Fix version numbers in upgrade page title

.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
-...
-

.gitattributes

@@ -1,5 +1,3 @@
 *.cc diff=cpp
 *.hh diff=cpp
 *.svg binary
-docs/_static/api/js/* binary
-pgo/profiles/** filter=lfs diff=lfs merge=lfs -text

.github/CODEOWNERS

@@ -1,5 +1,5 @@
 # AUTH
-auth/* @nuivall
+auth/* @elcallio @vladzcloudius
 
 # CACHE
 row_cache* @tgrabiec
@@ -7,36 +7,36 @@ row_cache* @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
+cdc/* @kbr- @elcallio @piodul @jul-stas
+test/cql/cdc_* @kbr- @elcallio @piodul @jul-stas
+test/boost/cdc_* @kbr- @elcallio @piodul @jul-stas
 
 # COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio @eliransin
+db/commitlog/* @elcallio
 db/batch* @elcallio
 
 # COORDINATOR
 service/storage_proxy* @gleb-cloudius
 
 # COMPACTION
-compaction/* @raphaelsc
+compaction/* @raphaelsc @nyh
 
 # CQL TRANSPORT LAYER
 transport/*
 
 # CQL QUERY LANGUAGE
-cql3/* @tgrabiec @nuivall
+cql3/* @tgrabiec @psarna @cvybhu
 
 # COUNTERS
-counters* @nuivall
-tests/counter_test* @nuivall
+counters* @jul-stas
+tests/counter_test* @jul-stas
 
 # DOCS
 docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh
+docs/alternator @annastuchlik @tzach @nyh @psarna
 
 # GOSSIP
-gms/* @tgrabiec @asias @kbr-scylla
+gms/* @tgrabiec @asias
 
 # DOCKER
 dist/docker/*
@@ -45,43 +45,44 @@ dist/docker/*
 utils/logalloc* @tgrabiec
 
 # MATERIALIZED VIEWS
-db/view/* @nyh @piodul
-cql3/statements/*view* @nyh @piodul
-test/boost/view_* @nyh @piodul
+db/view/* @nyh @psarna
+cql3/statements/*view* @nyh @psarna
+test/boost/view_* @nyh @psarna
 
 # PACKAGING
 dist/* @syuu1228
 
 # REPAIR
-repair/* @tgrabiec @asias
+repair/* @tgrabiec @asias @nyh
 
 # SCHEMA MANAGEMENT
-db/schema_tables* @tgrabiec
-service/migration* @tgrabiec
-schema* @tgrabiec
+db/schema_tables* @tgrabiec @nyh
+db/legacy_schema_migrator* @tgrabiec @nyh
+service/migration* @tgrabiec @nyh
+schema* @tgrabiec @nyh
 
 # SECONDARY INDEXES
-index/* @nyh @piodul
-cql3/statements/*index* @nyh @piodul
-test/boost/*index* @nyh @piodul
+db/index/* @nyh @psarna
+cql3/statements/*index* @nyh @psarna
+test/boost/*index* @nyh @psarna
 
 # SSTABLES
-sstables/* @tgrabiec @raphaelsc
+sstables/* @tgrabiec @raphaelsc @nyh
 
 # STREAMING
 streaming/* @tgrabiec @asias
 service/storage_service.* @tgrabiec @asias
 
 # ALTERNATOR
-alternator/* @nyh
-test/alternator/* @nyh
+alternator/* @nyh @psarna
+test/alternator/* @nyh @psarna
 
 # HINTED HANDOFF
-db/hints/* @piodul @vladzcloudius @eliransin
+db/hints/* @piodul @vladzcloudius
 
 # REDIS
-redis/* @syuu1228
-test/redis/* @syuu1228
+redis/* @nyh @syuu1228
+test/redis/* @nyh @syuu1228
 
 # READERS
 reader_* @denesb
@@ -90,14 +91,11 @@ test/boost/mutation_reader_test.cc @denesb
 test/boost/querier_cache_test.cc @denesb
 
 # PYTEST-BASED CQL TESTS
-test/cqlpy/* @nyh
+test/cql-pytest/* @nyh
 
 # RAFT
-raft/* @kbr-scylla @gleb-cloudius @kostja
-test/raft/* @kbr-scylla @gleb-cloudius @kostja
+raft/* @kbr- @gleb-cloudius @kostja
+test/raft/* @kbr- @gleb-cloudius @kostja
 
 # HEAT-WEIGHTED LOAD BALANCING
 db/heat_load_balance.* @nyh @gleb-cloudius
-
-# Tools
-tools/* @denesb

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,15 @@
+This is Scylla's bug tracker, to be used for reporting bugs only.
+If you have a question about Scylla, and not a bug, please ask it in
+our mailing-list at scylladb-dev@googlegroups.com or in our slack channel.
+
+- [] I have read the disclaimer above, and I am reporting a suspected malfunction in Scylla.
+
+*Installation details*
+Scylla version (or git commit hash):
+Cluster size:
+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

@@ -1,101 +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/<suite>/<test_name>.py
-
-# Run a single test case from a file
-./test.py --mode=<mode> test/<suite>/<test_name>.py::<test_function_name>
-
-# Run all tests in a directory
-./test.py --mode=<mode> test/<suite>/
-
-# Examples
-./test.py --mode=dev test/alternator/
-./test.py --mode=dev test/cluster/test_raft_voters.py::test_raft_limited_voters_retain_coordinator
-./test.py --mode=dev test/cqlpy/test_json.py
-
-# Optional flags
-./test.py --mode=dev test/cluster/test_raft_no_quorum.py -v  # Verbose output
-./test.py --mode=dev test/cluster/test_raft_no_quorum.py --repeat 5  # Repeat test 5 times
-```
-
-**Important:**
-- Use full path with `.py` extension (e.g., `test/cluster/test_raft_no_quorum.py`, not `cluster/test_raft_no_quorum`)
-- 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
-
-## Test Philosophy
-- Performance matters. Tests should run as quickly as possible. Sleeps in the code are highly discouraged and should be avoided, to reduce run time and flakiness.
-- Stability matters. Tests should be stable. New tests should be executed 100 times at least to ensure they pass 100 out of 100 times. (use --repeat 100 --max-failures 1 when running it)
-- Unit tests should ideally test one thing and one thing only.
-- Tests for bug fixes should run before the fix - and show the failure and after the fix - and show they now pass.
-- Tests for bug fixes should have in their comments which bug fixes (GitHub or JIRA issue) they test.
-- Tests in debug are always slower, so if needed, reduce number of iterations, rows, data used, cycles, etc. in debug mode.
-- Tests should strive to be repeatable, and not use random input that will make their results unpredictable.
-- Tests should consume as little resources as possible. Prefer running tests on a single node if it is sufficient, for example.
-

.github/dependabot.yml

@@ -1,9 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: "uv"
-  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

@@ -1,36 +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
-    permissions:
-      contents: read
-      issues: write
-    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+)|(?:https://scylladb\\.atlassian\\.net/browse/)?([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_backport_with_jira.yaml

@@ -1,53 +0,0 @@
-name: Backport with Jira Integration
-
-on:
-  push:
-    branches:
-      - master
-      - next-*.*
-      - branch-*.*
-  pull_request_target:
-    types: [labeled, closed]
-    branches: 
-      - master
-      - next
-      - next-*.*
-      - branch-*.*
-
-jobs:
-  backport-on-push:
-    if: github.event_name == 'push'
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'push'
-      base_branch: ${{ github.ref }}
-      commits: ${{ github.event.before }}..${{ github.sha }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  backport-on-label:
-    if: github.event_name == 'pull_request_target' && github.event.action == 'labeled'
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'labeled'
-      base_branch: refs/heads/${{ github.event.pull_request.base.ref }}
-      pull_request_number: ${{ github.event.pull_request.number }}
-      head_commit: ${{ github.event.pull_request.base.sha }}
-      label_name: ${{ github.event.label.name }}
-      pr_state: ${{ github.event.pull_request.state }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  backport-chain:
-    if: github.event_name == 'pull_request_target' && github.event.action == 'closed' && github.event.pull_request.merged == true
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'chain'
-      base_branch: refs/heads/${{ github.event.pull_request.base.ref }}
-      pull_request_number: ${{ github.event.pull_request.number }}
-      pr_body: ${{ github.event.pull_request.body }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_jira_sync.yml

@@ -1,18 +0,0 @@
-name: Sync Jira Based on PR Events
-
-on:
-  pull_request_target:
-    types: [opened, edited, ready_for_review, review_requested, labeled, unlabeled, closed]
-
-permissions:
-  contents: read
-  pull-requests: write
-  issues: write
-
-jobs:
-  jira-sync:
-    uses: scylladb/github-automation/.github/workflows/main_pr_events_jira_sync.yml@main
-    with:
-      caller_action: ${{ github.event.action }}
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_jira_sync_pr_milestone.yml

@@ -1,22 +0,0 @@
-name: Sync Jira Based on PR Milestone Events
-
-on:
-  pull_request_target:
-    types: [milestoned, demilestoned]
-
-permissions:
-  contents: read
-  pull-requests: read
-
-jobs:
-  jira-sync-milestone-set:
-    if: github.event.action == 'milestoned'
-    uses: scylladb/github-automation/.github/workflows/main_jira_sync_pr_milestone_set.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  jira-sync-milestone-removed:
-    if: github.event.action == 'demilestoned'
-    uses: scylladb/github-automation/.github/workflows/main_jira_sync_pr_milestone_removed.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, closed]
-
-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,SMI,RELENG,VECTOR"
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_validate_pr_author_email.yml

@@ -1,13 +0,0 @@
-name: validate_pr_author_email
-
-on:
-  pull_request_target:
-    types:
-      - opened
-      - synchronize
-      - reopened
-
-jobs:
-  validate_pr_author_email:
-    uses: scylladb/github-automation/.github/workflows/validate_pr_author_email.yml@main
-

.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/close_issue_for_scylla_associate.yml

@@ -1,62 +0,0 @@
-name: Close issues created by Scylla associates
-
-on:
-  issues:
-    types: [opened, reopened]
-
-permissions:
-  issues: write
-
-jobs:
-  comment-and-close:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Comment and close if author email is scylladb.com
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const issue = context.payload.issue;
-            const actor = context.actor;
-
-            // Get user data (only public email is available)
-            const { data: user } = await github.rest.users.getByUsername({
-              username: actor,
-            });
-
-            const email = user.email || "";
-            console.log(`Actor: ${actor}, public email: ${email || "<none>"}`);
-
-            // Only continue if email exists and ends with @scylladb.com
-            if (!email || !email.toLowerCase().endsWith("@scylladb.com")) {
-              console.log("User is not a scylladb.com email (or email not public); skipping.");
-              return;
-            }
-
-            const owner = context.repo.owner;
-            const repo = context.repo.repo;
-            const issue_number = issue.number;
-
-            const body = "Issues in this repository are closed automatically. Scylla associates should use Jira to manage issues.\nPlease move this issue to Jira https://scylladb.atlassian.net/jira/software/c/projects/SCYLLADB/list";
-
-            // Add the comment
-            await github.rest.issues.createComment({
-              owner,
-              repo,
-              issue_number,
-              body,
-            });
-
-            console.log(`Comment added to #${issue_number}`);
-
-            // Close the issue
-            await github.rest.issues.update({
-              owner,
-              repo,
-              issue_number,
-              state: "closed",
-              state_reason: "not_planned"
-            });
-
-            console.log(`Issue #${issue_number} closed.`);

.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,iif,tread"
-          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

@@ -2,48 +2,34 @@ 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-**'
+      - master
     paths:
       - "docs/**"
   workflow_dispatch:
 
 jobs:
   release:
-    permissions:
-      pages: write
-      id-token: write
-      contents: write
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
-          ref: ${{ env.DEFAULT_BRANCH }}
           persist-credentials: false
           fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v3
         with:
-          python-version: "3.12"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
+          python-version: 3.7
       - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
+        run: make -C docs setupenv
       - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" multiversion
+        run: make -C docs multiversion
       - name: Build redirects
-        run: make -C docs FLAG="${{ env.FLAG }}" redirects
+        run: make -C docs 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

@@ -2,37 +2,27 @@ name: "Docs / Build PR"
 # For more information,
 # see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
 
-permissions:
-  contents: read
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-
 on:
   pull_request:
     branches:
       - master
-      - enterprise
     paths:
       - "docs/**"
-      - "db/config.hh"
-      - "db/config.cc"
+
 jobs:
   build:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           persist-credentials: false
           fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v3
         with:
-          python-version: "3.12"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
+          python-version: 3.7
       - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
+        run: make -C docs setupenv
       - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" test
+        run: make -C docs test

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

@@ -1,37 +0,0 @@
-name: Docs / Validate metrics
-
-permissions:
-  contents: read
-
-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

@@ -1,103 +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:
-  contents: read
-
-# 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: ${{ needs.read-toolchain.outputs.image }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Generate compilation database
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=$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

@@ -1,25 +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
-    permissions:
-      contents: read
-    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

@@ -1,66 +0,0 @@
-name: Trigger Scylla CI Route
-permissions:
-  contents: read
-
-on:
-  issue_comment:
-    types: [created]
-  pull_request_target:
-    types:
-      - unlabeled
-
-jobs:
-  trigger-jenkins:
-    if: (github.event_name == 'issue_comment' && github.event.comment.user.login != 'scylladbbot') || github.event.label.name == 'conflicts'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Verify Org Membership
-        id: verify_author
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-          PR_ASSOCIATION: ${{ github.event.pull_request.author_association }}
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
-          COMMENT_ASSOCIATION: ${{ github.event.comment.author_association }}
-        shell: bash
-        run: |
-          if [[ "$EVENT_NAME" == "pull_request_target" ]]; then
-            AUTHOR="$PR_AUTHOR"
-            ASSOCIATION="$PR_ASSOCIATION"
-          else
-            AUTHOR="$COMMENT_AUTHOR"
-            ASSOCIATION="$COMMENT_ASSOCIATION"
-          fi
-          if [[ "$ASSOCIATION" == "MEMBER" || "$ASSOCIATION" == "OWNER" ]]; then
-            echo "member=true" >> $GITHUB_OUTPUT
-          else
-            echo "::warning::${AUTHOR} is not a member of scylladb (association: ${ASSOCIATION}); skipping CI trigger."
-            echo "member=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Validate Comment Trigger
-        if: github.event_name == 'issue_comment'
-        id: verify_comment
-        env:
-          COMMENT_BODY: ${{ github.event.comment.body }}
-        shell: bash
-        run: |
-          CLEAN_BODY=$(echo "$COMMENT_BODY" | grep -v '^[[:space:]]*>')
-
-          if echo "$CLEAN_BODY" | grep -qi '@scylladbbot' && echo "$CLEAN_BODY" | grep -qi 'trigger-ci'; then
-            echo "trigger=true" >> $GITHUB_OUTPUT
-          else
-            echo "trigger=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Trigger Scylla-CI-Route Jenkins Job
-        if: steps.verify_author.outputs.member == 'true' && (github.event_name == 'pull_request_target' || steps.verify_comment.outputs.trigger == 'true')
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          PR_NUMBER: "${{ github.event.issue.number || github.event.pull_request.number }}"
-          PR_REPO_NAME: "${{ github.event.repository.full_name }}"
-        run: |
-          curl -X POST "$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

.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

@@ -1,53 +0,0 @@
-name: Trigger next gating
-
-permissions:
-  contents: read
-
-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
@@ -14,14 +12,13 @@ dist/ami/scylla_deploy.sh
 Cql.tokens
 .kdev4
 *.kdev4
-.idea
 CMakeLists.txt.user
 .cache
 .tox
 *.egg-info
 __pycache__CMakeLists.txt.user
 .gdbinit
-/resources
+resources
 .pytest_cache
 /expressions.tokens
 tags
@@ -29,11 +26,10 @@ tags
 testlog
 test/*/*.reject
 .vscode
+docs/_build
+docs/poetry.lock
 compile_commands.json
 .ccls-cache/
 .mypy_cache
 .envrc
-clang_build
-.idea/
-nuke
-rust/target
+rust/Cargo.lock

.gitmodules

@@ -6,12 +6,18 @@
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
+[submodule "libdeflate"]
+	path = libdeflate
+	url = ../libdeflate
 [submodule "abseil"]
 	path = abseil
 	url = ../abseil-cpp
+[submodule "scylla-jmx"]
+	path = tools/jmx
+	url = ../scylla-jmx
+[submodule "scylla-tools"]
+	path = tools/java
+	url = ../scylla-tools-java
 [submodule "scylla-python3"]
 	path = tools/python3
 	url = ../scylla-python3
-[submodule "tools/cqlsh"]
-	path = tools/cqlsh
-	url = ../scylla-cqlsh

CONTRIBUTING.md

@@ -2,7 +2,7 @@
 
 ## Asking questions or requesting help
 
-Use the [ScyllaDB Community Forum](https://forum.scylladb.com) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+Use the [Scylla Users mailing list](https://groups.google.com/g/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
 
 Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
 
@@ -12,7 +12,7 @@ Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to re
 
 ## 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).
+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 cla@scylladb.com. You can then submit your changes as patches to the 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.

HACKING.md

@@ -19,18 +19,18 @@ $ 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.
+version of the C++20 compiler and numerous tools and libraries to build.
 
 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.
+will be too old, and not support the new C++20 standard that Scylla uses.
 
 Alternatively, to avoid having to upgrade your build machine or install
 various packages on it, we provide another option - the **frozen toolchain**.
 This is a script, `./tools/toolchain/dbuild`, that can execute build or run
-commands inside a container that contains exactly the right build tools and
+commands inside a Docker image that contains exactly the right build tools and
 libraries. The `dbuild` technique is useful for beginners, but is also the way
 in which ScyllaDB produces official releases, so it is highly recommended.
 
@@ -43,12 +43,6 @@ $ ./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
-```
-
 ### Build system
 
 **Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
@@ -91,7 +85,7 @@ You can also specify a single mode. For example
 $ ninja-build release
 ```
 
-Will build everything in release mode. The valid modes are
+Will build everytihng in release mode. The valid modes are
 
 * Debug: Enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer)
   and other sanity checks. It has no optimizations, which allows for debugging with tools like
@@ -122,13 +116,6 @@ 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,
@@ -208,11 +195,11 @@ $ # 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
 
@@ -220,9 +207,28 @@ 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.
+To interact with scylla it is recommended to build our versions of
+cqlsh and nodetool. They are available at
+https://github.com/scylladb/scylla-tools-java and can be built with
+
+```bash
+$ sudo ./install-dependencies.sh
+$ ant jar
+```
+
+cqlsh should work out of the box, but nodetool depends on a running
+scylla-jmx (https://github.com/scylladb/scylla-jmx). It can be build
+with
+
+```bash
+$ mvn package
+```
+
+and must be started with
+
+```bash
+$ ./scripts/scylla-jmx
+```
 
 ### Branches and tags
 
@@ -261,45 +267,21 @@ 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.
@@ -361,7 +343,7 @@ avoid that the gold linker can be told to create an index with
 
 More info at https://gcc.gnu.org/wiki/DebugFission.
 
-Both options can be enabled by passing `--split-dwarf` to configure.py.
+Both options can be enable by passing `--split-dwarf` to configure.py.
 
 Note that distcc is *not* compatible with it, but icecream
 (https://github.com/icecc/icecream) is.
@@ -370,7 +352,7 @@ Note that distcc is *not* compatible with it, but icecream
 
 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

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

@@ -1,6 +1,9 @@
 This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
 especially Apache Cassandra.
 
+It includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
+These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.
+
 It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)
 
 It includes modified tests from https://github.com/etcd-io/etcd.git (owned by The etcd Authors)

README.md

@@ -15,10 +15,10 @@ For more information, please see the [ScyllaDB web site].
 ## 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
+versions of the C++20 compiler and of many libraries to build. The document
 [HACKING.md](HACKING.md) includes detailed information on building and
 developing Scylla, but to get Scylla building quickly on (almost) any build
-machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md).
+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
@@ -30,9 +30,9 @@ requirements - you just need to meet the frozen toolchain's prerequisites
 Building Scylla with the frozen toolchain `dbuild` is as easy as:
 
 ```bash
-$ git submodule update --init --force --recursive
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
+$ git submodule update --init --force --recursive
+$ ./tools/toolchain/dbuild ./configure.py
+$ ./tools/toolchain/dbuild ninja build/release/scylla
 ```
 
 For further information, please see:
@@ -43,7 +43,7 @@ For further information, please see:
 
 [developer documentation]: HACKING.md
 [build documentation]: docs/dev/building.md
-[docker image build documentation]: dist/docker/redhat/README.md
+[docker image build documentation]: dist/docker/debian/README.md
 
 ## Running Scylla
 
@@ -60,18 +60,16 @@ Please note that you need to run Scylla with `dbuild` if you built it with the f
 For more run options, run:
 
 ```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --help
+$ ./tools/toolchain/dbuild ./build/release/scylla --help
 ```
 
 ## Testing
 
-[![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)
-
 See [test.py manual](docs/dev/testing.md).
 
 ## 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™,
+By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
+Thrift. There is also support for the API of Amazon DynamoDB™,
 which needs to be enabled and configured in order to be used. For more
 information on how to enable the DynamoDB™ API in Scylla,
 and the current compatibility of this feature as well as Scylla-specific extensions, see
@@ -84,11 +82,11 @@ 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/).
 
-## Training
+## Training 
 
-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,
+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.
 
 ## Contributing to Scylla
@@ -102,10 +100,10 @@ If you are a developer working on Scylla, please read the [developer guidelines]
 
 ## Contact
 
-* The [community forum] and [Slack channel] are for users to discuss configuration, management, and operations of ScyllaDB.
+* The [users mailing list] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
 * The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
 
-[Community forum]: https://forum.scylladb.com/
+[Users mailing list]: https://groups.google.com/forum/#!forum/scylladb-users
 
 [Slack channel]: http://slack.scylladb.com/
 

SCYLLA-VERSION-GEN

@@ -7,7 +7,6 @@ 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
@@ -28,15 +27,14 @@ The files created are:
 
 By default, these files are created in the 'build'
 subdirectory under the directory containing the script.
-The destination directory can be overridden by
+The destination directory can be overriden by
 using '-o PATH' option.
 END
 )
 
 DATE=""
-PRINT_VERSION=false
 
-while [ $# -gt 0 ]; do
+while [[ $# -gt 0 ]]; do
 	opt="$1"
 	case $opt in
 		-h|--help)
@@ -53,10 +51,6 @@ while [ $# -gt 0 ]; do
 			shift
 			shift
 			;;
-		-v|--verbose)
-			PRINT_VERSION=true
-			shift
-			;;
 		*)
 			echo "Unexpected argument found: $1"
 			echo
@@ -78,7 +72,7 @@ fi
 
 # Default scylla product/version tags
 PRODUCT=scylla
-VERSION=2026.2.0-dev
+VERSION=5.2.0-dev
 
 if test -f version
 then
@@ -87,14 +81,12 @@ then
 else
 	SCYLLA_VERSION=$VERSION
 	if [ -z "$SCYLLA_RELEASE" ]; then
+		DATE=$(date --utc +%Y%m%d)
 		GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1 --abbrev=12)
-		# For custom package builds, replace "0" with "counter.yourname",
+		# For custom package builds, replace "0" with "counter.your_name",
 		# where counter starts at 1 and increments for successive versions.
 		# This ensures that the package manager will select your custom
 		# package over the standard release.
-		# Do not use any special characters like - or _ in the name above!
-		# These characters either have special meaning or are illegal in
-		# version strings.
 		SCYLLA_BUILD=0
 		SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 	elif [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
@@ -104,15 +96,13 @@ else
 fi
 
 if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" | rev | cut -d . -f 1 | rev)
+	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" |cut -d . -f 3)
 	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
 		exit 0
 	fi
 fi
 
-if $PRINT_VERSION; then
-	echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-fi
+echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
 mkdir -p "$OUTPUT_DIR"
 echo "$SCYLLA_VERSION" > "$OUTPUT_DIR/SCYLLA-VERSION-FILE"
 echo "$SCYLLA_RELEASE" > "$OUTPUT_DIR/SCYLLA-RELEASE-FILE"

absl-flat_hash_map.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include "absl-flat_hash_map.hh"

absl-flat_hash_map.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once

alternator/CMakeLists.txt

@@ -1,42 +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
-    http_compression.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

@@ -3,66 +3,154 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include "alternator/error.hh"
-#include "auth/common.hh"
-#include "utils/log.hh"
+#include "log.hh"
 #include <string>
 #include <string_view>
+#include <gnutls/crypto.h>
+#include "hashers.hh"
+#include "bytes.hh"
 #include "alternator/auth.hh"
 #include <fmt/format.h>
-#include "db/consistency_level_type.hh"
-#include "db/system_keyspace.hh"
+#include "auth/common.hh"
+#include "auth/password_authenticator.hh"
+#include "auth/roles-metadata.hh"
 #include "service/storage_proxy.hh"
 #include "alternator/executor.hh"
 #include "cql3/selection/selection.hh"
+#include "query-result-set.hh"
 #include "cql3/result_set.hh"
-#include "types/types.hh"
 #include <seastar/core/coroutine.hh>
 
 namespace alternator {
 
 static logging::logger alogger("alternator-auth");
 
+static hmac_sha256_digest hmac_sha256(std::string_view key, std::string_view msg) {
+    hmac_sha256_digest digest;
+    int ret = gnutls_hmac_fast(GNUTLS_MAC_SHA256, key.data(), key.size(), msg.data(), msg.size(), digest.data());
+    if (ret) {
+        throw std::runtime_error(fmt::format("Computing HMAC failed ({}): {}", ret, gnutls_strerror(ret)));
+    }
+    return digest;
+}
+
+static hmac_sha256_digest get_signature_key(std::string_view key, std::string_view date_stamp, std::string_view region_name, std::string_view service_name) {
+    auto date = hmac_sha256("AWS4" + std::string(key), date_stamp);
+    auto region = hmac_sha256(std::string_view(date.data(), date.size()), region_name);
+    auto service = hmac_sha256(std::string_view(region.data(), region.size()), service_name);
+    auto signing = hmac_sha256(std::string_view(service.data(), service.size()), "aws4_request");
+    return signing;
+}
+
+static std::string apply_sha256(std::string_view msg) {
+    sha256_hasher hasher;
+    hasher.update(msg.data(), msg.size());
+    return to_hex(hasher.finalize());
+}
+
+static std::string apply_sha256(const std::vector<temporary_buffer<char>>& msg) {
+    sha256_hasher hasher;
+    for (const temporary_buffer<char>& buf : msg) {
+        hasher.update(buf.get(), buf.size());
+    }
+    return to_hex(hasher.finalize());
+}
+
+static std::string format_time_point(db_clock::time_point tp) {
+    time_t time_point_repr = db_clock::to_time_t(tp);
+    std::string time_point_str;
+    time_point_str.resize(17);
+    ::tm time_buf;
+    // strftime prints the terminating null character as well
+    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", ::gmtime_r(&time_point_repr, &time_buf));
+    time_point_str.resize(16);
+    return time_point_str;
+}
+
+void check_expiry(std::string_view signature_date) {
+    //FIXME: The default 15min can be changed with X-Amz-Expires header - we should honor it
+    std::string expiration_str = format_time_point(db_clock::now() - 15min);
+    std::string validity_str = format_time_point(db_clock::now() + 15min);
+    if (signature_date < expiration_str) {
+        throw api_error::invalid_signature(
+                fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
+                signature_date, expiration_str));
+    }
+    if (signature_date > validity_str) {
+        throw api_error::invalid_signature(
+                fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
+                signature_date, validity_str));
+    }
+}
+
+std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
+        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
+        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string) {
+    auto amz_date_it = signed_headers_map.find("x-amz-date");
+    if (amz_date_it == signed_headers_map.end()) {
+        throw api_error::invalid_signature("X-Amz-Date header is mandatory for signature verification");
+    }
+    std::string_view amz_date = amz_date_it->second;
+    check_expiry(amz_date);
+    std::string_view datestamp = amz_date.substr(0, 8);
+    if (datestamp != orig_datestamp) {
+        throw api_error::invalid_signature(
+                format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
+                        orig_datestamp, datestamp));
+    }
+    std::string_view canonical_uri = "/";
+
+    std::stringstream canonical_headers;
+    for (const auto& header : signed_headers_map) {
+        canonical_headers << fmt::format("{}:{}", header.first, header.second) << '\n';
+    }
+
+    std::string payload_hash = apply_sha256(body_content);
+    std::string canonical_request = fmt::format("{}\n{}\n{}\n{}\n{}\n{}", method, canonical_uri, query_string, canonical_headers.str(), signed_headers_str, payload_hash);
+
+    std::string_view algorithm = "AWS4-HMAC-SHA256";
+    std::string credential_scope = fmt::format("{}/{}/{}/aws4_request", datestamp, region, service);
+    std::string string_to_sign = fmt::format("{}\n{}\n{}\n{}", algorithm, amz_date, credential_scope,  apply_sha256(canonical_request));
+
+    hmac_sha256_digest signing_key = get_signature_key(secret_access_key, datestamp, region, service);
+    hmac_sha256_digest signature = hmac_sha256(std::string_view(signing_key.data(), signing_key.size()), string_to_sign);
+
+    return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
+}
+
 future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema(db::system_keyspace::NAME, "roles");
+    schema_ptr schema = proxy.data_dictionary().find_schema("system_auth", "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)));
+    if (!salted_hash_col) {
+        co_await coroutine::return_exception(api_error::unrecognized_client(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 selection = cql3::selection::selection::for_columns(schema, {salted_hash_col});
+    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_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 = db::consistency_level::LOCAL_ONE;
+    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());
+    cql3::selection::result_set_builder builder(*selection, gc_clock::now(), cql_serialization_format::latest());
     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)));
+        co_await coroutine::return_exception(api_error::unrecognized_client(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();
+    const bytes_opt& salted_hash = result_set->rows().front().front(); // We only asked for 1 row and 1 column
     if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("No password found for user: {}", username)));
+        co_await coroutine::return_exception(api_error::unrecognized_client(format("No password found for user: {}", username)));
     }
     co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
 }

alternator/auth.hh

@@ -3,14 +3,16 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
 
 #include <string>
+#include <string_view>
+#include <array>
+#include "gc_clock.hh"
 #include "utils/loading_cache.hh"
-#include "auth/service.hh"
 
 namespace service {
 class storage_proxy;
@@ -18,8 +20,14 @@ class storage_proxy;
 
 namespace alternator {
 
+using hmac_sha256_digest = std::array<char, 32>;
+
 using key_cache = utils::loading_cache<std::string, std::string, 1>;
 
+std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
+        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
+        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string);
+
 future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username);
 
 }

alternator/conditions.cc

@@ -3,18 +3,23 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
+#include <list>
+#include <map>
 #include <string_view>
 #include "alternator/conditions.hh"
 #include "alternator/error.hh"
+#include "cql3/constants.hh"
 #include <unordered_map>
 #include "utils/rjson.hh"
 #include "serialization.hh"
 #include "utils/base64.hh"
 #include "utils/rjson.hh"
 #include <stdexcept>
+#include <boost/algorithm/cxx11/all_of.hpp>
+#include <boost/algorithm/cxx11/any_of.hpp>
 #include "utils/overloaded_functor.hh"
 
 #include "expressions.hh"
@@ -40,12 +45,12 @@ comparison_operator_type get_comparison_operator(const rjson::value& comparison_
             {"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)));
+        throw api_error::validation(format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
     }
-    std::string op = rjson::to_string(comparison_operator);
+    std::string op = comparison_operator.GetString();
     auto it = ops.find(op);
     if (it == ops.end()) {
-        throw api_error::validation(fmt::format("Unsupported comparison operator {}", op));
+        throw api_error::validation(format("Unsupported comparison operator {}", op));
     }
     return it->second;
 }
@@ -227,14 +232,7 @@ bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
     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;
-        }
+        return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
     }
 }
 
@@ -243,7 +241,7 @@ static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
 }
 
 // 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) {
+bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
     if (!v1) {
         return false;
     }
@@ -252,12 +250,7 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from
     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;
+        return rjson::base64_decode(kv1.value).find(rjson::base64_decode(kv2.value)) != bytes::npos;
     } else if (is_set_of(kv1.name, kv2.name)) {
         for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
             if (*i == kv2.value) {
@@ -280,11 +273,11 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from
 }
 
 // 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) {
+static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
     if (!v1) {
         return false;
     }
-    return !check_CONTAINS(v1, v2, v1_from_query, v2_from_query);
+    return !check_CONTAINS(v1, v2);
 }
 
 // Check if a JSON-encoded value equals any element of an array, which must have at least one element.
@@ -337,7 +330,7 @@ static bool check_NOT_NULL(const rjson::value* val) {
 }
 
 // Only types S, N or B (string, number or bytes) may be compared by the
-// various comparison operators - lt, le, gt, ge, and between.
+// various comparion operators - lt, le, gt, ge, and between.
 // Note that in particular, if the value is missing (v->IsNull()), this
 // check returns false.
 static bool check_comparable_type(const rjson::value& v) {
@@ -377,16 +370,11 @@ bool check_compare(const rjson::value* v1, const rjson::value& v2, const Compara
         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));
+        return cmp(std::string_view(kv1.value.GetString(), kv1.value.GetStringLength()),
+                   std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
     }
     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);
+        return cmp(rjson::base64_decode(kv1.value), rjson::base64_decode(kv2.value));
     }
     // cannot reach here, as check_comparable_type() verifies the type is one
     // of the above options.
@@ -427,7 +415,7 @@ static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from
     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));
+                format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
         } else {
             return false;
         }
@@ -470,19 +458,13 @@ static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const r
         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),
+        return check_BETWEEN(std::string_view(kv_v.value.GetString(), kv_v.value.GetStringLength()),
+                             std::string_view(kv_lb.value.GetString(), kv_lb.value.GetStringLength()),
+                             std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()),
                              bounds_from_query);
     }
     if (kv_v.name == "B") {
-        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);
+        return check_BETWEEN(rjson::base64_decode(kv_v.value), rjson::base64_decode(kv_lb.value), rjson::base64_decode(kv_ub.value), bounds_from_query);
     }
     if (v_from_query) {
         throw api_error::validation(
@@ -575,7 +557,7 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
                             format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
                                     "got {} instead", argtype));
                 }
-                return check_CONTAINS(got, arg, false, true);
+                return check_CONTAINS(got, arg);
             }
         case comparison_operator_type::NOT_CONTAINS:
             {
@@ -589,7 +571,7 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
                             format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
                                     "got {} instead", argtype));
                 }
-                return check_NOT_CONTAINS(got, arg, false, true);
+                return check_NOT_CONTAINS(got, arg);
             }
         }
         throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
@@ -611,14 +593,14 @@ conditional_operator_type get_conditional_operator(const rjson::value& req) {
         return conditional_operator_type::OR;
     } else {
         throw api_error::validation(
-                fmt::format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
+                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 a ValidationException API error if there
+// 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");
@@ -741,9 +723,9 @@ bool verify_condition_expression(
             };
             switch (list.op) {
             case '&':
-                return std::ranges::all_of(list.conditions, verify_condition);
+                return boost::algorithm::all_of(list.conditions, verify_condition);
             case '|':
-                return std::ranges::any_of(list.conditions, verify_condition);
+                return boost::algorithm::any_of(list.conditions, verify_condition);
             default:
                 // Shouldn't happen unless we have a bug in the parser
                 throw std::logic_error("bad operator in condition_list");

alternator/conditions.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 /*
@@ -18,6 +18,8 @@
 
 #pragma once
 
+#include "cql3/restrictions/statement_restrictions.hh"
+#include "serialization.hh"
 #include "expressions_types.hh"
 
 namespace alternator {
@@ -36,7 +38,7 @@ 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_CONTAINS(const rjson::value* v1, const rjson::value& v2);
 bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
 
 bool verify_condition_expression(

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_response) {
-        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_response) : _should_add_to_response(should_add_to_response){}
-    bool operator()() const noexcept {
-        return _should_add_to_response;
-    }
-
-    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_response = 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

@@ -3,12 +3,10 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
-#include <seastar/core/with_scheduling_group.hh>
 #include <seastar/net/dns.hh>
-
 #include "controller.hh"
 #include "server.hh"
 #include "executor.hh"
@@ -28,19 +26,15 @@ static logging::logger logger("alternator_controller");
 controller::controller(
         sharded<gms::gossiper>& gossiper,
         sharded<service::storage_proxy>& proxy,
-        sharded<service::storage_service>& ss,
         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)
+        const db::config& config)
+    : _gossiper(gossiper)
     , _proxy(proxy)
-    , _ss(ss)
     , _mm(mm)
     , _sys_dist_ks(sys_dist_ks)
     , _cdc_gen_svc(cdc_gen_svc)
@@ -68,9 +62,7 @@ std::vector<socket_address> controller::listen_addresses() const {
 }
 
 future<> controller::start_server() {
-    seastar::thread_attributes attr;
-    attr.sched_group = _sched_group;
-    return seastar::async(std::move(attr), [this] {
+    return seastar::async([this] {
         _listen_addresses.clear();
 
         auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
@@ -81,19 +73,16 @@ future<> controller::start_server() {
         // shards - if necessary for LWT.
         smp_service_group_config c;
         c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get();
+        _ssg = create_smp_service_group(c).get0();
 
         rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
+        executor::set_default_timeout(std::chrono::milliseconds(_config.alternator_timeout_in_ms()));
 
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get();
+        net::inet_address addr = utils::resolve(_config.alternator_address, family).get0();
 
         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(_ss), 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();
+
+        _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()).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
@@ -105,23 +94,11 @@ future<> controller::start_server() {
             alternator_port = _config.alternator_port();
             _listen_addresses.push_back({addr, *alternator_port});
         }
-        std::optional<uint16_t> alternator_port_proxy_protocol;
-        if (_config.alternator_port_proxy_protocol()) {
-            alternator_port_proxy_protocol = _config.alternator_port_proxy_protocol();
-            _listen_addresses.push_back({addr, *alternator_port_proxy_protocol});
-        }
         std::optional<uint16_t> alternator_https_port;
-        std::optional<uint16_t> alternator_https_port_proxy_protocol;
         std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port() || _config.alternator_https_port_proxy_protocol()) {
-            if (_config.alternator_https_port()) {
-                alternator_https_port = _config.alternator_https_port();
-                _listen_addresses.push_back({addr, *alternator_https_port});
-            }
-            if (_config.alternator_https_port_proxy_protocol()) {
-                alternator_https_port_proxy_protocol = _config.alternator_https_port_proxy_protocol();
-                _listen_addresses.push_back({addr, *alternator_https_port_proxy_protocol});
-            }
+        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()) {
@@ -146,30 +123,19 @@ future<> controller::start_server() {
                 std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
             }
         }
+        bool alternator_enforce_authorization = _config.alternator_enforce_authorization();
         _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol, creds = std::move(creds)] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol, creds,
-                    _config.alternator_enforce_authorization,
-                    _config.alternator_warn_authorization,
-                    _config.alternator_max_users_query_size_in_trace_output,
+                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds), alternator_enforce_authorization] (server& server) mutable {
+            return server.init(addr, alternator_port, alternator_https_port, creds, alternator_enforce_authorization,
                     &_memory_limiter.local().get_semaphore(),
                     _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}, proxy-protocol port {}, TLS proxy-protocol port {}: {}",
-                    addr,
-                    alternator_port ? std::to_string(*alternator_port) : "OFF",
-                    alternator_https_port ? std::to_string(*alternator_https_port) : "OFF",
-                    alternator_port_proxy_protocol ? std::to_string(*alternator_port_proxy_protocol) : "OFF",
-                    alternator_https_port_proxy_protocol ? std::to_string(*alternator_https_port_proxy_protocol) : "OFF",
-                    ep);
+        }).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, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}, proxy-protocol port {}, TLS proxy-protocol port {}",
-                    addr,
-                    alternator_port ? std::to_string(*alternator_port) : "OFF",
-                    alternator_https_port ? std::to_string(*alternator_https_port) : "OFF",
-                    alternator_port_proxy_protocol ? std::to_string(*alternator_port_proxy_protocol) : "OFF",
-                    alternator_https_port_proxy_protocol ? std::to_string(*alternator_https_port_proxy_protocol) : "OFF");
+        }).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();
     });
 }
@@ -187,13 +153,7 @@ future<> controller::stop_server() {
 }
 
 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();
+    return stop_server();
 }
 
 }

alternator/controller.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -11,11 +11,10 @@
 #include <seastar/core/sharded.hh>
 #include <seastar/core/smp.hh>
 
-#include "transport/protocol_server.hh"
+#include "protocol_server.hh"
 
 namespace service {
 class storage_proxy;
-class storage_service;
 class migration_manager;
 class memory_limiter;
 }
@@ -58,7 +57,6 @@ class server;
 class controller : public protocol_server {
     sharded<gms::gossiper>& _gossiper;
     sharded<service::storage_proxy>& _proxy;
-    sharded<service::storage_service>& _ss;
     sharded<service::migration_manager>& _mm;
     sharded<db::system_distributed_keyspace>& _sys_dist_ks;
     sharded<cdc::generation_service>& _cdc_gen_svc;
@@ -76,15 +74,13 @@ public:
     controller(
         sharded<gms::gossiper>& gossiper,
         sharded<service::storage_proxy>& proxy,
-        sharded<service::storage_service>& ss,
         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);
+        const db::config& config);
 
     virtual sstring name() const override;
     virtual sstring protocol() const override;
@@ -93,10 +89,6 @@ public:
     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

@@ -3,14 +3,13 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
 
 #include <seastar/http/httpd.hh>
 #include "seastarx.hh"
-#include "utils/rjson.hh"
 
 namespace alternator {
 
@@ -24,20 +23,14 @@ namespace alternator {
 // 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;
+    using status_type = httpd::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())
+    api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request)
         : _http_code(std::move(http_code))
         , _type(std::move(type))
         , _msg(std::move(msg))
-        , _extra_fields(std::move(extra_fields))
     { }
 
     // Factory functions for some common types of DynamoDB API errors
@@ -65,13 +58,8 @@ public:
     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 conditional_check_failed(std::string msg) {
+        return api_error("ConditionalCheckFailedException", std::move(msg));
     }
     static api_error expired_iterator(std::string msg) {
         return api_error("ExpiredIteratorException", std::move(msg));
@@ -88,14 +76,8 @@ public:
     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);
+        return api_error("InternalServerError", std::move(msg), reply::status_type::internal_server_error);
     }
 
     // Provide the "std::exception" interface, to make it easier to print this

alternator/executor.hh

@@ -3,29 +3,25 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
 
 #include <seastar/core/future.hh>
+#include <seastar/http/httpd.hh>
 #include "seastarx.hh"
+#include <seastar/json/json_elements.hh>
 #include <seastar/core/sharded.hh>
-#include <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 "db/config.hh"
 
 #include "alternator/error.hh"
 #include "stats.hh"
 #include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
-#include "utils/simple_value_with_expiry.hh"
-
-#include "tracing/trace_state.hh"
 
 namespace db {
     class system_distributed_keyspace;
@@ -42,8 +38,6 @@ namespace cql3::selection {
 
 namespace service {
     class storage_proxy;
-    class cas_shard;
-    class storage_service;
 }
 
 namespace cdc {
@@ -56,13 +50,36 @@ class gossiper;
 
 }
 
-class schema_builder;
-
 namespace alternator {
 
-enum class table_status;
 class rmw_operation;
-class put_or_delete_item;
+
+struct make_jsonable : public json::jsonable {
+    rjson::value _value;
+public:
+    explicit make_jsonable(rjson::value&& value);
+    std::string to_json() const override;
+};
+
+/**
+ * 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
+ */ 
+json::json_return_type make_streamed(rjson::value&&);
+
+struct json_string : public json::jsonable {
+    std::string _value;
+public:
+    explicit json_string(std::string&& value);
+    std::string to_json() const override;
+};
+
+namespace parsed {
+class path;
+};
 
 schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
 bool is_alternator_keyspace(const sstring& ks_name);
@@ -134,62 +151,27 @@ using attrs_to_get_node = attribute_path_map_node<std::monostate>;
 // 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_service& _ss;
     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;
-
-    struct describe_table_info_manager;
-    std::unique_ptr<describe_table_info_manager> _describe_table_info_manager;
-
-    future<> cache_newly_calculated_size_on_all_shards(schema_ptr schema, std::uint64_t size_in_bytes, std::chrono::nanoseconds ttl);
-    future<> fill_table_size(rjson::value &table_description, schema_ptr schema, bool deleting);
 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>;
+    using request_return_type = std::variant<json::json_return_type, 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::storage_service& ss,
-             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();
+    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)
+        : _gossiper(gossiper), _proxy(proxy), _mm(mm), _sdks(sdks), _cdc_metadata(cdc_metadata), _ssg(ssg) {}
 
     future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
     future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
@@ -217,88 +199,44 @@ public:
     future<request_return_type> describe_continuous_backups(client_state& client_state, service_permit permit, rjson::value request);
 
     future<> start();
-    future<> stop();
+    future<> stop() { return make_ready_future<>(); }
 
     static sstring table_name(const schema&);
     static db::timeout_clock::time_point default_timeout();
+    static void set_default_timeout(db::timeout_clock::duration timeout);
 private:
-    static thread_local utils::updateable_value<uint32_t> s_default_timeout_in_ms;
+    static db::timeout_clock::duration s_default_timeout;
 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<rjson::value> fill_table_description(schema_ptr schema, table_status tbl_status, service::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit);
-    future<executor::request_return_type> create_table_on_shard0(service::client_state&& client_state, tracing::trace_state_ptr trace_state, rjson::value request, bool enforce_authorization, bool warn_authorization, const db::tablets_mode_t::mode tablets_mode);
-
-    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);
-
+    static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
+    static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
+    
 public:
-    static 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);
+        const std::optional<attrs_to_get>&);
 
-    // 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 std::vector<rjson::value> describe_multi_item(schema_ptr schema,
+        const query::partition_slice& slice,
+        const cql3::selection::selection& selection,
+        const query::result& query_result,
+        const std::optional<attrs_to_get>& attrs_to_get);
 
     static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<managed_bytes_opt>&,
+        const std::vector<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 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);
+    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, 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

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include "expressions.hh"
@@ -17,16 +17,19 @@
 
 #include "seastarx.hh"
 
-#include <seastar/core/format.hh>
+#include <seastar/core/print.hh>
 #include <seastar/util/log.hh>
 
+#include <boost/algorithm/cxx11/any_of.hpp>
+#include <boost/algorithm/cxx11/all_of.hpp>
+
 #include <functional>
 #include <unordered_map>
 
 namespace alternator {
 
-template <typename Func, typename Result = std::invoke_result_t<Func, expressionsParser&>>
-static Result do_with_parser(std::string_view input, Func&& f) {
+template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
+Result do_with_parser(std::string_view input, Func&& f) {
     expressionsLexer::InputStreamType input_stream{
         reinterpret_cast<const ANTLR_UINT8*>(input.data()),
         ANTLR_ENC_UTF8,
@@ -40,41 +43,31 @@ static Result do_with_parser(std::string_view input, Func&& f) {
     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));
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::update_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing UpdateExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 std::vector<parsed::path>
 parse_projection_expression(std::string_view query) {
-    return parse ("ProjectionExpression", query,  std::mem_fn(&expressionsParser::projection_expression));
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::projection_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing ProjectionExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 parsed::condition_expression
-parse_condition_expression(std::string_view query, const char* caller) {
-    return parse(caller, query,  std::mem_fn(&expressionsParser::condition_expression));
+parse_condition_expression(std::string_view query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::condition_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 namespace parsed {
@@ -130,6 +123,21 @@ void path::check_depth_limit() {
     }
 }
 
+std::ostream& operator<<(std::ostream& os, const path& p) {
+    os << p.root();
+    for (const auto& op : p.operators()) {
+        std::visit(overloaded_functor {
+            [&] (const std::string& member) {
+                os << '.' << member;
+            },
+            [&] (unsigned index) {
+                os << '[' << index << ']';
+            }
+        }, op);
+    }
+    return os;
+}
+
 } // namespace parsed
 
 // The following resolve_*() functions resolve references in parsed
@@ -157,17 +165,15 @@ static std::optional<std::string> resolve_path_component(const std::string& colu
     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));
+                    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));
+                    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::string(rjson::to_string_view(*value));
     }
     return std::nullopt;
 }
@@ -201,16 +207,16 @@ static void resolve_constant(parsed::constant& c,
         [&] (const std::string& valref) {
             if (!expression_attribute_values) {
                 throw api_error::validation(
-                        fmt::format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
+                        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));
+                        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));
+                        format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
             }
             validate_value(*value, "ExpressionAttributeValues");
             used_attribute_values.emplace(valref);
@@ -412,14 +418,9 @@ void for_condition_expression_on(const parsed::condition_expression& ce, const n
 // 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) {
+// It return a JSON-encoded "null" value if this value's type has no size
+// defined. Comparisons against this non-numeric value will later fail.
+static rjson::value calculate_size(const rjson::value& v) {
     // NOTE: If v is improperly formatted for our JSON value encoding, it
     // must come from the request itself, not from the database, so it makes
     // sense to throw a ValidationException if we see such a problem.
@@ -448,12 +449,10 @@ static rjson::value calculate_size(const rjson::value& v, bool from_data) {
             throw api_error::validation(format("invalid byte string: {}", v));
         }
         ret = base64_decoded_len(rjson::to_string_view(it->value));
-    } else if (from_data) {
+    } else {
         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)));
@@ -535,7 +534,7 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
                         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());
+            return calculate_size(v);
         }
     },
     {"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
@@ -635,8 +634,7 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
             }
             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()));
+            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2));
         }
     },
 };
@@ -663,7 +661,7 @@ static rjson::value extract_path(const rjson::value* item,
             // 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));
+            throw api_error::validation(format("{}: malformed item read: {}", *item));
         }
         const char* type = v->MemberBegin()->name.GetString();
         v = &(v->MemberBegin()->value);
@@ -707,7 +705,7 @@ rjson::value calculate_value(const parsed::value& v,
             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));
+                        format("{}: unknown function '{}' called.", caller, f._function_name));
             }
             return function_it->second(caller, previous_item, f);
         },
@@ -739,41 +737,4 @@ rjson::value calculate_value(const parsed::set_rhs& rhs,
     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

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 /*
@@ -74,34 +74,7 @@ options {
  */
 @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;
+        throw expressions_syntax_error("syntax error");
     }
 }
 @lexer::context {
@@ -110,23 +83,6 @@ options {
     }
 }
 
-/* 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.
@@ -196,29 +152,22 @@ 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");
-                }
-            }
+      | '[' INTEGER ']'           { $p.add_index(std::stoi($INTEGER.text)); }
     )*;
 
-/* See comment above why the "depth" counter was needed here */
-value[int depth] returns [parsed::value v]:
+value 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); })*
+    | NAME         { $v.set_func_name($NAME.text); }
+     '(' x=value   { $v.add_func_parameter($x.v); }
+     (',' x=value  { $v.add_func_parameter($x.v); })*
      ')'
     ;
 
 update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value[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)); }
+    v=value  { $rhs.set_value(std::move($v.v)); }
+    (   '+' v=value  { $rhs.set_plus(std::move($v.v)); }
+      | '-' v=value  { $rhs.set_minus(std::move($v.v)); }
     )?
     ;
 
@@ -248,7 +197,7 @@ update_expression_clause returns [parsed::update_expression e]:
 // 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($update_expression_clause.e); })+ EOF;
+    (update_expression_clause { e.append($update_expression_clause.e); })* EOF;
 
 projection_expression returns [std::vector<parsed::path> v]:
     p=path      { $v.push_back(std::move($p.p)); }
@@ -256,7 +205,7 @@ projection_expression returns [std::vector<parsed::path> v]:
 
 
 primitive_condition returns [parsed::primitive_condition c]:
-      v=value[0]      { $c.add_value(std::move($v.v));
+      v=value         { $c.add_value(std::move($v.v));
                         $c.set_operator(parsed::primitive_condition::type::VALUE); }
       (  (  '='       { $c.set_operator(parsed::primitive_condition::type::EQ); }
           | '<' '>'   { $c.set_operator(parsed::primitive_condition::type::NE); }
@@ -265,23 +214,16 @@ primitive_condition returns [parsed::primitive_condition c]:
           | '>'       { $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)); }
+         v=value      { $c.add_value(std::move($v.v)); }
        | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
+         v=value      { $c.add_value(std::move($v.v)); }
          AND
-         v=value[0]   { $c.add_value(std::move($v.v)); }
+         v=value      { $c.add_value(std::move($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)); })*
+         v=value      { $c.add_value(std::move($v.v)); }
+         (',' v=value { $c.add_value(std::move($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
@@ -289,20 +231,19 @@ primitive_condition returns [parsed::primitive_condition c]:
 // 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 returns [parsed::condition_expression e]:
+	  b=boolean_expression_1       { $e.append(std::move($b.e), '|'); }
+	  (OR b=boolean_expression_1   { $e.append(std::move($b.e), '|'); } )*
 	;
-boolean_expression_1[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_1 returns [parsed::condition_expression e]:
+	  b=boolean_expression_2       { $e.append(std::move($b.e), '&'); }
+	  (AND b=boolean_expression_2  { $e.append(std::move($b.e), '&'); } )*
 	;
-boolean_expression_2[int depth] returns [parsed::condition_expression e]:
+boolean_expression_2 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); }
+	| NOT b=boolean_expression_2   { $e = std::move($b.e); $e.apply_not(); }
+	| '(' b=boolean_expression ')' { $e = std::move($b.e); }
     ;
 
 condition_expression returns [parsed::condition_expression e]:
-    boolean_expression[0] { e=std::move($boolean_expression.e); } EOF;
+    boolean_expression { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -18,8 +18,6 @@
 
 #include "expressions_types.hh"
 #include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
-#include "stats.hh"
 
 namespace alternator {
 
@@ -28,29 +26,9 @@ 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);
+parsed::condition_expression parse_condition_expression(std::string_view query);
 
 void resolve_update_expression(parsed::update_expression& ue,
         const rjson::value* expression_attribute_names,
@@ -82,29 +60,23 @@ 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);
+inline std::ostream& operator<<(std::ostream& out, calculate_value_caller caller) {
+    switch (caller) {
+        case calculate_value_caller::UpdateExpression:
+            out << "UpdateExpression";
+            break;
+        case calculate_value_caller::ConditionExpression:
+            out << "ConditionExpression";
+            break;
+        case calculate_value_caller::ConditionExpressionAlone:
+            out << "ConditionExpression";
+            break;
+        default:
+            out << "unknown type of expression";
+            break;
     }
-};
-
-namespace alternator {
+    return out;
+}
 
 rjson::value calculate_value(const parsed::value& v,
         calculate_value_caller caller,
@@ -113,7 +85,5 @@ rjson::value calculate_value(const parsed::value& v,
 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

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -19,7 +19,7 @@
 /*
  * Parsed representation of expressions and their components.
  *
- * Types in alternator::parsed namespace are used for holding the parse
+ * Types in alternator::parse namespace are used for holding the parse
  * tree - objects generated by the Antlr rules after parsing an expression.
  * Because of the way Antlr works, all these objects are default-constructed
  * first, and then assigned when the rule is completed, so all these types
@@ -50,7 +50,7 @@ public:
         _operators.emplace_back(i);
         check_depth_limit();
     }
-    void add_dot(std::string name) {
+    void add_dot(std::string(name)) {
         _operators.emplace_back(std::move(name));
         check_depth_limit();
     }
@@ -66,6 +66,7 @@ public:
     std::vector<std::variant<std::string, unsigned>>& operators() {
         return _operators;
     }
+    friend std::ostream& operator<<(std::ostream&, const path&);
 };
 
 // When an expression is first parsed, all constants are references, like
@@ -85,7 +86,7 @@ struct constant {
     }
 };
 
-// "value" is a value used in the right hand side of an assignment
+// "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.
@@ -205,11 +206,13 @@ public:
 // 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 above (only the size()
+//    (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.).
+// 4. A single function call (attribute_exists etc.). The parser actually
+//    accepts a more general "value" here but later stages reject a value
+//    which is not a function call (because DynamoDB does it too).
 class primitive_condition {
 public:
     enum class type {
@@ -252,7 +255,3 @@ public:
 
 } // 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/http_compression.cc

@@ -1,301 +0,0 @@
-/*
- * Copyright 2025-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "alternator/http_compression.hh"
-#include "alternator/server.hh"
-#include <seastar/coroutine/maybe_yield.hh>
-#include <zlib.h>
-
-static logging::logger slogger("alternator-http-compression");
-
-namespace alternator {
-
-
-static constexpr size_t compressed_buffer_size = 1024;
-class zlib_compressor {
-    z_stream _zs;
-    temporary_buffer<char> _output_buf;
-    noncopyable_function<future<>(temporary_buffer<char>&&)> _write_func;
-public:
-    zlib_compressor(bool gzip, int compression_level, noncopyable_function<future<>(temporary_buffer<char>&&)> write_func)
-     : _write_func(std::move(write_func)) {
-        memset(&_zs, 0, sizeof(_zs));
-        if (deflateInit2(&_zs, std::clamp(compression_level, Z_NO_COMPRESSION, Z_BEST_COMPRESSION), Z_DEFLATED,
-                (gzip ? 16 : 0) + MAX_WBITS, 8, Z_DEFAULT_STRATEGY) != Z_OK) {
-            // Should only happen if memory allocation fails
-            throw std::bad_alloc();
-        }
-    }
-    ~zlib_compressor() {
-        deflateEnd(&_zs);
-    }
-    future<> close() {
-        return compress(nullptr, 0, true);
-    }
-
-    future<> compress(const char* buf, size_t len, bool is_last_chunk = false) {
-        _zs.next_in = reinterpret_cast<unsigned char*>(const_cast<char*>(buf));
-        _zs.avail_in = (uInt) len;
-        int mode = is_last_chunk ? Z_FINISH : Z_NO_FLUSH;
-        while(_zs.avail_in > 0 || is_last_chunk) {
-            co_await coroutine::maybe_yield();
-            if (_output_buf.empty()) {
-                if (is_last_chunk) {
-                    uint32_t max_buffer_size = 0;
-                    deflatePending(&_zs, &max_buffer_size, nullptr);
-                    max_buffer_size += deflateBound(&_zs, _zs.avail_in) + 1;
-                    _output_buf = temporary_buffer<char>(std::min(compressed_buffer_size, (size_t) max_buffer_size));
-                } else {
-                    _output_buf = temporary_buffer<char>(compressed_buffer_size);
-                }
-                _zs.next_out = reinterpret_cast<unsigned char*>(_output_buf.get_write());
-                _zs.avail_out = compressed_buffer_size;
-            }
-            int e = deflate(&_zs, mode);
-            if (e < Z_OK) {
-                throw api_error::internal("Error during compression of response body");
-            }
-            if (e == Z_STREAM_END || _zs.avail_out < compressed_buffer_size / 4) {
-                _output_buf.trim(compressed_buffer_size - _zs.avail_out);
-                co_await _write_func(std::move(_output_buf));
-                if (e == Z_STREAM_END) {
-                    break;
-                }
-            }
-        }
-    }
-};
-
-// Helper string_view functions for parsing Accept-Encoding header
-struct case_insensitive_cmp_sv {
-    bool operator()(std::string_view s1, std::string_view s2) const {
-        return std::equal(s1.begin(), s1.end(), s2.begin(), s2.end(),
-            [](char a, char b) { return ::tolower(a) == ::tolower(b); });
-    }
-};
-static inline std::string_view trim_left(std::string_view sv) {
-    while (!sv.empty() && std::isspace(static_cast<unsigned char>(sv.front())))
-        sv.remove_prefix(1);
-    return sv;
-}
-static inline std::string_view trim_right(std::string_view sv) {
-    while (!sv.empty() && std::isspace(static_cast<unsigned char>(sv.back())))
-        sv.remove_suffix(1);
-    return sv;
-}
-static inline std::string_view trim(std::string_view sv) {
-    return trim_left(trim_right(sv));
-}
-
-inline std::vector<std::string_view> split(std::string_view text, char separator) {
-    std::vector<std::string_view> tokens;
-    if (text == "") {
-        return tokens;
-    }
-
-    while (true) {
-        auto pos = text.find_first_of(separator);
-        if (pos != std::string_view::npos) {
-            tokens.emplace_back(text.data(), pos);
-            text.remove_prefix(pos + 1);
-        } else {
-            tokens.emplace_back(text);
-            break;
-        }
-    }
-    return tokens;
-}
-
-constexpr response_compressor::compression_type response_compressor::get_compression_type(std::string_view encoding) {
-    for (size_t i = 0; i < static_cast<size_t>(compression_type::count); ++i) {
-        if (case_insensitive_cmp_sv{}(encoding, compression_names[i])) {
-            return static_cast<compression_type>(i);
-        }
-    }
-    return compression_type::unknown;
-}
-
-response_compressor::compression_type response_compressor::find_compression(std::string_view accept_encoding, size_t response_size) {
-    std::optional<float> ct_q[static_cast<size_t>(compression_type::count)];
-    ct_q[static_cast<size_t>(compression_type::none)] = std::numeric_limits<float>::min(); // enabled, but lowest priority
-    compression_type selected_ct = compression_type::none;
-
-    std::vector<std::string_view> entries = split(accept_encoding, ',');
-    for (auto& e : entries) {
-        std::vector<std::string_view> params = split(e, ';');
-        if (params.size() == 0) {
-            continue;
-        }
-        compression_type ct = get_compression_type(trim(params[0]));
-        if (ct == compression_type::unknown) {
-            continue; // ignore unknown encoding types
-        }
-        if (ct_q[static_cast<size_t>(ct)].has_value() && ct_q[static_cast<size_t>(ct)] != 0.0f) {
-            continue; // already processed this encoding
-        }
-        if (response_size < _threshold[static_cast<size_t>(ct)]) {
-            continue; // below threshold treat as unknown
-        }
-        for (size_t i = 1; i < params.size(); ++i) { // find "q=" parameter
-            auto pos = params[i].find("q=");
-            if (pos == std::string_view::npos) {
-                continue;
-            }
-            std::string_view param = params[i].substr(pos + 2);
-            param = trim(param);
-            // parse quality value
-            float q_value = 1.0f;
-            auto [ptr, ec] = std::from_chars(param.data(), param.data() + param.size(), q_value);
-            if (ec != std::errc() || ptr != param.data() + param.size()) {
-                continue;
-            }
-            if (q_value < 0.0) {
-                q_value = 0.0;
-            } else if (q_value > 1.0) {
-                q_value = 1.0;
-            }
-            ct_q[static_cast<size_t>(ct)] = q_value;
-            break; // we parsed quality value
-        }
-        if (!ct_q[static_cast<size_t>(ct)].has_value()) {
-            ct_q[static_cast<size_t>(ct)] = 1.0f; // default quality value
-        }
-        // keep the highest encoding (in the order, unless 'any')
-        if (selected_ct == compression_type::any) {
-            if (ct_q[static_cast<size_t>(ct)] >= ct_q[static_cast<size_t>(selected_ct)]) {
-                selected_ct = ct;
-            }
-        } else {
-            if (ct_q[static_cast<size_t>(ct)] > ct_q[static_cast<size_t>(selected_ct)]) {
-                selected_ct = ct;
-            }
-        }
-    }
-    if (selected_ct == compression_type::any) {
-        // select any not mentioned or highest quality
-        selected_ct = compression_type::none;
-        for (size_t i = 0; i < static_cast<size_t>(compression_type::compressions_count); ++i) {
-            if (!ct_q[i].has_value()) {
-                return static_cast<compression_type>(i);
-            }
-            if (ct_q[i] > ct_q[static_cast<size_t>(selected_ct)]) {
-                selected_ct = static_cast<compression_type>(i);
-            }
-        }
-    }
-    return selected_ct;
-}
-
-static future<chunked_content> compress(response_compressor::compression_type ct, const db::config& cfg, std::string str) {
-    chunked_content compressed;
-    auto write = [&compressed](temporary_buffer<char>&& buf) -> future<> {
-        compressed.push_back(std::move(buf));
-        return make_ready_future<>();
-    };
-    zlib_compressor compressor(ct != response_compressor::compression_type::deflate,
-        cfg.alternator_response_gzip_compression_level(), std::move(write));
-    co_await compressor.compress(str.data(), str.size(), true);
-    co_return compressed;
-}
-
-static sstring flatten(chunked_content&& cc) {
-    size_t total_size = 0;
-    for (const auto& chunk : cc) {
-        total_size += chunk.size();
-    }
-    sstring result = sstring{ sstring::initialized_later{}, total_size };
-    size_t offset = 0;
-    for (const auto& chunk : cc) {
-        std::copy(chunk.begin(), chunk.end(), result.begin() + offset);
-        offset += chunk.size();
-    }
-    return result;
-}
-
-future<std::unique_ptr<http::reply>> response_compressor::generate_reply(std::unique_ptr<http::reply> rep, sstring accept_encoding, const char* content_type, std::string&& response_body) {
-    response_compressor::compression_type ct = find_compression(accept_encoding, response_body.size());
-    if (ct != response_compressor::compression_type::none) {
-        rep->add_header("Content-Encoding", get_encoding_name(ct));
-        rep->set_content_type(content_type);
-        return compress(ct, cfg, std::move(response_body)).then([rep = std::move(rep)] (chunked_content compressed) mutable {
-            rep->_content = flatten(std::move(compressed));
-            return make_ready_future<std::unique_ptr<http::reply>>(std::move(rep));
-        });
-    } else {
-        // Note that despite the move, there is a copy here -
-        // as str is std::string and rep->_content is sstring.
-        rep->_content = std::move(response_body);
-        rep->set_content_type(content_type);
-    }
-    return make_ready_future<std::unique_ptr<http::reply>>(std::move(rep));
-}
-
-template<typename Compressor>
-class compressed_data_sink_impl : public data_sink_impl {
-    output_stream<char> _out;
-    Compressor _compressor;
-public:
-    template<typename... Args>
-    compressed_data_sink_impl(output_stream<char>&& out, Args&&... args)
-     : _out(std::move(out)), _compressor(std::forward<Args>(args)..., [this](temporary_buffer<char>&& buf) {
-        return _out.write(std::move(buf));
-    }) { }
-
-    future<> put(std::span<temporary_buffer<char>> data) override {
-        return data_sink_impl::fallback_put(data, [this] (temporary_buffer<char>&& buf) {
-            return do_put(std::move(buf));
-        });
-    }
-
-private:
-    future<> do_put(temporary_buffer<char> buf) {
-        co_return co_await _compressor.compress(buf.get(), buf.size());
-
-    }
-    future<> close() override {
-        return _compressor.close().then([this] {
-            return _out.close();
-        });
-    }
-};
-
-executor::body_writer compress(response_compressor::compression_type ct, const db::config& cfg, executor::body_writer&& bw) {
-    return [bw = std::move(bw), ct, level = cfg.alternator_response_gzip_compression_level()](output_stream<char>&& out) mutable -> future<> {
-        output_stream_options opts;
-        opts.trim_to_size = true;
-        std::unique_ptr<data_sink_impl> data_sink_impl;
-        switch (ct) {
-            case response_compressor::compression_type::gzip:
-                data_sink_impl = std::make_unique<compressed_data_sink_impl<zlib_compressor>>(std::move(out), true, level);
-                break;
-            case response_compressor::compression_type::deflate:
-                data_sink_impl = std::make_unique<compressed_data_sink_impl<zlib_compressor>>(std::move(out), false, level);
-                break;
-            case response_compressor::compression_type::none:
-            case response_compressor::compression_type::any:
-            case response_compressor::compression_type::unknown:
-                on_internal_error(slogger,"Compression not selected");
-            default:
-                on_internal_error(slogger, "Unsupported compression type for data sink");
-        }
-        return bw(output_stream<char>(data_sink(std::move(data_sink_impl)), compressed_buffer_size, opts));
-    };
-}
-
-future<std::unique_ptr<http::reply>> response_compressor::generate_reply(std::unique_ptr<http::reply> rep, sstring accept_encoding, const char* content_type, executor::body_writer&& body_writer) {
-    response_compressor::compression_type ct = find_compression(accept_encoding, std::numeric_limits<size_t>::max());
-    if (ct != response_compressor::compression_type::none) {
-        rep->add_header("Content-Encoding", get_encoding_name(ct));
-        rep->write_body(content_type, compress(ct, cfg, std::move(body_writer)));
-    } else {
-        rep->write_body(content_type, std::move(body_writer));
-    }
-    return make_ready_future<std::unique_ptr<http::reply>>(std::move(rep));
-}
-
-} // namespace alternator

alternator/http_compression.hh

@@ -1,91 +0,0 @@
-/*
- * Copyright 2025-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "alternator/executor.hh"
-#include <seastar/http/httpd.hh>
-#include "db/config.hh"
-
-namespace alternator {
-
-class response_compressor {
-public:
-    enum class compression_type {
-        gzip,
-        deflate,
-        compressions_count,
-        any = compressions_count,
-        none,
-        count,
-        unknown = count
-    };
-    static constexpr std::string_view compression_names[] = {
-        "gzip",
-        "deflate",
-        "*",
-        "identity"
-    };
-
-    static sstring get_encoding_name(compression_type ct) {
-        return sstring(compression_names[static_cast<size_t>(ct)]);
-    }
-    static constexpr compression_type get_compression_type(std::string_view encoding);
-
-    sstring get_accepted_encoding(const http::request& req) {
-        if (get_threshold() == 0) {
-            return "";
-        }
-        return req.get_header("Accept-Encoding");
-    }
-    compression_type find_compression(std::string_view accept_encoding, size_t response_size);
-
-    response_compressor(const db::config& cfg)
-        : cfg(cfg)
-        ,_gzip_level_observer(
-            cfg.alternator_response_gzip_compression_level.observe([this](int v) {
-                    update_threshold();
-                }))
-        ,_gzip_threshold_observer(
-            cfg.alternator_response_compression_threshold_in_bytes.observe([this](uint32_t v) {
-                    update_threshold();
-                }))
-    {
-        update_threshold();
-    }
-    response_compressor(const response_compressor& rhs) : response_compressor(rhs.cfg) {}
-
-private:
-    const db::config& cfg;
-    utils::observable<int>::observer _gzip_level_observer;
-    utils::observable<uint32_t>::observer _gzip_threshold_observer;
-    uint32_t _threshold[static_cast<size_t>(compression_type::count)];
-
-    size_t get_threshold() { return _threshold[static_cast<size_t>(compression_type::any)]; }
-    void update_threshold() {
-        _threshold[static_cast<size_t>(compression_type::none)] = std::numeric_limits<uint32_t>::max();
-        _threshold[static_cast<size_t>(compression_type::any)] = std::numeric_limits<uint32_t>::max();
-        uint32_t gzip = cfg.alternator_response_gzip_compression_level() <= 0 ? std::numeric_limits<uint32_t>::max()
-            : cfg.alternator_response_compression_threshold_in_bytes();
-        _threshold[static_cast<size_t>(compression_type::gzip)] = gzip;
-        _threshold[static_cast<size_t>(compression_type::deflate)] = gzip;
-        for (size_t i = 0; i < static_cast<size_t>(compression_type::compressions_count); ++i) {
-            if (_threshold[i] < _threshold[static_cast<size_t>(compression_type::any)]) {
-                _threshold[static_cast<size_t>(compression_type::any)] = _threshold[i];
-            }
-        }
-    }
-
-public:
-    future<std::unique_ptr<http::reply>> generate_reply(std::unique_ptr<http::reply> rep,
-         sstring accept_encoding, const char* content_type, std::string&& response_body);
-    future<std::unique_ptr<http::reply>> generate_reply(std::unique_ptr<http::reply> rep,
-         sstring accept_encoding, const char* content_type, executor::body_writer&& body_writer);
-};
-
-}

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

@@ -3,31 +3,23 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #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
+// "Expected" parameter) which requir a read before the write, and UpdateItem
 // may also have an update expression which refers to the item's old value.
 //
 // The code below supports running the read and the write together as one
@@ -58,7 +50,7 @@ public:
     static write_isolation get_write_isolation_for_schema(schema_ptr schema);
 
     static write_isolation default_write_isolation;
-
+public:
     static void set_default_write_isolation(std::string_view mode);
 
 protected:
@@ -71,17 +63,13 @@ protected:
     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.
@@ -89,8 +77,6 @@ protected:
     // 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
@@ -109,27 +95,20 @@ public:
     // 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;
+    virtual std::optional<mutation> apply(std::unique_ptr<rjson::value> previous_item, api::timestamp_type ts) const = 0;
     // Convert the above apply() into the signature needed by cas_request:
-    virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts, cdc::per_request_options& cdc_opts) override;
+    virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts) override;
     virtual ~rmw_operation() = default;
-    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(); }
+            stats& stats);
+    std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
 };
 
 } // namespace alternator

alternator/serialization.cc

@@ -3,17 +3,18 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include "utils/base64.hh"
 #include "utils/rjson.hh"
-#include "utils/log.hh"
+#include "log.hh"
 #include "serialization.hh"
 #include "error.hh"
-#include "types/concrete_types.hh"
-#include "types/json_utils.hh"
-#include "mutation/position_in_partition.hh"
+#include "rapidjson/writer.h"
+#include "concrete_types.hh"
+#include "cql3/type_json.hh"
+#include "position_in_partition.hh"
 
 static logging::logger slogger("alternator-serialization");
 
@@ -49,115 +50,6 @@ type_representation represent_type(alternator_type 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;
@@ -167,19 +59,21 @@ struct from_json_visitor {
         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));
+        bo.write(rjson::base64_decode(v));
     }
     void operator()(const boolean_type_impl& t) const {
         bo.write(boolean_type->decompose(v.GetBool()));
     }
     void operator()(const decimal_type_impl& t) const {
-        bo.write(decimal_type->decompose(parse_and_validate_number(rjson::to_string_view(v))));
+        try {
+            bo.write(t.from_string(rjson::to_string_view(v)));
+        } catch (const marshal_exception& e) {
+            throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", v));
+        }
     }
     // default
     void operator()(const abstract_type& t) const {
-        bo.write(from_json_object(t, v));
+        bo.write(from_json_object(t, v, cql_serialization_format::internal()));
     }
 };
 
@@ -245,27 +139,6 @@ rjson::value deserialize_item(bytes_view 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"},
@@ -282,23 +155,15 @@ std::string type_to_string(data_type type) {
     return it->second;
 }
 
-std::optional<bytes> try_get_key_column_value(const rjson::value& item, const column_definition& column) {
+bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
     std::string column_name = column.name_as_text();
     const rjson::value* key_typed_value = rjson::find(item, column_name);
     if (!key_typed_value) {
-        return std::nullopt;
+        throw api_error::validation(format("Key column {} not found", column_name));
     }
     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
@@ -306,26 +171,19 @@ bytes get_key_column_value(const rjson::value& item, const column_definition& co
 // 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) {
+    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
+            !key_typed_value.MemberBegin()->value.IsString()) {
         throw api_error::validation(
-                fmt::format("Malformed value object for {} {}: {}",
+                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 {}",
+                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;
 }
 
@@ -340,11 +198,7 @@ bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column
                 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)));
+        return rjson::base64_decode(value);
     } else {
         return column.type->from_string(value_view);
     }
@@ -356,7 +210,7 @@ rjson::value json_key_column_value(bytes_view cell, const column_definition& col
         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());
+        return rjson::from_string(std::string(reinterpret_cast<const char*>(cell.data()), cell.size()));
     } else if (column.type == decimal_type) {
         // FIXME: use specialized Alternator number type, not the more
         // general "decimal_type". A dedicated type can be more efficient
@@ -388,43 +242,26 @@ clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
         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.
+    // FIXME: this is a loop, but we really allow only one clustering key column.
     for (const column_definition& cdef : schema->clustering_key_columns()) {
-        auto raw_value = get_key_column_value(item,  cdef);
+        bytes 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));
+    auto ck = ck_from_json(item, schema);
+    if (is_alternator_keyspace(schema->ks_name())) {
+        return position_in_partition::for_key(std::move(ck));
     }
-    
     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");
     }
+    partition_region region;
     bound_weight weight;
     if (region_item) {
         auto region_view = rjson::to_string_view(get_typed_value(*region_item, "S", scylla_paging_region, "key region"));
@@ -439,30 +276,32 @@ position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema)
         } 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);
+        return position_in_partition(region, weight, region == partition_region::clustered ? std::optional(std::move(ck)) : std::nullopt);
     }
-    auto ck = ck_from_json(item, schema);
     if (ck.is_empty()) {
-        return position_in_partition::for_partition_start();
+        return position_in_partition(position_in_partition::partition_start_tag_t());
     }
     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));
+        throw api_error::validation(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));
+        throw api_error::validation(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));
+    try {
+        if (!it->value.IsString()) {
+            // We shouldn't reach here. Callers normally validate their input
+            // earlier with validate_value().
+            throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
+        }
+        return big_decimal(rjson::to_string_view(it->value));
+    } catch (const marshal_exception& e) {
+        throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", it->value));
     }
-    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) {
@@ -474,19 +313,8 @@ std::optional<big_decimal> try_unwrap_number(const rjson::value& v) {
         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 big_decimal(rjson::to_string_view(it->value));
+    } catch (const marshal_exception& e) {
         return std::nullopt;
     }
 }
@@ -496,7 +324,7 @@ const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value&
         return {"", nullptr};
     }
     auto it = v.MemberBegin();
-    const std::string it_key = rjson::to_string(it->name);
+    const std::string it_key = it->name.GetString();
     if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
         return {std::move(it_key), nullptr};
     }
@@ -520,7 +348,7 @@ 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();
+    std::string str_ret = std::string((n1 + n2).to_string());
     rjson::add(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
@@ -529,7 +357,7 @@ 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();
+    std::string str_ret = std::string((n1 - n2).to_string());
     rjson::add(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
@@ -540,7 +368,7 @@ 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));
+        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
     }
     if (!set1 || !set2) {
         throw api_error::validation("UpdateExpression: ADD operation for sets must be given sets as arguments");
@@ -568,7 +396,7 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
     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));
+        throw api_error::validation(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");

alternator/serialization.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -11,9 +11,9 @@
 #include <string>
 #include <string_view>
 #include <optional>
-#include "types/types.hh"
-#include "schema/schema_fwd.hh"
-#include "keys/keys.hh"
+#include "types.hh"
+#include "schema_fwd.hh"
+#include "keys.hh"
 #include "utils/rjson.hh"
 #include "utils/big_decimal.hh"
 
@@ -43,7 +43,6 @@ 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);
 
@@ -55,7 +54,7 @@ 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,
+// 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);
 
@@ -63,11 +62,6 @@ big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
 // 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}
@@ -95,12 +89,5 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::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.cc

@@ -3,47 +3,36 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include "alternator/server.hh"
-#include "gms/application_state.hh"
-#include "utils/log.hh"
-#include <fmt/ranges.h>
+#include "log.hh"
 #include <seastar/http/function_handlers.hh>
 #include <seastar/http/short_streams.hh>
 #include <seastar/core/coroutine.hh>
-#include <seastar/coroutine/maybe_yield.hh>
+#include <seastar/json/json_elements.hh>
 #include <seastar/util/defer.hh>
 #include <seastar/util/short_streams.hh>
 #include "seastarx.hh"
 #include "error.hh"
-#include "service/client_state.hh"
 #include "service/qos/service_level_controller.hh"
-#include "utils/assert.hh"
-#include "timeout_config.hh"
 #include "utils/rjson.hh"
 #include "auth.hh"
 #include <cctype>
-#include <string_view>
-#include <utility>
 #include "service/storage_proxy.hh"
 #include "gms/gossiper.hh"
 #include "utils/overloaded_functor.hh"
-#include "utils/aws_sigv4.hh"
-#include "client_data.hh"
-#include "utils/updateable_value.hh"
-#include <zlib.h>
-#include "alternator/http_compression.hh"
+#include "utils/fb_utilities.hh"
 
 static logging::logger slogger("alternator-server");
 
 using namespace httpd;
-using request = http::request;
-using reply = http::reply;
 
 namespace alternator {
 
+static constexpr auto TARGET = "X-Amz-Target";
+
 inline std::vector<std::string_view> split(std::string_view text, char separator) {
     std::vector<std::string_view> tokens;
     if (text == "") {
@@ -104,20 +93,10 @@ static void handle_CORS(const request& req, reply& rep, bool preflight) {
 // the user directly. Other exceptions are unexpected, and reported as
 // Internal Server Error.
 class api_handler : public handler_base {
-    // Although the the DynamoDB API responses are JSON, additional
-    // conventions apply to these responses. For this reason, DynamoDB uses
-    // the content type "application/x-amz-json-1.0" instead of the standard
-    // "application/json". Some other AWS services use later versions instead
-    // of "1.0", but DynamoDB currently uses "1.0". Note that this content
-    // type applies to all replies, both success and error.
-    static constexpr const char* REPLY_CONTENT_TYPE = "application/x-amz-json-1.0";
 public:
-    api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle,
-                const db::config& config) : _response_compressor(config), _f_handle(
+    api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle) : _f_handle(
          [this, _handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
-         sstring accept_encoding = _response_compressor.get_accepted_encoding(*req);
-         return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped(
-            [this, rep = std::move(rep), accept_encoding=std::move(accept_encoding)](future<executor::request_return_type> resf) mutable {
+         return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped([this, rep = std::move(rep)](future<executor::request_return_type> resf) mutable {
              if (resf.failed()) {
                  // Exceptions of type api_error are wrapped as JSON and
                  // returned to the client as expected. Other types of
@@ -136,21 +115,26 @@ public:
                  }
                  return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
              }
-             auto res = resf.get();
-             return std::visit(overloaded_functor {
-                [&] (std::string&& str) {
-                    return _response_compressor.generate_reply(std::move(rep), std::move(accept_encoding),
-                                                               REPLY_CONTENT_TYPE, std::move(str));
-                },
-                [&] (executor::body_writer&& body_writer) {
-                    return _response_compressor.generate_reply(std::move(rep), std::move(accept_encoding),
-                                                               REPLY_CONTENT_TYPE, std::move(body_writer));
-                },
-                [&] (const api_error& err) {
-                    generate_error_reply(*rep, err);
-                    return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-                }
-             }, std::move(res));
+             auto res = resf.get0();
+             std::visit(overloaded_functor {
+                 [&] (const json::json_return_type& json_return_value) {
+                     slogger.trace("api_handler success case");
+                     if (json_return_value._body_writer) {
+                         // Unfortunately, write_body() forces us to choose
+                         // from a fixed and irrelevant list of "mime-types"
+                         // at this point. But we'll override it with the
+                         // one (application/x-amz-json-1.0) below.
+                         rep->write_body("json", std::move(json_return_value._body_writer));
+                     } else {
+                         rep->_content += json_return_value._res;
+                     }
+                 },
+                 [&] (const api_error& err) {
+                     generate_error_reply(*rep, err);
+                 }
+             }, res);
+
+             return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
          });
     }) { }
 
@@ -159,7 +143,8 @@ public:
             std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
         handle_CORS(*req, *rep, false);
         return _f_handle(std::move(req), std::move(rep)).then(
-                [](std::unique_ptr<reply> rep) {
+                [this](std::unique_ptr<reply> rep) {
+                    rep->set_mime_type("application/x-amz-json-1.0");
                     rep->done();
                     return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
                 });
@@ -168,18 +153,13 @@ public:
 protected:
     void generate_error_reply(reply& rep, const api_error& err) {
         rjson::value results = rjson::empty_object();
-        if (!err._extra_fields.IsNull() && err._extra_fields.IsObject()) {
-            results = rjson::copy(err._extra_fields);
-        }
         rjson::add(results, "__type", rjson::from_string("com.amazonaws.dynamodb.v20120810#" + err._type));
         rjson::add(results, "message", err._msg);
         rep._content = rjson::print(std::move(results));
         rep._status = err._http_code;
-        rep.set_content_type(REPLY_CONTENT_TYPE);
         slogger.trace("api_handler error case: {}", rep._content);
     }
 
-    response_compressor _response_compressor;
     future_handler_function _f_handle;
 };
 
@@ -222,35 +202,11 @@ protected:
         // using _gossiper().get_live_members(). But getting
         // just the list of live nodes in this DC needs more elaborate code:
         auto& topology = _proxy.get_token_metadata_ptr()->get_topology();
-        // /localnodes lists nodes in a single DC. By default the DC of this
-        // server is used, but it can be overridden by a "dc" query option.
-        // If the DC does not exist, we return an empty list - not an error.
-        sstring query_dc = req->get_query_param("dc");
-        sstring local_dc = query_dc.empty() ? topology.get_datacenter() : query_dc;
-        std::unordered_set<locator::host_id> local_dc_nodes;
-        const auto& endpoints = topology.get_datacenter_endpoints();
-        auto dc_it = endpoints.find(local_dc);
-        if (dc_it != endpoints.end()) {
-            local_dc_nodes = dc_it->second;
-        }
-        // By default, /localnodes lists the nodes of all racks in the given
-        // DC, unless a single rack is selected by the "rack" query option.
-        // If the rack does not exist, we return an empty list - not an error.
-        sstring query_rack = req->get_query_param("rack");
-        for (auto& id : local_dc_nodes) {
-            if (!query_rack.empty()) {
-                auto rack = _gossiper.get_application_state_value(id, gms::application_state::RACK);
-                if (rack != query_rack) {
-                    continue;
-                }
-            }
-            // Note that it's not enough for the node to be is_alive() - a
-            // node joining the cluster is also "alive" but not responsive to
-            // requests. We alive *and* normal. See #19694, #21538.
-            if (_gossiper.is_alive(id) && _gossiper.is_normal(id)) {
-                // Use the gossiped broadcast_rpc_address if available instead
-                // of the internal IP address "ip". See discussion in #18711.
-                rjson::push_back(results, rjson::from_string(_gossiper.get_rpc_address(id)));
+        sstring local_dc = topology.get_datacenter();
+        std::unordered_set<gms::inet_address> local_dc_nodes = topology.get_datacenter_endpoints().at(local_dc);
+        for (auto& ip : local_dc_nodes) {
+            if (_gossiper.is_alive(ip)) {
+                rjson::push_back(results, rjson::from_string(ip.to_sstring()));
             }
         }
         rep->set_status(reply::status_type::ok);
@@ -276,57 +232,24 @@ protected:
     }
 };
 
-// This function increments the authentication_failures counter, and may also
-// log a warn-level message and/or throw an exception, depending on what
-// enforce_authorization and warn_authorization are set to.
-// The username and client address are only used for logging purposes -
-// they are not included in the error message returned to the client, since
-// the client knows who it is.
-// Note that if enforce_authorization is false, this function will return
-// without throwing. So a caller that doesn't want to continue after an
-// authentication_error must explicitly return after calling this function.
-template<typename Exception>
-static void authentication_error(alternator::stats& stats, bool enforce_authorization, bool warn_authorization, Exception&& e, std::string_view user, gms::inet_address client_address) {
-    stats.authentication_failures++;
-    if (enforce_authorization) {
-        if (warn_authorization) {
-            slogger.warn("alternator_warn_authorization=true: {} for user {}, client address {}", e.what(), user, client_address);
-        }
-        throw std::move(e);
-    } else {
-        if (warn_authorization) {
-            slogger.warn("If you set alternator_enforce_authorization=true the following will be enforced: {} for user {}, client address {}", e.what(), user, client_address);
-        }
-    }
-}
-
 future<std::string> server::verify_signature(const request& req, const chunked_content& content) {
-    if (!_enforce_authorization.get() && !_warn_authorization.get()) {
+    if (!_enforce_authorization) {
         slogger.debug("Skipping authorization");
         return make_ready_future<std::string>();
     }
     auto host_it = req._headers.find("Host");
     if (host_it == req._headers.end()) {
-        authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-            api_error::invalid_signature("Host header is mandatory for signature verification"), 
-            "", req.get_client_address());
-        return make_ready_future<std::string>();
+        throw api_error::invalid_signature("Host header is mandatory for signature verification");
     }
     auto authorization_it = req._headers.find("Authorization");
     if (authorization_it == req._headers.end()) {
-        authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-            api_error::missing_authentication_token("Authorization header is mandatory for signature verification"),
-            "", req.get_client_address());
-        return make_ready_future<std::string>();
+        throw api_error::missing_authentication_token("Authorization header is mandatory for signature verification");
     }
     std::string host = host_it->second;
     std::string_view authorization_header = authorization_it->second;
     auto pos = authorization_header.find_first_of(' ');
     if (pos == std::string_view::npos || authorization_header.substr(0, pos) != "AWS4-HMAC-SHA256") {
-        authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-            api_error::invalid_signature(fmt::format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header)),
-            "", req.get_client_address());
-        return make_ready_future<std::string>();
+        throw api_error::invalid_signature(format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header));
     }
     authorization_header.remove_prefix(pos+1);
     std::string credential;
@@ -361,9 +284,7 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
 
     std::vector<std::string_view> credential_split = split(credential, '/');
     if (credential_split.size() != 5) {
-        authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-            api_error::validation(fmt::format("Incorrect credential information format: {}", credential)), "", req.get_client_address());
-        return make_ready_future<std::string>();
+        throw api_error::validation(format("Incorrect credential information format: {}", credential));
     }
     std::string user(credential_split[0]);
     std::string datestamp(credential_split[1]);
@@ -374,81 +295,34 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
     for (const auto& header : signed_headers) {
         signed_headers_map.emplace(header, std::string_view());
     }
-    std::vector<std::string> modified_values;
     for (auto& header : req._headers) {
         std::string header_str;
         header_str.resize(header.first.size());
         std::transform(header.first.begin(), header.first.end(), header_str.begin(), ::tolower);
         auto it = signed_headers_map.find(header_str);
         if (it != signed_headers_map.end()) {
-            // replace multiple spaces in the header value header.second with
-            // a single space, as required by AWS SigV4 header canonization.
-            // If we modify the value, we need to save it in modified_values
-            // to keep it alive.
-            std::string value;
-            value.reserve(header.second.size());
-            bool prev_space = false;
-            bool modified = false;
-            for (char ch : header.second) {
-                if (ch == ' ') {
-                    if (!prev_space) {
-                        value += ch;
-                        prev_space = true;
-                    } else {
-                        modified = true; // skip a space
-                    }
-                } else {
-                    value += ch;
-                    prev_space = false;
-                }
-            }
-            if (modified) {
-                modified_values.emplace_back(std::move(value));
-                it->second = std::string_view(modified_values.back());
-            } else {
-                it->second = std::string_view(header.second);
-            }
+            it->second = std::string_view(header.second);
         }
     }
 
     auto cache_getter = [&proxy = _proxy] (std::string username) {
         return get_key_from_roles(proxy, std::move(username));
     };
-    return _key_cache.get_ptr(user, cache_getter).then_wrapped([this, &req, &content,
+    return _key_cache.get_ptr(user, cache_getter).then([this, &req, &content,
                                                     user = std::move(user),
                                                     host = std::move(host),
                                                     datestamp = std::move(datestamp),
                                                     signed_headers_str = std::move(signed_headers_str),
                                                     signed_headers_map = std::move(signed_headers_map),
-                                                    modified_values = std::move(modified_values),
                                                     region = std::move(region),
                                                     service = std::move(service),
-                                                    user_signature = std::move(user_signature)] (future<key_cache::value_ptr> key_ptr_fut) {
-        key_cache::value_ptr key_ptr(nullptr);
-        try {
-            key_ptr = key_ptr_fut.get();
-        } catch (const api_error& e) {
-            authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-                e, user, req.get_client_address());
-            return std::string();
-        }
-        std::string signature;
-        try {
-            signature = utils::aws::get_signature(user, *key_ptr, std::string_view(host), "/", req._method,
-                datestamp, signed_headers_str, signed_headers_map, &content, region, service, "");
-        } catch (const std::exception& e) {
-            authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-                api_error::invalid_signature(fmt::format("invalid signature: {}", e.what())),
-                user, req.get_client_address());
-            return std::string();
-        }
+                                                    user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
+        std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
+                datestamp, signed_headers_str, signed_headers_map, content, region, service, "");
 
         if (signature != std::string_view(user_signature)) {
             _key_cache.remove(user);
-            authentication_error(_executor._stats, _enforce_authorization.get(), _warn_authorization.get(),
-                api_error::unrecognized_client("wrong signature"),
-                user, req.get_client_address());
-            return std::string();
+            throw api_error::unrecognized_client("The security token included in the request is invalid.");
         }
         return user;
     });
@@ -461,83 +335,36 @@ static tracing::trace_state_ptr create_tracing_session(tracing::tracing& tracing
     return tracing_instance.create_session(tracing::trace_type::QUERY, props);
 }
 
-// A helper class to represent a potentially truncated view of a chunked_content.
-// If the content is short enough and single chunked, it just holds a view into the content.
-// Otherwise it will be copied into an internal buffer, possibly truncated (depending on maximum allowed size passed in),
-// and the view will point into that buffer.
-// `as_view()` method will return the view.
-// `take_as_sstring()` will either move out the internal buffer (if any), or create a new sstring from the view.
-// You should consider `as_view()` valid as long both the original chunked_content and the truncated_content object are alive.
-class truncated_content {
-    std::string_view _view;
-    sstring _content_maybe;
-
-    void copy_from_content(const chunked_content& content) {
-        size_t offset = 0;
-        for(auto &tmp : content) {
-            size_t to_copy = std::min(tmp.size(), _content_maybe.size() - offset);
-            std::copy(tmp.get(), tmp.get() + to_copy, _content_maybe.data() + offset);
-            offset += to_copy;
-            if (offset >= _content_maybe.size()) {
-                break;
-            }
-        }
+// truncated_content_view() prints a potentially long chunked_content for
+// debugging purposes. In the common case when the content is not excessively
+// long, it just returns a view into the given content, without any copying.
+// But when the content is very long, it is truncated after some arbitrary
+// max_len (or one chunk, whichever comes first), with "<truncated>" added at
+// the end. To do this modification to the string, we need to create a new
+// std::string, so the caller must pass us a reference to one, "buf", where
+// we can store the content. The returned view is only alive for as long this
+// buf is kept alive.
+static std::string_view truncated_content_view(const chunked_content& content, std::string& buf) {
+    constexpr size_t max_len = 1024;
+    if (content.empty()) {
+        return std::string_view();
+    } else if (content.size() == 1 && content.begin()->size() <= max_len) {
+        return std::string_view(content.begin()->get(), content.begin()->size());
+    } else {
+        buf = std::string(content.begin()->get(), std::min(content.begin()->size(), max_len)) + "<truncated>";
+        return std::string_view(buf);
     }
-public:
-    truncated_content(const chunked_content& content, size_t max_len = std::numeric_limits<size_t>::max()) {
-        if (content.empty()) return;
-        if (content.size() == 1 && content.begin()->size() <= max_len) {
-            _view = std::string_view(content.begin()->get(), content.begin()->size());
-            return;
-        }
-
-        constexpr std::string_view truncated_text = "<truncated>";
-        size_t content_size = 0;
-        for(auto &tmp : content) {
-            content_size += tmp.size();
-        }
-        if (content_size <= max_len) {
-            _content_maybe = sstring{ sstring::initialized_later{}, content_size };
-            copy_from_content(content);
-        }
-        else {
-            _content_maybe = sstring{ sstring::initialized_later{}, max_len + truncated_text.size() };
-            copy_from_content(content);
-            std::copy(truncated_text.begin(), truncated_text.end(), _content_maybe.data() + _content_maybe.size() - truncated_text.size());
-        }
-        _view = std::string_view(_content_maybe);
-    }
-
-    std::string_view as_view() const { return _view; }
-    sstring take_as_sstring() && {
-        if (_content_maybe.empty() && !_view.empty()) {
-            return sstring{_view};
-        }
-        return std::move(_content_maybe);
-    }
-};
-
-// `truncated_content_view` will produce an object representing a view to a passed content
-// possibly truncated at some length. The value returned is used in two ways:
-// - to print it in logs (use `as_view()` method for this)
-// - to pass it to tracing object, where it will be stored and used later
-//   (use `take_as_sstring()` method as this produces a copy in form of a sstring)
-// `truncated_content` delays constructing `sstring` object until it's actually needed.
-// `truncated_content` is valid as long as passed `content` is alive.
-// if the content is truncated, `<truncated>` will be appended at the maximum size limit
-// and total size will be `max_users_query_size_in_trace_output() + strlen("<truncated>")`.
-static truncated_content truncated_content_view(const chunked_content& content, size_t max_size) {
-    return truncated_content{content, max_size};
 }
 
-static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_state, std::string_view username, std::string_view op, const chunked_content& query, size_t max_users_query_size_in_trace_output) {
+static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_state, std::string_view username, sstring_view op, const chunked_content& query) {
     tracing::trace_state_ptr trace_state;
     tracing::tracing& tracing_instance = tracing::tracing::get_local_tracing_instance();
     if (tracing_instance.trace_next_query() || tracing_instance.slow_query_tracing_enabled()) {
         trace_state = create_tracing_session(tracing_instance);
+        std::string buf;
         tracing::add_session_param(trace_state, "alternator_op", op);
-        tracing::add_query(trace_state, truncated_content_view(query, max_users_query_size_in_trace_output).take_as_sstring());
-        tracing::begin(trace_state, seastar::format("Alternator {}", op), client_state.get_client_address());
+        tracing::add_query(trace_state, truncated_content_view(query, buf));
+        tracing::begin(trace_state, format("Alternator {}", op), client_state.get_client_address());
         if (!username.empty()) {
             tracing::set_username(trace_state, auth::authenticated_user(username));
         }
@@ -545,220 +372,35 @@ static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_
     return trace_state;
 }
 
-// This read_entire_stream() is similar to Seastar's read_entire_stream()
-// which reads the given content_stream until its end into non-contiguous
-// memory. The difference is that this implementation takes an extra length
-// limit, and throws an error if we read more than this limit.
-// This length-limited variant would not have been needed if Seastar's HTTP
-// server's set_content_length_limit() worked in every case, but unfortunately
-// it does not - it only works if the request has a Content-Length header (see
-// issue #8196). In contrast this function can limit the request's length no
-// matter how it's encoded. We need this limit to protect Alternator from
-// oversized requests that can deplete memory.
-static future<chunked_content>
-read_entire_stream(input_stream<char>& inp, size_t length_limit) {
-    chunked_content ret;
-    // We try to read length_limit + 1 bytes, so that we can throw an
-    // exception if we managed to read more than length_limit.
-    ssize_t remain = length_limit + 1;
-    do {
-        temporary_buffer<char> buf = co_await inp.read_up_to(remain);
-        if (buf.empty()) {
-            break;
-        }
-        remain -= buf.size();
-        ret.push_back(std::move(buf));
-    } while (remain > 0);
-    // If we read the full length_limit + 1 bytes, we went over the limit:
-    if (remain <= 0) {
-        // By throwing here an error, we may send a reply (the error message)
-        // without having read the full request body. Seastar's httpd will
-        // realize that we have not read the entire content stream, and
-        // correctly mark the connection unreusable, i.e., close it.
-        // This means we are currently exposed to issue #12166 caused by
-        // Seastar issue 1325), where the client may get an RST instead of
-        // a FIN, and may rarely get a "Connection reset by peer" before
-        // reading the error we send.
-        throw api_error::payload_too_large(fmt::format("Request content length limit of {} bytes exceeded", length_limit));
-    }
-    co_return ret;
-}
-
-// safe_gzip_stream is an exception-safe wrapper for zlib's z_stream.
-// The "z_stream" struct is used by zlib to hold state while decompressing a
-// stream of data. It allocates memory which must be freed with inflateEnd(),
-// which the destructor of this class does.
-class safe_gzip_zstream {
-    z_stream _zs;
-public:
-    // If gzip is true, decode a gzip header (for "Content-Encoding: gzip").
-    // Otherwise, a zlib header (for "Content-Encoding: deflate").
-    safe_gzip_zstream(bool gzip = true) {
-        memset(&_zs, 0, sizeof(_zs));
-        if (inflateInit2(&_zs, gzip ? 16 + MAX_WBITS : MAX_WBITS) != Z_OK) {
-            // Should only happen if memory allocation fails
-            throw std::bad_alloc();
-        }
-    }
-    ~safe_gzip_zstream() {
-        inflateEnd(&_zs);
-    }
-    z_stream* operator->() {
-        return &_zs;
-    }
-    z_stream* get() {
-        return &_zs;
-    }
-    void reset() {
-        inflateReset(&_zs);
-    }
-};
-
-// ungzip() takes a chunked_content of a compressed request body, and returns
-// the uncompressed content as a chunked_content. If gzip is true, we expect
-// gzip header (for "Content-Encoding: gzip"), if gzip is false, we expect a
-// zlib header (for "Content-Encoding: deflate").
-// If the uncompressed content exceeds length_limit, an error is thrown.
-static future<chunked_content>
-ungzip(chunked_content&& compressed_body, size_t length_limit, bool gzip = true) {
-    chunked_content ret;
-    // output_buf can be any size - when uncompressing input_buf, it doesn't
-    // need to fit in a single output_buf, we'll use multiple output_buf for
-    // a single input_buf if needed.
-    constexpr size_t OUTPUT_BUF_SIZE = 4096;
-    temporary_buffer<char> output_buf;
-    safe_gzip_zstream strm(gzip);
-    bool complete_stream = false; // empty input is not a valid gzip/deflate
-    size_t total_out_bytes = 0;
-    for (const temporary_buffer<char>& input_buf : compressed_body) {
-        if (input_buf.empty()) {
-            continue;
-        }
-        complete_stream = false;
-        strm->next_in = (Bytef*) input_buf.get();
-        strm->avail_in = (uInt) input_buf.size();
-        do {
-            co_await coroutine::maybe_yield();
-            if (output_buf.empty()) {
-                output_buf = temporary_buffer<char>(OUTPUT_BUF_SIZE);
-            }
-            strm->next_out = (Bytef*) output_buf.get();
-            strm->avail_out = OUTPUT_BUF_SIZE;
-            int e = inflate(strm.get(), Z_NO_FLUSH);
-            size_t out_bytes = OUTPUT_BUF_SIZE - strm->avail_out;
-            if (out_bytes > 0) {
-                // If output_buf is nearly full, we save it as-is in ret. But
-                // if it only has little data, better copy to a small buffer.
-                if (out_bytes > OUTPUT_BUF_SIZE/2) {
-                    ret.push_back(std::move(output_buf).prefix(out_bytes));
-                    // output_buf is now empty. if this loop finds more input,
-                    // we'll allocate a new output buffer.
-                } else {
-                    ret.push_back(temporary_buffer<char>(output_buf.get(), out_bytes));
-                }
-                total_out_bytes += out_bytes;
-                if (total_out_bytes > length_limit) {
-                    throw api_error::payload_too_large(fmt::format("Request content length limit of {} bytes exceeded", length_limit));
-                }
-            }
-            if (e == Z_STREAM_END) {
-                // There may be more input after the first gzip stream - in
-                // either this input_buf or the next one. The additional input
-                // should be a second concatenated gzip. We need to allow that
-                // by resetting the gzip stream and continuing the input loop
-                // until there's no more input.
-                strm.reset();
-                if (strm->avail_in == 0) {
-                    complete_stream = true;
-                    break;
-                }
-            } else if (e != Z_OK && e != Z_BUF_ERROR) {
-                // DynamoDB returns an InternalServerError when given a bad
-                // gzip request body. See test test_broken_gzip_content
-                throw api_error::internal("Error during gzip decompression of request body");
-            }
-        } while (strm->avail_in > 0 || strm->avail_out == 0);
-    }
-    if (!complete_stream) {
-        // The gzip stream was not properly finished with Z_STREAM_END
-        throw api_error::internal("Truncated gzip in request body");
-    }
-    co_return ret;
-}
-
 future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request> req) {
     _executor._stats.total_operations++;
-    sstring target = req->get_header("X-Amz-Target");
-    // target is DynamoDB API version followed by a dot '.' and operation type (e.g. CreateTable)
-    auto dot = target.find('.');
-    std::string_view op = (dot == sstring::npos) ? std::string_view() : std::string_view(target).substr(dot+1);
-    if (req->content_length > request_content_length_limit) {
-        // If we have a Content-Length header and know the request will be too
-        // long, we don't need to wait for read_entire_stream() below to
-        // discover it. And we definitely mustn't try to get_units() below for
-        // for such a size.
-        co_return api_error::payload_too_large(fmt::format("Request content length limit of {} bytes exceeded", request_content_length_limit));
-    }
+    sstring target = req->get_header(TARGET);
+    std::vector<std::string_view> split_target = split(target, '.');
+    //NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
+    std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
     // JSON parsing can allocate up to roughly 2x the size of the raw
     // document, + a couple of bytes for maintenance.
-    // If the Content-Length of the request is not available, we assume
-    // the largest possible request (request_content_length_limit, i.e., 16 MB)
-    // and after reading the request we return_units() the excess.
-    size_t mem_estimate = (req->content_length ? req->content_length : request_content_length_limit) * 2 + 8000;
+    // TODO: consider the case where req->content_length is missing. Maybe
+    // we need to take the content_length_limit and return some of the units
+    // when we finish read_content_and_verify_signature?
+    size_t mem_estimate = req->content_length * 2 + 8000;
     auto units_fut = get_units(*_memory_limiter, mem_estimate);
     if (_memory_limiter->waiters()) {
         ++_executor._stats.requests_blocked_memory;
     }
     auto units = co_await std::move(units_fut);
-    throwing_assert(req->content_stream);
-    chunked_content content = co_await read_entire_stream(*req->content_stream, request_content_length_limit);
-    // If the request had no Content-Length, we reserved too many units
-    // so need to return some
-    if (req->content_length == 0) {
-        size_t content_length = 0;
-        for (const auto& chunk : content) {
-            content_length += chunk.size();
-        }
-        size_t new_mem_estimate = content_length * 2 + 8000;
-        units.return_units(mem_estimate - new_mem_estimate);
-    }
+    assert(req->content_stream);
+    chunked_content content = co_await util::read_entire_stream(*req->content_stream);
     auto username = co_await verify_signature(*req, content);
-    // If the request is compressed, uncompress it now, after we checked
-    // the signature (the signature is computed on the compressed content).
-    // We apply the request_content_length_limit again to the uncompressed
-    // content - we don't want to allow a tiny compressed request to
-    // expand to a huge uncompressed request.
-    sstring content_encoding = req->get_header("Content-Encoding");
-    if (content_encoding == "gzip") {
-        content = co_await ungzip(std::move(content), request_content_length_limit);
-    } else if (content_encoding == "deflate") {
-        content = co_await ungzip(std::move(content), request_content_length_limit, false);
-    } else if (!content_encoding.empty()) {
-        // DynamoDB returns a 500 error for unsupported Content-Encoding.
-        // I'm not sure if this is the best error code, but let's do it too.
-        // See the test test_garbage_content_encoding confirming this case.
-        co_return api_error::internal("Unsupported Content-Encoding");
-    }
-
-    // As long as the system_clients_entry object is alive, this request will
-    // be visible in the "system.clients" virtual table. When requested, this
-    // entry will be formatted by server::ongoing_request::make_client_data().
-    auto user_agent_header = co_await _connection_options_keys_and_values.get_or_load(req->get_header("User-Agent"), [] (const client_options_cache_key_type&) {
-        return make_ready_future<options_cache_value_type>(options_cache_value_type{});
-    });
-
-    auto system_clients_entry = _ongoing_requests.emplace(
-        req->get_client_address(), std::move(user_agent_header),
-        username, current_scheduling_group(),
-        req->get_protocol_name() == "https");
 
     if (slogger.is_enabled(log_level::trace)) {
-        slogger.trace("Request: {} {} {}", op, truncated_content_view(content, _max_users_query_size_in_trace_output).as_view(), req->_headers);
+        std::string buf;
+        slogger.trace("Request: {} {} {}", op, truncated_content_view(content, buf), req->_headers);
     }
     auto callback_it = _callbacks.find(op);
     if (callback_it == _callbacks.end()) {
         _executor._stats.unsupported_operations++;
-        co_return api_error::unknown_operation(fmt::format("Unsupported operation {}", op));
+        co_return api_error::unknown_operation(format("Unsupported operation {}", op));
     }
     if (_pending_requests.get_count() >= _max_concurrent_requests) {
         _executor._stats.requests_shed++;
@@ -766,34 +408,24 @@ future<executor::request_return_type> server::handle_api_request(std::unique_ptr
     }
     _pending_requests.enter();
     auto leave = defer([this] () noexcept { _pending_requests.leave(); });
-    executor::client_state client_state(service::client_state::external_tag(),
-        _auth_service, &_sl_controller, _timeout_config.current_values(), req->get_client_address());
-    if (!username.empty()) {
-        client_state.set_login(auth::authenticated_user(username));
-    }
-    client_state.maybe_update_per_service_level_params();
+    //FIXME: Client state can provide more context, e.g. client's endpoint address
+    // We use unique_ptr because client_state cannot be moved or copied
+    executor::client_state client_state = username.empty()
+        ? service::client_state{service::client_state::internal_tag()}
+        : service::client_state{service::client_state::internal_tag(), _auth_service, _sl_controller, username};
+    co_await client_state.maybe_update_per_service_level_params();
 
-    tracing::trace_state_ptr trace_state = maybe_trace_query(client_state, username, op, content, _max_users_query_size_in_trace_output.get());
-    tracing::trace(trace_state, "{}", op);
-
-    auto user = client_state.user();
-    auto f = [this, content = std::move(content), &callback = callback_it->second,
-            client_state = std::move(client_state), trace_state = std::move(trace_state),
-            units = std::move(units), req = std::move(req)] () mutable -> future<executor::request_return_type> {
-                rjson::value json_request = co_await _json_parser.parse(std::move(content));
-                if (!json_request.IsObject()) {
-                    co_return api_error::validation("Request content must be an object");
-                }
-                co_return co_await callback(_executor, client_state, trace_state,
-                    make_service_permit(std::move(units)), std::move(json_request), std::move(req));
-    };
-    co_return co_await _sl_controller.with_user_service_level(user, std::ref(f));
+    tracing::trace_state_ptr trace_state = maybe_trace_query(client_state, username, op, content);
+    tracing::trace(trace_state, op);
+    rjson::value json_request = co_await _json_parser.parse(std::move(content));
+    co_return co_await callback_it->second(_executor, client_state, trace_state,
+            make_service_permit(std::move(units)), std::move(json_request), std::move(req));
 }
 
 void server::set_routes(routes& r) {
     api_handler* req_handler = new api_handler([this] (std::unique_ptr<request> req) mutable {
         return handle_api_request(std::move(req));
-    }, _proxy.data_dictionary().get_config());
+    });
 
     r.put(operation_type::POST, "/", req_handler);
     r.put(operation_type::GET, "/", new health_handler(_pending_requests));
@@ -824,10 +456,9 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
         , _auth_service(auth_service)
         , _sl_controller(sl_controller)
         , _key_cache(1024, 1min, slogger)
-        , _max_users_query_size_in_trace_output(1024)
+        , _enforce_authorization(false)
         , _enabled_servers{}
-        , _pending_requests("alternator::server::pending_requests")
-        , _timeout_config(_proxy.data_dictionary().get_config())
+        , _pending_requests{}
       , _callbacks{
         {"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
             return e.create_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
@@ -904,66 +535,37 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
     } {
 }
 
-future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port,
-        std::optional<uint16_t> port_proxy_protocol, std::optional<uint16_t> https_port_proxy_protocol,
-        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<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
+        bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests) {
     _memory_limiter = memory_limiter;
-    _enforce_authorization = std::move(enforce_authorization);
-    _warn_authorization = std::move(warn_authorization);
+    _enforce_authorization = enforce_authorization;
     _max_concurrent_requests = std::move(max_concurrent_requests);
-    _max_users_query_size_in_trace_output = std::move(max_users_query_size_in_trace_output);
-    if (!port && !https_port && !port_proxy_protocol && !https_port_proxy_protocol) {
+    if (!port && !https_port) {
         return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
                 " must be specified in order to init an alternator HTTP server instance"));
     }
-    return seastar::async([this, addr, port, https_port, port_proxy_protocol, https_port_proxy_protocol, creds] {
+    return seastar::async([this, addr, port, https_port, creds] {
         _executor.start().get();
 
-        if (port || port_proxy_protocol) {
+        if (port) {
             set_routes(_http_server._routes);
+            _http_server.set_content_length_limit(server::content_length_limit);
             _http_server.set_content_streaming(true);
-            if (port) {
-                _http_server.listen(socket_address{addr, *port}).get();
-            }
-            if (port_proxy_protocol) {
-                listen_options lo;
-                lo.reuse_address = true;
-                lo.proxy_protocol = true;
-                _http_server.listen(socket_address{addr, *port_proxy_protocol}, lo).get();
-            }
+            _http_server.listen(socket_address{addr, *port}).get();
             _enabled_servers.push_back(std::ref(_http_server));
         }
-        if (https_port || https_port_proxy_protocol) {
+        if (https_port) {
             set_routes(_https_server._routes);
+            _https_server.set_content_length_limit(server::content_length_limit);
             _https_server.set_content_streaming(true);
-
-            if (this_shard_id() == 0) {
-                _credentials = creds->build_reloadable_server_credentials([this](const tls::credentials_builder& b, const std::unordered_set<sstring>& files, std::exception_ptr ep) -> future<> {
-                    if (ep) {
-                        slogger.warn("Exception loading {}: {}", files, ep);
-                    } else {
-                        co_await container().invoke_on_others([&b](server& s) {
-                            if (s._credentials) {
-                                b.rebuild(*s._credentials);
-                            }
-                        });
-                        slogger.info("Reloaded {}", files);
-                    }
-                }).get();
-            } else {
-                _credentials = creds->build_server_credentials();
-            }
-            if (https_port) {
-                _https_server.listen(socket_address{addr, *https_port}, _credentials).get();
-            }
-            if (https_port_proxy_protocol) {
-                listen_options lo;
-                lo.reuse_address = true;
-                lo.proxy_protocol = true;
-                _https_server.listen(socket_address{addr, *https_port_proxy_protocol}, lo, _credentials).get();
-            }
+            _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
+                if (ep) {
+                    slogger.warn("Exception loading {}: {}", files, ep);
+                } else {
+                    slogger.info("Reloaded {}", files);
+                }
+            }).get0());
+            _https_server.listen(socket_address{addr, *https_port}).get();
             _enabled_servers.push_back(std::ref(_https_server));
         }
     });
@@ -1019,39 +621,9 @@ future<> server::json_parser::stop() {
     return std::move(_run_parse_json_thread);
 }
 
-// Convert an entry in the server's list of ongoing Alternator requests
-// (_ongoing_requests) into a client_data object. This client_data object
-// will then be used to produce a row for the "system.clients" virtual table.
-client_data server::ongoing_request::make_client_data() const {
-    client_data cd;
-    cd.ct = client_type::alternator;
-    cd.ip = _client_address.addr();
-    cd.port = _client_address.port();
-    cd.shard_id = this_shard_id();
-    cd.connection_stage = client_connection_stage::established;
-    cd.username = _username;
-    cd.scheduling_group_name = _scheduling_group.name();
-    cd.ssl_enabled = _is_https;
-    // For now, we save the full User-Agent header as the "driver name"
-    // and keep "driver_version" unset.
-    cd.driver_name = _user_agent;
-    // Leave "protocol_version" unset, it has no meaning in Alternator.
-    // Leave "hostname", "ssl_protocol" and "ssl_cipher_suite" unset for Alternator.
-    // Note: CQL sets ssl_protocol and ssl_cipher_suite via generic_server::connection base class.
-    return cd;
-}
-
-future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> server::get_client_data() {
-    utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>> ret;
-    co_await _ongoing_requests.for_each_gently([&ret] (const ongoing_request& r) {
-        ret.emplace_back(make_foreign(std::make_unique<client_data>(r.make_client_data())));
-    });
-    co_return ret;
-}
-
 const char* api_error::what() const noexcept {
     if (_what_string.empty()) {
-        _what_string = fmt::format("{} {}: {}", std::to_underlying(_http_code), _type, _msg);
+        _what_string = format("{} {}: {}", static_cast<int>(_http_code), _type, _msg);
     }
     return _what_string.c_str();
 }

alternator/server.hh

@@ -3,13 +3,12 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #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>
@@ -21,24 +20,18 @@
 #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;
+class server {
+    static constexpr size_t content_length_limit = 16*MB;
     using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
-            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<http::request>)>;
+            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
     using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
 
-    httpd::http_server _http_server;
-    httpd::http_server _https_server;
+    http_server _http_server;
+    http_server _https_server;
     executor& _executor;
     service::storage_proxy& _proxy;
     gms::gossiper& _gossiper;
@@ -46,24 +39,14 @@ class server : public peering_sharded_service<server> {
     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;
+    bool _enforce_authorization;
     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;
-
+    gate _pending_requests;
     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;
@@ -84,38 +67,17 @@ class server : public peering_sharded_service<server> {
     };
     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<uint16_t> port_proxy_protocol, std::optional<uint16_t> https_port_proxy_protocol,
-            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<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
+            bool enforce_authorization, semaphore* memory_limiter, 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);
+    future<std::string> verify_signature(const seastar::httpd::request&, const chunked_content&);
+    future<executor::request_return_type> handle_api_request(std::unique_ptr<request> req);
 };
 
 }

alternator/stats.cc

@@ -3,55 +3,36 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #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::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) {
-
+stats::stats() : api_operations{} {
     // 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()}); \
-            }
 
+    _metrics.add_group("alternator", {
+#define OPERATION(name, CamelCaseName) \
+                seastar::metrics::make_total_operations("operation", api_operations.name, \
+                        seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
+#define OPERATION_LATENCY(name, CamelCaseName) \
+                seastar::metrics::make_histogram("op_latency", \
+                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return to_metrics_histogram(api_operations.name);}),
             OPERATION(batch_get_item, "BatchGetItem")
             OPERATION(batch_write_item, "BatchWriteItem")
             OPERATION(create_backup, "CreateBackup")
             OPERATION(create_global_table, "CreateGlobalTable")
+            OPERATION(create_table, "CreateTable")
             OPERATION(delete_backup, "DeleteBackup")
             OPERATION(delete_item, "DeleteItem")
+            OPERATION(delete_table, "DeleteTable")
             OPERATION(describe_backup, "DescribeBackup")
             OPERATION(describe_continuous_backups, "DescribeContinuousBackups")
             OPERATION(describe_endpoints, "DescribeEndpoints")
@@ -80,117 +61,39 @@ static void register_metrics_with_optional_table(seastar::metrics::metric_groups
             OPERATION(update_item, "UpdateItem")
             OPERATION(update_table, "UpdateTable")
             OPERATION(update_time_to_live, "UpdateTimeToLive")
+            OPERATION_LATENCY(put_item_latency, "PutItem")
+            OPERATION_LATENCY(get_item_latency, "GetItem")
+            OPERATION_LATENCY(delete_item_latency, "DeleteItem")
+            OPERATION_LATENCY(update_item_latency, "UpdateItem")
             OPERATION(list_streams, "ListStreams")
             OPERATION(describe_stream, "DescribeStream")
             OPERATION(get_shard_iterator, "GetShardIterator")
             OPERATION(get_records, "GetRecords")
+            OPERATION_LATENCY(get_records_latency, "GetRecords")
     });
-    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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(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 to_metrics_histogram(stats.operation_sizes.batch_write_item_op_size_kb);})(op("BatchWriteItem")).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(),
+    _metrics.add_group("alternator", {
+            seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
+                    seastar::metrics::description("number of unsupported operations via Alternator API")),
+            seastar::metrics::make_total_operations("total_operations", total_operations,
+                    seastar::metrics::description("number of total operations via Alternator API")),
+            seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
+                    seastar::metrics::description("number of performed read-before-write operations")),
+            seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
+                    seastar::metrics::description("number of writes that used LWT")),
+            seastar::metrics::make_total_operations("shard_bounce_for_lwt", shard_bounce_for_lwt,
+                    seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
+            seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
+                    seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
+            seastar::metrics::make_total_operations("requests_shed", requests_shed,
+                    seastar::metrics::description("Counts a number of requests shed due to overload.")),
+            seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
+                    seastar::metrics::description("number of rows read during filtering operations")),
+            seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,
+                    seastar::metrics::description("number of rows read and matched during filtering operations")),
+            seastar::metrics::make_total_operations("filtered_rows_dropped_total", [this] { return cql_stats.filtered_rows_read_total - cql_stats.filtered_rows_matched_total; },
+                    seastar::metrics::description("number of rows read and dropped during filtering operations")),
     });
-
-    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

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -11,25 +11,22 @@
 #include <cstdint>
 
 #include <seastar/core/metrics_registration.hh>
-#include "utils/histogram.hh"
+#include "seastarx.hh"
 #include "utils/estimated_histogram.hh"
 #include "cql3/stats.hh"
 
 namespace alternator {
-using batch_histogram = utils::estimated_histogram_with_max<128>;
-using op_size_histogram = utils::estimated_histogram_with_max<512>;
 
 // Object holding per-shard statistics related to Alternator.
 // While this object is alive, these metrics are also registered to be
 // visible by the metrics REST API, with the "alternator" prefix.
 class stats {
 public:
+    stats();
     // Count of DynamoDB API operations by types
     struct {
         uint64_t batch_get_item = 0;
         uint64_t batch_write_item = 0;
-        uint64_t 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;
@@ -69,55 +66,12 @@ public:
         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;
-
-        batch_histogram batch_get_item_histogram;
-        batch_histogram batch_write_item_histogram;
+        utils::time_estimated_histogram put_item_latency;
+        utils::time_estimated_histogram get_item_latency;
+        utils::time_estimated_histogram delete_item_latency;
+        utils::time_estimated_histogram update_item_latency;
+        utils::time_estimated_histogram get_records_latency;
     } api_operations;
-    // Operation size metrics
-    struct {
-        // Item size statistics collected per table and aggregated per node.
-        // Each histogram covers the range 0 - 512. Resolves #25143.
-        // A size is the retrieved item's size.
-        op_size_histogram get_item_op_size_kb;
-        // A size is the maximum of the new item's size and the old item's size.
-        op_size_histogram put_item_op_size_kb;
-        // 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.
-        op_size_histogram delete_item_op_size_kb;
-        // 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.
-        op_size_histogram update_item_op_size_kb;
-
-        // 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.
-        op_size_histogram batch_get_item_op_size_kb;
-        // The sizes are the the written items' sizes grouped per table.
-        op_size_histogram batch_write_item_op_size_kb;
-    } 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;
@@ -126,47 +80,12 @@ public:
     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);
+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;
-    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) / 1024;
-}
 
 }

alternator/streams.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include <type_traits>
@@ -13,6 +13,8 @@
 
 #include <seastar/json/formatter.hh>
 
+#include "utils/base64.hh"
+#include "log.hh"
 #include "db/config.hh"
 
 #include "cdc/log.hh"
@@ -23,17 +25,15 @@
 #include "utils/UUID_gen.hh"
 #include "cql3/selection/selection.hh"
 #include "cql3/result_set.hh"
+#include "cql3/type_json.hh"
 #include "cql3/column_identifier.hh"
-#include "schema/schema_builder.hh"
+#include "schema_builder.hh"
 #include "service/storage_proxy.hh"
 #include "gms/feature.hh"
 #include "gms/feature_service.hh"
 
 #include "executor.hh"
-#include "data_dictionary/data_dictionary.hh"
-#include "utils/rjson.hh"
-
-static logging::logger elogger("alternator-streams");
+#include "rmw_operation.hh"
 
 /**
  * Base template type to implement  rapidjson::internal::TypeHelper<...>:s
@@ -128,7 +128,7 @@ public:
     }
 };
 
-} // namespace alternator
+}
 
 template<typename ValueType>
 struct rapidjson::internal::TypeHelper<ValueType, alternator::stream_arn>
@@ -140,43 +140,24 @@ namespace alternator {
 future<alternator::executor::request_return_type> alternator::executor::list_streams(client_state& client_state, service_permit permit, rjson::value request) {
     _stats.api_operations.list_streams++;
 
-    auto limit = rjson::get_opt<int>(request, "Limit").value_or(100);
+    auto limit = rjson::get_opt<int>(request, "Limit").value_or(std::numeric_limits<int>::max());
     auto streams_start = rjson::get_opt<stream_arn>(request, "ExclusiveStartStreamArn");
     auto table = find_table(_proxy, request);
     auto db = _proxy.data_dictionary();
+    auto cfs = db.get_tables();
+    auto i = cfs.begin();
+    auto e = cfs.end();
 
     if (limit < 1) {
         throw api_error::validation("Limit must be 1 or more");
     }
 
-    std::vector<data_dictionary::table> cfs;
-
-    if (table) {
-        auto log_name = cdc::log_name(table->cf_name());
-        try {
-            cfs.emplace_back(db.find_table(table->ks_name(), log_name));
-        } catch (data_dictionary::no_such_column_family&) {
-            cfs.clear();
-        }
-    } else {
-        cfs = db.get_tables();
-    }
-
-    // # 12601 (maybe?) - sort the set of tables on ID. This should ensure we never
-    // generate duplicates in a paged listing here. Can obviously miss things if they 
-    // are added between paged calls and end up with a "smaller" UUID/ARN, but that 
-    // is to be expected.
-    if (std::cmp_less(limit, cfs.size()) || streams_start) {
-        std::sort(cfs.begin(), cfs.end(), [](const data_dictionary::table& t1, const data_dictionary::table& t2) {
-            return t1.schema()->id().uuid() < t2.schema()->id().uuid();
-        });
-    }
-
-    auto i = cfs.begin();
-    auto e = cfs.end();
-
+    // TODO: the unordered_map here is not really well suited for partial
+    // querying - we're sorting on local hash order, and creating a table
+    // between queries may or may not miss info. But that should be rare,
+    // and we can probably expect this to be a single call.
     if (streams_start) {
-        i = std::find_if(i, e, [&](const data_dictionary::table& t) {
+        i = std::find_if(i, e, [&](data_dictionary::table t) {
             return t.schema()->id().uuid() == streams_start
                 && cdc::get_base_table(db.real_database(), *t.schema())
                 && is_alternator_keyspace(t.schema()->ks_name())
@@ -200,7 +181,14 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
         if (!is_alternator_keyspace(ks_name)) {
             continue;
         }
+        if (table && ks_name != table->ks_name()) {
+            continue;
+        }
         if (cdc::is_log_for_some_table(db.real_database(), ks_name, cf_name)) {
+            if (table && table != cdc::get_base_table(db.real_database(), *s)) {
+                continue;
+            }
+
             rjson::value new_entry = rjson::empty_object();
 
             last = i->schema()->id();
@@ -219,7 +207,7 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
         rjson::add(ret, "LastEvaluatedStreamArn", *last);
     }
 
-    return make_ready_future<executor::request_return_type>(rjson::print(std::move(ret)));
+    return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
 }
 
 struct shard_id {
@@ -236,8 +224,11 @@ struct shard_id {
 
     // dynamo specifies shardid as max 65 chars. 
     friend std::ostream& operator<<(std::ostream& os, const shard_id& id) {
-        fmt::print(os, "{} {:x}:{}", marker, id.time.time_since_epoch().count(), id.id.to_bytes());
-        return os;
+        boost::io::ios_flags_saver fs(os);
+        return os << marker << std::hex  
+            << id.time.time_since_epoch().count()
+            << ':' << id.id.to_bytes()
+            ;
     }
 };
 
@@ -276,7 +267,7 @@ struct sequence_number {
          * Timeuuids viewed as msb<<64|lsb are _not_,
          * but they are still sorted as
          *  timestamp() << 64|lsb
-         * so we can simply unpack the mangled msb
+         * so we can simpy unpack the mangled msb
          * and use as hi 64 in our "bignum".
          */
         uint128_t hi = uint64_t(num.uuid.timestamp());
@@ -298,7 +289,7 @@ sequence_number::sequence_number(std::string_view v)
     }())
 {}
 
-} // namespace alternator
+}
 
 template<typename ValueType>
 struct rapidjson::internal::TypeHelper<ValueType, alternator::shard_id>
@@ -358,7 +349,7 @@ static stream_view_type cdc_options_to_steam_view_type(const cdc::options& opts)
     return type;
 }
 
-} // namespace alternator
+}
 
 template<typename ValueType>
 struct rapidjson::internal::TypeHelper<ValueType, alternator::stream_view_type>
@@ -415,7 +406,7 @@ using namespace std::string_literals;
  *
  * In scylla, this is sort of akin to an ID having corresponding ID/ID:s
  * that cover the token range it represents. Because ID:s are per
- * vnode shard however, this relation can be somewhat ambiguous.
+ * vnode shard however, this relation can be somewhat ambigous.
  * We still provide some semblance of this by finding the ID in
  * older generation that has token start < current ID token start.
  * This will be a partial overlap, but it is the best we can do.
@@ -425,30 +416,9 @@ static std::chrono::seconds confidence_interval(data_dictionary::database db) {
     return std::chrono::seconds(db.get_config().alternator_streams_time_window_s());
 }
 
-using namespace std::chrono_literals;
-
 // Dynamo docs says no data shall live longer than 24h.
 static constexpr auto dynamodb_streams_max_window = 24h;
 
-// find the parent shard in previous generation for the given child shard
-// takes care of wrap-around case in vnodes
-// prev_streams must be sorted by token
-const cdc::stream_id& find_parent_shard_in_previous_generation(db_clock::time_point prev_timestamp, const utils::chunked_vector<cdc::stream_id> &prev_streams, const cdc::stream_id &child) {
-    if (prev_streams.empty()) {
-        // something is really wrong - streams are empty
-        // let's try internal_error in hope it will be notified and fixed
-        on_internal_error(elogger, fmt::format("streams are empty for cdc generation at {} ({})", prev_timestamp, prev_timestamp.time_since_epoch().count()));
-    }
-    auto it = std::lower_bound(prev_streams.begin(), prev_streams.end(), child.token(), [](const cdc::stream_id& id, const dht::token& t) {
-        return id.token() < t;
-    });
-    if (it == prev_streams.end()) {
-        // wrap around case - take first
-        it = prev_streams.begin();
-    }
-    return *it;
-}
-
 future<executor::request_return_type> executor::describe_stream(client_state& client_state, service_permit permit, rjson::value request) {
     _stats.api_operations.describe_stream++;
 
@@ -496,10 +466,10 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
         } else {
             status = "ENABLED";
         }
-    }
+    } 
 
     auto ttl = std::chrono::seconds(opts.ttl());
-
+    
     rjson::add(stream_desc, "StreamStatus", rjson::from_string(status));
 
     stream_view_type type = cdc_options_to_steam_view_type(opts);
@@ -512,7 +482,7 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
 
     if (!opts.enabled()) {
         rjson::add(ret, "StreamDescription", std::move(stream_desc));
-        co_return rjson::print(std::move(ret));
+        return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
     }
 
     // TODO: label
@@ -523,113 +493,123 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
     // filter out cdc generations older than the table or now() - cdc::ttl (typically dynamodb_streams_max_window - 24h)
     auto low_ts = std::max(as_timepoint(schema->id()), db_clock::now() - ttl);
 
-    std::map<db_clock::time_point, cdc::streams_version> topologies = co_await _sdks.cdc_get_versioned_streams(low_ts, { normal_token_owners });
-    auto e = topologies.end();
-    auto prev = e;
-    auto shards = rjson::empty_array();
+    return _sdks.cdc_get_versioned_streams(low_ts, { normal_token_owners }).then([this, db, shard_start, limit, ret = std::move(ret), stream_desc = std::move(stream_desc)] (std::map<db_clock::time_point, cdc::streams_version> topologies) mutable {
 
-    std::optional<shard_id> last;
+        auto e = topologies.end();
+        auto prev = e;
+        auto shards = rjson::empty_array();
 
-    auto i = topologies.begin();
-    // if we're a paged query, skip to the generation where we left of.
-    if (shard_start) {
-        i = topologies.find(shard_start->time);
-    }
+        std::optional<shard_id> last;
 
-    // for parent-child stuff we need id:s to be sorted by token
-    // (see explanation above) since we want to find closest
-    // token boundary when determining parent.
-    // #7346 - we processed and searched children/parents in
-    // stored order, which is not necessarily token order,
-    // so the finding of "closest" token boundary (using upper bound)
-    // could give somewhat weird results.
-    static auto token_cmp = [](const cdc::stream_id& id1, const cdc::stream_id& id2) {
-        return id1.token() < id2.token();
-    };
+        auto i = topologies.begin();
+        // if we're a paged query, skip to the generation where we left of.
+        if (shard_start) {
+            i = topologies.find(shard_start->time);
+        }
 
-    // #7409 - shards must be returned in lexicographical order,
-    // normal bytes compare is string_traits<int8_t>::compare.
-    // thus bytes 0x8000 is less than 0x0000. By doing unsigned
-    // compare instead we inadvertently will sort in string lexical.
-    static auto id_cmp = [](const cdc::stream_id& id1, const cdc::stream_id& id2) {
-        return compare_unsigned(id1.to_bytes(), id2.to_bytes()) < 0;
-    };
-
-    // need a prev even if we are skipping stuff
-    if (i != topologies.begin()) {
-        prev = std::prev(i);
-    }
-
-    for (; limit > 0 && i != e; prev = i, ++i) {
-        auto& [ts, sv] = *i;
-
-        last = std::nullopt;
-
-        auto lo = sv.streams.begin();
-        auto end = sv.streams.end();
+        // for parent-child stuff we need id:s to be sorted by token
+        // (see explanation above) since we want to find closest
+        // token boundary when determining parent.
+        // #7346 - we processed and searched children/parents in
+        // stored order, which is not neccesarily token order,
+        // so the finding of "closest" token boundary (using upper bound)
+        // could give somewhat weird results.
+        static auto token_cmp = [](const cdc::stream_id& id1, const cdc::stream_id& id2) {
+            return id1.token() < id2.token();
+        };
 
         // #7409 - shards must be returned in lexicographical order,
-        std::sort(lo, end, id_cmp);
+        // normal bytes compare is string_traits<int8_t>::compare.
+        // thus bytes 0x8000 is less than 0x0000. By doing unsigned
+        // compare instead we inadvertently will sort in string lexical.
+        static auto id_cmp = [](const cdc::stream_id& id1, const cdc::stream_id& id2) {
+            return compare_unsigned(id1.to_bytes(), id2.to_bytes()) < 0;
+        };
 
-        if (shard_start) {
-            // find next shard position
-            lo = std::upper_bound(lo, end, shard_start->id, id_cmp);
-            shard_start = std::nullopt;
+        // need a prev even if we are skipping stuff
+        if (i != topologies.begin()) {
+            prev = std::prev(i);
         }
 
-        if (lo != end && prev != e) {
-            // We want older stuff sorted in token order so we can find matching
-            // token range when determining parent shard.
-            std::stable_sort(prev->second.streams.begin(), prev->second.streams.end(), token_cmp);
-        }
-
-        auto expired = [&]() -> std::optional<db_clock::time_point> {
-            auto j = std::next(i);
-            if (j == e) {
-                return std::nullopt;
-            }
-            // add this so we sort of match potential 
-            // sequence numbers in get_records result.
-            return j->first + confidence_interval(db);
-        }();
-
-        while (lo != end) {
-            auto& id = *lo++;
-
-            auto shard = rjson::empty_object();
-
-            if (prev != e) {
-                auto &pid = find_parent_shard_in_previous_generation(prev->first, prev->second.streams, id);
-                rjson::add(shard, "ParentShardId", shard_id(prev->first, pid));
-            }
-
-            last.emplace(ts, id);
-            rjson::add(shard, "ShardId", *last);
-            auto range = rjson::empty_object();
-            rjson::add(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch())));
-            if (expired) {
-                rjson::add(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch())));
-            }
-
-            rjson::add(shard, "SequenceNumberRange", std::move(range));
-            rjson::push_back(shards, std::move(shard));
-            
-            if (--limit == 0) {
-                break;
-            }
+        for (; limit > 0 && i != e; prev = i, ++i) {
+            auto& [ts, sv] = *i;
 
             last = std::nullopt;
+
+            auto lo = sv.streams.begin();
+            auto end = sv.streams.end();
+
+            // #7409 - shards must be returned in lexicographical order,
+            std::sort(lo, end, id_cmp);
+
+            if (shard_start) {
+                // find next shard position
+                lo = std::upper_bound(lo, end, shard_start->id, id_cmp);
+                shard_start = std::nullopt;
+            }
+
+            if (lo != end && prev != e) {
+                // We want older stuff sorted in token order so we can find matching
+                // token range when determining parent shard.
+                std::stable_sort(prev->second.streams.begin(), prev->second.streams.end(), token_cmp);
+            }
+
+            auto expired = [&]() -> std::optional<db_clock::time_point> {
+                auto j = std::next(i);
+                if (j == e) {
+                    return std::nullopt;
+                }
+                // add this so we sort of match potential 
+                // sequence numbers in get_records result.
+                return j->first + confidence_interval(db);
+            }();
+
+            while (lo != end) {
+                auto& id = *lo++;
+
+                auto shard = rjson::empty_object();
+
+                if (prev != e) {
+                    auto& pids = prev->second.streams;
+                    auto pid = std::upper_bound(pids.begin(), pids.end(), id.token(), [](const dht::token& t, const cdc::stream_id& id) {
+                        return t < id.token();
+                    });
+                    if (pid != pids.begin()) {
+                        pid = std::prev(pid);
+                    }
+                    if (pid != pids.end()) {
+                        rjson::add(shard, "ParentShardId", shard_id(prev->first, *pid));
+                    }
+                }
+
+                last.emplace(ts, id);
+                rjson::add(shard, "ShardId", *last);
+                auto range = rjson::empty_object();
+                rjson::add(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch())));
+                if (expired) {
+                    rjson::add(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch())));
+                }
+
+                rjson::add(shard, "SequenceNumberRange", std::move(range));
+                rjson::push_back(shards, std::move(shard));
+                
+                if (--limit == 0) {
+                    break;
+                }
+
+                last = std::nullopt;
+            }
         }
-    }
 
-    if (last) {
-        rjson::add(stream_desc, "LastEvaluatedShardId", *last);
-    }
+        if (last) {
+            rjson::add(stream_desc, "LastEvaluatedShardId", *last);
+        }
 
-    rjson::add(stream_desc, "Shards", std::move(shards));
-    rjson::add(ret, "StreamDescription", std::move(stream_desc));
-        
-    co_return rjson::print(std::move(ret));
+        rjson::add(stream_desc, "Shards", std::move(shards));
+        rjson::add(ret, "StreamDescription", std::move(stream_desc));
+            
+        return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
+    });
 }
 
 enum class shard_iterator_type {
@@ -725,7 +705,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
 
     auto type = rjson::get<shard_iterator_type>(request, "ShardIteratorType");
     auto seq_num = rjson::get_opt<sequence_number>(request, "SequenceNumber");
-
+    
     if (type < shard_iterator_type::TRIM_HORIZON && !seq_num) {
         throw api_error::validation("Missing required parameter \"SequenceNumber\"");
     }
@@ -735,7 +715,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
 
     auto stream_arn = rjson::get<alternator::stream_arn>(request, "StreamArn");
     auto db = _proxy.data_dictionary();
-
+    
     schema_ptr schema = nullptr;
     std::optional<shard_id> sid;
 
@@ -781,14 +761,14 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
     auto ret = rjson::empty_object();
     rjson::add(ret, "ShardIterator", iter);
 
-    return make_ready_future<executor::request_return_type>(rjson::print(std::move(ret)));
+    return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
 }
 
 struct event_id {
     cdc::stream_id stream;
     utils::UUID timestamp;
 
-    static constexpr auto marker = 'E';
+    static const auto marker = 'E';
 
     event_id(cdc::stream_id s, utils::UUID ts)
         : stream(s)
@@ -796,11 +776,13 @@ struct event_id {
     {}
     
     friend std::ostream& operator<<(std::ostream& os, const event_id& id) {
-        fmt::print(os, "{}{}:{}", marker, id.stream.to_bytes(), id.timestamp);
-        return os;
+        boost::io::ios_flags_saver fs(os);
+        return os << marker << std::hex << id.stream.to_bytes()
+            << ':' << id.timestamp
+            ;
     }
 };
-} // namespace alternator
+}
 
 template<typename ValueType>
 struct rapidjson::internal::TypeHelper<ValueType, alternator::event_id>
@@ -819,9 +801,6 @@ future<executor::request_return_type> executor::get_records(client_state& client
     if (limit < 1) {
         throw api_error::validation("Limit must be 1 or more");
     }
-    if (limit > 1000) {
-        throw api_error::validation("Limit must be less than or equal to 1000");
-    }
 
     auto db = _proxy.data_dictionary();
     schema_ptr schema, base;
@@ -833,13 +812,11 @@ future<executor::request_return_type> executor::get_records(client_state& client
     }
 
     if (!schema || !base || !is_alternator_keyspace(schema->ks_name())) {
-        co_return api_error::resource_not_found(fmt::to_string(iter.table));
+        throw api_error::resource_not_found(boost::lexical_cast<std::string>(iter.table));
     }
 
     tracing::add_table_name(trace_state, schema->ks_name(), schema->cf_name());
 
-    co_await verify_permission(_enforce_authorization, _warn_authorization, client_state, schema, auth::permission::SELECT, _stats);
-
     db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
     partition_key pk = iter.shard.id.to_partition_key(*schema);
 
@@ -858,21 +835,19 @@ future<executor::request_return_type> executor::get_records(client_state& client
     static const bytes op_column_name = cdc::log_meta_column_name_bytes("operation");
     static const bytes eor_column_name = cdc::log_meta_column_name_bytes("end_of_batch");
 
-    std::optional<attrs_to_get> key_names =
-        base->primary_key_columns()
-        | std::views::transform([&] (const column_definition& cdef) {
+    std::optional<attrs_to_get> key_names = boost::copy_range<attrs_to_get>(
+        boost::range::join(std::move(base->partition_key_columns()), std::move(base->clustering_key_columns()))
+        | boost::adaptors::transformed([&] (const column_definition& cdef) {
             return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
-        | std::ranges::to<attrs_to_get>()
-    ;
+    );
     // Include all base table columns as values (in case pre or post is enabled).
     // This will include attributes not stored in the frozen map column
-    std::optional<attrs_to_get> attr_names = base->regular_columns()
+    std::optional<attrs_to_get> attr_names = boost::copy_range<attrs_to_get>(base->regular_columns()
         // this will include the :attrs column, which we will also force evaluating. 
         // But not having this set empty forces out any cdc columns from actual result 
-        | std::views::transform([] (const column_definition& cdef) {
+        | boost::adaptors::transformed([] (const column_definition& cdef) {
             return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
-        | std::ranges::to<attrs_to_get>()
-    ;
+    );
 
     std::vector<const column_definition*> columns;
     columns.reserve(schema->all_columns().size());
@@ -882,14 +857,11 @@ future<executor::request_return_type> executor::get_records(client_state& client
 
     std::transform(pks.begin(), pks.end(), std::back_inserter(columns), [](auto& c) { return &c; });
     std::transform(cks.begin(), cks.end(), std::back_inserter(columns), [](auto& c) { return &c; });
-    auto regular_column_start_idx = columns.size();
-    auto regular_column_filter = std::views::filter([](const column_definition& cdef) { return cdef.name() == op_column_name || cdef.name() == eor_column_name || !cdc::is_cdc_metacolumn_name(cdef.name_as_text()); });
-    std::ranges::transform(schema->regular_columns() | regular_column_filter, std::back_inserter(columns), [](auto& c) { return &c; });
 
-    auto regular_columns = std::ranges::subrange(columns.begin() + regular_column_start_idx, columns.end())
-        | std::views::transform(&column_definition::id)
-        | std::ranges::to<query::column_id_vector>()
-    ;
+    auto regular_columns = boost::copy_range<query::column_id_vector>(schema->regular_columns() 
+        | boost::adaptors::filtered([](const column_definition& cdef) { return cdef.name() == op_column_name || cdef.name() == eor_column_name || !cdc::is_cdc_metacolumn_name(cdef.name_as_text()); })
+        | boost::adaptors::transformed([&] (const column_definition& cdef) { columns.emplace_back(&cdef); return cdef.id; })
+    );
 
     stream_view_type type = cdc_options_to_steam_view_type(base->cdc_options());
 
@@ -909,179 +881,176 @@ future<executor::request_return_type> executor::get_records(client_state& client
     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()), query::row_limit(limit * mul));
 
-    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(default_timeout(), std::move(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));
+    return _proxy.query(schema, std::move(command), std::move(partition_ranges), cl, service::storage_proxy::coordinator_query_options(default_timeout(), std::move(permit), client_state)).then(
+            [this, schema, partition_slice = std::move(partition_slice), selection = std::move(selection), start_time = std::move(start_time), limit, key_names = std::move(key_names), attr_names = std::move(attr_names), type, iter, high_ts] (service::storage_proxy::coordinator_query_result qr) mutable {       
+        cql3::selection::result_set_builder builder(*selection, gc_clock::now(), cql_serialization_format::latest());
+        query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
 
-    auto result_set = builder.build();
-    auto records = rjson::empty_array();
+        auto result_set = builder.build();
+        auto records = rjson::empty_array();
 
-    auto& metadata = result_set->get_metadata();
+        auto& metadata = result_set->get_metadata();
 
-    auto op_index = std::distance(metadata.get_names().begin(), 
-        std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
-            return cdef->name->name() == op_column_name;
-        })
-    );
-    auto ts_index = std::distance(metadata.get_names().begin(), 
-        std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
-            return cdef->name->name() == timestamp_column_name;
-        })
-    );
-    auto eor_index = std::distance(metadata.get_names().begin(), 
-        std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
-            return cdef->name->name() == eor_column_name;
-        })
-    );
+        auto op_index = std::distance(metadata.get_names().begin(), 
+            std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
+                return cdef->name->name() == op_column_name;
+            })
+        );
+        auto ts_index = std::distance(metadata.get_names().begin(), 
+            std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
+                return cdef->name->name() == timestamp_column_name;
+            })
+        );
+        auto eor_index = std::distance(metadata.get_names().begin(), 
+            std::find_if(metadata.get_names().begin(), metadata.get_names().end(), [](const lw_shared_ptr<cql3::column_specification>& cdef) {
+                return cdef->name->name() == eor_column_name;
+            })
+        );
 
-    std::optional<utils::UUID> timestamp;
-    auto dynamodb = rjson::empty_object();
-    auto record = rjson::empty_object();
-    const auto dc_name = _proxy.get_token_metadata_ptr()->get_topology().get_datacenter();
+        std::optional<utils::UUID> timestamp;
+        auto dynamodb = rjson::empty_object();
+        auto record = rjson::empty_object();
 
-    using op_utype = std::underlying_type_t<cdc::operation>;
+        using op_utype = std::underlying_type_t<cdc::operation>;
 
-    auto maybe_add_record = [&] {
-        if (!dynamodb.ObjectEmpty()) {
-            rjson::add(record, "dynamodb", std::move(dynamodb));
-            dynamodb = rjson::empty_object();
-        }
-        if (!record.ObjectEmpty()) {
-            rjson::add(record, "awsRegion", rjson::from_string(dc_name));
-            rjson::add(record, "eventID", event_id(iter.shard.id, *timestamp));
-            rjson::add(record, "eventSource", "scylladb:alternator");
-            rjson::add(record, "eventVersion", "1.1");
-            rjson::push_back(records, std::move(record));
-            record = rjson::empty_object();
-            --limit;
-        }
-    };
+        auto maybe_add_record = [&] {
+            if (!dynamodb.ObjectEmpty()) {
+                rjson::add(record, "dynamodb", std::move(dynamodb));
+                dynamodb = rjson::empty_object();
+            }
+            if (!record.ObjectEmpty()) {
+                // TODO: awsRegion?
+                rjson::add(record, "eventID", event_id(iter.shard.id, *timestamp));
+                rjson::add(record, "eventSource", "scylladb:alternator");
+                rjson::push_back(records, std::move(record));
+                record = rjson::empty_object();
+                --limit;
+            }
+        };
 
-    for (auto& row : result_set->rows()) {
-        auto op = static_cast<cdc::operation>(value_cast<op_utype>(data_type_for<op_utype>()->deserialize(*row[op_index])));
-        auto ts = value_cast<utils::UUID>(data_type_for<utils::UUID>()->deserialize(*row[ts_index]));
-        auto eor = row[eor_index].has_value() ? value_cast<bool>(boolean_type->deserialize(*row[eor_index])) : false;
+        for (auto& row : result_set->rows()) {
+            auto op = static_cast<cdc::operation>(value_cast<op_utype>(data_type_for<op_utype>()->deserialize(*row[op_index])));
+            auto ts = value_cast<utils::UUID>(data_type_for<utils::UUID>()->deserialize(*row[ts_index]));
+            auto eor = row[eor_index].has_value() ? value_cast<bool>(boolean_type->deserialize(*row[eor_index])) : false;
 
-        if (!dynamodb.HasMember("Keys")) {
-            auto keys = rjson::empty_object();
-            describe_single_item(*selection, row, key_names, keys);
-            rjson::add(dynamodb, "Keys", std::move(keys));
-            rjson::add(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
-            rjson::add(dynamodb, "SequenceNumber", sequence_number(ts));
-            rjson::add(dynamodb, "StreamViewType", type);
-            // TODO: SizeBytes
-        }
+            if (!dynamodb.HasMember("Keys")) {
+                auto keys = rjson::empty_object();
+                describe_single_item(*selection, row, key_names, keys);
+                rjson::add(dynamodb, "Keys", std::move(keys));
+                rjson::add(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
+                rjson::add(dynamodb, "SequenceNumber", sequence_number(ts));
+                rjson::add(dynamodb, "StreamViewType", type);
+                //TODO: SizeInBytes
+            }
 
-        /**
-         * We merge rows with same timestamp into a single event.
-         * This is pretty much needed, because a CDC row typically
-         * encodes ~half the info of an alternator write. 
-         * 
-         * A big, big downside to how alternator records are written
-         * (i.e. CQL), is that the distinction between INSERT and UPDATE
-         * is somewhat lost/unmappable to actual eventName. 
-         * A write (currently) always looks like an insert+modify
-         * regardless whether we wrote existing record or not. 
-         * 
-         * Maybe RMW ops could be done slightly differently so 
-         * we can distinguish them here...
-         * 
-         * For now, all writes will become MODIFY.
-         * 
-         * Note: we do not check the current pre/post
-         * flags on CDC log, instead we use data to 
-         * drive what is returned. This is (afaict)
-         * consistent with dynamo streams
-         */
-        switch (op) {
-        case cdc::operation::pre_image:
-        case cdc::operation::post_image:
-        {
-            auto item = rjson::empty_object();
-            describe_single_item(*selection, row, attr_names, item, nullptr, true);
-            describe_single_item(*selection, row, key_names, item);
-            rjson::add(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
-            break;
-        }
-        case cdc::operation::update:
-            rjson::add(record, "eventName", "MODIFY");
-            break;
-        case cdc::operation::insert:
-            rjson::add(record, "eventName", "INSERT");
-            break;
-        case cdc::operation::service_row_delete:
-        case cdc::operation::service_partition_delete:
-        {
-            auto user_identity = rjson::empty_object();
-            rjson::add(user_identity, "Type", "Service");
-            rjson::add(user_identity, "PrincipalId", "dynamodb.amazonaws.com");
-            rjson::add(record, "userIdentity", std::move(user_identity));
-            rjson::add(record, "eventName", "REMOVE");
-            break;
-        }
-        default:
-            rjson::add(record, "eventName", "REMOVE");
-            break;
-        }
-        if (eor) {
-            maybe_add_record();
-            timestamp = ts;
-            if (limit == 0) {
+            /**
+             * We merge rows with same timestamp into a single event.
+             * This is pretty much needed, because a CDC row typically
+             * encodes ~half the info of an alternator write. 
+             * 
+             * A big, big downside to how alternator records are written
+             * (i.e. CQL), is that the distinction between INSERT and UPDATE
+             * is somewhat lost/unmappable to actual eventName. 
+             * A write (currently) always looks like an insert+modify
+             * regardless whether we wrote existing record or not. 
+             * 
+             * Maybe RMW ops could be done slightly differently so 
+             * we can distinguish them here...
+             * 
+             * For now, all writes will become MODIFY.
+             * 
+             * Note: we do not check the current pre/post
+             * flags on CDC log, instead we use data to 
+             * drive what is returned. This is (afaict)
+             * consistent with dynamo streams
+             */
+            switch (op) {
+            case cdc::operation::pre_image:
+            case cdc::operation::post_image:
+            {
+                auto item = rjson::empty_object();
+                describe_single_item(*selection, row, attr_names, item, true);
+                describe_single_item(*selection, row, key_names, item);
+                rjson::add(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
                 break;
             }
+            case cdc::operation::update:
+                rjson::add(record, "eventName", "MODIFY");
+                break;
+            case cdc::operation::insert:
+                rjson::add(record, "eventName", "INSERT");
+                break;
+            default:
+                rjson::add(record, "eventName", "REMOVE");
+                break;
+            }
+            if (eor) {
+                maybe_add_record();
+                timestamp = ts;
+                if (limit == 0) {
+                    break;
+                }
+            }
         }
-    }
 
-    auto ret = rjson::empty_object();
-    auto nrecords = records.Size();
-    rjson::add(ret, "Records", std::move(records));
+        auto ret = rjson::empty_object();
+        auto nrecords = records.Size();
+        rjson::add(ret, "Records", std::move(records));
 
-    if (nrecords != 0) {
-        // #9642. Set next iterators threshold to > last
-        shard_iterator next_iter(iter.table, iter.shard, *timestamp, false);
-        // Note that here we unconditionally return NextShardIterator,
-        // without checking if maybe we reached the end-of-shard. If the
-        // shard did end, then the next read will have nrecords == 0 and
-        // will notice end end of shard and not return NextShardIterator.
-        rjson::add(ret, "NextShardIterator", next_iter);
-        _stats.api_operations.get_records_latency.mark(std::chrono::steady_clock::now() - start_time);
-        co_return rjson::print(std::move(ret));
-    }
+        if (nrecords != 0) {
+            // #9642. Set next iterators threshold to > last
+            shard_iterator next_iter(iter.table, iter.shard, *timestamp, false);
+            // Note that here we unconditionally return NextShardIterator,
+            // without checking if maybe we reached the end-of-shard. If the
+            // shard did end, then the next read will have nrecords == 0 and
+            // will notice end end of shard and not return NextShardIterator.
+            rjson::add(ret, "NextShardIterator", next_iter);
+            _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
+            return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
+        }
 
-    // ugh. figure out if we are and end-of-shard
-    auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
+        // ugh. figure out if we are and end-of-shard
+        auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
 
-    db_clock::time_point ts = co_await _sdks.cdc_current_generation_timestamp({ normal_token_owners });
-    auto& shard = iter.shard;
+        return _sdks.cdc_current_generation_timestamp({ normal_token_owners }).then([this, iter, high_ts, start_time, ret = std::move(ret), nrecords](db_clock::time_point ts) mutable {
+            auto& shard = iter.shard;            
 
-    if (shard.time < ts && ts < high_ts) {
-        // The DynamoDB documentation states that when a shard is
-        // closed, reading it until the end has NextShardIterator
-        // "set to null". Our test test_streams_closed_read
-        // confirms that by "null" they meant not set at all.
-    } else {
-        // We could have return the same iterator again, but we did
-        // a search from it until high_ts and found nothing, so we
-        // can also start the next search from high_ts.
-        // TODO: but why? It's simpler just to leave the iterator be.
-        shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch()), true);
-        rjson::add(ret, "NextShardIterator", iter);
-    }
-    _stats.api_operations.get_records_latency.mark(std::chrono::steady_clock::now() - start_time);
-    if (is_big(ret)) {
-        co_return make_streamed(std::move(ret));
-    }
-    co_return rjson::print(std::move(ret));
+            if (shard.time < ts && ts < high_ts) {
+                // The DynamoDB documentation states that when a shard is
+                // closed, reading it until the end has NextShardIterator
+                // "set to null". Our test test_streams_closed_read
+                // confirms that by "null" they meant not set at all.
+            } else {
+                // We could have return the same iterator again, but we did
+                // a search from it until high_ts and found nothing, so we
+                // can also start the next search from high_ts.
+                // TODO: but why? It's simpler just to leave the iterator be.
+                shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch()), true);
+                rjson::add(ret, "NextShardIterator", iter);
+            }
+            _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
+            // TODO: determine a better threshold...
+            if (nrecords > 10) {
+                return make_ready_future<executor::request_return_type>(make_streamed(std::move(ret)));
+            }
+            return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
+        });
+    });
 }
 
-bool executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder, service::storage_proxy& sp) {
+void executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder, service::storage_proxy& sp) {
     auto stream_enabled = rjson::find(stream_specification, "StreamEnabled");
     if (!stream_enabled || !stream_enabled->IsBool()) {
         throw api_error::validation("StreamSpecification needs boolean StreamEnabled");
     }
 
     if (stream_enabled->GetBool()) {
-        if (!sp.features().alternator_streams) {
+        auto db = sp.data_dictionary();
+
+        if (!db.features().cdc) {
+            throw api_error::validation("StreamSpecification: streams (CDC) feature not enabled in cluster.");
+        }
+        if (!db.features().alternator_streams) {
             throw api_error::validation("StreamSpecification: alternator streams feature not enabled in cluster.");
         }
 
@@ -1106,16 +1075,14 @@ bool executor::add_stream_options(const rjson::value& stream_specification, sche
                 break;
         }
         builder.with_cdc_options(opts);
-        return true;
     } else {
         cdc::options opts;
         opts.enabled(false);
         builder.with_cdc_options(opts);
-        return false;
     }
 }
 
-void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema, const service::storage_proxy& sp) {
+void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp) {
     auto& opts = schema.cdc_options();
     if (opts.enabled()) {
         auto db = sp.data_dictionary();
@@ -1140,4 +1107,4 @@ void executor::supplement_table_stream_info(rjson::value& descr, const schema& s
     }
 }
 
-} // namespace alternator
+}

alternator/ttl.cc

@@ -3,12 +3,11 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #include <chrono>
 #include <cstdint>
-#include <exception>
 #include <optional>
 #include <seastar/core/sstring.hh>
 #include <seastar/core/coroutine.hh>
@@ -16,29 +15,28 @@
 #include <seastar/core/future.hh>
 #include <seastar/core/lowres_clock.hh>
 #include <seastar/coroutine/maybe_yield.hh>
+#include <boost/multiprecision/cpp_int.hpp>
 
-#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 "log.hh"
 #include "gc_clock.hh"
 #include "replica/database.hh"
-#include "service/client_state.hh"
 #include "service_permit.hh"
-#include "mutation/timestamp.hh"
+#include "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 "sstables/types.hh"
+#include "mutation.hh"
+#include "types.hh"
 #include "types/map.hh"
-#include "utils/assert.hh"
 #include "utils/rjson.hh"
 #include "utils/big_decimal.hh"
+#include "utils/fb_utilities.hh"
 #include "cql3/selection/selection.hh"
 #include "cql3/values.hh"
 #include "cql3/query_options.hh"
@@ -46,11 +44,9 @@
 #include "alternator/executor.hh"
 #include "alternator/controller.hh"
 #include "alternator/serialization.hh"
-#include "alternator/ttl_tag.hh"
 #include "dht/sharder.hh"
 #include "db/config.hh"
 #include "db/tags/utils.hh"
-#include "utils/labels.hh"
 
 #include "ttl.hh"
 
@@ -58,10 +54,19 @@ static logging::logger tlogger("alternator_ttl");
 
 namespace alternator {
 
+// We write the expiration-time attribute enabled on a table using 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).
+static const sstring TTL_TAG_KEY("system:ttl_attribute");
+
 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. Upgrade all nodes to a version that supports it.");
+    if (!_proxy.data_dictionary().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);
@@ -85,33 +90,31 @@ future<executor::request_return_type> executor::update_time_to_live(client_state
     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);
+    sstring attribute_name(v->GetString(), v->GetStringLength());
 
-    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);
+    std::map<sstring, sstring> tags_map = get_tags_of_table_or_throw(schema);
+    if (enabled) {
+        if (tags_map.contains(TTL_TAG_KEY)) {
+            co_return 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()) {
+            co_return api_error::validation("TTL is already disabled");
+        } else if (i->second != attribute_name) {
+            co_return 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);
+    }
+    co_await db::update_tags(_mm, schema, std::move(tags_map));
     // 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));
+    co_return make_jsonable(std::move(response));
 }
 
 future<executor::request_return_type> executor::describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
@@ -128,12 +131,12 @@ future<executor::request_return_type> executor::describe_time_to_live(client_sta
     }
     rjson::value response = rjson::empty_object();
     rjson::add(response, "TimeToLiveDescription", std::move(desc));
-    co_return rjson::print(std::move(response));
+    co_return make_jsonable(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 an UpdateTimeToLive request.
+// Alternator tables with TTL configured via a UpdateTimeToLive request.
 //
 // Here is a brief overview of how the expiration service works:
 //
@@ -149,7 +152,7 @@ future<executor::request_return_type> executor::describe_time_to_live(client_sta
 // 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
+// An expiration thread is reponsible 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
@@ -235,7 +238,7 @@ static bool is_expired(const rjson::value& expiration_time, gc_clock::time_point
 // 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,
+                            const std::vector<bytes_opt>& row,
                             schema_ptr schema,
                             api::timestamp_type ts) {
     // Prepare the row key to delete
@@ -254,7 +257,7 @@ static future<> expire_item(service::storage_proxy& proxy,
             // FIXME: log or increment a metric if this happens.
             return make_ready_future<>();
         }
-        exploded_pk.push_back(to_bytes(*row_c));
+        exploded_pk.push_back(*row_c);
     }
     auto pk = partition_key::from_exploded(exploded_pk);
     mutation m(schema, pk);
@@ -274,23 +277,18 @@ static future<> expire_item(service::storage_proxy& proxy,
                 // FIXME: log or increment a metric if this happens.
                 return make_ready_future<>();
             }
-            exploded_ck.push_back(to_bytes(*row_c));
+            exploded_ck.push_back(*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;
+    std::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,
-        }
-    );
+        db::allow_per_partition_rate_limit::no);
 }
 
 static size_t random_offset(size_t min, size_t max) {
@@ -308,20 +306,18 @@ static size_t random_offset(size_t min, size_t max) {
 // 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) {
+static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary_ranges(
+        const locator::effective_replication_map_ptr& erm,
+        gms::inet_address 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;
-    throwing_assert(!sorted_tokens.empty());
+    std::vector<std::pair<dht::token_range, gms::inet_address>> 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);
+        inet_address_vector_replica_set eps = erm->get_natural_endpoints(tok);
         if (eps.size() <= 1 || eps[1] != ep) {
             prev_tok = tok;
             continue;
@@ -348,7 +344,7 @@ static future<std::vector<std::pair<dht::token_range, locator::host_id>>> get_se
         }
         prev_tok = tok;
     }
-    co_return ret;
+    return ret;
 }
 
 
@@ -381,68 +377,61 @@ static future<std::vector<std::pair<dht::token_range, locator::host_id>>> get_se
 // 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>
+enum primary_or_secondary_t {primary, secondary};
+template<primary_or_secondary_t primary_or_secondary>
 class token_ranges_owned_by_this_shard {
+    // ranges_holder_primary holds just the primary ranges themselves
+    class ranges_holder_primary {
+        const dht::token_range_vector _token_ranges;
+     public:
+        ranges_holder_primary(const locator::effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
+            : _token_ranges(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, gms::inet_address>> _token_ranges;
+        gms::gossiper& _gossiper;
+     public:
+        ranges_holder_secondary(const locator::effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
+            : _token_ranges(get_secondary_ranges(erm, ep))
+            , _gossiper(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);
+        }
+    };
+
     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;
+    using ranges_holder = std::conditional_t<
+            primary_or_secondary == primary_or_secondary_t::primary,
+            ranges_holder_primary,
+            ranges_holder_secondary>;
+    const ranges_holder _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)
+    token_ranges_owned_by_this_shard(replica::database& db, gms::gossiper& g, schema_ptr s)
         :  _s(s)
-        , _erm(s->table().get_effective_replication_map())
-        , _token_ranges(std::move(token_ranges))
+        , _token_ranges(db.find_keyspace(s->ks_name()).get_effective_replication_map(),
+                g, utils::fb_utilities::get_broadcast_address())
         , _range_idx(random_offset(0, _token_ranges.size() - 1))
         , _end_idx(_range_idx + _token_ranges.size())
     {
@@ -477,7 +466,7 @@ public:
                     return std::nullopt;
                 }
             }
-            _intersecter.emplace(_erm->get_sharder(*_s), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
+            _intersecter.emplace(_s->get_sharder(), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
         }
     }
 
@@ -498,7 +487,6 @@ struct scan_ranges_context {
     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;
@@ -508,7 +496,6 @@ struct scan_ranges_context {
         : 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
@@ -517,9 +504,8 @@ struct scan_ranges_context {
         // 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>();
+        auto regular_columns = boost::copy_range<query::column_id_vector>(
+            s->regular_columns() | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.id; }));
         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>();
@@ -528,9 +514,10 @@ struct scan_ranges_context {
         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()));
+        executor::client_state client_state{executor::client_state::internal_tag()};
         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());
+        query_state_ptr = std::make_unique<service::query_state>(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.
@@ -553,7 +540,7 @@ static future<> scan_table_ranges(
         expiration_service::stats& expiration_stats)
 {
     const schema_ptr& s = scan_ctx.s;
-    throwing_assert(partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
+    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()) {
@@ -561,34 +548,13 @@ static future<> scan_table_ranges(
             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.
+        // We don't 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 and 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);
-        }
+        // FIXME: which timeout?
+        // FIXME: if read times out, need to retry it.
+        std::unique_ptr<cql3::result_set> rs = co_await p->fetch_page(limit, gc_clock::now(), executor::default_timeout());
         auto rows = rs->rows();
         auto meta = rs->get_metadata().get_names();
         std::optional<unsigned> expiration_column;
@@ -603,7 +569,7 @@ static future<> scan_table_ranges(
             continue;
         }
         for (const auto& row : rows) {
-            const managed_bytes_opt& cell = row[*expiration_column];
+            const bytes_opt& cell = row[*expiration_column];
             if (!cell) {
                 continue;
             }
@@ -630,38 +596,13 @@ static future<> scan_table_ranges(
                 }
             } else {
                 // For a real column to contain an expiration time, it
-                // must be a numeric type. We currently support decimal
-                // (used by Alternator TTL) as well as bigint, int and
-                // timestamp (used by CQL per-row TTL).
-                switch (meta[*expiration_column]->type->get_kind()) {
-                    case abstract_type::kind::decimal:
-                        // Used by Alternator TTL for key columns not stored
-                        // in the map. The value is in seconds, fractional
-                        // part is ignored.
-                        expired = is_expired(value_cast<big_decimal>(v), now);
-                        break;
-                    case abstract_type::kind::long_kind:
-                        // Used by CQL per-row TTL. The value is in seconds.
-                        expired = is_expired(gc_clock::time_point(std::chrono::seconds(value_cast<int64_t>(v))), now);
-                        break;
-                    case abstract_type::kind::int32:
-                        // Used by CQL per-row TTL. The value is in seconds.
-                        // Using int type is not recommended because it will
-                        // overflow in 2038, but we support it to allow users
-                        // to use existing int columns for expiration.
-                        expired = is_expired(gc_clock::time_point(std::chrono::seconds(value_cast<int32_t>(v))), now);
-                        break;
-                    case abstract_type::kind::timestamp:
-                        // Used by CQL per-row TTL. The value is in milliseconds
-                        // but we truncate it to gc_clock's precision (whole seconds).
-                        expired = is_expired(gc_clock::time_point(std::chrono::duration_cast<gc_clock::duration>(value_cast<db_clock::time_point>(v).time_since_epoch())), now);
-                        break;
-                    default:
-                        // Should never happen - we verified the column's type
-                        // before starting the scan.
-                        [[unlikely]]
-                        on_internal_error(tlogger, format("expiration scanner value of unsupported type {} in column {}", meta[*expiration_column]->type->cql3_type_name(), scan_ctx.column_name) );
-                }
+                // 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++;
@@ -676,17 +617,6 @@ static future<> scan_table_ranges(
     }
 }
 
-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
@@ -723,12 +653,16 @@ static future<bool> scan_table(
         co_return false;
     }
     // attribute_name may be one of the schema's columns (in Alternator, this
-    // means a key column, in CQL it's a regular column), or an element in
-    // Alternator's attrs map encoded in Alternator's JSON encoding (which we
-    // decode). If attribute_name is a real column, in Alternator it will have
-    // the type decimal, counting seconds since the UNIX epoch, while in CQL
-    // it will one of the types bigint or int (counting seconds) or timestamp
-    // (counting milliseconds).
+    // 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;
@@ -747,83 +681,43 @@ static future<bool> scan_table(
     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
-    // be decimal_type (Alternator), bigint, int or timestamp (CQL).
-    // If the column has the wrong type nothing can get expired in
-    // this table, and it's pointless to scan it.
+    // (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 &&
-         column_type->get_kind() != abstract_type::kind::long_kind &&
-         column_type->get_kind() != abstract_type::kind::int32 &&
-         column_type->get_kind() != abstract_type::kind::timestamp)) {
+        (!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, erm->get_topology()); // 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);
-        }
+    token_ranges_owned_by_this_shard<primary> my_ranges(db.real_database(), gossiper, s);
+    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<secondary> my_secondary_ranges(db.real_database(), gossiper, s);
+    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;
 }
@@ -892,10 +786,12 @@ future<> expiration_service::run() {
 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 (!shutting_down()) {
-        _end = run().handle_exception([] (std::exception_ptr ep) {
-            tlogger.error("expiration_service failed: {}", ep);
-        });
+    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<>();
 }
@@ -915,13 +811,13 @@ future<> expiration_service::stop() {
 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::description("number of passes over the database")),
         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::description("number of table scans (counting each scan of each table that enabled expiration)")),
         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::description("number of items deleted after expiration")),
         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(),
+            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down")),
     });
 }
 

alternator/ttl.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 #pragma once
@@ -30,7 +30,7 @@ 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 an UpdateTimeToLive request.
+// 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.
@@ -52,7 +52,7 @@ private:
     data_dictionary::database _db;
     service::storage_proxy& _proxy;
     gms::gossiper& _gossiper;
-    // _end is set by start(), and resolves when the background service
+    // _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;

alternator/ttl_tag.hh

@@ -1,26 +0,0 @@
-/*
- * Copyright 2026-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include <seastar/core/sstring.hh>
-
-namespace alternator {
-// We use the table tag TTL_TAG_KEY ("system:ttl_attribute") to remember
-// which attribute was chosen as the expiration-time attribute for
-// Alternator's TTL and CQL's per-row TTL features.
-// Currently, the *value* of this tag is simply the name of the attribute:
-// It can refer to a real column or if that doesn't exist, to a member of
-// the ":attrs" map column (which Alternator uses).
-extern const sstring TTL_TAG_KEY;
-} // namespace alternator
-
-// let users use TTL_TAG_KEY without the "alternator::" prefix,
-// to make it easier to move it to a different namespace later.
-using alternator::TTL_TAG_KEY;

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

@@ -12,7 +12,7 @@
       "operations":[
         {
           "method":"POST",
-          "summary":"Resets authorized prepared statements cache",
+          "summary":"Reset cache",
           "type":"void",
           "nickname":"authorization_cache_reset",
           "produces":[

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

@@ -84,22 +84,6 @@
                      "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",
@@ -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":[
@@ -453,68 +437,6 @@
             }
          ]
       },
-      {
-         "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",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/column_family/estimate_keys/{name}",
          "operations":[

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

@@ -246,24 +246,6 @@
             }
          }
       },
-      "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",
@@ -345,10 +327,6 @@
                "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 +335,9 @@
                "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 +353,6 @@
                   "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"
             }
         }
       }