringLength() < 1 || v->GetStringLength() > 255) {
-        co_return api_error::validation("The length of AttributeName must be between 1 and 255");
-    }
-    sstring attribute_name = rjson::to_sstring(*v);
-
-    co_await verify_permission(_enforce_authorization, _warn_authorization, client_state, schema, auth::permission::ALTER, _stats);
-    co_await db::modify_tags(_mm, schema->ks_name(), schema->cf_name(), [&](std::map<sstring, sstring>& tags_map) {
-        if (enabled) {
-            if (tags_map.contains(TTL_TAG_KEY)) {
-                throw api_error::validation("TTL is already enabled");
-            }
-            tags_map[TTL_TAG_KEY] = attribute_name;
-        } else {
-            auto i = tags_map.find(TTL_TAG_KEY);
-            if (i == tags_map.end()) {
-                throw api_error::validation("TTL is already disabled");
-            } else if (i->second != attribute_name) {
-                throw api_error::validation(format(
-                    "Requested to disable TTL on attribute {}, but a different attribute {} is enabled.",
-                    attribute_name, i->second));
-            }
-            tags_map.erase(TTL_TAG_KEY);
-        }
-    });
-
-    // Prepare the response, which contains a TimeToLiveSpecification
-    // basically identical to the request's
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveSpecification", std::move(*spec));
-    co_return rjson::print(std::move(response));
-}
-
-future<executor::request_return_type> executor::describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.describe_time_to_live++;
-    schema_ptr schema = get_table(_proxy, request);
-    std::map<sstring, sstring> tags_map = get_tags_of_table_or_throw(schema);
-    rjson::value desc = rjson::empty_object();
-    auto i = tags_map.find(TTL_TAG_KEY);
-    if (i == tags_map.end()) {
-        rjson::add(desc, "TimeToLiveStatus", "DISABLED");
-    } else {
-        rjson::add(desc, "TimeToLiveStatus", "ENABLED");
-        rjson::add(desc, "AttributeName", rjson::from_string(i->second));
-    }
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveDescription", std::move(desc));
-    co_return rjson::print(std::move(response));
-}
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLive request.
-//
-// Here is a brief overview of how the expiration service works:
-//
-// An expiration thread on each shard periodically scans the items (i.e.,
-// rows) owned by this shard, looking for items whose chosen expiration-time
-// attribute indicates they are expired, and deletes those items.
-// The expiration-time "attribute" can be either an actual Scylla column
-// (must be numeric) or an Alternator "attribute" - i.e., an element in
-// the ATTRS_COLUMN_NAME map<utf8,bytes> column where the numeric expiration
-// time is encoded in DynamoDB's JSON encoding inside the bytes value.
-// To avoid scanning the same items RF times in RF replicas, only one node is
-// responsible for scanning a token range at a time. Normally, this is the
-// node owning this range as a "primary range" (the first node in the ring
-// with this range), but when this node is down, the secondary owner (the
-// second in the ring) may take over.
-// An expiration thread is responsible for all tables which need expiration
-// scans. Currently, the different tables are scanned sequentially (not in
-// parallel).
-// The expiration thread scans item using CL=QUORUM to ensures that it reads
-// a consistent expiration-time attribute. This means that the items are read
-// locally and in addition QUORUM-1 additional nodes (one additional node
-// when RF=3) need to read the data and send digests.
-// When the expiration thread decides that an item has expired and wants
-// to delete it, it does it using a CL=QUORUM write. This allows this
-// deletion to be visible for consistent (quorum) reads. The deletion,
-// like user deletions, will also appear on the CDC log and therefore
-// Alternator Streams if enabled - currently as ordinary deletes (the
-// userIdentity flag is currently missing this is issue #11523).
-expiration_service::expiration_service(data_dictionary::database db, service::storage_proxy& proxy, gms::gossiper& g)
-        : _db(db)
-        , _proxy(proxy)
-        , _gossiper(g)
-{
-}
-
-// Convert the big_decimal used to represent expiration time to an integer.
-// Any fractional part is dropped. If the number is negative or invalid,
-// 0 is returned, and if it's too high, the maximum unsigned long is returned.
-static unsigned long bigdecimal_to_ul(const big_decimal& bd) {
-    // The big_decimal format has an integer mantissa of arbitrary length
-    // "unscaled_value" and then a (power of 10) exponent "scale".
-    if (bd.unscaled_value() <= 0) {
-        return 0;
-    }
-    if (bd.scale() == 0) {
-        // The fast path, when the expiration time is an integer, scale==0.
-        return static_cast<unsigned long>(bd.unscaled_value());
-    }
-    // Because the mantissa can be of arbitrary length, we work on it
-    // as a string. TODO: find a less ugly algorithm.
-    auto str = bd.unscaled_value().str();
-    if (bd.scale() > 0) {
-        int len = str.length();
-        if (len < bd.scale()) {
-            return 0;
-        }
-        str = str.substr(0, len-bd.scale());
-    } else {
-        if (bd.scale() < -20) {
-            return std::numeric_limits<unsigned long>::max();
-        }
-        for (int i = 0; i < -bd.scale(); i++) {
-            str.push_back('0');
-        }
-    }
-    // strtoul() returns ULONG_MAX if the number is too large, or 0 if not
-    // a number.
-    return strtoul(str.c_str(), nullptr, 10);
-}
-
-// The following is_expired() functions all check if an item with the given
-// expiration time has expired, according to the DynamoDB API rules.
-// The rules are:
-// 1. If the expiration time attribute's value is not a number type,
-//    the item is not expired.
-// 2. The expiration time is measured in seconds since the UNIX epoch.
-// 3. If the expiration time is more than 5 years in the past, it is assumed
-//    to be malformed and ignored - and the item does not expire.
-static bool is_expired(gc_clock::time_point expiration_time, gc_clock::time_point now) {
-    return expiration_time <= now &&
-           expiration_time > now - std::chrono::years(5);
-}
-
-static bool is_expired(const big_decimal& expiration_time, gc_clock::time_point now) {
-    unsigned long t = bigdecimal_to_ul(expiration_time);
-    // We assume - and the assumption turns out to be correct - that the
-    // epoch of gc_clock::time_point and the one used by the DynamoDB protocol
-    // are the same (the UNIX epoch in UTC). The resolution (seconds) is also
-    // the same.
-    return is_expired(gc_clock::time_point(gc_clock::duration(std::chrono::seconds(t))), now);
-}
-static bool is_expired(const rjson::value& expiration_time, gc_clock::time_point now) {
-    std::optional<big_decimal> n = try_unwrap_number(expiration_time);
-    return n && is_expired(*n, now);
-}
-
-// expire_item() expires an item - i.e., deletes it as appropriate for
-// expiration - with CL=QUORUM and (FIXME!) in a way Alternator Streams
-// understands it is an expiration event - not a user-initiated deletion.
-static future<> expire_item(service::storage_proxy& proxy,
-                            const service::query_state& qs,
-                            const std::vector<managed_bytes_opt>& row,
-                            schema_ptr schema,
-                            api::timestamp_type ts) {
-    // Prepare the row key to delete
-    // NOTICE: the order of columns is guaranteed by the fact that selection::wildcard
-    // is used, which indicates that columns appear in the order defined by
-    // schema::all_columns_in_select_order() - partition key columns goes first,
-    // immediately followed by clustering key columns
-    std::vector<bytes> exploded_pk;
-    const unsigned pk_size = schema->partition_key_size();
-    const unsigned ck_size = schema->clustering_key_size();
-    for (unsigned c = 0; c < pk_size; ++c) {
-        const auto& row_c = row[c];
-        if (!row_c) {
-            // This shouldn't happen - all key columns must have values.
-            // But if it ever happens, let's just *not* expire the item.
-            // FIXME: log or increment a metric if this happens.
-            return make_ready_future<>();
-        }
-        exploded_pk.push_back(to_bytes(*row_c));
-    }
-    auto pk = partition_key::from_exploded(exploded_pk);
-    mutation m(schema, pk);
-    // If there's no clustering key, a tombstone should be created directly
-    // on a partition, not on a clustering row - otherwise it will look like
-    // an open-ended range tombstone, which will crash on KA/LA sstable format.
-    // See issue #6035
-    if (ck_size == 0) {
-        m.partition().apply(tombstone(ts, gc_clock::now()));
-    } else {
-        std::vector<bytes> exploded_ck;
-        for (unsigned c = pk_size; c < pk_size + ck_size; ++c) {
-            const auto& row_c = row[c];
-            if (!row_c) {
-                // This shouldn't happen - all key columns must have values.
-                // But if it ever happens, let's just *not* expire the item.
-                // FIXME: log or increment a metric if this happens.
-                return make_ready_future<>();
-            }
-            exploded_ck.push_back(to_bytes(*row_c));
-        }
-        auto ck = clustering_key::from_exploded(exploded_ck);
-        m.partition().clustered_row(*schema, ck).apply(tombstone(ts, gc_clock::now()));
-    }
-    utils::chunked_vector<mutation> mutations;
-    mutations.push_back(std::move(m));
-    return proxy.mutate(std::move(mutations),
-        db::consistency_level::LOCAL_QUORUM,
-        executor::default_timeout(), // FIXME - which timeout?
-        qs.get_trace_state(), qs.get_permit(),
-        db::allow_per_partition_rate_limit::no,
-        false,
-        cdc::per_request_options{
-            .is_system_originated = true,
-        }
-    );
-}
-
-static size_t random_offset(size_t min, size_t max) {
-    static thread_local std::default_random_engine re{std::random_device{}()};
-    std::uniform_int_distribution<size_t> dist(min, max);
-    return dist(re);
-}
-
-// Get a list of secondary token ranges for the given node, and the primary
-// node responsible for each of these token ranges.
-// A "secondary range" is a range of tokens where for each token, the second
-// node (in ring order) out of the RF replicas that hold this token is the
-// given node.
-// In the expiration scanner, we want to scan a secondary range but only if
-// this range's primary node is down. For this we need to return not just
-// a list of this node's secondary ranges - but also the primary owner of
-// each of those ranges.
-//
-// The function is to be used with vnodes only
-static future<std::vector<std::pair<dht::token_range, locator::host_id>>> get_secondary_ranges(
-        const locator::effective_replication_map* erm,
-        locator::host_id ep) {
-    const auto& tm = *erm->get_token_metadata_ptr();
-    const auto& sorted_tokens = tm.sorted_tokens();
-    std::vector<std::pair<dht::token_range, locator::host_id>> ret;
-    if (sorted_tokens.empty()) {
-        on_internal_error(tlogger, "Token metadata is empty");
-    }
-    auto prev_tok = sorted_tokens.back();
-    for (const auto& tok : sorted_tokens) {
-        co_await coroutine::maybe_yield();
-        // FIXME: pass is_vnode=true to get_natural_replicas since the token is in tm.sorted_tokens()
-        host_id_vector_replica_set eps = erm->get_natural_replicas(tok);
-        if (eps.size() <= 1 || eps[1] != ep) {
-            prev_tok = tok;
-            continue;
-        }
-        // Add the range (prev_tok, tok] to ret. However, if the range wraps
-        // around, split it to two non-wrapping ranges.
-        if (prev_tok < tok) {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        } else {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    std::nullopt},
-                eps[0]);
-            ret.emplace_back(
-                dht::token_range{
-                    std::nullopt,
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        }
-        prev_tok = tok;
-    }
-    co_return ret;
-}
-
-
-// A class for iterating over all the token ranges *owned* by this shard.
-// To avoid code duplication, it is a template with two distinct cases -
-// <primary> and <secondary>:
-//
-// In the <primary> case, we consider a token *owned* by this shard if:
-// 1. This node is a replica for this token.
-// 2. Moreover, this node is the *primary* replica of the token (i.e., the
-//    first replica in the ring).
-// 3. In this node, this shard is responsible for this token.
-// We will use this definition of which shard in the cluster owns which tokens
-// to split the expiration scanner's work between all the shards of the
-// system.
-//
-// In the <secondary> case, we consider a token *owned* by this shard if:
-// 1. This node is the *secondary* replica for this token (i.e., the second
-//    replica in the ring).
-// 2. The primary replica for this token is currently marked down.
-// 3. In this node, this shard is responsible for this token.
-// We use the <secondary> case to handle the possibility that some of the
-// nodes in the system are down. A dead node will not be expiring
-// the tokens owned by it, so we want the secondary owner to take over its
-// primary ranges.
-//
-// FIXME: need to decide how to choose primary ranges in multi-DC setup!
-// We could call get_primary_ranges_within_dc() below instead of get_primary_ranges().
-// NOTICE: Iteration currently starts from a random token range in order to improve
-// the chances of covering all ranges during a scan when restarts occur.
-// A more deterministic way would be to regularly persist the scanning state,
-// but that incurs overhead that we want to avoid if not needed.
-//
-// FIXME: Check if this algorithm is safe with tablet migration.
-// https://github.com/scylladb/scylladb/issues/16567
-
-// ranges_holder_primary holds just the primary ranges themselves
-class ranges_holder_primary {
-    dht::token_range_vector _token_ranges;
-public:
-    explicit ranges_holder_primary(dht::token_range_vector token_ranges) : _token_ranges(std::move(token_ranges)) {}
-    static future<ranges_holder_primary> make(const locator::vnode_effective_replication_map* erm, locator::host_id ep) {
-        co_return ranges_holder_primary(co_await erm->get_primary_ranges(ep));
-    }
-    std::size_t size() const { return _token_ranges.size(); }
-    const dht::token_range& operator[](std::size_t i) const {
-        return _token_ranges[i];
-    }
-    bool should_skip(std::size_t i) const {
-        return false;
-    }
-};
-// ranges_holder<secondary> holds the secondary token ranges plus each
-// range's primary owner, needed to implement should_skip().
-class ranges_holder_secondary {
-    std::vector<std::pair<dht::token_range, locator::host_id>> _token_ranges;
-    const gms::gossiper& _gossiper;
-public:
-    explicit ranges_holder_secondary(std::vector<std::pair<dht::token_range, locator::host_id>> token_ranges, const gms::gossiper& g)
-        : _token_ranges(std::move(token_ranges))
-        , _gossiper(g) {}
-    static future<ranges_holder_secondary> make(const locator::vnode_effective_replication_map* erm, locator::host_id ep, const gms::gossiper& g) {
-        co_return ranges_holder_secondary(co_await get_secondary_ranges(erm, ep), g);
-    }
-    std::size_t size() const { return _token_ranges.size(); }
-    const dht::token_range& operator[](std::size_t i) const {
-        return _token_ranges[i].first;
-    }
-    // range i should be skipped if its primary owner is alive.
-    bool should_skip(std::size_t i) const {
-        return _gossiper.is_alive(_token_ranges[i].second);
-    }
-};
-
-// The token_ranges_owned_by_this_shard class is only used for vnodes, where the vnodes give a partition range for the entire node
-// and such range still needs to be divided between the shards.
-template<class primary_or_secondary_t>
-class token_ranges_owned_by_this_shard {
-    schema_ptr _s;
-    locator::effective_replication_map_ptr _erm;
-    // _token_ranges will contain a list of token ranges owned by this node.
-    // We'll further need to split each such range to the pieces owned by
-    // the current shard, using _intersecter.
-    const primary_or_secondary_t _token_ranges;
-    // NOTICE: _range_idx is used modulo _token_ranges size when accessing
-    // the data to ensure that it doesn't go out of bounds
-    size_t _range_idx;
-    size_t _end_idx;
-    std::optional<dht::selective_token_range_sharder> _intersecter;
-public:
-    token_ranges_owned_by_this_shard(schema_ptr s, primary_or_secondary_t token_ranges)
-        :  _s(s)
-        , _erm(s->table().get_effective_replication_map())
-        , _token_ranges(std::move(token_ranges))
-        , _range_idx(random_offset(0, _token_ranges.size() - 1))
-        , _end_idx(_range_idx + _token_ranges.size())
-    {
-        tlogger.debug("Generating token ranges starting from base range {} of {}", _range_idx, _token_ranges.size());
-    }
-
-    // Return the next token_range owned by this shard, or nullopt when the
-    // iteration ends.
-    std::optional<dht::token_range> next() {
-        // We may need three or more iterations in the following loop if a
-        // vnode doesn't intersect with the given shard at all (such a small
-        // vnode is unlikely, but possible). The loop cannot be infinite
-        // because each iteration of the loop advances _range_idx.
-        for (;;) {
-            if (_intersecter) {
-                std::optional<dht::token_range> ret = _intersecter->next();
-                if (ret) {
-                    return ret;
-                }
-                // done with this range, go to next one
-                ++_range_idx;
-                _intersecter = std::nullopt;
-            }
-            if (_range_idx == _end_idx) {
-                return std::nullopt;
-            }
-            // If should_skip(), the range should be skipped. This happens for
-            // a secondary range whose primary owning node is still alive.
-            while (_token_ranges.should_skip(_range_idx % _token_ranges.size())) {
-                ++_range_idx;
-                if (_range_idx == _end_idx) {
-                    return std::nullopt;
-                }
-            }
-            _intersecter.emplace(_erm->get_sharder(*_s), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
-        }
-    }
-
-    // Same as next(), just return a partition_range instead of token_range
-    std::optional<dht::partition_range> next_partition_range() {
-        std::optional<dht::token_range> ret = next();
-        if (ret) {
-            return dht::to_partition_range(*ret);
-        } else {
-            return std::nullopt;
-        }
-    }
-};
-
-// Precomputed information needed to perform a scan on partition ranges
-struct scan_ranges_context {
-    schema_ptr s;
-    bytes column_name;
-    std::optional<std::string> member;
-
-    service::client_state internal_client_state;
-    ::shared_ptr<cql3::selection::selection> selection;
-    std::unique_ptr<service::query_state> query_state_ptr;
-    std::unique_ptr<cql3::query_options> query_options;
-    ::lw_shared_ptr<query::read_command> command;
-
-    scan_ranges_context(schema_ptr s, service::storage_proxy& proxy, bytes column_name, std::optional<std::string> member)
-        : s(s)
-        , column_name(column_name)
-        , member(member)
-        , internal_client_state(service::client_state::internal_tag())
-    {
-        // FIXME: don't read the entire items - read only parts of it.
-        // We must read the key columns (to be able to delete) and also
-        // the requested attribute. If the requested attribute is a map's
-        // member we may be forced to read the entire map - but it would
-        // be good if we can read only the single item of the map - it
-        // should be possible (and a must for issue #7751!).
-        lw_shared_ptr<service::pager::paging_state> paging_state = nullptr;
-        auto regular_columns =
-            s->regular_columns() | std::views::transform(&column_definition::id)
-            | std::ranges::to<query::column_id_vector>();
-        selection = cql3::selection::selection::wildcard(s);
-        query::partition_slice::option_set opts = selection->get_query_options();
-        opts.set<query::partition_slice::option::allow_short_read>();
-        // It is important that the scan bypass cache to avoid polluting it:
-        opts.set<query::partition_slice::option::bypass_cache>();
-        std::vector<query::clustering_range> ck_bounds{query::clustering_range::make_open_ended_both_sides()};
-        auto partition_slice = query::partition_slice(std::move(ck_bounds), {}, std::move(regular_columns), opts);
-        command = ::make_lw_shared<query::read_command>(s->id(), s->version(), partition_slice, proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
-        tracing::trace_state_ptr trace_state;
-        // NOTICE: empty_service_permit is used because the TTL service has fixed parallelism
-        query_state_ptr = std::make_unique<service::query_state>(internal_client_state, trace_state, empty_service_permit());
-        // FIXME: What should we do on multi-DC? Will we run the expiration on the same ranges on all
-        // DCs or only once for each range? If the latter, we need to change the CLs in the
-        // scanner and deleter.
-        db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
-        query_options = std::make_unique<cql3::query_options>(cl, std::vector<cql3::raw_value>{});
-        query_options = std::make_unique<cql3::query_options>(std::move(query_options), std::move(paging_state));
-    }
-};
-
-// Scan data in a list of token ranges in one table, looking for expired
-// items and deleting them.
-// Because of issue #9167, partition_ranges must have a single partition
-// range for this code to work correctly.
-static future<> scan_table_ranges(
-        service::storage_proxy& proxy,
-        const scan_ranges_context& scan_ctx,
-        dht::partition_range_vector&& partition_ranges,
-        abort_source& abort_source,
-        named_semaphore& page_sem,
-        expiration_service::stats& expiration_stats)
-{
-    const schema_ptr& s = scan_ctx.s;
-    SCYLLA_ASSERT (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
-    auto p = service::pager::query_pagers::pager(proxy, s, scan_ctx.selection, *scan_ctx.query_state_ptr,
-            *scan_ctx.query_options, scan_ctx.command, std::move(partition_ranges), nullptr);
-    while (!p->is_exhausted()) {
-        if (abort_source.abort_requested()) {
-            co_return;
-        }
-        auto units = co_await get_units(page_sem, 1);
-        // We don't need to limit page size in number of rows because there is
-        // a builtin limit of the page's size in bytes. Setting this limit to
-        // 1 is useful for debugging the paging code with moderate-size data.
-        uint32_t limit = std::numeric_limits<uint32_t>::max();
-        // Read a page, and if that times out, try again after a small sleep.
-        // If we didn't catch the timeout exception, it would cause the scan
-        // be aborted and only be restarted at the next scanning period.
-        // If we retry too many times, give up and restart the scan later.
-        std::unique_ptr<cql3::result_set> rs;
-        for (int retries=0; ; retries++) {
-            try {
-                // FIXME: which timeout?
-                rs = co_await p->fetch_page(limit, gc_clock::now(), executor::default_timeout());
-                break;
-            } catch(exceptions::read_timeout_exception&) {
-                tlogger.warn("expiration scanner read timed out, will retry: {}",
-                    std::current_exception());
-            }
-            // If we didn't break out of this loop, add a minimal sleep
-            if (retries >= 10) {
-                // Don't get stuck forever asking the same page, maybe there's
-                // a bug or a real problem in several replicas. Give up on
-                // this scan an retry the scan from a random position later,
-                // in the next scan period.
-                throw runtime_exception("scanner thread failed after too many timeouts for the same page");
-            }
-            co_await sleep_abortable(std::chrono::seconds(1), abort_source);
-        }
-        auto rows = rs->rows();
-        auto meta = rs->get_metadata().get_names();
-        std::optional<unsigned> expiration_column;
-        for (unsigned i = 0; i < meta.size(); i++) {
-            const cql3::column_specification& col = *meta[i];
-            if (col.name->name() == scan_ctx.column_name) {
-                expiration_column = i;
-                break;
-            }
-        }
-        if (!expiration_column) {
-            continue;
-        }
-        for (const auto& row : rows) {
-            const managed_bytes_opt& cell = row[*expiration_column];
-            if (!cell) {
-                continue;
-            }
-            auto v = meta[*expiration_column]->type->deserialize(*cell);
-            bool expired = false;
-            // FIXME: don't recalculate "now" all the time
-            auto now = gc_clock::now();
-            if (scan_ctx.member) {
-                // In this case, the expiration-time attribute we're
-                // looking for is a member in a map, saved serialized
-                // into bytes using Alternator's serialization (basically
-                // a JSON serialized into bytes)
-                // FIXME: is it possible to find a specific member of a map
-                // without iterating through it like we do here and compare
-                // the key?
-                for (const auto& entry : value_cast<map_type_impl::native_type>(v)) {
-                    std::string attr_name = value_cast<sstring>(entry.first);
-                    if (value_cast<sstring>(entry.first) == *scan_ctx.member) {
-                        bytes value = value_cast<bytes>(entry.second);
-                        rjson::value json = deserialize_item(value);
-                        expired = is_expired(json, now);
-                        break;
-                    }
-                }
-            } else {
-                // For a real column to contain an expiration time, it
-                // must be a numeric type.
-                // FIXME: Currently we only support decimal_type (which is
-                // what Alternator uses), but other numeric types can be
-                // supported as well to make this feature more useful in CQL.
-                // Note that kind::decimal is also checked above.
-                big_decimal n = value_cast<big_decimal>(v);
-                expired = is_expired(n, now);
-            }
-            if (expired) {
-                expiration_stats.items_deleted++;
-                // FIXME: maybe don't recalculate new_timestamp() all the time
-                // FIXME: if expire_item() throws on timeout, we need to retry it.
-                auto ts = api::new_timestamp();
-                co_await expire_item(proxy, *scan_ctx.query_state_ptr, row, s, ts);
-            }
-        }
-        // FIXME: once in a while, persist p->state(), so on reboot
-        // we don't start from scratch.
-    }
-}
-
-static future<> scan_tablet(locator::tablet_id tablet, service::storage_proxy& proxy, abort_source& abort_source, named_semaphore& page_sem,
-            expiration_service::stats& expiration_stats, const scan_ranges_context& scan_ctx, const locator::tablet_map& tablet_map) {
-    auto tablet_token_range = tablet_map.get_token_range(tablet);
-    dht::ring_position tablet_start(tablet_token_range.start()->value(), dht::ring_position::token_bound::start),
-                       tablet_end(tablet_token_range.end()->value(), dht::ring_position::token_bound::end);
-    auto partition_range = dht::partition_range::make(std::move(tablet_start), std::move(tablet_end));
-    // Note that because of issue #9167 we need to run a separate query on each partition range, and can't pass
-    // several of them into one partition_range_vector that is passed to scan_table_ranges().
-    return scan_table_ranges(proxy, scan_ctx, {partition_range}, abort_source, page_sem, expiration_stats);
-}
-
-// scan_table() scans, in one table, data "owned" by this shard, looking for
-// expired items and deleting them.
-// We consider each node to "own" its primary token ranges, i.e., the tokens
-// that this node is their first replica in the ring. Inside the node, each
-// shard "owns" subranges of the node's token ranges - according to the node's
-// sharding algorithm.
-// When a node goes down, the token ranges owned by it will not be scanned
-// and items in those token ranges will not expire, so in the future (FIXME)
-// this function should additionally work on token ranges whose primary owner
-// is down and this node is the range's secondary owner.
-// If the TTL (expiration-time scanning) feature is not enabled for this
-// table, scan_table() returns false without doing anything. Remember that the
-// TTL feature may be enabled later so this function will need to be called
-// again when the feature is enabled.
-// Currently this function scans the entire table (or, rather the parts owned
-// by this shard) at full rate, once. In the future (FIXME) we should consider
-// how to pace this scan, how and when to repeat it, how to interleave or
-// parallelize scanning of multiple tables, and how to continue scans after a
-// reboot.
-static future<bool> scan_table(
-    service::storage_proxy& proxy,
-    data_dictionary::database db,
-    gms::gossiper& gossiper,
-    schema_ptr s,
-    abort_source& abort_source,
-    named_semaphore& page_sem,
-    expiration_service::stats& expiration_stats)
-{
-    // Check if an expiration-time attribute is enabled for this table.
-    // If not, just return false immediately.
-    // FIXME: the setting of the TTL may change in the middle of a long scan!
-    std::optional<std::string> attribute_name = db::find_tag(*s, TTL_TAG_KEY);
-    if (!attribute_name) {
-        co_return false;
-    }
-    // attribute_name may be one of the schema's columns (in Alternator, this
-    // means it's a key column), or an element in Alternator's attrs map
-    // encoded in Alternator's JSON encoding.
-    // FIXME: To make this less Alternators-specific, we should encode in the
-    // single key's value three things:
-    // 1. The name of a column
-    // 2. Optionally if column is a map, a member in the map
-    // 3. The deserializer for the value: CQL or Alternator (JSON).
-    // The deserializer can be guessed: If the given column or map item is
-    // numeric, it can be used directly. If it is a "bytes" type, it needs to
-    // be deserialized using Alternator's deserializer.
-    bytes column_name = to_bytes(*attribute_name);
-    const column_definition *cd = s->get_column_definition(column_name);
-    std::optional<std::string> member;
-    if (!cd) {
-        member = std::move(attribute_name);
-        column_name = bytes(executor::ATTRS_COLUMN_NAME);
-        cd = s->get_column_definition(column_name);
-        tlogger.info("table {} TTL enabled with attribute {} in {}", s->cf_name(), *member, executor::ATTRS_COLUMN_NAME);
-    } else {
-        tlogger.info("table {} TTL enabled with attribute {}", s->cf_name(), *attribute_name);
-    }
-    if (!cd) {
-        tlogger.info("table {} TTL column is missing, not scanning", s->cf_name());
-        co_return false;
-    }
-    data_type column_type = cd->type;
-    // Verify that the column has the right type: If "member" exists
-    // the column must be a map, and if it doesn't, the column must
-    // (currently) be a decimal_type. If the column has the wrong type
-    // nothing can get expired in this table, and it's pointless to
-    // scan it.
-    if ((member && column_type->get_kind() != abstract_type::kind::map) ||
-        (!member && column_type->get_kind() != abstract_type::kind::decimal)) {
-        tlogger.info("table {} TTL column has unsupported type, not scanning", s->cf_name());
-        co_return false;
-    }
-    expiration_stats.scan_table++;
-    // FIXME: need to pace the scan, not do it all at once.
-    scan_ranges_context scan_ctx{s, proxy, std::move(column_name), std::move(member)};
-
-    if (s->table().uses_tablets()) {
-        locator::effective_replication_map_ptr erm = s->table().get_effective_replication_map();
-        auto my_host_id = erm->get_topology().my_host_id();
-        const auto &tablet_map = erm->get_token_metadata().tablets().get_tablet_map(s->id());
-        for (std::optional tablet = tablet_map.first_tablet(); tablet; tablet = tablet_map.next_tablet(*tablet)) {
-            auto tablet_primary_replica = tablet_map.get_primary_replica(*tablet, erm->get_topology());
-            // check if this is the primary replica for the current tablet
-            if (tablet_primary_replica.host == my_host_id && tablet_primary_replica.shard == this_shard_id()) {
-                co_await scan_tablet(*tablet, proxy, abort_source, page_sem, expiration_stats, scan_ctx, tablet_map);
-            } else if(erm->get_replication_factor() > 1) {
-                // Check if this is the secondary replica for the current tablet
-                // and if the primary replica is down which means we will take over this work.
-                // If each node only scans its own primary ranges, then when any node is
-                // down part of the token range will not get scanned. This can be viewed
-                // as acceptable (when the comes back online, it will resume its scan),
-                // but as noted in issue #9787, we can allow more prompt expiration
-                // by tasking another node to take over scanning of the dead node's primary
-                // ranges. What we do here is that this node will also check expiration
-                // on its *secondary* ranges - but only those whose primary owner is down.
-                auto tablet_secondary_replica = tablet_map.get_secondary_replica(*tablet); // throws if no secondary replica
-                if (tablet_secondary_replica.host == my_host_id && tablet_secondary_replica.shard == this_shard_id()) {
-                    if (!gossiper.is_alive(tablet_primary_replica.host)) {
-                        co_await scan_tablet(*tablet, proxy, abort_source, page_sem, expiration_stats, scan_ctx, tablet_map);
-                    }
-                }
-            }
-        }
-    } else {  // VNodes
-        locator::static_effective_replication_map_ptr ermp =
-                db.real_database().find_keyspace(s->ks_name()).get_static_effective_replication_map();
-        auto* erm = ermp->maybe_as_vnode_effective_replication_map();
-        if (!erm) {
-            on_internal_error(tlogger, format("Keyspace {} is local", s->ks_name()));
-        }
-        auto my_host_id = erm->get_topology().my_host_id();
-        token_ranges_owned_by_this_shard my_ranges(s, co_await ranges_holder_primary::make(erm, my_host_id));
-        while (std::optional<dht::partition_range> range = my_ranges.next_partition_range()) {
-            // Note that because of issue #9167 we need to run a separate
-            // query on each partition range, and can't pass several of
-            // them into one partition_range_vector.
-            dht::partition_range_vector partition_ranges;
-            partition_ranges.push_back(std::move(*range));
-            // FIXME: if scanning a single range fails, including network errors,
-            // we fail the entire scan (and rescan from the beginning). Need to
-            // reconsider this. Saving the scan position might be a good enough
-            // solution for this problem.
-            co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-        }
-        // If each node only scans its own primary ranges, then when any node is
-        // down part of the token range will not get scanned. This can be viewed
-        // as acceptable (when the comes back online, it will resume its scan),
-        // but as noted in issue #9787, we can allow more prompt expiration
-        // by tasking another node to take over scanning of the dead node's primary
-        // ranges. What we do here is that this node will also check expiration
-        // on its *secondary* ranges - but only those whose primary owner is down.
-        token_ranges_owned_by_this_shard my_secondary_ranges(s, co_await ranges_holder_secondary::make(erm, my_host_id, gossiper));
-        while (std::optional<dht::partition_range> range = my_secondary_ranges.next_partition_range()) {
-            expiration_stats.secondary_ranges_scanned++;
-            dht::partition_range_vector partition_ranges;
-            partition_ranges.push_back(std::move(*range));
-            co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-        }
-    }
-    co_return true;
-}
-
-
-future<> expiration_service::run() {
-    // FIXME: don't just tight-loop, think about timing, pace, and
-    // store position in durable storage, etc.
-    // FIXME: think about working on different tables in parallel.
-    // also need to notice when a new table is added, a table is
-    // deleted or when ttl is enabled or disabled for a table!
-    for (;;) {
-        auto start = lowres_clock::now();
-        // _db.tables() may change under our feet during a
-        // long-living loop, so we must keep our own copy of the list of
-        // schemas.
-        std::vector<schema_ptr> schemas;
-        for (auto cf : _db.get_tables()) {
-            schemas.push_back(cf.schema());
-        }
-        for (schema_ptr s : schemas) {
-            co_await coroutine::maybe_yield();
-            if (shutting_down()) {
-                co_return;
-            }
-            try {
-                co_await scan_table(_proxy, _db, _gossiper, s, _abort_source, _page_sem, _expiration_stats);
-            } catch (...) {
-                // The scan of a table may fail in the middle for many
-                // reasons, including network failure and even the table
-                // being removed. We'll continue scanning this table later
-                // (if it still exists). In any case it's important to catch
-                // the exception and not let the scanning service die for
-                // good.
-                // If the table has been deleted, it is expected that the scan
-                // will fail at some point, and even a warning is excessive.
-                if (_db.has_schema(s->ks_name(), s->cf_name())) {
-                    tlogger.warn("table {}.{} expiration scan failed: {}",
-                        s->ks_name(), s->cf_name(), std::current_exception());
-                } else {
-                    tlogger.info("expiration scan failed when table {}.{} was deleted",
-                        s->ks_name(), s->cf_name());
-                }
-            }
-        }
-        _expiration_stats.scan_passes++;
-        // The TTL scanner runs above once over all tables, at full steam.
-        // After completing such a scan, we sleep until it's time start
-        // another scan. TODO: If the scan went too fast, we can slow it down
-        // in the next iteration by reducing the scanner's scheduling-group
-        // share (if using a separate scheduling group), or introduce
-        // finer-grain sleeps into the scanning code.
-        std::chrono::milliseconds scan_duration(std::chrono::duration_cast<std::chrono::milliseconds>(lowres_clock::now() - start));
-        std::chrono::milliseconds period(long(_db.get_config().alternator_ttl_period_in_seconds() * 1000));
-        if (scan_duration < period) {
-            try {
-                tlogger.info("sleeping {} seconds until next period", (period - scan_duration).count()/1000.0);
-                co_await seastar::sleep_abortable(period - scan_duration, _abort_source);
-            } catch(seastar::sleep_aborted&) {}
-        } else {
-                tlogger.warn("scan took {} seconds, longer than period - not sleeping", scan_duration.count()/1000.0);
-        }
-    }
-}
-
-future<> expiration_service::start() {
-    // Called by main() on each shard to start the expiration-service
-    // thread. Just runs run() in the background and allows stop().
-    if (_db.features().alternator_ttl) {
-        if (!shutting_down()) {
-            _end = run().handle_exception([] (std::exception_ptr ep) {
-                tlogger.error("expiration_service failed: {}", ep);
-            });
-        }
-    }
-    return make_ready_future<>();
-}
-
-future<> expiration_service::stop() {
-    if (_abort_source.abort_requested()) {
-        throw std::logic_error("expiration_service::stop() called a second time");
-    }
-    _abort_source.request_abort();
-    if (!_end) {
-        // if _end is was not set, start() was never called
-        return make_ready_future<>();
-    }
-    return std::move(*_end);
-}
-
-expiration_service::stats::stats() {
-    _metrics.add_group("expiration", {
-        seastar::metrics::make_total_operations("scan_passes", scan_passes,
-            seastar::metrics::description("number of passes over the database"))(alternator_label).set_skip_when_empty(),
-        seastar::metrics::make_total_operations("scan_table", scan_table,
-            seastar::metrics::description("number of table scans (counting each scan of each table that enabled expiration)"))(alternator_label).set_skip_when_empty(),
-        seastar::metrics::make_total_operations("items_deleted", items_deleted,
-            seastar::metrics::description("number of items deleted after expiration"))(basic_level)(alternator_label).set_skip_when_empty(),
-        seastar::metrics::make_total_operations("secondary_ranges_scanned", secondary_ranges_scanned,
-            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down"))(alternator_label).set_skip_when_empty(),
-    });
-}
-
-
-} // namespace alternator

alternator/ttl.hh

@@ -1,80 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include <seastar/core/sharded.hh>
-#include <seastar/core/abort_source.hh>
-#include <seastar/core/semaphore.hh>
-#include "data_dictionary/data_dictionary.hh"
-
-namespace gms {
-class gossiper;
-}
-
-namespace replica {
-class database;
-}
-
-namespace service {
-    class storage_proxy;
-}
-
-namespace alternator {
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLeave request.
-class expiration_service final : public seastar::peering_sharded_service<expiration_service> {
-public:
-    // Object holding per-shard statistics related to the expiration service.
-    // While this object is alive, these metrics are also registered to be
-    // visible by the metrics REST API, with the "expiration_" prefix.
-    class stats {
-    public:
-        stats();
-        uint64_t scan_passes = 0;
-        uint64_t scan_table = 0;
-        uint64_t items_deleted = 0;
-        uint64_t secondary_ranges_scanned = 0;
-    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;
-    };
-private:
-    data_dictionary::database _db;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-    // _end is set by start(), and resolves when the the background service
-    // started by it ends. To ask the background service to end, _abort_source
-    // should be triggered. stop() below uses both _abort_source and _end.
-    std::optional<future<>> _end;
-    abort_source _abort_source;
-    // Ensures that at most 1 page of scan results at a time is processed by the TTL service
-    named_semaphore _page_sem{1, named_semaphore_exception_factory{"alternator_ttl"}};
-    bool shutting_down() { return _abort_source.abort_requested(); }
-    stats _expiration_stats;
-public:
-    // sharded_service<expiration_service>::start() creates this object on
-    // all shards, so calls this constructor on each shard. Later, the
-    // additional start() function should be invoked on all shards.
-    expiration_service(data_dictionary::database, service::storage_proxy&, gms::gossiper&);
-    future<> start();
-    future<> run();
-    // sharded_service<expiration_service>::stop() calls the following stop()
-    // method on each shard. This stop() asks the service on this shard to
-    // shut down as quickly as it can. The returned future indicates when the
-    // service is no longer running.
-    // stop() may be called even before start(), but may only be called once -
-    // calling it twice will result in an exception.
-    future<> stop();
-};
-
-} // namespace alternator

amplify.yml

@@ -1,15 +0,0 @@
-version: 1
-applications:
-  - frontend:
-      phases:
-        build:
-          commands:
-            - make setupenv
-            - make dirhtml
-      artifacts:
-        baseDirectory: _build/dirhtml
-        files:
-          - '**/*'
-      cache:
-        paths: []
-    appRoot: docs

api/CMakeLists.txt

@@ -1,115 +0,0 @@
-# Generate C++ sources from Swagger definitions
-
-function(generate_swagger)
-  set(one_value_args TARGET VAR IN_FILE OUT_DIR)
-  cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
-  get_filename_component(in_file_name ${args_IN_FILE} NAME)
-  set(generator ${PROJECT_SOURCE_DIR}/seastar/scripts/seastar-json2code.py)
-  set(header_out ${args_OUT_DIR}/${in_file_name}.hh)
-  set(source_out ${args_OUT_DIR}/${in_file_name}.cc)
-
-  add_custom_command(
-    DEPENDS
-      ${args_IN_FILE}
-      ${generator}
-    OUTPUT ${header_out} ${source_out}
-    COMMAND ${CMAKE_COMMAND} -E make_directory ${args_OUT_DIR}
-    COMMAND ${generator} --create-cc -f ${args_IN_FILE} -o ${header_out})
-
-  add_custom_target(${args_TARGET}
-    DEPENDS
-      ${header_out}
-      ${source_out})
-
-  set(${args_VAR} ${header_out} ${source_out} PARENT_SCOPE)
-endfunction()
-
-set(swagger_files
-  api-doc/authorization_cache.json
-  api-doc/cache_service.json
-  api-doc/collectd.json
-  api-doc/column_family.json
-  api-doc/commitlog.json
-  api-doc/compaction_manager.json
-  api-doc/client_routes.json
-  api-doc/config.json
-  api-doc/cql_server_test.json
-  api-doc/endpoint_snitch_info.json
-  api-doc/error_injection.json
-  api-doc/failure_detector.json
-  api-doc/gossiper.json
-  api-doc/hinted_handoff.json
-  api-doc/lsa.json
-  api-doc/messaging_service.json
-  api-doc/metrics.json
-  api-doc/raft.json
-  api-doc/service_levels.json
-  api-doc/storage_proxy.json
-  api-doc/storage_service.json
-  api-doc/stream_manager.json
-  api-doc/system.json
-  api-doc/tasks.json
-  api-doc/task_manager.json
-  api-doc/task_manager_test.json
-  api-doc/utils.json)
-
-foreach(f ${swagger_files})
-  get_filename_component(fname "${f}" NAME_WE)
-  get_filename_component(dir "${f}" DIRECTORY)
-  generate_swagger(
-    TARGET scylla_swagger_gen_${fname}
-    VAR scylla_swagger_gen_${fname}_files
-    IN_FILE "${CMAKE_CURRENT_SOURCE_DIR}/${f}"
-    OUT_DIR "${scylla_gen_build_dir}/api/${dir}")
-  list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
-endforeach()
-
-add_library(api STATIC)
-target_sources(api
-  PRIVATE
-    api.cc
-    cache_service.cc
-    client_routes.cc
-    collectd.cc
-    column_family.cc
-    commitlog.cc
-    compaction_manager.cc
-    config.cc
-    cql_server_test.cc
-    endpoint_snitch.cc
-    error_injection.cc
-    authorization_cache.cc
-    failure_detector.cc
-    gossiper.cc
-    hinted_handoff.cc
-    lsa.cc
-    messaging_service.cc
-    raft.cc
-    service_levels.cc
-    storage_proxy.cc
-    storage_service.cc
-    stream_manager.cc
-    system.cc
-    tasks.cc
-    task_manager.cc
-    task_manager_test.cc
-    token_metadata.cc
-    ${swagger_gen_files})
-target_include_directories(api
-  PUBLIC
-    ${CMAKE_SOURCE_DIR}
-    ${scylla_gen_build_dir})
-target_link_libraries(api
-  PUBLIC
-    Seastar::seastar
-    xxHash::xxhash
-  PRIVATE
-    idl
-    wasmtime_bindings
-    absl::headers)
-
-if (Scylla_USE_PRECOMPILED_HEADER_USE)
-  target_precompile_headers(api REUSE_FROM scylla-precompiled-header)
-endif()
-check_headers(check-headers api
-  GLOB_RECURSE ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)

api/api-doc/authorization_cache.json

@@ -1,29 +0,0 @@
-{
-  "apiVersion":"0.0.1",
-  "swaggerVersion":"1.2",
-  "basePath":"{{Protocol}}://{{Host}}",
-  "resourcePath":"/authorization_cache",
-  "produces":[
-    "application/json"
-  ],
-  "apis":[
-    {
-      "path":"/authorization_cache/reset",
-      "operations":[
-        {
-          "method":"POST",
-          "summary":"Reset cache",
-          "type":"void",
-          "nickname":"authorization_cache_reset",
-          "produces":[
-            "application/json"
-          ],
-          "parameters":[
-          ]
-        }
-      ]
-    }
-  ],
-  "models":{
-  }
-}

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/client_routes.def.json

@@ -1,23 +0,0 @@
-    , "client_routes_entry": {
-        "id": "client_routes_entry",
-        "summary": "An entry storing client routes",
-        "properties": {
-            "connection_id": {"type": "string"},
-            "host_id": {"type": "string", "format": "uuid"},
-            "address": {"type": "string"},
-            "port": {"type": "integer"},
-            "tls_port": {"type": "integer"},
-            "alternator_port": {"type": "integer"},
-            "alternator_https_port": {"type": "integer"}
-        },
-        "required": ["connection_id", "host_id", "address"]
-    }
-    , "client_routes_key": {
-        "id": "client_routes_key",
-        "summary": "A key of client_routes_entry",
-        "properties": {
-            "connection_id": {"type": "string"},
-            "host_id": {"type": "string", "format": "uuid"}
-        }
-    }
-

api/api-doc/client_routes.json

@@ -1,74 +0,0 @@
-    , "/v2/client-routes":{
-        "get": {
-            "description":"List all client route entries",
-            "operationId":"get_client_routes",
-            "tags":["client_routes"],
-            "produces":[
-                "application/json"
-            ],
-            "parameters":[],
-            "responses":{
-                "200":{
-                    "schema":{
-                        "type":"array",
-                        "items":{ "$ref":"#/definitions/client_routes_entry" }
-                    }
-                },
-                "default":{
-                    "description":"unexpected error",
-                    "schema":{"$ref":"#/definitions/ErrorModel"}
-                }
-            }
-        },
-        "post": {
-            "description":"Upsert one or more client route entries",
-            "operationId":"set_client_routes",
-            "tags":["client_routes"],
-            "parameters":[
-                {
-                    "name":"body",
-                    "in":"body",
-                    "required":true,
-                    "schema":{
-                        "type":"array",
-                        "items":{ "$ref":"#/definitions/client_routes_entry" }
-                    }
-                }
-            ],
-            "responses":{
-                "200":{ "description": "OK" },
-                "default":{
-                    "description":"unexpected error",
-                    "schema":{ "$ref":"#/definitions/ErrorModel" }
-                }
-            }
-        },
-        "delete": {
-            "description":"Delete one or more client route entries",
-            "operationId":"delete_client_routes",
-            "tags":["client_routes"],
-            "parameters":[
-                {
-                    "name":"body",
-                    "in":"body",
-                    "required":true,
-                    "schema":{
-                        "type":"array",
-                        "items":{ "$ref":"#/definitions/client_routes_key" }
-                    }
-                }
-            ],
-            "responses":{
-                "200":{
-                    "description": "OK"
-                },
-                "default":{
-                    "description":"unexpected error",
-                    "schema":{
-                        "$ref":"#/definitions/ErrorModel"
-                    }
-                }
-            }
-        }
-    }
-

api/api-doc/collectd.json

@@ -67,7 +67,7 @@
                "parameters":[
                   {
                      "name":"pluginid",
-                     "description":"The plugin ID, describe the component the metric belongs to. Examples are cache and alternator, etc'. Regex are supported.",
+                     "description":"The plugin ID, describe the component the metric belongs to. Examples are cache, thrift, etc'. Regex are supported.The plugin ID, describe the component the metric belong to. Examples are: cache, thrift etc'. regex are supported",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -199,4 +199,4 @@
          }
       }
    }
-}
+}

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"
@@ -84,28 +84,12 @@
                      "type":"string",
                      "paramType":"path"
                   },
-                  {
-                     "name":"flush_memtables",
-                     "description":"Controls flushing of memtables before compaction (true by default). Set to \"false\" to skip automatic flushing of memtables before compaction, e.g. when the table is flushed explicitly before invoking the compaction api.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"consider_only_existing_data",
-                     "description":"Set to \"true\" to flush all memtables and force tombstone garbage collection to check only the sstables being compacted (false by default). The memtable, commitlog and other uncompacted sstables will not be checked during tombstone garbage collection.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  },
                   {
                      "name":"split_output",
                      "description":"true if the output of the major compaction should be split in several sstables",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"boolean",
+                     "type":"bool",
                      "paramType":"query"
                   }
                ]
@@ -137,7 +121,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -188,7 +172,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -219,7 +203,7 @@
          "operations":[
             {
                "method":"POST",
-               "summary":"Sets the minimum and maximum number of sstables in queue before compaction kicks off",
+               "summary":"Sets the minumum and maximum number of sstables in queue before compaction kicks off",
                "type":"string",
                "nickname":"set_compaction_threshold",
                "produces":[
@@ -239,7 +223,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   },
                   {
@@ -247,7 +231,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -396,116 +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",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/column_family/tombstone_gc/{name}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Check if tombstone GC is enabled for a given table",
-               "type":"boolean",
-               "nickname":"get_tombstone_gc",
-               "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 tombstone GC for a given table",
-               "type":"void",
-               "nickname":"enable_tombstone_gc",
-               "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 tombstone GC for a given table",
-               "type":"void",
-               "nickname":"disable_tombstone_gc",
-               "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",
@@ -571,7 +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"
@@ -591,7 +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",
@@ -660,7 +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":[
@@ -727,54 +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":[
@@ -1037,7 +873,7 @@
             {
                "method":"GET",
                "summary":"Get memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -1061,7 +897,7 @@
             {
                "method":"GET",
                "summary":"Get all memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -1198,7 +1034,7 @@
             {
                "method":"GET",
                "summary":"Get read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_read_latency",
                "produces":[
                   "application/json"
@@ -1351,7 +1187,7 @@
             {
                "method":"GET",
                "summary":"Get all read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_read_latency",
                "produces":[
                   "application/json"
@@ -1367,7 +1203,7 @@
             {
                "method":"GET",
                "summary":"Get range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_range_latency",
                "produces":[
                   "application/json"
@@ -1391,7 +1227,7 @@
             {
                "method":"GET",
                "summary":"Get all range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_range_latency",
                "produces":[
                   "application/json"
@@ -1407,7 +1243,7 @@
             {
                "method":"GET",
                "summary":"Get write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_write_latency",
                "produces":[
                   "application/json"
@@ -1560,7 +1396,7 @@
             {
                "method":"GET",
                "summary":"Get all write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_write_latency",
                "produces":[
                   "application/json"
@@ -1576,7 +1412,7 @@
             {
                "method":"GET",
                "summary":"Get pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_flushes",
                "produces":[
                   "application/json"
@@ -1600,7 +1436,7 @@
             {
                "method":"GET",
                "summary":"Get all pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_flushes",
                "produces":[
                   "application/json"
@@ -1616,7 +1452,7 @@
             {
                "method":"GET",
                "summary":"Get pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_compactions",
                "produces":[
                   "application/json"
@@ -1640,7 +1476,7 @@
             {
                "method":"GET",
                "summary":"Get all pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_compactions",
                "produces":[
                   "application/json"
@@ -1656,7 +1492,7 @@
             {
                "method":"GET",
                "summary":"Get live ss table count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_ss_table_count",
                "produces":[
                   "application/json"
@@ -1680,7 +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"
@@ -1696,7 +1532,7 @@
             {
                "method":"GET",
                "summary":"Get live disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_disk_space_used",
                "produces":[
                   "application/json"
@@ -1720,7 +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"
@@ -1736,7 +1572,7 @@
             {
                "method":"GET",
                "summary":"Get total disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_disk_space_used",
                "produces":[
                   "application/json"
@@ -1760,7 +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"
@@ -2216,7 +2052,7 @@
             {
                "method":"GET",
                "summary":"Get speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_speculative_retries",
                "produces":[
                   "application/json"
@@ -2240,7 +2076,7 @@
             {
                "method":"GET",
                "summary":"Get all speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_speculative_retries",
                "produces":[
                   "application/json"
@@ -2320,7 +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"
@@ -2344,7 +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"
@@ -2360,7 +2196,7 @@
             {
                "method":"GET",
                "summary":"Get row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2384,7 +2220,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2400,7 +2236,7 @@
             {
                "method":"GET",
                "summary":"Get row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2424,7 +2260,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2440,7 +2276,7 @@
             {
                "method":"GET",
                "summary":"Get cas prepare",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_prepare",
                "produces":[
                   "application/json"
@@ -2464,7 +2300,7 @@
             {
                "method":"GET",
                "summary":"Get cas propose",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_propose",
                "produces":[
                   "application/json"
@@ -2488,7 +2324,7 @@
             {
                "method":"GET",
                "summary":"Get cas commit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_commit",
                "produces":[
                   "application/json"
@@ -2980,52 +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_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
-            "read":{
-               "type":"array",
-               "items":{
-                  "type":"toppartitions_record"
-               },
-               "description":"Read results"
-            },
-            "write_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
-            "write":{
-               "type":"array",
-               "items":{
-                  "type":"toppartitions_record"
-               },
-               "description":"Write results"
-            }
-         }
       }
    }
 }

api/api-doc/commitlog.json

@@ -144,21 +144,6 @@
           "parameters": []
         }
       ]
-    },
-    {
-      "path": "/commitlog/metrics/max_disk_size",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get max disk size",
-          "type": "long",
-          "nickname": "get_max_disk_size",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
     }
    ]
 }

api/api-doc/compaction_manager.json

@@ -102,47 +102,7 @@
                "parameters":[
                   {
                      "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/compaction_manager/stop_keyspace_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Stop all running compaction-like tasks in the given keyspace and tables having the provided type.",
-               "type":"void",
-               "nickname":"stop_keyspace_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to stop compaction in",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"tables",
-                     "description":"Comma-separated tables to stop compaction in",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
+                     "description":"the type of compaction to stop. Can be one of: - COMPACTION - VALIDATION - CLEANUP - SCRUB - INDEX_BUILD",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -158,7 +118,7 @@
         {
           "method": "GET",
           "summary": "Get pending tasks",
-          "type": "long",
+          "type": "int",
           "nickname": "get_pending_tasks",
           "produces": [
             "application/json"
@@ -167,24 +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": [
@@ -221,7 +163,7 @@
         {
           "method": "GET",
           "summary": "Get bytes compacted",
-          "type": "long",
+          "type": "int",
           "nickname": "get_bytes_compacted",
           "produces": [
             "application/json"
@@ -237,7 +179,7 @@
          "description":"A row merged information",
          "properties":{
             "key":{
-               "type": "long",
+               "type":"int",
                "description":"The number of sstable"
             },
             "value":{
@@ -246,24 +188,6 @@
             }
          }
       },
-      "sstableinfo":{
-         "id":"sstableinfo",
-         "description":"Compacted sstable information",
-         "properties":{
-            "generation":{
-               "type": "string",
-               "description":"Generation of the sstable"
-            },
-            "origin":{
-               "type":"string",
-               "description":"Origin of the sstable"
-            },
-            "size":{
-               "type":"long",
-               "description":"Size of the sstable"
-            }
-         }
-      },
       "compaction_info" :{
           "id": "compaction_info",
           "description":"A key value mapping",
@@ -320,23 +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",
@@ -345,10 +252,6 @@
                "type":"string",
                "description":"The UUID"
             },
-            "shard_id":{
-               "type":"int",
-               "description":"The shard id the compaction was executed on"
-            },
             "cf":{
                "type":"string",
                "description":"The column family name"
@@ -357,17 +260,9 @@
                "type":"string",
                "description":"The keyspace name"
             },
-            "compaction_type":{
-               "type":"string",
-               "description":"Type of compaction"
-            },
-            "started_at":{
-               "type":"long",
-               "description":"The time compaction started"
-            },
             "compacted_at":{
                "type":"long",
-               "description":"The time compaction completed"
+               "description":"The time of compaction"
             },
             "bytes_in":{
                "type":"long",
@@ -383,32 +278,6 @@
                   "type":"row_merged"
                },
                "description":"The merged rows"
-            },
-            "sstables_in": {
-               "type":"array",
-               "items":{
-                  "type":"sstableinfo"
-               },
-               "description":"List of input sstables for compaction"
-            },
-            "sstables_out": {
-               "type":"array",
-               "items":{
-                  "type":"sstableinfo"
-               },
-               "description":"List of output sstables from compaction"
-            },
-            "total_tombstone_purge_attempt":{
-               "type":"long",
-               "description":"Total number of tombstone purge attempts"
-            },
-            "total_tombstone_purge_failure_due_to_overlapping_with_memtable":{
-               "type":"long",
-               "description":"Number of tombstone purge failures due to data overlapping with memtables"
-            },
-            "total_tombstone_purge_failure_due_to_overlapping_with_uncompacting_sstable":{
-               "type":"long",
-               "description":"Number of tombstone purge failures due to data overlapping with non-compacting sstables"
             }
         }
       }