./github/scripts/auto-backport.py: don't remove backport label when backport process has an error

Today, when the `Fixes` prefix is missing or the developer is not a collaborator with `scylladbbot` we remove the backport labels to prevent the process from starting and notifying the developers.

Developers are worried that removing these backport labels will cause us to forget we need to do these backports. @nyh suggested to add a `scylladbbot/backport_error` label instead

Applied those changes, so when a `Fixes` prefix is missing we will add a `scylladbbot/backport_error` label and stop the process

When a user doesn't accept the invite we will still open the PR but he will not be assigned and will not be able to edit the branch when we have conflicts

Fixes: https://github.com/scylladb/scylla-pkg/issues/4898
Fixes: https://github.com/scylladb/scylla-pkg/issues/4897

.clang-format

@@ -0,0 +1,209 @@
+---
+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

@@ -2,3 +2,4 @@
 *.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/* @elcallio @vladzcloudius
+auth/* @nuivall @ptrsmrn @KrzaQ
 
 # CACHE
 row_cache* @tgrabiec
@@ -7,9 +7,9 @@ row_cache* @tgrabiec
 test/boost/mvcc* @tgrabiec
 
 # CDC
-cdc/* @kbr- @elcallio @piodul @jul-stas
-test/cql/cdc_* @kbr- @elcallio @piodul @jul-stas
-test/boost/cdc_* @kbr- @elcallio @piodul @jul-stas
+cdc/* @kbr-scylla @elcallio @piodul
+test/cql/cdc_* @kbr-scylla @elcallio @piodul
+test/boost/cdc_* @kbr-scylla @elcallio @piodul
 
 # COMMITLOG / BATCHLOG
 db/commitlog/* @elcallio @eliransin
@@ -25,18 +25,18 @@ compaction/* @raphaelsc
 transport/*
 
 # CQL QUERY LANGUAGE
-cql3/* @tgrabiec
+cql3/* @tgrabiec @nuivall @ptrsmrn @KrzaQ
 
 # COUNTERS
-counters* @jul-stas
-tests/counter_test* @jul-stas
+counters* @nuivall @ptrsmrn @KrzaQ
+tests/counter_test* @nuivall @ptrsmrn @KrzaQ
 
 # DOCS
 docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh @havaker @nuivall
+docs/alternator @annastuchlik @tzach @nyh @nuivall @ptrsmrn @KrzaQ
 
 # GOSSIP
-gms/* @tgrabiec @asias
+gms/* @tgrabiec @asias @kbr-scylla
 
 # DOCKER
 dist/docker/*
@@ -74,8 +74,8 @@ streaming/* @tgrabiec @asias
 service/storage_service.* @tgrabiec @asias
 
 # ALTERNATOR
-alternator/* @havaker @nuivall
-test/alternator/* @havaker @nuivall
+alternator/* @nyh @nuivall @ptrsmrn @KrzaQ
+test/alternator/* @nyh @nuivall @ptrsmrn @KrzaQ
 
 # HINTED HANDOFF
 db/hints/* @piodul @vladzcloudius @eliransin
@@ -91,11 +91,14 @@ test/boost/mutation_reader_test.cc @denesb
 test/boost/querier_cache_test.cc @denesb
 
 # PYTEST-BASED CQL TESTS
-test/cql-pytest/* @nyh
+test/cqlpy/* @nyh
 
 # RAFT
-raft/* @kbr- @gleb-cloudius @kostja
-test/raft/* @kbr- @gleb-cloudius @kostja
+raft/* @kbr-scylla @gleb-cloudius @kostja
+test/raft/* @kbr-scylla @gleb-cloudius @kostja
 
 # HEAT-WEIGHTED LOAD BALANCING
 db/heat_load_balance.* @nyh @gleb-cloudius
+
+# Tools
+tools/* @denesb

.github/dependabot.yml

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

.github/mergify.yml

@@ -15,7 +15,7 @@ pull_request_rules:
         - closed
     actions:
       delete_head_branch:
-  - name: Automate backport pull request 5.2
+  - name: Automate backport pull request 6.2
     conditions:
       - or:
         - closed
@@ -23,36 +23,11 @@ pull_request_rules:
       - or:
           - base=master
           - base=next
-      - label=backport/5.2 # The PR must have this label to trigger the backport
+      - label=backport/6.2 # The PR must have this label to trigger the backport
       - label=promoted-to-master
     actions:
       copy:
-        title: "[Backport 5.2] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-           Refs #{{number}}
-        branches:
-          - branch-5.2
-        assignees:
-          - "{{ author }}"
-  - name: Automate backport pull request 5.4
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/5.4 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 5.4] {{ title }}"
+        title: "[Backport 6.2] {{ title }}"
         body: |
           {{ body }}
 
@@ -62,7 +37,32 @@ pull_request_rules:
 
           Refs #{{number}}
         branches:
-          - branch-5.4
+          - 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

.github/scripts/auto-backport.py

@@ -0,0 +1,213 @@
+#!/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}")
+        if is_collaborator:
+            backport_pr.add_to_assignees(pr.user)
+        if is_draft:
+            backport_pr.add_to_labels("conflicts")
+            pr_comment = f"@{pr.user.login} - This PR was marked as draft because it has conflicts\n"
+            pr_comment += "Please resolve them and mark this PR as ready for review"
+            backport_pr.create_issue_comment(pr_comment)
+        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')
+            repo_local.git.push(fork_repo, new_branch_name, force=True)
+            create_pull_request(repo, new_branch_name, backport_base_branch, pr, backport_pr_title, commits,
+                                is_draft, is_collaborator)
+
+        except GitCommandError as e:
+            logging.warning(f"GitCommandError: {e}")
+
+
+def with_github_keyword_prefix(repo, pr):
+    pattern = rf"(?:fix(?:|es|ed))\s*:?\s*(?:(?:(?:{repo.full_name})?#)|https://github\.com/{repo.full_name}/issues/)(\d+)"
+    match = re.findall(pattern, pr.body, re.IGNORECASE)
+    if not match:
+        for commit in pr.get_commits():
+            match = re.findall(pattern, commit.commit.message, re.IGNORECASE)
+            if match:
+                print(f'{pr.number} has a valid close reference in commit message {commit.sha}')
+                break
+    if not match:
+        print(f'No valid close reference for {pr.number}')
+        return False
+    else:
+        return True
+
+
+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

@@ -0,0 +1,81 @@
+#!/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

@@ -16,13 +16,8 @@ def parser():
     parser = argparse.ArgumentParser()
     parser.add_argument('--repository', type=str, required=True,
                         help='Github repository name (e.g., scylladb/scylladb)')
-    parser.add_argument('--commit_before_merge', type=str, required=True, help='Git commit ID to start labeling from ('
-                                                                               'newest commit).')
-    parser.add_argument('--commit_after_merge', type=str, required=True,
-                        help='Git commit ID to end labeling at (oldest '
-                             'commit, exclusive).')
-    parser.add_argument('--update_issue', type=bool, default=False, help='Set True to update issues when backport was '
-                                                                         'done')
+    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()
 
@@ -53,38 +48,41 @@ def main():
     target_branch = re.search(r'branch-(\d+\.\d+)', args.ref)
     g = Github(github_token)
     repo = g.get_repo(args.repository, lazy=False)
-    commits = repo.compare(head=args.commit_after_merge, base=args.commit_before_merge)
+    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.commits:
+    for commit in commits:
         print(f'Commit sha is: {commit.sha}')
-        match = pr_pattern.search(commit.commit.message)
-        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'Refs (?:#|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 merge 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_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)
-                    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)
+                    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__":

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

@@ -5,9 +5,10 @@ on:
     branches:
       - master
       - branch-*.*
-
-env:
-  DEFAULT_BRANCH: 'master'
+      - enterprise
+  pull_request_target:
+    types: [labeled, unlabeled]
+    branches: [master, next, enterprise]
 
 jobs:
   check-commit:
@@ -20,17 +21,60 @@ jobs:
         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
-
+        run: sudo apt-get install -y python3-github python3-git
       - name: Run python script
+        if: github.event_name == 'push'
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/label_promoted_commits.py --commit_before_merge ${{ github.event.before }} --commit_after_merge ${{ github.event.after }} --repository ${{ github.repository }} --ref ${{ github.ref }}
+          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
+        id: check_label
+        run: |
+          labels_json='${{ toJson(github.event.pull_request.labels) }}'
+          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

@@ -22,5 +22,12 @@ jobs:
             const regex = new RegExp(pattern);
             
             if (!regex.test(body)) {
-              core.setFailed("PR body does not contain a valid 'Fixes' reference.");
+              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

@@ -13,10 +13,14 @@ on:
         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
-    # be consistent with tools/toolchain/image
-    container: scylladb/scylla-toolchain:fedora-40-20240621
+    container: ${{ needs.read-toolchain.outputs.image }}
     outputs:
       md5sum: ${{ steps.checksum.outputs.md5sum }}
     steps:

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

@@ -0,0 +1,52 @@
+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

@@ -7,7 +7,7 @@ on:
 
 env:
   # use the development branch explicitly
-  CLANG_VERSION: 19
+  CLANG_VERSION: 21
   BUILD_DIR: build
 
 permissions: {}
@@ -20,6 +20,7 @@ concurrency:
 jobs:
   clang-dev:
     name: Build with clang nightly
+    if: github.repository == 'scylladb/scylladb'
     runs-on: ubuntu-latest
     container: fedora:40
     strategy:

.github/workflows/clang-tidy.yaml

@@ -10,9 +10,9 @@ on:
       - 'docs/**'
       - '.github/**'
   workflow_dispatch:
-  schedule:
-    # only at 5AM Saturday
-    - cron: '0 5 * * SAT'
+  issue_comment:
+    types:
+      - created
 
 env:
   BUILD_TYPE: RelWithDebInfo
@@ -28,11 +28,13 @@ concurrency:
 
 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:

.github/workflows/conflict_reminder.yaml

@@ -0,0 +1,45 @@
+name: Notify PR Authors of Conflicts
+
+on:
+  schedule:
+    - cron: '0 10 * * 1,4'  # Runs every Monday and Thursday at 10:00am
+  workflow_dispatch:      # Manual trigger for testing
+
+jobs:
+  notify_conflict_prs:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Notify PR Authors of Conflicts
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const prs = await github.paginate(github.rest.pulls.list, {
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              state: 'open',
+              per_page: 100
+            });
+            const branchPrefix = 'branch-';
+            const threeDaysAgo = new Date();
+            const conflictLabel = 'conflicts';          
+            threeDaysAgo.setDate(threeDaysAgo.getDate() - 3);
+            for (const pr of prs) {
+              if (!pr.base.ref.startsWith(branchPrefix)) continue;
+              const hasConflictLabel = pr.labels.some(label => label.name === conflictLabel);
+              if (!hasConflictLabel) continue;
+              const updatedDate = new Date(pr.updated_at);
+              if (updatedDate >= threeDaysAgo) continue;
+              if (pr.assignee === null) continue;
+              const assignee = pr.assignee.login;
+              if (assignee) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pr.number,
+                  body: `@${assignee}, this PR has been open with conflicts. Please resolve the conflicts so we can merge it.`,
+                });
+                console.log(`Notified @${assignee} for PR #${pr.number}`);
+              } 
+            }
+            console.log(`Total PRs checked: ${prs.length}`);

.github/workflows/differential-shellcheck.yaml

@@ -0,0 +1,32 @@
+---
+# 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-pr.yaml

@@ -12,7 +12,8 @@ on:
       - enterprise
     paths:
       - "docs/**"
-
+      - "db/config.hh"
+      - "db/config.cc"
 jobs:
   build:
     runs-on: ubuntu-latest

.github/workflows/iwyu.yaml

@@ -9,7 +9,9 @@ env:
   BUILD_TYPE: RelWithDebInfo
   BUILD_DIR: build
   CLEANER_OUTPUT_PATH: build/clang-include-cleaner.log
-  CLEANER_DIRS: test/unit exceptions alternator api auth cdc compaction
+  # 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 redis replica
 
 permissions: {}
 
@@ -43,6 +45,10 @@ jobs:
             -G Ninja                                    \
             -B $BUILD_DIR                               \
             -S .
+      - run: |
+          cmake                       \
+          --build $BUILD_DIR          \
+          --target wasmtime_bindings
       - name: Build headers
         run: |
           swagger_targets=''

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

@@ -0,0 +1,22 @@
+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: 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

@@ -17,6 +17,6 @@ jobs:
         with:
           mode: minimum
           count: 1
-          labels: "backport/none\nbackport/\\d.\\d"
+          labels: "backport/none\nbackport/\\d{4}\\.\\d+\nbackport/\\d+\\.\\d+"
           use_regex: true
           add_comment: false

.github/workflows/reproducible-build.yaml

@@ -19,6 +19,7 @@ jobs:
     with:
       build_mode: release
   compare-checksum:
+    if: github.repository == 'scylladb/scylladb'
     runs-on: ubuntu-latest
     needs:
       - build-a

.github/workflows/seastar.yaml

@@ -15,10 +15,13 @@ 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
-    # be consistent with tools/toolchain/image
-    container: scylladb/scylla-toolchain:fedora-40-20240621
+    container: ${{ needs.read-toolchain.outputs.image }}
     strategy:
       matrix:
         build_type:

.github/workflows/trigger_jenkins.yaml

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

.github/workflows/urgent_issue_reminder.yml

@@ -0,0 +1,58 @@
+name: Urgent Issue Reminder
+
+on:
+  schedule:
+    - cron: '10 8 * * 1' # Runs every Monday 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

@@ -3,6 +3,7 @@
 .settings
 build
 build.ninja
+cmake-build-*
 build.ninja.new
 cscope.*
 /debian/
@@ -13,13 +14,14 @@ 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
@@ -32,3 +34,4 @@ compile_commands.json
 .mypy_cache
 .envrc
 clang_build
+.idea/

.gitmodules

@@ -9,9 +9,6 @@
 [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

CMakeLists.txt

@@ -2,8 +2,6 @@ cmake_minimum_required(VERSION 3.27)
 
 project(scylla)
 
-include(CTest)
-
 list(APPEND CMAKE_MODULE_PATH
   ${CMAKE_CURRENT_SOURCE_DIR}/cmake
   ${CMAKE_CURRENT_SOURCE_DIR}/seastar/cmake)
@@ -24,8 +22,11 @@ if(DEFINED CMAKE_BUILD_TYPE)
     endif()
 endif(DEFINED CMAKE_BUILD_TYPE)
 
+option(Scylla_ENABLE_LTO "Turn on link-time optimization for the 'release' mode." ON)
+
 include(mode.common)
-if(CMAKE_CONFIGURATION_TYPES)
+get_property(is_multi_config GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
+if(is_multi_config)
     foreach(config ${CMAKE_CONFIGURATION_TYPES})
         include(mode.${config})
         list(APPEND scylla_build_modes ${scylla_build_mode_${config}})
@@ -43,32 +44,82 @@ else()
 endif()
 
 include(limit_jobs)
+
 # Configure Seastar compile options to align with Scylla
 set(CMAKE_CXX_STANDARD "23" CACHE INTERNAL "")
 set(CMAKE_CXX_EXTENSIONS ON CACHE INTERNAL "")
 set(CMAKE_CXX_SCAN_FOR_MODULES OFF CACHE INTERNAL "")
 set(CMAKE_CXX_VISIBILITY_PRESET hidden)
 
-set(Seastar_TESTING ON CACHE BOOL "" FORCE)
-set(Seastar_API_LEVEL 7 CACHE STRING "" FORCE)
-set(Seastar_DEPRECATED_OSTREAM_FORMATTERS OFF CACHE BOOL "" FORCE)
-set(Seastar_APPS ON CACHE BOOL "" FORCE)
-set(Seastar_EXCLUDE_APPS_FROM_ALL ON CACHE BOOL "" FORCE)
-set(Seastar_EXCLUDE_TESTS_FROM_ALL ON CACHE BOOL "" FORCE)
-set(Seastar_UNUSED_RESULT_ERROR ON CACHE BOOL "" FORCE)
-add_subdirectory(seastar)
+if(is_multi_config)
+    find_package(Seastar)
+    # this is atypical compared to standard ExternalProject usage:
+    # - Seastar's build system should already be configured at this point.
+    # - We maintain separate project variants for each configuration type.
+    #
+    # Benefits of this approach:
+    # - Allows the parent project to consume the compile options exposed by
+    #   .pc file. as the compile options vary from one config to another.
+    # - Allows application of config-specific settings
+    # - Enables building Seastar within the parent project's build system
+    # - Facilitates linking of artifacts with the external project target,
+    #   establishing proper dependencies between them
+    include(ExternalProject)
+
+    # should be consistent with configure_seastar() in configure.py
+    set(seastar_build_dir "${CMAKE_BINARY_DIR}/$<CONFIG>/seastar")
+    ExternalProject_Add(Seastar
+        SOURCE_DIR "${PROJECT_SOURCE_DIR}/seastar"
+        CONFIGURE_COMMAND ""
+        BUILD_COMMAND ${CMAKE_COMMAND} --build "${seastar_build_dir}"
+          --target seastar
+          --target seastar_testing
+          --target seastar_perf_testing
+          --target app_iotune
+        BUILD_ALWAYS ON
+        BUILD_BYPRODUCTS
+          ${seastar_build_dir}/libseastar.$<IF:$<CONFIG:Debug,Dev>,so,a>
+          ${seastar_build_dir}/libseastar_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
+          ${seastar_build_dir}/libseastar_perf_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
+          ${seastar_build_dir}/apps/iotune/iotune
+          ${seastar_build_dir}/gen/include/seastar/http/chunk_parsers.hh
+          ${seastar_build_dir}/gen/include/seastar/http/request_parser.hh
+          ${seastar_build_dir}/gen/include/seastar/http/response_parser.hh
+        INSTALL_COMMAND "")
+    add_dependencies(Seastar::seastar Seastar)
+    add_dependencies(Seastar::seastar_testing Seastar)
+else()
+    set(Seastar_TESTING ON CACHE BOOL "" FORCE)
+    set(Seastar_API_LEVEL 7 CACHE STRING "" FORCE)
+    set(Seastar_DEPRECATED_OSTREAM_FORMATTERS OFF CACHE BOOL "" FORCE)
+    set(Seastar_APPS ON CACHE BOOL "" FORCE)
+    set(Seastar_EXCLUDE_APPS_FROM_ALL ON CACHE BOOL "" FORCE)
+    set(Seastar_EXCLUDE_TESTS_FROM_ALL ON CACHE BOOL "" FORCE)
+    set(Seastar_IO_URING ON CACHE BOOL "" FORCE)
+    set(Seastar_SCHEDULING_GROUPS_COUNT 19 CACHE STRING "" FORCE)
+    set(Seastar_UNUSED_RESULT_ERROR ON CACHE BOOL "" FORCE)
+    add_subdirectory(seastar)
+    target_compile_definitions (seastar
+      PRIVATE
+        SEASTAR_NO_EXCEPTION_HACK)
+endif()
+
 set(ABSL_PROPAGATE_CXX_STD ON CACHE BOOL "" FORCE)
 
+if(Scylla_ENABLE_LTO)
+    list(APPEND absl_cxx_flags $<$<CONFIG:RelWithDebInfo>:${CMAKE_CXX_COMPILE_OPTIONS_IPO};-ffat-lto-objects>)
+endif()
+
 find_package(Sanitizers QUIET)
-set(sanitizer_cxx_flags
-    $<$<IN_LIST:$<CONFIG>,Debug;Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_COMPILE_OPTIONS>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_COMPILE_OPTIONS>>)
+list(APPEND absl_cxx_flags
+    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_COMPILE_OPTIONS>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_COMPILE_OPTIONS>>)
 if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-    set(ABSL_GCC_FLAGS ${sanitizer_cxx_flags})
+    list(APPEND ABSL_GCC_FLAGS ${absl_cxx_flags})
 elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
-    set(ABSL_LLVM_FLAGS ${sanitizer_cxx_flags})
+    list(APPEND ABSL_LLVM_FLAGS ${absl_cxx_flags})
 endif()
 set(ABSL_DEFAULT_LINKOPTS
-    $<$<IN_LIST:$<CONFIG>,Debug;Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_LINK_LIBRARIES>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_LINK_LIBRARIES>>)
+    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_LINK_LIBRARIES>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_LINK_LIBRARIES>>)
 add_subdirectory(abseil)
 add_library(absl-headers INTERFACE)
 target_include_directories(absl-headers SYSTEM INTERFACE
@@ -95,13 +146,16 @@ target_link_libraries(Boost::regex
 find_package(Lua REQUIRED)
 find_package(ZLIB REQUIRED)
 find_package(ICU COMPONENTS uc i18n REQUIRED)
-find_package(fmt 9.0.0 REQUIRED)
+find_package(fmt 10.0.0 REQUIRED)
 find_package(libdeflate REQUIRED)
 find_package(libxcrypt REQUIRED)
+find_package(p11-kit REQUIRED)
 find_package(Snappy REQUIRED)
 find_package(RapidJSON REQUIRED)
 find_package(xxHash REQUIRED)
+find_package(yaml-cpp REQUIRED)
 find_package(zstd REQUIRED)
+find_package(lz4 REQUIRED)
 
 set(scylla_gen_build_dir "${CMAKE_BINARY_DIR}/gen")
 file(MAKE_DIRECTORY "${scylla_gen_build_dir}")
@@ -138,6 +192,7 @@ target_sources(scylla-main
     keys.cc
     multishard_mutation_query.cc
     mutation_query.cc
+    node_ops/task_manager_module.cc
     partition_slice_builder.cc
     querier.cc
     query.cc
@@ -146,11 +201,12 @@ target_sources(scylla-main
     tombstone_gc_options.cc
     tombstone_gc.cc
     reader_concurrency_semaphore.cc
-    row_cache.cc
+    reader_concurrency_semaphore_group.cc
     schema_mutations.cc
     serializer.cc
     sstables_loader.cc
     table_helper.cc
+    tasks/task_handler.cc
     tasks/task_manager.cc
     timeout_config.cc
     unimplemented.cc
@@ -167,7 +223,10 @@ target_link_libraries(scylla-main
     Seastar::seastar
     Snappy::snappy
     systemd
-    ZLIB::ZLIB)
+    ZLIB::ZLIB
+    lz4::lz4_static
+    zstd::zstd_static
+)
 
 option(Scylla_CHECK_HEADERS
   "Add check-headers target for checking the self-containness of headers")
@@ -194,8 +253,15 @@ include(check_headers)
 check_headers(check-headers scylla-main
   GLOB ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)
 
+option(Scylla_DIST
+  "Build dist targets"
+  ON)
+
+add_custom_target(compiler-training)
+
 add_subdirectory(api)
 add_subdirectory(alternator)
+add_subdirectory(audit)
 add_subdirectory(db)
 add_subdirectory(auth)
 add_subdirectory(cdc)
@@ -203,6 +269,7 @@ add_subdirectory(compaction)
 add_subdirectory(cql3)
 add_subdirectory(data_dictionary)
 add_subdirectory(dht)
+add_subdirectory(ent)
 add_subdirectory(gms)
 add_subdirectory(idl)
 add_subdirectory(index)
@@ -233,7 +300,8 @@ add_version_library(scylla_version
 
 add_executable(scylla
   main.cc)
-target_link_libraries(scylla PRIVATE
+set(scylla_libs
+    audit
     scylla-main
     api
     auth
@@ -244,10 +312,12 @@ target_link_libraries(scylla PRIVATE
     cql3
     data_dictionary
     dht
+    encryption
     gms
     idl
     index
     lang
+    ldap
     locator
     message
     mutation
@@ -268,14 +338,36 @@ target_link_libraries(scylla PRIVATE
     transport
     types
     utils)
+target_link_libraries(scylla PRIVATE
+    ${scylla_libs})
+
+if(Scylla_ENABLE_LTO)
+  include(enable_lto)
+  foreach(target scylla ${scylla_libs})
+    enable_lto(${target})
+  endforeach()
+endif()
 
 target_link_libraries(scylla PRIVATE
-    seastar
+    p11-kit::p11-kit
+    Seastar::seastar
     absl::headers
+    yaml-cpp::yaml-cpp
     Boost::program_options)
 
 target_include_directories(scylla PRIVATE
     "${CMAKE_CURRENT_SOURCE_DIR}"
     "${scylla_gen_build_dir}")
 
-add_subdirectory(dist)
+add_custom_target(maybe-scylla
+  DEPENDS $<$<CONFIG:Dev>:$<TARGET_FILE:scylla>>)
+add_dependencies(compiler-training
+  maybe-scylla)
+
+if(Scylla_DIST)
+  add_subdirectory(dist)
+endif()
+
+if(Scylla_BUILD_INSTRUMENTED)
+  add_subdirectory(pgo)
+endif()

CONTRIBUTING.md

@@ -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 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).
+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 [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++20 compiler and numerous tools and libraries to build.
+version of the C++23 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++20 standard that Scylla uses.
+will be too old, and not support the new C++23 standard that Scylla uses.
 
 Alternatively, to avoid having to upgrade your build machine or install
 various packages on it, we provide another option - the **frozen toolchain**.
 This is a script, `./tools/toolchain/dbuild`, that can execute build or run
-commands inside a Docker image that contains exactly the right build tools and
+commands inside a container that contains exactly the right build tools and
 libraries. The `dbuild` technique is useful for beginners, but is also the way
 in which ScyllaDB produces official releases, so it is highly recommended.
 
@@ -43,6 +43,12 @@ $ ./tools/toolchain/dbuild ninja build/release/scylla
 $ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
 ```
 
+Note: do not mix environemtns - 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
@@ -116,6 +122,13 @@ 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,
@@ -267,21 +280,45 @@ 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`, for use only with development environments (not for building) so that they can properly analyze the source code.
+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.
 
-[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.
+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).
 
-Other good options that directly parse CMake files are [KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
+[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.
 
-To use the `CMakeLists.txt` file with these programs, define the `FOR_IDE` CMake variable or shell environmental variable.
+#### CLion
 
-[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.
+[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.
 
 ### 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 re-uses them when possible
+- [ccache](https://ccache.samba.org/) caches compiled object files on disk and reuses 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.

LICENSE-ScyllaDB-Source-Available.md

@@ -0,0 +1,62 @@
+## **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

@@ -1,661 +0,0 @@
-                    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/>.

README.md

@@ -15,7 +15,7 @@ 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++20 compiler and of many libraries to build. The document
+versions of the C++23 compiler and of many libraries to build. The document
 [HACKING.md](HACKING.md) includes detailed information on building and
 developing Scylla, but to get Scylla building quickly on (almost) any build
 machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md),
@@ -84,11 +84,11 @@ 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
@@ -102,7 +102,7 @@ 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 the ScyllaDB open source.
+* The [community forum] and [Slack channel] are for users to discuss configuration, management, and operations of ScyllaDB.
 * The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
 
 [Community forum]: https://forum.scylladb.com/

SCYLLA-VERSION-GEN

@@ -78,7 +78,7 @@ fi
 
 # Default scylla product/version tags
 PRODUCT=scylla
-VERSION=6.1.0-dev
+VERSION=2025.2.0-dev
 
 if test -f version
 then
@@ -104,7 +104,7 @@ else
 fi
 
 if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" |cut -d . -f 3)
+	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" | rev | cut -d . -f 1 | rev)
 	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
 		exit 0
 	fi

absl-flat_hash_map.cc

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

absl-flat_hash_map.hh

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

alternator/CMakeLists.txt

@@ -15,6 +15,7 @@ target_sources(alternator
     conditions.cc
     auth.cc
     streams.cc
+    consumed_capacity.cc
     ttl.cc
     ${cql_grammar_srcs})
 target_include_directories(alternator
@@ -24,11 +25,13 @@ target_include_directories(alternator
   PRIVATE
     ${RAPIDJSON_INCLUDE_DIRS})
 target_link_libraries(alternator
-  cql3
-  idl
-  Seastar::seastar
-  xxHash::xxhash
-  absl::headers)
+  PUBLIC
+    Seastar::seastar
+    xxHash::xxhash
+  PRIVATE
+    cql3
+    idl
+    absl::headers)
 
 check_headers(check-headers alternator
   GLOB_RECURSE ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)

alternator/auth.cc

@@ -3,12 +3,12 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "alternator/error.hh"
 #include "auth/common.hh"
-#include "log.hh"
+#include "utils/log.hh"
 #include <string>
 #include <string_view>
 #include "bytes.hh"
@@ -19,6 +19,7 @@
 #include "alternator/executor.hh"
 #include "cql3/selection/selection.hh"
 #include "cql3/result_set.hh"
+#include "types/types.hh"
 #include <seastar/core/coroutine.hh>
 
 namespace alternator {
@@ -31,11 +32,12 @@ future<std::string> get_key_from_roles(service::storage_proxy& proxy, auth::serv
     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"));
-    if (!salted_hash_col) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("Credentials cannot be fetched for: {}", username)));
+    const column_definition* can_login_col = schema->get_column_definition(bytes("can_login"));
+    if (!salted_hash_col || !can_login_col) {
+        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Credentials cannot be fetched for: {}", username)));
     }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id}, selection->get_query_options());
+    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col, can_login_col});
+    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id, can_login_col->id}, selection->get_query_options());
     auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice,
             proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
     auto cl = auth::password_authenticator::consistency_for_user(username);
@@ -49,11 +51,18 @@ future<std::string> get_key_from_roles(service::storage_proxy& proxy, auth::serv
 
     auto result_set = builder.build();
     if (result_set->empty()) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("User not found: {}", username)));
+        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("User not found: {}", username)));
     }
-    const managed_bytes_opt& salted_hash = result_set->rows().front().front(); // We only asked for 1 row and 1 column
+    const auto& result = result_set->rows().front();
+    bool can_login = result[1] && value_cast<bool>(boolean_type->deserialize(*result[1]));
+    if (!can_login) {
+        // This is a valid role name, but has "login=False" so should not be
+        // usable for authentication (see #19735).
+        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Role {} has login=false so cannot be used for login", username)));
+    }
+    const managed_bytes_opt& salted_hash = result.front();
     if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("No password found for user: {}", username)));
+        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("No password found for user: {}", username)));
     }
     co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
 }

alternator/auth.hh

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

alternator/conditions.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <string_view>
@@ -15,8 +15,6 @@
 #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"
@@ -42,12 +40,12 @@ 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(format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
+        throw api_error::validation(fmt::format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
     }
     std::string op = comparison_operator.GetString();
     auto it = ops.find(op);
     if (it == ops.end()) {
-        throw api_error::validation(format("Unsupported comparison operator {}", op));
+        throw api_error::validation(fmt::format("Unsupported comparison operator {}", op));
     }
     return it->second;
 }
@@ -429,7 +427,7 @@ 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(
-                format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
+                fmt::format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
         } else {
             return false;
         }
@@ -613,7 +611,7 @@ conditional_operator_type get_conditional_operator(const rjson::value& req) {
         return conditional_operator_type::OR;
     } else {
         throw api_error::validation(
-                format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
+                fmt::format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
     }
 }
 
@@ -743,9 +741,9 @@ bool verify_condition_expression(
             };
             switch (list.op) {
             case '&':
-                return boost::algorithm::all_of(list.conditions, verify_condition);
+                return std::ranges::all_of(list.conditions, verify_condition);
             case '|':
-                return boost::algorithm::any_of(list.conditions, verify_condition);
+                return std::ranges::any_of(list.conditions, verify_condition);
             default:
                 // Shouldn't happen unless we have a bug in the parser
                 throw std::logic_error("bad operator in condition_list");

alternator/conditions.hh

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

alternator/consumed_capacity.cc

@@ -0,0 +1,87 @@
+/*
+ * Copyright 2024-present ScyllaDB
+ */
+
+/*
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ */
+
+#include "consumed_capacity.hh"
+#include "error.hh"
+
+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;
+
+static bool 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 consumed = return_consumed->GetString();
+    if (consumed == "INDEXES") {
+        throw api_error::validation("INDEXES consumed capacity is not supported");
+    }
+    if (consumed != "TOTAL") {
+        throw api_error::validation("Unknown consumed capacity "+ consumed);
+    }
+    return true;
+}
+
+void consumed_capacity_counter::add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept {
+    if (_should_add_to_reponse) {
+        auto consumption = rjson::empty_object();
+        rjson::add(consumption, "CapacityUnits", get_consumed_capacity_units());
+        rjson::add(response, "ConsumedCapacity", std::move(consumption));
+    }
+}
+
+static uint64_t calculate_half_units(uint64_t unit_block_size, uint64_t total_bytes, bool is_quorum) {
+    uint64_t half_units = (total_bytes + unit_block_size -1) / unit_block_size; //divide by unit_block_size and round up
+
+    if (is_quorum) {
+        half_units *= 2;
+    }
+    return half_units;
+}
+
+rcu_consumed_capacity_counter::rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum) :
+        consumed_capacity_counter(should_add_capacity(request)),_is_quorum(is_quorum) {
+}
+
+uint64_t rcu_consumed_capacity_counter::get_half_units() const noexcept {
+    return calculate_half_units(RCU_BLOCK_SIZE_LENGTH, _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);
+}
+
+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

@@ -0,0 +1,62 @@
+/*
+ * Copyright 2024-present ScyllaDB
+ */
+
+/*
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ */
+
+#pragma once
+
+#include "utils/rjson.hh"
+
+namespace alternator {
+
+/**
+ * \brief consumed_capacity_counter is a base class that holds the bookkeeping
+ *  to calculate RCU and WCU
+ *
+ * DynamoDB counts read capacity in half-integers - a short
+ * eventually-consistent read is counted as 0.5 unit.
+ * Because we want our counter to be an integer, we counts half units in
+ * our internal calculations.
+ *
+ * We use consumed_capacity_counter for calculation of a specific action
+ *
+ * It is also used to update the response if needed.
+ */
+class consumed_capacity_counter {
+public:
+    consumed_capacity_counter() = default;
+    consumed_capacity_counter(bool should_add_to_reponse) : _should_add_to_reponse(should_add_to_reponse){}
+    bool operator()() const noexcept {
+        return _should_add_to_reponse;
+    }
+
+    consumed_capacity_counter& operator +=(uint64_t bytes);
+    double get_consumed_capacity_units() const noexcept;
+    void add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept;
+    virtual ~consumed_capacity_counter() = default;
+    /**
+     * \brief get_half_units calculate the half units from the total bytes based on the type of the request
+     */
+    virtual uint64_t get_half_units() const noexcept = 0;
+    uint64_t _total_bytes = 0;
+protected:
+    bool _should_add_to_reponse = false;
+};
+
+class rcu_consumed_capacity_counter : public consumed_capacity_counter {
+    virtual uint64_t get_half_units() const noexcept;
+    bool _is_quorum = false;
+public:
+    rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum);
+};
+
+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);
+};
+
+}

alternator/controller.cc

@@ -3,10 +3,12 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
+#include <seastar/core/with_scheduling_group.hh>
 #include <seastar/net/dns.hh>
+
 #include "controller.hh"
 #include "server.hh"
 #include "executor.hh"
@@ -130,10 +132,10 @@ 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, creds = std::move(creds), alternator_enforce_authorization] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, creds, alternator_enforce_authorization,
+                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds)] (server& server) mutable {
+            return server.init(addr, alternator_port, alternator_https_port, creds,
+                    _config.alternator_enforce_authorization,
                     &_memory_limiter.local().get_semaphore(),
                     _config.max_concurrent_requests_per_shard);
         }).handle_exception([this, addr, alternator_port, alternator_https_port] (std::exception_ptr ep) {

alternator/controller.hh

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

alternator/error.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -88,6 +88,9 @@ 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);
     }

alternator/executor.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -23,6 +23,8 @@
 #include "utils/rjson.hh"
 #include "utils/updateable_value.hh"
 
+#include "tracing/trace_state.hh"
+
 namespace db {
     class system_distributed_keyspace;
 }
@@ -50,6 +52,8 @@ class gossiper;
 
 }
 
+class schema_builder;
+
 namespace alternator {
 
 class rmw_operation;
@@ -67,7 +71,7 @@ public:
  * (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 {
@@ -158,6 +162,7 @@ class executor : public peering_sharded_service<executor> {
     service::migration_manager& _mm;
     db::system_distributed_keyspace& _sdks;
     cdc::metadata& _cdc_metadata;
+    utils::updateable_value<bool> _enforce_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;
@@ -176,10 +181,7 @@ public:
              db::system_distributed_keyspace& sdks,
              cdc::metadata& cdc_metadata,
              smp_service_group ssg,
-             utils::updateable_value<uint32_t> default_timeout_in_ms)
-        : _gossiper(gossiper), _proxy(proxy), _mm(mm), _sdks(sdks), _cdc_metadata(cdc_metadata), _ssg(ssg) {
-        s_default_timeout_in_ms = std::move(default_timeout_in_ms);
-    }
+             utils::updateable_value<uint32_t> default_timeout_in_ms);
 
     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);
@@ -224,7 +226,7 @@ private:
     friend class rmw_operation;
 
     static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
-    
+
 public:
     static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
 
@@ -232,7 +234,8 @@ public:
         const query::partition_slice&,
         const cql3::selection::selection&,
         const query::result&,
-        const std::optional<attrs_to_get>&);
+        const std::optional<attrs_to_get>&,
+        uint64_t* = nullptr);
 
     static future<std::vector<rjson::value>> describe_multi_item(schema_ptr schema,
         const query::partition_slice&& slice,
@@ -244,6 +247,7 @@ public:
         const std::vector<managed_bytes_opt>&,
         const std::optional<attrs_to_get>&,
         rjson::value&,
+        uint64_t* item_length_in_bytes = nullptr,
         bool = false);
 
     static void add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
@@ -262,4 +266,9 @@ public:
 // 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, const service::client_state&, const schema_ptr&, auth::permission);
+
 }

alternator/expressions.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "expressions.hh"
@@ -17,12 +17,9 @@
 
 #include "seastarx.hh"
 
-#include <seastar/core/print.hh>
+#include <seastar/core/format.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>
 
@@ -57,10 +54,10 @@ static Result parse(const char* input_name, std::string_view input, Func&& f) {
         // 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(format("Failed parsing {} '{}': {}",
+        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
             input_name, input, e.what()));
     } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing {} '{}': {}",
+        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
             input_name, input, std::current_exception()));
     }
 }
@@ -160,12 +157,12 @@ 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(
-                    format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
+                    fmt::format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
         }
         const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
         if (!value || !value->IsString()) {
             throw api_error::validation(
-                    format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
+                    fmt::format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
         }
         used_attribute_names.emplace(column_name);
         return std::string(rjson::to_string_view(*value));
@@ -202,16 +199,16 @@ static void resolve_constant(parsed::constant& c,
         [&] (const std::string& valref) {
             if (!expression_attribute_values) {
                 throw api_error::validation(
-                        format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
+                        fmt::format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
             }
             const rjson::value* value = rjson::find(*expression_attribute_values, valref);
             if (!value) {
                 throw api_error::validation(
-                        format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
+                        fmt::format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
             }
             if (value->IsNull()) {
                 throw api_error::validation(
-                        format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
+                        fmt::format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
             }
             validate_value(*value, "ExpressionAttributeValues");
             used_attribute_values.emplace(valref);
@@ -708,7 +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(
-                        format("{}: unknown function '{}' called.", caller, f._function_name));
+                        fmt::format("{}: unknown function '{}' called.", caller, f._function_name));
             }
             return function_it->second(caller, previous_item, f);
         },

alternator/expressions.g

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

alternator/expressions.hh

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

alternator/expressions_types.hh

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

alternator/extract_from_attrs.hh

@@ -0,0 +1,73 @@
+/*
+ * 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 "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/rmw_operation.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -11,10 +11,15 @@
 #include "seastarx.hh"
 #include "service/paxos/cas_request.hh"
 #include "utils/rjson.hh"
+#include "consumed_capacity.hh"
 #include "executor.hh"
+#include "tracing/trace_state.hh"
+#include "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,
@@ -63,7 +68,7 @@ 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 {
@@ -113,7 +118,8 @@ public:
             tracing::trace_state_ptr trace_state,
             service_permit permit,
             bool needs_read_before_write,
-            stats& stats);
+            stats& stats,
+            uint64_t& wcu_total);
     std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
 };
 

alternator/serialization.cc

@@ -3,12 +3,12 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "utils/base64.hh"
 #include "utils/rjson.hh"
-#include "log.hh"
+#include "utils/log.hh"
 #include "serialization.hh"
 #include "error.hh"
 #include "concrete_types.hh"
@@ -143,17 +143,17 @@ static big_decimal parse_and_validate_number(std::string_view s) {
         big_decimal ret(s);
         auto [magnitude, precision] = internal::get_magnitude_and_precision(s);
         if (magnitude > 125) {
-            throw api_error::validation(format("Number overflow: {}. Attempting to store a number with magnitude larger than supported range.", s));
+            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(format("Number underflow: {}. Attempting to store a number with magnitude lower than supported range.", s));
+            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(format("Number too precise: {}. Attempting to store a number with more significant digits than supported.", s));
+            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(format("The parameter cannot be converted to a numeric value: {}", s));
+        throw api_error::validation(fmt::format("The parameter cannot be converted to a numeric value: {}", s));
     }
 
 }
@@ -245,6 +245,27 @@ 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"},
@@ -265,7 +286,7 @@ bytes get_key_column_value(const rjson::value& item, const column_definition& co
     std::string column_name = column.name_as_text();
     const rjson::value* key_typed_value = rjson::find(item, column_name);
     if (!key_typed_value) {
-        throw api_error::validation(format("Key column {} not found", column_name));
+        throw api_error::validation(fmt::format("Key column {} not found", column_name));
     }
     return get_key_from_typed_value(*key_typed_value, column);
 }
@@ -277,19 +298,26 @@ 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 ||
-            !key_typed_value.MemberBegin()->value.IsString()) {
+    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1) {
         throw api_error::validation(
-                format("Malformed value object for {} {}: {}",
+                fmt::format("Malformed value object for {} {}: {}",
                         value_name, name, key_typed_value));
     }
 
     auto it = key_typed_value.MemberBegin();
     if (rjson::to_string_view(it->name) != type_str) {
         throw api_error::validation(
-                format("Type mismatch: expected type {} for {} {}, got type {}",
+                fmt::format("Type mismatch: expected type {} for {} {}, got type {}",
                         type_str, value_name, name, it->name));
     }
+    // We assume this function is called just for key types (S, B, N), and
+    // all of those always have a string value in the JSON.
+    if (!it->value.IsString()) {
+        throw api_error::validation(
+            fmt::format("Malformed value object for {} {}: {}",
+                    value_name, name, key_typed_value));
+
+    }
     return it->value;
 }
 
@@ -395,16 +423,16 @@ position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema)
 
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
     if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("{}: invalid number object", diagnostic));
+        throw api_error::validation(fmt::format("{}: invalid number object", diagnostic));
     }
     auto it = v.MemberBegin();
     if (it->name != "N") {
-        throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
+        throw api_error::validation(fmt::format("{}: expected number, found type '{}'", diagnostic, it->name));
     }
     if (!it->value.IsString()) {
         // We shouldn't reach here. Callers normally validate their input
         // earlier with validate_value().
-        throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
+        throw api_error::validation(fmt::format("{}: improperly formatted number constant", diagnostic));
     }
     big_decimal ret = parse_and_validate_number(rjson::to_string_view(it->value));
     return ret;
@@ -485,7 +513,7 @@ 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(format("Mismatched set types: {} and {}", set1_type, set2_type));
+        throw api_error::validation(fmt::format("Mismatched set types: {} and {}", set1_type, set2_type));
     }
     if (!set1 || !set2) {
         throw api_error::validation("UpdateExpression: ADD operation for sets must be given sets as arguments");
@@ -513,7 +541,7 @@ 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(format("Set DELETE type mismatch: {} and {}", set1_type, set2_type));
+        throw api_error::validation(fmt::format("Set DELETE type mismatch: {} and {}", set1_type, set2_type));
     }
     if (!set1 || !set2) {
         throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");

alternator/serialization.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -43,6 +43,7 @@ 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);
 

alternator/server.cc

@@ -3,11 +3,12 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "alternator/server.hh"
-#include "log.hh"
+#include "gms/application_state.hh"
+#include "utils/log.hh"
 #include <fmt/ranges.h>
 #include <seastar/http/function_handlers.hh>
 #include <seastar/http/short_streams.hh>
@@ -17,7 +18,10 @@
 #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>
@@ -208,10 +212,33 @@ 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();
-        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)) {
+        // /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) {
+            auto ip = _gossiper.get_address_map().get(id);
+            if (!query_rack.empty()) {
+                auto rack = _gossiper.get_application_state_value(ip, 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(ip) && _gossiper.is_normal(ip)) {
                 // 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(ip)));
@@ -257,7 +284,7 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
     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") {
-        throw api_error::invalid_signature(format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header));
+        throw api_error::invalid_signature(fmt::format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header));
     }
     authorization_header.remove_prefix(pos+1);
     std::string credential;
@@ -292,7 +319,7 @@ 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) {
-        throw api_error::validation(format("Incorrect credential information format: {}", credential));
+        throw api_error::validation(fmt::format("Incorrect credential information format: {}", credential));
     }
     std::string user(credential_split[0]);
     std::string datestamp(credential_split[1]);
@@ -369,7 +396,7 @@ static std::string_view truncated_content_view(const chunked_content& content, s
     }
 }
 
-static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_state, std::string_view username, sstring_view op, const chunked_content& query) {
+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) {
     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()) {
@@ -377,7 +404,7 @@ static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_
         std::string buf;
         tracing::add_session_param(trace_state, "alternator_op", op);
         tracing::add_query(trace_state, truncated_content_view(query, buf));
-        tracing::begin(trace_state, format("Alternator {}", op), client_state.get_client_address());
+        tracing::begin(trace_state, seastar::format("Alternator {}", op), client_state.get_client_address());
         if (!username.empty()) {
             tracing::set_username(trace_state, auth::authenticated_user(username));
         }
@@ -402,7 +429,7 @@ future<executor::request_return_type> server::handle_api_request(std::unique_ptr
         ++_executor._stats.requests_blocked_memory;
     }
     auto units = co_await std::move(units_fut);
-    assert(req->content_stream);
+    SCYLLA_ASSERT(req->content_stream);
     chunked_content content = co_await util::read_entire_stream(*req->content_stream);
     auto username = co_await verify_signature(*req, content);
 
@@ -413,7 +440,7 @@ future<executor::request_return_type> server::handle_api_request(std::unique_ptr
     auto callback_it = _callbacks.find(op);
     if (callback_it == _callbacks.end()) {
         _executor._stats.unsupported_operations++;
-        co_return api_error::unknown_operation(format("Unsupported operation {}", op));
+        co_return api_error::unknown_operation(fmt::format("Unsupported operation {}", op));
     }
     if (_pending_requests.get_count() >= _max_concurrent_requests) {
         _executor._stats.requests_shed++;
@@ -421,18 +448,25 @@ future<executor::request_return_type> server::handle_api_request(std::unique_ptr
     }
     _pending_requests.enter();
     auto leave = defer([this] () noexcept { _pending_requests.leave(); });
-    //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};
+    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));
+    }
     co_await client_state.maybe_update_per_service_level_params();
 
     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));
+
+    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));
+                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));
 }
 
 void server::set_routes(routes& r) {
@@ -472,6 +506,7 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
         , _enforce_authorization(false)
         , _enabled_servers{}
         , _pending_requests{}
+        , _timeout_config(_proxy.data_dictionary().get_config())
       , _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));
@@ -549,9 +584,9 @@ 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<tls::credentials_builder> creds,
-        bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests) {
+        utils::updateable_value<bool> enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests) {
     _memory_limiter = memory_limiter;
-    _enforce_authorization = enforce_authorization;
+    _enforce_authorization = std::move(enforce_authorization);
     _max_concurrent_requests = std::move(max_concurrent_requests);
     if (!port && !https_port) {
         return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
@@ -571,14 +606,24 @@ future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std:
             set_routes(_https_server._routes);
             _https_server.set_content_length_limit(server::content_length_limit);
             _https_server.set_content_streaming(true);
-            auto server_creds = 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);
-                }
-            }).get();
-            _https_server.listen(socket_address{addr, *https_port}, std::move(server_creds)).get();
+
+            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();
+            }
+            _https_server.listen(socket_address{addr, *https_port}, _credentials).get();
             _enabled_servers.push_back(std::ref(_https_server));
         }
     });
@@ -636,7 +681,7 @@ future<> server::json_parser::stop() {
 
 const char* api_error::what() const noexcept {
     if (_what_string.empty()) {
-        _what_string = format("{} {}: {}", std::to_underlying(_http_code), _type, _msg);
+        _what_string = fmt::format("{} {}: {}", std::to_underlying(_http_code), _type, _msg);
     }
     return _what_string.c_str();
 }

alternator/server.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -24,7 +24,7 @@ namespace alternator {
 
 using chunked_content = rjson::chunked_content;
 
-class server {
+class server : public peering_sharded_service<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>)>;
@@ -39,14 +39,21 @@ class server {
     qos::service_level_controller& _sl_controller;
 
     key_cache _key_cache;
-    bool _enforce_authorization;
+    utils::updateable_value<bool> _enforce_authorization;
     utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
     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;
+
     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;
@@ -71,7 +78,7 @@ public:
     server(executor& executor, service::storage_proxy& proxy, gms::gossiper& gossiper, auth::service& service, qos::service_level_controller& sl_controller);
 
     future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-            bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests);
+            utils::updateable_value<bool> enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests);
     future<> stop();
 private:
     void set_routes(seastar::httpd::routes& r);

alternator/stats.cc

@@ -3,12 +3,13 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "stats.hh"
 #include "utils/histogram_metrics_helper.hh"
 #include <seastar/core/metrics.hh>
+#include "utils/labels.hh"
 
 namespace alternator {
 
@@ -21,12 +22,12 @@ stats::stats() : api_operations{} {
     _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)}).set_skip_when_empty(),
+                        seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName), alternator_label, basic_level}).set_skip_when_empty(),
 #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.histogram());}).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(), \
+                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName), alternator_label, basic_level}, [this]{return to_metrics_histogram(api_operations.name.histogram());}).aggregate({seastar::metrics::shard_label}).set_skip_when_empty(), \
 				seastar::metrics::make_summary("op_latency_summary", \
-						                        seastar::metrics::description("Latency summary of an operation via Alternator API"), [this]{return to_metrics_summary(api_operations.name.summary());})(op(CamelCaseName)).set_skip_when_empty(),
+						                        seastar::metrics::description("Latency summary of an operation via Alternator API"), [this]{return to_metrics_summary(api_operations.name.summary());})(op(CamelCaseName))(basic_level)(alternator_label).set_skip_when_empty(),
             OPERATION(batch_get_item, "BatchGetItem")
             OPERATION(batch_write_item, "BatchWriteItem")
             OPERATION(create_backup, "CreateBackup")
@@ -67,6 +68,8 @@ stats::stats() : api_operations{} {
             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(list_streams, "ListStreams")
             OPERATION(describe_stream, "DescribeStream")
             OPERATION(get_shard_iterator, "GetShardIterator")
@@ -75,25 +78,39 @@ stats::stats() : api_operations{} {
     });
     _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::description("number of unsupported operations via Alternator API"))(alternator_label).set_skip_when_empty(),
             seastar::metrics::make_total_operations("total_operations", total_operations,
-                    seastar::metrics::description("number of total operations via Alternator API")),
+                    seastar::metrics::description("number of total operations via Alternator API"))(basic_level)(alternator_label).set_skip_when_empty(),
             seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
-                    seastar::metrics::description("number of performed read-before-write operations")),
+                    seastar::metrics::description("number of performed read-before-write operations"))(alternator_label).set_skip_when_empty(),
             seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
-                    seastar::metrics::description("number of writes that used LWT")),
+                    seastar::metrics::description("number of writes that used LWT"))(alternator_label).set_skip_when_empty(),
             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::description("number writes that had to be bounced from this shard because of LWT requirements"))(alternator_label).set_skip_when_empty(),
             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::description("Counts a number of requests blocked due to memory pressure."))(alternator_label).set_skip_when_empty(),
             seastar::metrics::make_total_operations("requests_shed", requests_shed,
-                    seastar::metrics::description("Counts a number of requests shed due to overload.")),
+                    seastar::metrics::description("Counts a number of requests shed due to overload."))(alternator_label).set_skip_when_empty(),
             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::description("number of rows read during filtering operations"))(alternator_label).set_skip_when_empty(),
             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_counter("rcu_total", rcu_total,
+                    seastar::metrics::description("total number of consumed read units, counted as half units"))(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("wcu_total", wcu_total[wcu_types::PUT_ITEM],
+                    seastar::metrics::description("total number of consumed write units, counted as half units"),{op("PutItem")})(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("wcu_total", wcu_total[wcu_types::DELETE_ITEM],
+                    seastar::metrics::description("total number of consumed write units, counted as half units"),{op("DeleteItem")})(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("wcu_total", wcu_total[wcu_types::UPDATE_ITEM],
+                    seastar::metrics::description("total number of consumed write units, counted as half units"),{op("UpdateItem")})(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("wcu_total", wcu_total[wcu_types::INDEX],
+                    seastar::metrics::description("total number of consumed write units, counted as half units"),{op("Index")})(alternator_label).set_skip_when_empty(),
             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::description("number of rows read and dropped during filtering operations"))(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("batch_item_count", seastar::metrics::description("The total number of items processed across all batches"),{op("BatchWriteItem")},
+                    api_operations.batch_write_item_batch_total)(alternator_label).set_skip_when_empty(),
+            seastar::metrics::make_counter("batch_item_count", seastar::metrics::description("The total number of items processed across all batches"),{op("BatchGetItem")},
+                    api_operations.batch_get_item_batch_total)(alternator_label).set_skip_when_empty(),
     });
 }
 

alternator/stats.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -26,6 +26,8 @@ public:
     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;
@@ -65,10 +67,13 @@ 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;
     } api_operations;
     // Miscellaneous event counters
@@ -79,6 +84,18 @@ public:
     uint64_t shard_bounce_for_lwt = 0;
     uint64_t requests_blocked_memory = 0;
     uint64_t requests_shed = 0;
+    uint64_t rcu_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;
 private:

alternator/streams.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <type_traits>
@@ -13,6 +13,7 @@
 
 #include <seastar/json/formatter.hh>
 
+#include "auth/permission.hh"
 #include "db/config.hh"
 
 #include "cdc/log.hh"
@@ -818,11 +819,13 @@ future<executor::request_return_type> executor::get_records(client_state& client
     }
 
     if (!schema || !base || !is_alternator_keyspace(schema->ks_name())) {
-        throw api_error::resource_not_found(fmt::to_string(iter.table));
+        co_return api_error::resource_not_found(fmt::to_string(iter.table));
     }
 
     tracing::add_table_name(trace_state, schema->ks_name(), schema->cf_name());
 
+    co_await verify_permission(_enforce_authorization, client_state, schema, auth::permission::SELECT);
+
     db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
     partition_key pk = iter.shard.id.to_partition_key(*schema);
 
@@ -841,19 +844,21 @@ 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 = 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) {
+    std::optional<attrs_to_get> key_names =
+        base->primary_key_columns()
+        | std::views::transform([&] (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 = boost::copy_range<attrs_to_get>(base->regular_columns()
+    std::optional<attrs_to_get> attr_names = 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 
-        | boost::adaptors::transformed([] (const column_definition& cdef) {
+        | std::views::transform([] (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());
@@ -864,10 +869,11 @@ 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_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; })
-    );
+    auto regular_columns = schema->regular_columns()
+        | 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::views::transform([&] (const column_definition& cdef) { columns.emplace_back(&cdef); return cdef.id; })
+        | std::ranges::to<query::column_id_vector>()
+    ;
 
     stream_view_type type = cdc_options_to_steam_view_type(base->cdc_options());
 
@@ -887,7 +893,7 @@ 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));
 
-    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(
+    co_return 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)).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());
         query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
@@ -975,7 +981,7 @@ future<executor::request_return_type> executor::get_records(client_state& client
             case cdc::operation::post_image:
             {
                 auto item = rjson::empty_object();
-                describe_single_item(*selection, row, attr_names, item, true);
+                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;

alternator/ttl.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <chrono>
@@ -16,16 +16,16 @@
 #include <seastar/core/future.hh>
 #include <seastar/core/lowres_clock.hh>
 #include <seastar/coroutine/maybe_yield.hh>
-#include <boost/multiprecision/cpp_int.hpp>
 
 #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 "log.hh"
+#include "utils/log.hh"
 #include "gc_clock.hh"
 #include "replica/database.hh"
+#include "service/client_state.hh"
 #include "service_permit.hh"
 #include "timestamp.hh"
 #include "service/storage_proxy.hh"
@@ -35,6 +35,7 @@
 #include "mutation/mutation.hh"
 #include "types/types.hh"
 #include "types/map.hh"
+#include "utils/assert.hh"
 #include "utils/rjson.hh"
 #include "utils/big_decimal.hh"
 #include "cql3/selection/selection.hh"
@@ -47,6 +48,7 @@
 #include "dht/sharder.hh"
 #include "db/config.hh"
 #include "db/tags/utils.hh"
+#include "utils/labels.hh"
 
 #include "ttl.hh"
 
@@ -97,6 +99,7 @@ future<executor::request_return_type> executor::update_time_to_live(client_state
     }
     sstring attribute_name(v->GetString(), v->GetStringLength());
 
+    co_await verify_permission(_enforce_authorization, client_state, schema, auth::permission::ALTER);
     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)) {
@@ -312,18 +315,19 @@ 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.
-static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary_ranges(
+static future<std::vector<std::pair<dht::token_range, locator::host_id>>> get_secondary_ranges(
         const locator::effective_replication_map_ptr& erm,
-        gms::inet_address ep) {
+        locator::host_id ep) {
     const auto& tm = *erm->get_token_metadata_ptr();
     const auto& sorted_tokens = tm.sorted_tokens();
-    std::vector<std::pair<dht::token_range, gms::inet_address>> ret;
+    std::vector<std::pair<dht::token_range, locator::host_id>> ret;
     if (sorted_tokens.empty()) {
         on_internal_error(tlogger, "Token metadata is empty");
     }
     auto prev_tok = sorted_tokens.back();
     for (const auto& tok : sorted_tokens) {
-        inet_address_vector_replica_set eps = erm->get_natural_endpoints(tok);
+        co_await coroutine::maybe_yield();
+        host_id_vector_replica_set eps = erm->get_natural_replicas(tok);
         if (eps.size() <= 1 || eps[1] != ep) {
             prev_tok = tok;
             continue;
@@ -350,7 +354,7 @@ static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary
         }
         prev_tok = tok;
     }
-    return ret;
+    co_return ret;
 }
 
 
@@ -386,63 +390,63 @@ static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary
 //
 // FIXME: Check if this algorithm is safe with tablet migration.
 // https://github.com/scylladb/scylladb/issues/16567
-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::vnode_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);
-        }
-    };
 
+// 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_ptr& 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::effective_replication_map_ptr& 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);
+    }
+};
+
+template<class primary_or_secondary_t>
+class token_ranges_owned_by_this_shard {
     schema_ptr _s;
     locator::effective_replication_map_ptr _erm;
     // _token_ranges will contain a list of token ranges owned by this node.
     // We'll further need to split each such range to the pieces owned by
     // the current shard, using _intersecter.
-    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;
+    const primary_or_secondary_t _token_ranges;
     // NOTICE: _range_idx is used modulo _token_ranges size when accessing
     // the data to ensure that it doesn't go out of bounds
     size_t _range_idx;
     size_t _end_idx;
     std::optional<dht::selective_token_range_sharder> _intersecter;
 public:
-    token_ranges_owned_by_this_shard(replica::database& db, gms::gossiper& g, schema_ptr s)
+    token_ranges_owned_by_this_shard(schema_ptr s, primary_or_secondary_t token_ranges)
         :  _s(s)
         , _erm(s->table().get_effective_replication_map())
-        , _token_ranges(db.find_keyspace(s->ks_name()).get_vnode_effective_replication_map(),
-                g, _erm->get_topology().my_address())
+        , _token_ranges(std::move(token_ranges))
         , _range_idx(random_offset(0, _token_ranges.size() - 1))
         , _end_idx(_range_idx + _token_ranges.size())
     {
@@ -498,6 +502,7 @@ 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;
@@ -507,6 +512,7 @@ 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
@@ -515,8 +521,9 @@ 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 = boost::copy_range<query::column_id_vector>(
-            s->regular_columns() | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.id; }));
+        auto regular_columns =
+            s->regular_columns() | std::views::transform([] (const column_definition& cdef) { return cdef.id; })
+            | std::ranges::to<query::column_id_vector>();
         selection = cql3::selection::selection::wildcard(s);
         query::partition_slice::option_set opts = selection->get_query_options();
         opts.set<query::partition_slice::option::allow_short_read>();
@@ -525,10 +532,9 @@ 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>(client_state, trace_state, empty_service_permit());
+        query_state_ptr = std::make_unique<service::query_state>(internal_client_state, trace_state, empty_service_permit());
         // FIXME: What should we do on multi-DC? Will we run the expiration on the same ranges on all
         // DCs or only once for each range? If the latter, we need to change the CLs in the
         // scanner and deleter.
@@ -551,7 +557,7 @@ static future<> scan_table_ranges(
         expiration_service::stats& expiration_stats)
 {
     const schema_ptr& s = scan_ctx.s;
-    assert (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
+    SCYLLA_ASSERT (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
     auto p = service::pager::query_pagers::pager(proxy, s, scan_ctx.selection, *scan_ctx.query_state_ptr,
             *scan_ctx.query_options, scan_ctx.command, std::move(partition_ranges), nullptr);
     while (!p->is_exhausted()) {
@@ -724,7 +730,9 @@ static future<bool> scan_table(
     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)};
-    token_ranges_owned_by_this_shard<primary> my_ranges(db.real_database(), gossiper, s);
+    auto erm = db.real_database().find_keyspace(s->ks_name()).get_vnode_effective_replication_map();
+    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
@@ -744,7 +752,7 @@ static future<bool> scan_table(
     // 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);
+    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;
@@ -843,13 +851,13 @@ 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")),
+            seastar::metrics::description("number of passes over the database"))(alternator_label).set_skip_when_empty(),
         seastar::metrics::make_total_operations("scan_table", scan_table,
-            seastar::metrics::description("number of table scans (counting each scan of each table that enabled expiration)")),
+            seastar::metrics::description("number of table scans (counting each scan of each table that enabled expiration)"))(alternator_label).set_skip_when_empty(),
         seastar::metrics::make_total_operations("items_deleted", items_deleted,
-            seastar::metrics::description("number of items deleted after expiration")),
+            seastar::metrics::description("number of items deleted after expiration"))(basic_level)(alternator_label).set_skip_when_empty(),
         seastar::metrics::make_total_operations("secondary_ranges_scanned", secondary_ranges_scanned,
-            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down")),
+            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down"))(alternator_label).set_skip_when_empty(),
     });
 }
 

alternator/ttl.hh

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

api/CMakeLists.txt

@@ -1,4 +1,29 @@
 # 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
@@ -7,6 +32,7 @@ set(swagger_files
   api-doc/commitlog.json
   api-doc/compaction_manager.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
@@ -16,6 +42,7 @@ set(swagger_files
   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
@@ -28,7 +55,7 @@ set(swagger_files
 foreach(f ${swagger_files})
   get_filename_component(fname "${f}" NAME_WE)
   get_filename_component(dir "${f}" DIRECTORY)
-  seastar_generate_swagger(
+  generate_swagger(
     TARGET scylla_swagger_gen_${fname}
     VAR scylla_swagger_gen_${fname}_files
     IN_FILE "${CMAKE_CURRENT_SOURCE_DIR}/${f}"
@@ -36,7 +63,7 @@ foreach(f ${swagger_files})
   list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
 endforeach()
 
-add_library(api)
+add_library(api STATIC)
 target_sources(api
   PRIVATE
     api.cc
@@ -46,6 +73,7 @@ target_sources(api
     commitlog.cc
     compaction_manager.cc
     config.cc
+    cql_server_test.cc
     endpoint_snitch.cc
     error_injection.cc
     authorization_cache.cc
@@ -55,6 +83,7 @@ target_sources(api
     lsa.cc
     messaging_service.cc
     raft.cc
+    service_levels.cc
     storage_proxy.cc
     storage_service.cc
     stream_manager.cc
@@ -69,11 +98,13 @@ target_include_directories(api
     ${CMAKE_SOURCE_DIR}
     ${scylla_gen_build_dir})
 target_link_libraries(api
-  idl
-  wasmtime_bindings
-  Seastar::seastar
-  xxHash::xxhash
-  absl::headers)
+  PUBLIC
+    Seastar::seastar
+    xxHash::xxhash
+  PRIVATE
+    idl
+    wasmtime_bindings
+    absl::headers)
 
 check_headers(check-headers api
   GLOB_RECURSE ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)

api/api-doc/column_family.json

@@ -92,6 +92,14 @@
                      "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",

api/api-doc/cql_server_test.json

@@ -0,0 +1,26 @@
+{
+    "apiVersion":"0.0.1",
+    "swaggerVersion":"1.2",
+    "basePath":"{{Protocol}}://{{Host}}",
+    "resourcePath":"/cql_server_test",
+    "produces":[
+        "application/json"
+    ],
+    "apis":[
+        {
+            "path":"/cql_server_test/connections_params",
+            "operations":[
+                {
+                    "method":"GET",
+                    "summary":"Get service level params of each CQL connection",
+                    "type":"connections_service_level_params",
+                    "nickname":"connections_params",
+                    "produces":[
+                        "application/json"
+                    ],
+                    "parameters":[]
+                }
+            ]
+        }
+    ]
+}

api/api-doc/raft.json

@@ -94,6 +94,38 @@
                ]
             }
          ]
+      },
+      {
+         "path":"/raft/trigger_stepdown/",
+         "operations":[
+            {
+               "method":"POST",
+               "summary":"Triggers stepdown of a leader for given Raft group or group0 if not provided (returns an error if the node is not a leader)",
+               "type":"string",
+               "nickname":"trigger_stepdown",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+                  {
+                     "name":"group_id",
+                     "description":"The ID of the group which leader should stepdown",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"timeout",
+                     "description":"Timeout in seconds after which the endpoint returns a failure. If not provided, 60s is used.",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"long",
+                     "paramType":"query"
+                  }
+               ]
+            }
+         ]
       }
    ]
 }

api/api-doc/service_levels.json

@@ -0,0 +1,56 @@
+{
+    "apiVersion":"0.0.1",
+    "swaggerVersion":"1.2",
+    "basePath":"{{Protocol}}://{{Host}}",
+    "resourcePath":"/service_levels",
+    "produces":[
+        "application/json"
+    ],
+    "apis":[
+        {
+            "path":"/service_levels/switch_tenants",
+            "operations":[
+                {
+                    "method":"POST",
+                    "summary":"Switch tenants on all opened connections if needed",
+                    "type":"void",
+                    "nickname":"do_switch_tenants",
+                    "produces":[
+                        "application/json"
+                    ],
+                    "parameters":[]
+                }
+            ]
+        },
+        {
+            "path":"/service_levels/count_connections",
+            "operations":[
+                {
+                    "method":"GET",
+                    "summary":"Count opened CQL connections per scheduling group per user",
+                    "type":"connections_count_map",
+                    "nickname":"count_connections",
+                    "produces":[
+                        "application/json"
+                    ],
+                    "parameters":[]
+                }
+            ]
+        }
+    ],
+    "models":{},
+    "components": {
+        "schemas": {
+          "connections_count_map": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "object",
+              "additionalProperties": {
+                "type": "integer"
+              }
+            }
+          }
+        }
+      }
+
+}

api/api-doc/storage_service.json

@@ -741,11 +741,168 @@
                      "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"
                   }
                ]
             }
          ]
       },
+      {
+          "path":"/storage_service/backup",
+          "operations":[
+              {
+                  "method":"POST",
+                  "summary":"Starts copying SSTables from a specified keyspace to a designated bucket in object storage",
+                  "type":"string",
+                  "nickname":"start_backup",
+                  "produces":[
+                      "application/json"
+                  ],
+                  "parameters":[
+                      {
+                          "name":"endpoint",
+                          "description":"ID of the configured object storage endpoint to copy sstables to",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"bucket",
+                          "description":"Name of the bucket to backup sstables to",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                           "name":"prefix",
+                           "description":"The prefix of the objects for the backuped sstables",
+                           "required":true,
+                           "allowMultiple":false,
+                           "type":"string",
+                           "paramType":"query"
+                      },
+                      {
+                          "name":"keyspace",
+                          "description":"Name of a keyspace to copy sstables from",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"table",
+                          "description":"Name of a table to copy sstables from",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"snapshot",
+                          "description":"Name of a snapshot to copy sstables from",
+                          "required":false,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"move_files",
+                          "description":"Move component files instead of copying them",
+                          "required":false,
+                          "allowMultiple":false,
+                          "type":"boolean",
+                          "paramType":"query"
+                      }
+                  ]
+              }
+          ]
+      },
+      {
+          "path":"/storage_service/restore",
+          "operations":[
+              {
+                  "method":"POST",
+                  "summary":"Starts copying SSTables from a designated bucket in object storage to a specified keyspace",
+                  "type":"string",
+                  "nickname":"start_restore",
+                  "produces":[
+                      "application/json"
+                  ],
+                  "parameters":[
+                      {
+                          "name":"endpoint",
+                          "description":"ID of the configured object storage endpoint to copy SSTables from",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"bucket",
+                          "description":"Name of the bucket to read SSTables from",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"prefix",
+                          "description":"The prefix of the object keys for the backuped SSTables",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "in": "body",
+                          "name": "sstables",
+                          "description": "The list of the object keys of the TOC component of the SSTables to be restored",
+                          "required":true,
+                          "schema" :{
+                              "type": "array",
+                              "items": {
+                                  "type": "string"
+                              }
+                          }
+                      },
+                      {
+                          "name":"keyspace",
+                          "description":"Name of a keyspace to copy SSTables to",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"table",
+                          "description":"Name of a table to copy SSTables to",
+                          "required":true,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query"
+                      },
+                      {
+                          "name":"scope",
+                          "description":"Defines the set of nodes to which mutations can be streamed",
+                          "required":false,
+                          "allowMultiple":false,
+                          "type":"string",
+                          "paramType":"query",
+                          "enum": ["all", "dc", "rack", "node"]
+                      }
+                  ]
+              }
+          ]
+      },
       {
          "path":"/storage_service/keyspace_compaction/{keyspace}",
          "operations":[
@@ -781,6 +938,14 @@
                      "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"
                   }
                ]
             }
@@ -1491,38 +1656,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/truncate/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Truncates (deletes) the given columnFamily from the provided keyspace. Calling truncate results in actual deletion of all data in the cluster under the given columnFamily and it will fail unless all hosts are up. All data in the given column family will be deleted, but its definition will not be affected.",
-               "type":"void",
-               "nickname":"truncate",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Column family name",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/storage_service/keyspaces",
          "operations":[
@@ -1891,6 +2024,14 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
+                  },
+                  {
+                     "name":"force",
+                     "description":"Enforce the source_dc option, even if it unsafe to use for rebuild",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"boolean",
+                     "paramType":"query"
                   }
                ]
             }
@@ -2696,6 +2837,70 @@
             }
          ]
       },
+      {
+         "path":"/storage_service/tablets/repair",
+         "operations":[
+            {
+               "nickname":"repair_tablet",
+               "method":"POST",
+               "summary":"Repair a tablet",
+               "type":"tablet_repair_result",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+                  {
+                     "name":"ks",
+                     "description":"Keyspace name to repair",
+                     "required":true,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"table",
+                     "description":"Table name to repair",
+                     "required":true,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"tokens",
+                     "description":"Tokens owned by the tablets to repair. Multiple tokens can be provided using a comma-separated list. When set to the special word 'all', all tablets will be repaired",
+                     "required":true,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"hosts_filter",
+                     "description":"Repair replicas listed in the comma-separated host_id list.",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"dcs_filter",
+                     "description":"Repair replicas listed in the comma-separated DC list",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"await_completion",
+                     "description":"Set true to wait for the repair to complete. Set false to skip waiting for the repair to complete. When the option is not provided, it defaults to false.",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  }
+               ]
+            }
+         ]
+      },
       {
          "path":"/storage_service/tablets/balancing",
          "operations":[
@@ -3114,6 +3319,15 @@
                 }
             }
         }
+      },
+      "tablet_repair_result":{
+        "id":"tablet_repair_result",
+        "description":"Tablet repair result",
+        "properties":{
+            "tablet_task_id":{
+                "type":"string"
+            }
+        }
       }
    }
 }

api/api-doc/swagger20_header.json

@@ -11,8 +11,8 @@
       "url": "http://scylladb.com"
     },
     "license": {
-      "name": "AGPL",
-      "url": "https://github.com/scylladb/scylla/blob/master/LICENSE.AGPL"
+      "name": "ScyllaDB-Source-Available-1.0",
+      "url": "https://github.com/scylladb/scylla/blob/master/LICENSE-ScyllaDB-Source-Available.md"
     }
   },
   "host": "{{Host}}",

api/api-doc/system.json

@@ -194,6 +194,21 @@
                "parameters":[]
             }
          ]
+      },
+      {
+         "path":"/system/highest_supported_sstable_version",
+         "operations":[
+            {
+               "method":"GET",
+               "summary":"Get highest supported sstable version",
+               "type":"string",
+               "nickname":"get_highest_supported_sstable_version",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[]
+            }
+         ]
       }
    ]
 }

api/api-doc/task_manager.json

@@ -115,7 +115,7 @@
                "parameters":[
                   {
                      "name":"task_id",
-                     "description":"The uuid of a task to abort",
+                     "description":"The uuid of a task to abort; if the task is not abortable, 403 status code is returned",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -144,6 +144,14 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"path"
+                  },
+                  {
+                     "name":"timeout",
+                     "description":"Timeout for waiting; if times out, 408 status code is returned",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"long",
+                     "paramType":"query"
                   }
                ]
             }
@@ -190,18 +198,102 @@
                "parameters":[
                   {
                      "name":"ttl",
-                     "description":"The number of seconds for which the tasks will be kept in memory after it finishes",
+                     "description":"The number of seconds for which the task started internally will be kept in memory after it finishes",
                      "required":true,
                      "allowMultiple":false,
                      "type":"long",
                      "paramType":"query"
                   }
                ]
+            },
+            {
+               "method":"GET",
+               "summary":"Get current ttl value",
+               "type":"long",
+               "nickname":"get_ttl",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+               ]
+            }
+         ]
+      },
+      {
+         "path":"/task_manager/user_ttl",
+         "operations":[
+            {
+               "method":"POST",
+               "summary":"Set user task ttl in seconds and get last value",
+               "type":"long",
+               "nickname":"get_and_update_user_ttl",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+                  {
+                     "name":"user_ttl",
+                     "description":"The number of seconds for which the task started by user will be kept in memory after it finishes",
+                     "required":true,
+                     "allowMultiple":false,
+                     "type":"long",
+                     "paramType":"query"
+                  }
+               ]
+            },
+            {
+               "method":"GET",
+               "summary":"Get current user task ttl value",
+               "type":"long",
+               "nickname":"get_user_ttl",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+               ]
+            }
+         ]
+      },
+      {
+         "path":"/task_manager/drain/{module}",
+         "operations":[
+            {
+               "method":"POST",
+               "summary":"Drain finished local tasks",
+               "type":"void",
+               "nickname":"drain_tasks",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+                  {
+                     "name":"module",
+                     "description":"The module to drain",
+                     "required":true,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"path"
+                  }
+               ]
             }
          ]
       }
    ],
    "models":{
+      "task_identity":{
+         "id": "task_identity",
+         "description":"Id and node of a task",
+         "properties":{
+            "task_id":{
+               "type":"string",
+               "description":"The uuid of a task"
+            },
+            "node":{
+               "type":"string",
+               "description":"Address of a server on which a task is created"
+            }
+         }
+      },
       "task_stats" :{
          "id": "task_stats",
          "description":"A task statistics object",
@@ -216,7 +308,8 @@
                   "created",
                   "running",
                   "done",
-                  "failed"
+                  "failed",
+                  "suspended"
                ],
                "description":"The state of a task"
             },
@@ -224,6 +317,14 @@
                "type":"string",
                "description":"The description of the task"
             },
+            "kind":{
+               "type":"string",
+               "enum":[
+                  "node",
+                  "cluster"
+               ],
+               "description":"The kind of a task"
+            },
             "scope":{
                "type":"string",
                "description":"The scope of the task"
@@ -243,6 +344,18 @@
             "sequence_number":{
                "type":"long",
                "description":"The running sequence number of the task"
+            },
+            "shard":{
+               "type":"long",
+               "description":"The shard the task is running on"
+            },
+            "start_time":{
+               "type":"datetime",
+               "description":"The start time of the task; unspecified (equal to epoch) when state == created"
+            },
+            "end_time":{
+               "type":"datetime",
+               "description":"The end time of the task; unspecified (equal to epoch) when the task is not completed"
             }
          }
       },
@@ -258,6 +371,14 @@
                "type":"string",
                "description":"The description of the task"
             },
+            "kind":{
+               "type":"string",
+               "enum":[
+                  "node",
+                  "cluster"
+               ],
+               "description":"The kind of a task"
+            },
             "scope":{
                "type":"string",
                "description":"The scope of the task"
@@ -268,7 +389,8 @@
                   "created",
                   "running",
                   "done",
-                  "failed"
+                  "failed",
+                  "suspended"
                ],
                "description":"The state of the task"
             },
@@ -327,9 +449,9 @@
             "children_ids":{
                "type":"array",
                "items":{
-                  "type":"string"
+                  "type":"task_identity"
                },
-               "description":"Task IDs of children of this task"
+               "description":"Task identities of children of this task"
             }
          }
       }

api/api-doc/task_manager_test.json

@@ -93,6 +93,14 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
+                  },
+                  {
+                     "name":"user_task",
+                     "description":"A flag indicating whether a task was started by user (false by default)",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"boolean",
+                     "paramType":"query"
                   }
                ]
             },

api/api.cc

@@ -3,13 +3,14 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "api.hh"
 #include <seastar/http/file_handler.hh>
 #include <seastar/http/transformers.hh>
 #include <seastar/http/api_docs.hh>
+#include "cql_server_test.hh"
 #include "storage_service.hh"
 #include "token_metadata.hh"
 #include "commitlog.hh"
@@ -34,6 +35,8 @@
 #include "task_manager_test.hh"
 #include "tasks.hh"
 #include "raft.hh"
+#include "gms/gossip_address_map.hh"
+#include "service_levels.hh"
 
 logging::logger apilog("api");
 
@@ -73,10 +76,12 @@ future<> set_server_init(http_context& ctx) {
         set_error_injection(ctx, r);
         rb->register_function(r, "storage_proxy",
                 "The storage proxy API");
+        rb->register_function(r, "storage_service",
+                "The storage service API");
     });
 }
 
-future<> set_server_config(http_context& ctx, const db::config& cfg) {
+future<> set_server_config(http_context& ctx, db::config& cfg) {
     auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
     return ctx.http_server.set_routes([&ctx, &cfg, rb02](routes& r) {
         set_config(rb02, ctx, r, cfg, false);
@@ -115,7 +120,7 @@ future<> unset_thrift_controller(http_context& ctx) {
 }
 
 future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, service::raft_group0_client& group0_client) {
-    return register_api(ctx, "storage_service", "The storage service API", [&ss, &group0_client] (http_context& ctx, routes& r) {
+    return ctx.http_server.set_routes([&ctx, &ss, &group0_client] (routes& r) {
             set_storage_service(ctx, r, ss, group0_client);
         });
 }
@@ -132,6 +137,14 @@ future<> unset_load_meter(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_load_meter(ctx, r); });
 }
 
+future<> set_format_selector(http_context& ctx, db::sstables_format_selector& sel) {
+    return ctx.http_server.set_routes([&ctx, &sel] (routes& r) { set_format_selector(ctx, r, sel); });
+}
+
+future<> unset_format_selector(http_context& ctx) {
+    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_format_selector(ctx, r); });
+}
+
 future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader) {
     return ctx.http_server.set_routes([&ctx, &sst_loader] (routes& r) { set_sstables_loader(ctx, r, sst_loader); });
 }
@@ -140,16 +153,16 @@ future<> unset_server_sstables_loader(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_sstables_loader(ctx, r); });
 }
 
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb) {
-    return ctx.http_server.set_routes([&ctx, &vb] (routes& r) { set_view_builder(ctx, r, vb); });
+future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb, sharded<gms::gossiper>& g) {
+    return ctx.http_server.set_routes([&ctx, &vb, &g] (routes& r) { set_view_builder(ctx, r, vb, g); });
 }
 
 future<> unset_server_view_builder(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_view_builder(ctx, r); });
 }
 
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair) {
-    return ctx.http_server.set_routes([&ctx, &repair] (routes& r) { set_repair(ctx, r, repair); });
+future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair, sharded<gms::gossip_address_map>& am) {
+    return ctx.http_server.set_routes([&ctx, &repair, &am] (routes& r) { set_repair(ctx, r, repair, am); });
 }
 
 future<> unset_server_repair(http_context& ctx) {
@@ -175,8 +188,8 @@ future<> unset_server_snapshot(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_snapshot(ctx, r); });
 }
 
-future<> set_server_token_metadata(http_context& ctx, sharded<locator::shared_token_metadata>& tm) {
-    return ctx.http_server.set_routes([&ctx, &tm] (routes& r) { set_token_metadata(ctx, r, tm); });
+future<> set_server_token_metadata(http_context& ctx, sharded<locator::shared_token_metadata>& tm, sharded<gms::gossiper>& g) {
+    return ctx.http_server.set_routes([&ctx, &tm, &g] (routes& r) { set_token_metadata(ctx, r, tm, g); });
 }
 
 future<> unset_server_token_metadata(http_context& ctx) {
@@ -256,10 +269,14 @@ future<> set_server_cache(http_context& ctx) {
             "The cache service API", set_cache_service);
 }
 
-future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& proxy) {
+future<> unset_server_cache(http_context& ctx) {
+    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_cache_service(ctx, r); });
+}
+
+future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& proxy, sharded<gms::gossiper>& g) {
     return register_api(ctx, "hinted_handoff",
-                "The hinted handoff API", [&proxy] (http_context& ctx, routes& r) {
-                    set_hinted_handoff(ctx, r, proxy);
+                "The hinted handoff API", [&proxy, &g] (http_context& ctx, routes& r) {
+                    set_hinted_handoff(ctx, r, proxy, g);
                 });
 }
 
@@ -267,16 +284,16 @@ future<> unset_hinted_handoff(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_hinted_handoff(ctx, r); });
 }
 
-future<> set_server_compaction_manager(http_context& ctx) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx](routes& r) {
-        rb->register_function(r, "compaction_manager",
-                "The Compaction manager API");
-        set_compaction_manager(ctx, r);
+future<> set_server_compaction_manager(http_context& ctx, sharded<compaction_manager>& cm) {
+    return register_api(ctx, "compaction_manager", "The Compaction manager API", [&cm] (http_context& ctx, routes& r) {
+        set_compaction_manager(ctx, r, cm);
     });
 }
 
+future<> unset_server_compaction_manager(http_context& ctx) {
+    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_compaction_manager(ctx, r); });
+}
+
 future<> set_server_done(http_context& ctx) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 
@@ -284,22 +301,29 @@ future<> set_server_done(http_context& ctx) {
         rb->register_function(r, "lsa", "Log-structured allocator API");
         set_lsa(ctx, r);
 
-        rb->register_function(r, "commitlog",
-                "The commit log API");
-        set_commitlog(ctx,r);
         rb->register_function(r, "collectd",
                 "The collectd API");
         set_collectd(ctx, r);
     });
 }
 
-future<> set_server_task_manager(http_context& ctx, sharded<tasks::task_manager>& tm, lw_shared_ptr<db::config> cfg) {
+future<> set_server_commitlog(http_context& ctx, sharded<replica::database>& db) {
+    return register_api(ctx, "commitlog", "The commit log API", [&db] (http_context& ctx, routes& r) {
+        set_commitlog(ctx, r, db);
+    });
+}
+
+future<> unset_server_commitlog(http_context& ctx) {
+    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_commitlog(ctx, r); });
+}
+
+future<> set_server_task_manager(http_context& ctx, sharded<tasks::task_manager>& tm, lw_shared_ptr<db::config> cfg, sharded<gms::gossiper>& gossiper) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 
-    return ctx.http_server.set_routes([rb, &ctx, &tm, &cfg = *cfg](routes& r) {
+    return ctx.http_server.set_routes([rb, &ctx, &tm, &cfg = *cfg, &gossiper](routes& r) {
         rb->register_function(r, "task_manager",
                 "The task manager API");
-        set_task_manager(ctx, r, tm, cfg);
+        set_task_manager(ctx, r, tm, cfg, gossiper);
     });
 }
 
@@ -323,8 +347,24 @@ future<> unset_server_task_manager_test(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_task_manager_test(ctx, r); });
 }
 
+future<> set_server_cql_server_test(http_context& ctx, cql_transport::controller& ctl) {
+    return register_api(ctx, "cql_server_test", "The CQL server test API", [&ctl] (http_context& ctx, routes& r) {
+        set_cql_server_test(ctx, r, ctl);
+    });
+}
+
+future<> unset_server_cql_server_test(http_context& ctx) {
+    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_cql_server_test(ctx, r); });
+}
+
 #endif
 
+future<> set_server_service_levels(http_context &ctx, cql_transport::controller& ctl, sharded<cql3::query_processor>& qp) {
+    return register_api(ctx, "service_levels", "The service levels API", [&ctl, &qp] (http_context& ctx, routes& r) {
+        set_service_levels(ctx, r, ctl, qp);
+    });
+}
+
 future<> set_server_tasks_compaction_module(http_context& ctx, sharded<service::storage_service>& ss, sharded<db::snapshot_ctl>& snap_ctl) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 

api/api.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -219,11 +219,10 @@ template <class T, class Base = T>
 class req_param {
 public:
     sstring name;
-    sstring param;
     T value;
 
     req_param(const request& req, sstring name, T default_val) : name(name) {
-        param = req.get_query_param(name);
+        sstring param = req.get_query_param(name);
         if (param.empty()) {
             value = default_val;
             return;
@@ -246,7 +245,7 @@ public:
                 value = T{boost::lexical_cast<Base>(param)};
             }
         } catch (boost::bad_lexical_cast&) {
-            throw httpd::bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
+            throw httpd::bad_param_exception(fmt::format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
         }
     }
 

api/api_init.hh

@@ -3,13 +3,14 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 #pragma once
 
 #include <seastar/http/httpd.hh>
 #include <seastar/core/future.hh>
 
+#include "gms/gossip_address_map.hh"
 #include "replica/database_fwd.hh"
 #include "tasks/task_manager.hh"
 #include "seastarx.hh"
@@ -17,6 +18,8 @@
 using request = http::request;
 using reply = http::reply;
 
+class compaction_manager;
+
 namespace service {
 
 class load_meter;
@@ -49,6 +52,7 @@ namespace cql_transport { class controller; }
 namespace db {
 class snapshot_ctl;
 class config;
+class sstables_format_selector;
 namespace view {
 class view_builder;
 }
@@ -69,6 +73,10 @@ namespace tasks {
 class task_manager;
 }
 
+namespace cql3 {
+class query_processor;
+}
+
 namespace api {
 
 struct http_context {
@@ -84,7 +92,7 @@ struct http_context {
 };
 
 future<> set_server_init(http_context& ctx);
-future<> set_server_config(http_context& ctx, const db::config& cfg);
+future<> set_server_config(http_context& ctx, db::config& cfg);
 future<> unset_server_config(http_context& ctx);
 future<> set_server_snitch(http_context& ctx, sharded<locator::snitch_ptr>& snitch);
 future<> unset_server_snitch(http_context& ctx);
@@ -92,9 +100,9 @@ future<> set_server_storage_service(http_context& ctx, sharded<service::storage_
 future<> unset_server_storage_service(http_context& ctx);
 future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader);
 future<> unset_server_sstables_loader(http_context& ctx);
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb);
+future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb, sharded<gms::gossiper>& g);
 future<> unset_server_view_builder(http_context& ctx);
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair);
+future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair, sharded<gms::gossip_address_map>& am);
 future<> unset_server_repair(http_context& ctx);
 future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
 future<> unset_transport_controller(http_context& ctx);
@@ -104,7 +112,7 @@ future<> set_server_authorization_cache(http_context& ctx, sharded<auth::service
 future<> unset_server_authorization_cache(http_context& ctx);
 future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
 future<> unset_server_snapshot(http_context& ctx);
-future<> set_server_token_metadata(http_context& ctx, sharded<locator::shared_token_metadata>& tm);
+future<> set_server_token_metadata(http_context& ctx, sharded<locator::shared_token_metadata>& tm, sharded<gms::gossiper>& g);
 future<> unset_server_token_metadata(http_context& ctx);
 future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g);
 future<> unset_server_gossip(http_context& ctx);
@@ -116,12 +124,14 @@ future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_pr
 future<> unset_server_storage_proxy(http_context& ctx);
 future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm);
 future<> unset_server_stream_manager(http_context& ctx);
-future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& p);
+future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& p, sharded<gms::gossiper>& g);
 future<> unset_hinted_handoff(http_context& ctx);
 future<> set_server_cache(http_context& ctx);
-future<> set_server_compaction_manager(http_context& ctx);
+future<> unset_server_cache(http_context& ctx);
+future<> set_server_compaction_manager(http_context& ctx, sharded<compaction_manager>& cm);
+future<> unset_server_compaction_manager(http_context& ctx);
 future<> set_server_done(http_context& ctx);
-future<> set_server_task_manager(http_context& ctx, sharded<tasks::task_manager>& tm, lw_shared_ptr<db::config> cfg);
+future<> set_server_task_manager(http_context& ctx, sharded<tasks::task_manager>& tm, lw_shared_ptr<db::config> cfg, sharded<gms::gossiper>& gossiper);
 future<> unset_server_task_manager(http_context& ctx);
 future<> set_server_task_manager_test(http_context& ctx, sharded<tasks::task_manager>& tm);
 future<> unset_server_task_manager_test(http_context& ctx);
@@ -131,5 +141,12 @@ future<> set_server_raft(http_context&, sharded<service::raft_group_registry>&);
 future<> unset_server_raft(http_context&);
 future<> set_load_meter(http_context& ctx, service::load_meter& lm);
 future<> unset_load_meter(http_context& ctx);
+future<> set_format_selector(http_context& ctx, db::sstables_format_selector& sel);
+future<> unset_format_selector(http_context& ctx);
+future<> set_server_cql_server_test(http_context& ctx, cql_transport::controller& ctl);
+future<> unset_server_cql_server_test(http_context& ctx);
+future<> set_server_service_levels(http_context& ctx, cql_transport::controller& ctl, sharded<cql3::query_processor>& qp);
+future<> set_server_commitlog(http_context& ctx, sharded<replica::database>&);
+future<> unset_server_commitlog(http_context& ctx);
 
 }

api/authorization_cache.cc

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

api/authorization_cache.hh

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

api/cache_service.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "cache_service.hh"
@@ -320,5 +320,50 @@ void set_cache_service(http_context& ctx, routes& r) {
     });
 }
 
+void unset_cache_service(http_context& ctx, routes& r) {
+    cs::get_row_cache_save_period_in_seconds.unset(r);
+    cs::set_row_cache_save_period_in_seconds.unset(r);
+    cs::get_key_cache_save_period_in_seconds.unset(r);
+    cs::set_key_cache_save_period_in_seconds.unset(r);
+    cs::get_counter_cache_save_period_in_seconds.unset(r);
+    cs::set_counter_cache_save_period_in_seconds.unset(r);
+    cs::get_row_cache_keys_to_save.unset(r);
+    cs::set_row_cache_keys_to_save.unset(r);
+    cs::get_key_cache_keys_to_save.unset(r);
+    cs::set_key_cache_keys_to_save.unset(r);
+    cs::get_counter_cache_keys_to_save.unset(r);
+    cs::set_counter_cache_keys_to_save.unset(r);
+    cs::invalidate_key_cache.unset(r);
+    cs::invalidate_counter_cache.unset(r);
+    cs::set_row_cache_capacity_in_mb.unset(r);
+    cs::set_key_cache_capacity_in_mb.unset(r);
+    cs::set_counter_cache_capacity_in_mb.unset(r);
+    cs::save_caches.unset(r);
+    cs::get_key_capacity.unset(r);
+    cs::get_key_hits.unset(r);
+    cs::get_key_requests.unset(r);
+    cs::get_key_hit_rate.unset(r);
+    cs::get_key_hits_moving_avrage.unset(r);
+    cs::get_key_requests_moving_avrage.unset(r);
+    cs::get_key_size.unset(r);
+    cs::get_key_entries.unset(r);
+    cs::get_row_capacity.unset(r);
+    cs::get_row_hits.unset(r);
+    cs::get_row_requests.unset(r);
+    cs::get_row_hit_rate.unset(r);
+    cs::get_row_hits_moving_avrage.unset(r);
+    cs::get_row_requests_moving_avrage.unset(r);
+    cs::get_row_size.unset(r);
+    cs::get_row_entries.unset(r);
+    cs::get_counter_capacity.unset(r);
+    cs::get_counter_hits.unset(r);
+    cs::get_counter_requests.unset(r);
+    cs::get_counter_hit_rate.unset(r);
+    cs::get_counter_hits_moving_avrage.unset(r);
+    cs::get_counter_requests_moving_avrage.unset(r);
+    cs::get_counter_size.unset(r);
+    cs::get_counter_entries.unset(r);
+}
+
 }
 

api/cache_service.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -16,5 +16,6 @@ namespace api {
 
 struct http_context;
 void set_cache_service(http_context& ctx, seastar::httpd::routes& r);
+void unset_cache_service(http_context& ctx, seastar::httpd::routes& r);
 
 }

api/collectd.cc

@@ -3,14 +3,14 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "collectd.hh"
 #include "api/api-doc/collectd.json.hh"
 #include <seastar/core/scollectd.hh>
 #include <seastar/core/scollectd_api.hh>
-#include <boost/range/irange.hpp>
+#include <ranges>
 #include <regex>
 #include "api/api_init.hh"
 
@@ -61,7 +61,7 @@ void set_collectd(http_context& ctx, routes& r) {
 
         return do_with(std::vector<cd::collectd_value>(), [id] (auto& vec) {
             vec.resize(smp::count);
-            return parallel_for_each(boost::irange(0u, smp::count), [&vec, id] (auto cpu) {
+            return parallel_for_each(std::views::iota(0u, smp::count), [&vec, id] (auto cpu) {
                 return smp::submit_to(cpu, [id = *id] {
                     return scollectd::get_collectd_value(id);
                 }).then([&vec, cpu] (auto res) {

api/collectd.hh

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

api/column_family.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <fmt/ranges.h>
@@ -15,6 +15,7 @@
 #include <seastar/http/exception.hh>
 #include "sstables/sstables.hh"
 #include "sstables/metadata_collector.hh"
+#include "utils/assert.hh"
 #include "utils/estimated_histogram.hh"
 #include <algorithm>
 #include "db/system_keyspace.hh"
@@ -47,25 +48,9 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
     return std::make_tuple(name.substr(0, pos), name.substr(end));
 }
 
-table_id get_uuid(const sstring& ks, const sstring& cf, const replica::database& db) {
-    try {
-        return db.find_uuid(ks, cf);
-    } catch (replica::no_such_column_family& e) {
-        throw bad_param_exception(e.what());
-    }
-}
-
-table_id get_uuid(const sstring& name, const replica::database& db) {
+table_info parse_table_info(const sstring& name, const replica::database& db) {
     auto [ks, cf] = parse_fully_qualified_cf_name(name);
-    return get_uuid(ks, cf, db);
-}
-
-future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(replica::column_family&)> f) {
-    auto uuid = get_uuid(name, ctx.db.local());
-
-    return ctx.db.invoke_on_all([f, uuid](replica::database& db) {
-        f(db.find_column_family(uuid));
-    });
+    return table_info{ .name = cf, .id = validate_table(db, ks, cf) };
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
@@ -82,15 +67,11 @@ future<json::json_return_type>  get_cf_stats(http_context& ctx,
     }, std::plus<int64_t>());
 }
 
-static future<json::json_return_type> set_tables(http_context& ctx, const sstring& keyspace, std::vector<sstring> tables, std::function<future<>(replica::table&)> set) {
-    if (tables.empty()) {
-        tables = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
-    }
-
-    return do_with(keyspace, std::move(tables), [&ctx, set] (const sstring& keyspace, const std::vector<sstring>& tables) {
-        return ctx.db.invoke_on_all([&keyspace, &tables, set] (replica::database& db) {
-            return parallel_for_each(tables, [&db, &keyspace, set] (const sstring& table) {
-                replica::table& t = db.find_column_family(keyspace, table);
+static future<json::json_return_type> for_tables_on_all_shards(http_context& ctx, std::vector<table_info> tables, std::function<future<>(replica::table&)> set) {
+    return do_with(std::move(tables), [&ctx, set] (const std::vector<table_info>& tables) {
+        return ctx.db.invoke_on_all([&tables, set] (replica::database& db) {
+            return parallel_for_each(tables, [&db, set] (const table_info& table) {
+                replica::table& t = db.find_column_family(table.id);
                 return set(t);
             });
         });
@@ -103,7 +84,7 @@ class autocompaction_toggle_guard {
     replica::database& _db;
 public:
     autocompaction_toggle_guard(replica::database& db) : _db(db) {
-        assert(this_shard_id() == 0);
+        SCYLLA_ASSERT(this_shard_id() == 0);
         if (!_db._enable_autocompaction_toggle) {
             throw std::runtime_error("Autocompaction toggle is busy");
         }
@@ -112,17 +93,17 @@ public:
     autocompaction_toggle_guard(const autocompaction_toggle_guard&) = delete;
     autocompaction_toggle_guard(autocompaction_toggle_guard&&) = default;
     ~autocompaction_toggle_guard() {
-        assert(this_shard_id() == 0);
+        SCYLLA_ASSERT(this_shard_id() == 0);
         _db._enable_autocompaction_toggle = true;
     }
 };
 
-static future<json::json_return_type> set_tables_autocompaction(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
-    apilog.info("set_tables_autocompaction: enabled={} keyspace={} tables={}", enabled, keyspace, tables);
+static future<json::json_return_type> set_tables_autocompaction(http_context& ctx, std::vector<table_info> tables, bool enabled) {
+    apilog.info("set_tables_autocompaction: enabled={} tables={}", enabled, tables);
 
-    return ctx.db.invoke_on(0, [&ctx, keyspace, tables = std::move(tables), enabled] (replica::database& db) {
+    return ctx.db.invoke_on(0, [&ctx, tables = std::move(tables), enabled] (replica::database& db) {
         auto g = autocompaction_toggle_guard(db);
-        return set_tables(ctx, keyspace, tables, [enabled] (replica::table& cf) {
+        return for_tables_on_all_shards(ctx, tables, [enabled] (replica::table& cf) {
             if (enabled) {
                 cf.enable_auto_compaction();
             } else {
@@ -133,9 +114,9 @@ static future<json::json_return_type> set_tables_autocompaction(http_context& ct
     });
 }
 
-static future<json::json_return_type> set_tables_tombstone_gc(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
-    apilog.info("set_tables_tombstone_gc: enabled={} keyspace={} tables={}", enabled, keyspace, tables);
-    return set_tables(ctx, keyspace, std::move(tables), [enabled] (replica::table& t) {
+static future<json::json_return_type> set_tables_tombstone_gc(http_context& ctx, std::vector<table_info> tables, bool enabled) {
+    apilog.info("set_tables_tombstone_gc: enabled={} tables={}", enabled, tables);
+    return for_tables_on_all_shards(ctx, std::move(tables), [enabled] (replica::table& t) {
         t.set_tombstone_gc_enabled(enabled);
         return make_ready_future<>();
     });
@@ -150,7 +131,7 @@ static future<json::json_return_type>  get_cf_stats_count(http_context& ctx, con
 
 static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const sstring& name,
         utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
+    auto uuid = parse_table_info(name, ctx.db.local()).id;
     return ctx.db.map_reduce0([uuid, f](replica::database& db) {
         // Histograms information is sample of the actual load
         // so to get an estimation of sum, we multiply the mean
@@ -173,7 +154,7 @@ static future<json::json_return_type>  get_cf_stats_count(http_context& ctx,
 
 static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
         utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
+    auto uuid = parse_table_info(name, ctx.db.local()).id;
     return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
         return (p.find_column_family(uuid).get_stats().*f).hist;},
             utils::ihistogram(),
@@ -185,7 +166,7 @@ static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const
 
 static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
         utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
+    auto uuid = parse_table_info(name, ctx.db.local()).id;
     return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
         return (p.find_column_family(uuid).get_stats().*f).hist;},
             utils::ihistogram(),
@@ -205,14 +186,14 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
     };
     return ctx.db.map(fun).then([](const std::vector<utils::ihistogram> &res) {
         std::vector<httpd::utils_json::histogram> r;
-        boost::copy(res | boost::adaptors::transformed(to_json), std::back_inserter(r));
-        return make_ready_future<json::json_return_type>(r);
+        std::ranges::copy(res | std::views::transform(to_json), std::back_inserter(r));
+        return make_ready_future<json::json_return_type>(std::move(r));
     });
 }
 
 static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
         utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
+    auto uuid = parse_table_info(name, ctx.db.local()).id;
     return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
         return (p.find_column_family(uuid).get_stats().*f).rate();},
             utils::rate_moving_average_and_histogram(),
@@ -232,7 +213,7 @@ static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ct
     };
     return ctx.db.map(fun).then([](const std::vector<utils::rate_moving_average_and_histogram> &res) {
         std::vector<httpd::utils_json::rate_moving_average_and_histogram> r;
-        boost::copy(res | boost::adaptors::transformed(timer_to_json), std::back_inserter(r));
+        std::ranges::copy(res | std::views::transform(timer_to_json), std::back_inserter(r));
         return make_ready_future<json::json_return_type>(r);
     });
 }
@@ -269,48 +250,29 @@ static integral_ratio_holder mean_partition_size(replica::column_family& cf) {
     return res;
 }
 
-static std::unordered_map<sstring, uint64_t> merge_maps(std::unordered_map<sstring, uint64_t> a,
-        const std::unordered_map<sstring, uint64_t>& b) {
-    a.insert(b.begin(), b.end());
-    return a;
-}
-
-static json::json_return_type sum_map(const std::unordered_map<sstring, uint64_t>& val) {
-    uint64_t res = 0;
-    for (auto i : val) {
-        res += i.second;
+static auto count_bytes_on_disk(const replica::column_family& cf, bool total) {
+    uint64_t bytes_on_disk = 0;
+    auto sstables = (total) ? cf.get_sstables_including_compacted_undeleted() : cf.get_sstables();
+    for (auto t : *sstables) {
+        bytes_on_disk += t->bytes_on_disk();
     }
-    return res;
+    return bytes_on_disk;
 }
 
 static future<json::json_return_type>  sum_sstable(http_context& ctx, const sstring name, bool total) {
-    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([uuid, total](replica::database& db) {
-        std::unordered_map<sstring, uint64_t> m;
-        auto sstables = (total) ? db.find_column_family(uuid).get_sstables_including_compacted_undeleted() :
-                db.find_column_family(uuid).get_sstables();
-        for (auto t : *sstables) {
-            m[t->get_filename()] = t->bytes_on_disk();
-        }
-        return m;
-    }, std::unordered_map<sstring, uint64_t>(), merge_maps).
-            then([](const std::unordered_map<sstring, uint64_t>& val) {
-        return sum_map(val);
+    return map_reduce_cf_raw(ctx, name, uint64_t(0), [total](replica::column_family& cf) {
+        return count_bytes_on_disk(cf, total);
+    }, std::plus<>()).then([] (uint64_t val) {
+        return make_ready_future<json::json_return_type>(val);
     });
 }
 
 
 static future<json::json_return_type> sum_sstable(http_context& ctx, bool total) {
-    return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](replica::column_family& cf) {
-        std::unordered_map<sstring, uint64_t> m;
-        auto sstables = (total) ? cf.get_sstables_including_compacted_undeleted() :
-                cf.get_sstables();
-        for (auto t : *sstables) {
-            m[t->get_filename()] = t->bytes_on_disk();
-        }
-        return m;
-    },merge_maps).then([](const std::unordered_map<sstring, uint64_t>& val) {
-        return sum_map(val);
+    return map_reduce_cf_raw(ctx, uint64_t(0), [total](replica::column_family& cf) {
+        return count_bytes_on_disk(cf, total);
+    }, std::plus<>()).then([] (uint64_t val) {
+        return make_ready_future<json::json_return_type>(val);
     });
 }
 
@@ -722,25 +684,25 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
 
     cf::get_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<http::request> req) {
         return map_reduce_cf(ctx, req->get_path_param("name"), ratio_holder(), [] (replica::column_family& cf) {
-            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
+            return std::ranges::fold_left(*cf.get_sstables() | std::views::transform(filter_false_positive_as_ratio_holder), ratio_holder(), std::plus{});
         }, std::plus<>());
     });
 
     cf::get_all_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<http::request> req) {
         return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
-            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
+            return std::ranges::fold_left(*cf.get_sstables() | std::views::transform(filter_false_positive_as_ratio_holder), ratio_holder(), std::plus{});
         }, std::plus<>());
     });
 
     cf::get_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<http::request> req) {
         return map_reduce_cf(ctx, req->get_path_param("name"), ratio_holder(), [] (replica::column_family& cf) {
-            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
+            return std::ranges::fold_left(*cf.get_sstables() | std::views::transform(filter_recent_false_positive_as_ratio_holder), ratio_holder(), std::plus{});
         }, std::plus<>());
     });
 
     cf::get_all_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<http::request> req) {
         return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
-            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
+            return std::ranges::fold_left(*cf.get_sstables() | std::views::transform(filter_recent_false_positive_as_ratio_holder), ratio_holder(), std::plus{});
         }, std::plus<>());
     });
 
@@ -922,94 +884,92 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
     });
 
     cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
-        auto uuid = get_uuid(req.get_path_param("name"), ctx.db.local());
+        auto uuid = parse_table_info(req.get_path_param("name"), ctx.db.local()).id;
         replica::column_family& cf = ctx.db.local().find_column_family(uuid);
         return !cf.is_auto_compaction_disabled_by_user();
     });
 
     cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<http::request> req) {
         apilog.info("column_family/enable_auto_compaction: name={}", req->get_path_param("name"));
-        auto [ks, cf] = parse_fully_qualified_cf_name(req->get_path_param("name"));
-        validate_table(ctx, ks, cf);
-        return set_tables_autocompaction(ctx, ks, {std::move(cf)}, true);
+        auto ti = parse_table_info(req->get_path_param("name"), ctx.db.local());
+        return set_tables_autocompaction(ctx, {std::move(ti)}, true);
     });
 
     cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<http::request> req) {
         apilog.info("column_family/disable_auto_compaction: name={}", req->get_path_param("name"));
-        auto [ks, cf] = parse_fully_qualified_cf_name(req->get_path_param("name"));
-        validate_table(ctx, ks, cf);
-        return set_tables_autocompaction(ctx, ks, {std::move(cf)}, false);
+        auto ti = parse_table_info(req->get_path_param("name"), ctx.db.local());
+        return set_tables_autocompaction(ctx, {std::move(ti)}, false);
     });
 
     ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<http::request> req) {
         auto keyspace = validate_keyspace(ctx, req);
-        auto tables = parse_tables(keyspace, ctx, req->query_parameters, "cf");
+        auto tables = parse_table_infos(keyspace, ctx, req->query_parameters, "cf");
 
         apilog.info("enable_auto_compaction: keyspace={} tables={}", keyspace, tables);
-        return set_tables_autocompaction(ctx, keyspace, tables, true);
+        return set_tables_autocompaction(ctx, std::move(tables), true);
     });
 
     ss::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<http::request> req) {
         auto keyspace = validate_keyspace(ctx, req);
-        auto tables = parse_tables(keyspace, ctx, req->query_parameters, "cf");
+        auto tables = parse_table_infos(keyspace, ctx, req->query_parameters, "cf");
 
         apilog.info("disable_auto_compaction: keyspace={} tables={}", keyspace, tables);
-        return set_tables_autocompaction(ctx, keyspace, tables, false);
+        return set_tables_autocompaction(ctx, std::move(tables), false);
     });
 
     cf::get_tombstone_gc.set(r, [&ctx] (const_req req) {
-        auto uuid = get_uuid(req.get_path_param("name"), ctx.db.local());
+        auto uuid = parse_table_info(req.get_path_param("name"), ctx.db.local()).id;
         replica::table& t = ctx.db.local().find_column_family(uuid);
         return t.tombstone_gc_enabled();
     });
 
     cf::enable_tombstone_gc.set(r, [&ctx](std::unique_ptr<http::request> req) {
         apilog.info("column_family/enable_tombstone_gc: name={}", req->get_path_param("name"));
-        auto [ks, cf] = parse_fully_qualified_cf_name(req->get_path_param("name"));
-        validate_table(ctx, ks, cf);
-        return set_tables_tombstone_gc(ctx, ks, {std::move(cf)}, true);
+        auto ti = parse_table_info(req->get_path_param("name"), ctx.db.local());
+        return set_tables_tombstone_gc(ctx, {std::move(ti)}, true);
     });
 
     cf::disable_tombstone_gc.set(r, [&ctx](std::unique_ptr<http::request> req) {
         apilog.info("column_family/disable_tombstone_gc: name={}", req->get_path_param("name"));
-        auto [ks, cf] = parse_fully_qualified_cf_name(req->get_path_param("name"));
-        validate_table(ctx, ks, cf);
-        return set_tables_tombstone_gc(ctx, ks, {std::move(cf)}, false);
+        auto ti = parse_table_info(req->get_path_param("name"), ctx.db.local());
+        return set_tables_tombstone_gc(ctx, {std::move(ti)}, false);
     });
 
     ss::enable_tombstone_gc.set(r, [&ctx](std::unique_ptr<http::request> req) {
         auto keyspace = validate_keyspace(ctx, req);
-        auto tables = parse_tables(keyspace, ctx, req->query_parameters, "cf");
+        auto tables = parse_table_infos(keyspace, ctx, req->query_parameters, "cf");
 
         apilog.info("enable_tombstone_gc: keyspace={} tables={}", keyspace, tables);
-        return set_tables_tombstone_gc(ctx, keyspace, tables, true);
+        return set_tables_tombstone_gc(ctx, std::move(tables), true);
     });
 
     ss::disable_tombstone_gc.set(r, [&ctx](std::unique_ptr<http::request> req) {
         auto keyspace = validate_keyspace(ctx, req);
-        auto tables = parse_tables(keyspace, ctx, req->query_parameters, "cf");
+        auto tables = parse_table_infos(keyspace, ctx, req->query_parameters, "cf");
 
         apilog.info("disable_tombstone_gc: keyspace={} tables={}", keyspace, tables);
-        return set_tables_tombstone_gc(ctx, keyspace, tables, false);
+        return set_tables_tombstone_gc(ctx, std::move(tables), false);
     });
 
     cf::get_built_indexes.set(r, [&ctx, &sys_ks](std::unique_ptr<http::request> req) {
         auto ks_cf = parse_fully_qualified_cf_name(req->get_path_param("name"));
         auto&& ks = std::get<0>(ks_cf);
         auto&& cf_name = std::get<1>(ks_cf);
-        return sys_ks.local().load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace_view_build_progress>& vb) mutable {
+        // Use of load_built_views() as filtering table should be in sync with
+        // built_indexes_virtual_reader filtering with BUILT_VIEWS table
+        return sys_ks.local().load_built_views().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_name>& vb) mutable {
             std::set<sstring> vp;
             for (auto b : vb) {
-                if (b.view.first == ks) {
-                    vp.insert(b.view.second);
+                if (b.first == ks) {
+                    vp.insert(b.second);
                 }
             }
             std::vector<sstring> res;
-            auto uuid = get_uuid(ks, cf_name, ctx.db.local());
+            auto uuid = validate_table(ctx.db.local(), ks, cf_name);
             replica::column_family& cf = ctx.db.local().find_column_family(uuid);
             res.reserve(cf.get_index_manager().list_indexes().size());
             for (auto&& i : cf.get_index_manager().list_indexes()) {
-                if (!vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
+                if (vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
                     res.emplace_back(i.metadata().name());
                 }
             }
@@ -1032,7 +992,7 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
     });
 
     cf::get_compression_ratio.set(r, [&ctx](std::unique_ptr<http::request> req) {
-        auto uuid = get_uuid(req->get_path_param("name"), ctx.db.local());
+        auto uuid = parse_table_info(req->get_path_param("name"), ctx.db.local()).id;
 
         return ctx.db.map_reduce(sum_ratio<double>(), [uuid](replica::database& db) {
             replica::column_family& cf = db.find_column_family(uuid);
@@ -1055,17 +1015,17 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
     });
 
     cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<http::request> req) {
+        auto ti = parse_table_info(req->get_path_param("name"), ctx.db.local());
         sstring strategy = req->get_query_param("class_name");
         apilog.info("column_family/set_compaction_strategy_class: name={} strategy={}", req->get_path_param("name"), strategy);
-        return foreach_column_family(ctx, req->get_path_param("name"), [strategy](replica::column_family& cf) {
+        return for_tables_on_all_shards(ctx, {std::move(ti)}, [strategy] (replica::table& cf) {
             cf.set_compaction_strategy(sstables::compaction_strategy::type(strategy));
-        }).then([] {
-                return make_ready_future<json::json_return_type>(json_void());
+            return make_ready_future<>();
         });
     });
 
     cf::get_compaction_strategy_class.set(r, [&ctx](const_req req) {
-        return ctx.db.local().find_column_family(get_uuid(req.get_path_param("name"), ctx.db.local())).get_compaction_strategy().name();
+        return ctx.db.local().find_column_family(parse_table_info(req.get_path_param("name"), ctx.db.local()).id).get_compaction_strategy().name();
     });
 
     cf::set_compression_parameters.set(r, [](std::unique_ptr<http::request> req) {
@@ -1090,11 +1050,11 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
 
     cf::get_sstables_for_key.set(r, [&ctx](std::unique_ptr<http::request> req) {
         auto key = req->get_query_param("key");
-        auto uuid = get_uuid(req->get_path_param("name"), ctx.db.local());
+        auto uuid = parse_table_info(req->get_path_param("name"), ctx.db.local()).id;
 
         return ctx.db.map_reduce0([key, uuid] (replica::database& db) -> future<std::unordered_set<sstring>> {
             auto sstables = co_await db.find_column_family(uuid).get_sstables_by_partition_key(key);
-            co_return boost::copy_range<std::unordered_set<sstring>>(sstables | boost::adaptors::transformed([] (auto s) { return s->get_filename(); }));
+            co_return sstables | std::views::transform([] (auto s) { return s->get_filename(); }) | std::ranges::to<std::unordered_set>();
         }, std::unordered_set<sstring>(),
         [](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
             a.merge(b);
@@ -1114,7 +1074,7 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
         api::req_param<unsigned> list_size(*req, "list_size", 10);
 
         apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
-            name, duration.param, list_size.param, capacity.param);
+            name, duration.value, list_size.value, capacity.value);
 
         return seastar::do_with(db::toppartitions_query(ctx.db, {{ks, cf}}, {}, duration.value, list_size, capacity), [&ctx] (db::toppartitions_query& q) {
             return run_toppartitions_query(q, ctx, true);
@@ -1125,6 +1085,7 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
         auto params = req_params({
             std::pair("name", mandatory::yes),
             std::pair("flush_memtables", mandatory::no),
+            std::pair("consider_only_existing_data", mandatory::no),
             std::pair("split_output", mandatory::no),
         });
         params.process(*req);
@@ -1133,7 +1094,8 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
         }
         auto [ks, cf] = parse_fully_qualified_cf_name(*params.get("name"));
         auto flush = params.get_as<bool>("flush_memtables").value_or(true);
-        apilog.info("column_family/force_major_compaction: name={} flush={}", req->get_path_param("name"), flush);
+        auto consider_only_existing_data = params.get_as<bool>("consider_only_existing_data").value_or(false);
+        apilog.info("column_family/force_major_compaction: name={} flush={} consider_only_existing_data={}", req->get_path_param("name"), flush, consider_only_existing_data);
 
         auto keyspace = validate_keyspace(ctx, ks);
         std::vector<table_info> table_infos = {table_info{
@@ -1143,10 +1105,10 @@ void set_column_family(http_context& ctx, routes& r, sharded<db::system_keyspace
 
         auto& compaction_module = ctx.db.local().get_compaction_manager().get_task_manager_module();
         std::optional<flush_mode> fmopt;
-        if (!flush) {
+        if (!flush && !consider_only_existing_data) {
             fmopt = flush_mode::skip;
         }
-        auto task = co_await compaction_module.make_and_start_task<major_keyspace_compaction_task_impl>({}, std::move(keyspace), tasks::task_id::create_null_id(), ctx.db, std::move(table_infos), fmopt);
+        auto task = co_await compaction_module.make_and_start_task<major_keyspace_compaction_task_impl>({}, std::move(keyspace), tasks::task_id::create_null_id(), ctx.db, std::move(table_infos), fmopt, consider_only_existing_data);
         co_await task->done();
         co_return json_void();
     });

api/column_family.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -22,14 +22,12 @@ namespace api {
 void set_column_family(http_context& ctx, httpd::routes& r, sharded<db::system_keyspace>& sys_ks);
 void unset_column_family(http_context& ctx, httpd::routes& r);
 
-table_id get_uuid(const sstring& name, const replica::database& db);
-future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(replica::column_family&)> f);
-
+table_info parse_table_info(const sstring& name, const replica::database& db);
 
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer) {
-    auto uuid = get_uuid(name, ctx.db.local());
+    auto uuid = parse_table_info(name, ctx.db.local()).id;
     using mapper_type = std::function<std::unique_ptr<std::any>(replica::database&)>;
     using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
     return ctx.db.map_reduce0(mapper_type([mapper, uuid](replica::database& db) {

api/commitlog.cc

@@ -3,24 +3,26 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "commitlog.hh"
 #include "db/commitlog/commitlog.hh"
 #include "api/api-doc/commitlog.json.hh"
+#include "api/api-doc/storage_service.json.hh"
 #include "api/api_init.hh"
 #include "replica/database.hh"
 #include <vector>
 
 namespace api {
 using namespace seastar::httpd;
+namespace ss = httpd::storage_service_json;
 
 template<typename T>
-static auto acquire_cl_metric(http_context& ctx, std::function<T (const db::commitlog*)> func) {
+static auto acquire_cl_metric(sharded<replica::database>& db, std::function<T (const db::commitlog*)> func) {
     typedef T ret_type;
 
-    return ctx.db.map_reduce0([func = std::move(func)](replica::database& db) {
+    return db.map_reduce0([func = std::move(func)](replica::database& db) {
         if (db.commitlog() == nullptr) {
             return make_ready_future<ret_type>();
         }
@@ -30,11 +32,11 @@ static auto acquire_cl_metric(http_context& ctx, std::function<T (const db::comm
     });
 }
 
-void set_commitlog(http_context& ctx, routes& r) {
+void set_commitlog(http_context& ctx, routes& r, sharded<replica::database>& db) {
     httpd::commitlog_json::get_active_segment_names.set(r,
-            [&ctx](std::unique_ptr<request> req) {
+            [&db](std::unique_ptr<request> req) {
         auto res = make_shared<std::vector<sstring>>();
-        return ctx.db.map_reduce([res](std::vector<sstring> names) {
+        return db.map_reduce([res](std::vector<sstring> names) {
             res->insert(res->end(), names.begin(), names.end());
         }, [](replica::database& db) {
             if (db.commitlog() == nullptr) {
@@ -52,20 +54,35 @@ void set_commitlog(http_context& ctx, routes& r) {
         return res;
     });
 
-    httpd::commitlog_json::get_completed_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
+    httpd::commitlog_json::get_completed_tasks.set(r, [&db](std::unique_ptr<request> req) {
+        return acquire_cl_metric<uint64_t>(db, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
     });
 
-    httpd::commitlog_json::get_pending_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
+    httpd::commitlog_json::get_pending_tasks.set(r, [&db](std::unique_ptr<request> req) {
+        return acquire_cl_metric<uint64_t>(db, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
     });
 
-    httpd::commitlog_json::get_total_commit_log_size.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
+    httpd::commitlog_json::get_total_commit_log_size.set(r, [&db](std::unique_ptr<request> req) {
+        return acquire_cl_metric<uint64_t>(db, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
     });
-    httpd::commitlog_json::get_max_disk_size.set(r, [&ctx](std::unique_ptr<request> req) {
-        return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::disk_limit, std::placeholders::_1));
+    httpd::commitlog_json::get_max_disk_size.set(r, [&db](std::unique_ptr<request> req) {
+        return acquire_cl_metric<uint64_t>(db, std::bind(&db::commitlog::disk_limit, std::placeholders::_1));
     });
+
+    ss::get_commitlog.set(r, [&db](const_req req) {
+        return db.local().commitlog()->active_config().commit_log_location;
+    });
+
+}
+
+void unset_commitlog(http_context& ctx, routes& r) {
+    httpd::commitlog_json::get_active_segment_names.unset(r);
+    httpd::commitlog_json::get_archiving_segment_names.unset(r);
+    httpd::commitlog_json::get_completed_tasks.unset(r);
+    httpd::commitlog_json::get_pending_tasks.unset(r);
+    httpd::commitlog_json::get_total_commit_log_size.unset(r);
+    httpd::commitlog_json::get_max_disk_size.unset(r);
+    ss::get_commitlog.unset(r);
 }
 
 }

api/commitlog.hh

@@ -3,17 +3,22 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
 
+#include <seastar/core/sharded.hh>
+
 namespace seastar::httpd {
 class routes;
 }
 
+namespace replica { class database; }
+
 namespace api {
 struct http_context;
-void set_commitlog(http_context& ctx, seastar::httpd::routes& r);
+void set_commitlog(http_context& ctx, seastar::httpd::routes& r, seastar::sharded<replica::database>&);
+void unset_commitlog(http_context& ctx, seastar::httpd::routes& r);
 
 }

api/compaction_manager.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <seastar/core/coroutine.hh>
@@ -13,6 +13,7 @@
 #include "compaction/compaction_manager.hh"
 #include "api/api.hh"
 #include "api/api-doc/compaction_manager.json.hh"
+#include "api/api-doc/storage_service.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
 #include "unimplemented.hh"
@@ -23,13 +24,14 @@
 namespace api {
 
 namespace cm = httpd::compaction_manager_json;
+namespace ss = httpd::storage_service_json;
 using namespace json;
 using namespace seastar::httpd;
 
-static future<json::json_return_type> get_cm_stats(http_context& ctx,
+static future<json::json_return_type> get_cm_stats(sharded<compaction_manager>& cm,
         int64_t compaction_manager::stats::*f) {
-    return ctx.db.map_reduce0([f](replica::database& db) {
-        return db.get_compaction_manager().get_stats().*f;
+    return cm.map_reduce0([f](compaction_manager& cm) {
+        return cm.get_stats().*f;
     }, int64_t(0), std::plus<int64_t>()).then([](const int64_t& res) {
         return make_ready_future<json::json_return_type>(res);
     });
@@ -44,11 +46,10 @@ static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_ha
     return std::move(a);
 }
 
-void set_compaction_manager(http_context& ctx, routes& r) {
-    cm::get_compactions.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) {
+void set_compaction_manager(http_context& ctx, routes& r, sharded<compaction_manager>& cm) {
+    cm::get_compactions.set(r, [&cm] (std::unique_ptr<http::request> req) {
+        return cm.map_reduce0([](compaction_manager& cm) {
             std::vector<cm::summary> summaries;
-            const compaction_manager& cm = db.get_compaction_manager();
 
             for (const auto& c : cm.get_compactions()) {
                 cm::summary s;
@@ -100,10 +101,9 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cm::stop_compaction.set(r, [&ctx] (std::unique_ptr<http::request> req) {
+    cm::stop_compaction.set(r, [&cm] (std::unique_ptr<http::request> req) {
         auto type = req->get_query_param("type");
-        return ctx.db.invoke_on_all([type] (replica::database& db) {
-            auto& cm = db.get_compaction_manager();
+        return cm.invoke_on_all([type] (compaction_manager& cm) {
             return cm.stop_compaction(type);
         }).then([] {
             return make_ready_future<json::json_return_type>(json_void());
@@ -112,15 +112,12 @@ void set_compaction_manager(http_context& ctx, routes& r) {
 
     cm::stop_keyspace_compaction.set(r, [&ctx] (std::unique_ptr<http::request> req) -> future<json::json_return_type> {
         auto ks_name = validate_keyspace(ctx, req);
-        auto table_names = parse_tables(ks_name, ctx, req->query_parameters, "tables");
-        if (table_names.empty()) {
-            table_names = map_keys(ctx.db.local().find_keyspace(ks_name).metadata().get()->cf_meta_data());
-        }
+        auto tables = parse_table_infos(ks_name, ctx, req->query_parameters, "tables");
         auto type = req->get_query_param("type");
         co_await ctx.db.invoke_on_all([&] (replica::database& db) {
             auto& cm = db.get_compaction_manager();
-            return parallel_for_each(table_names, [&] (sstring& table_name) {
-                auto& t = db.find_column_family(ks_name, table_name);
+            return parallel_for_each(tables, [&] (const table_info& ti) {
+                auto& t = db.find_column_family(ti.id);
                 return t.parallel_foreach_table_state([&] (compaction::table_state& ts) {
                     return cm.stop_compaction(type, &ts);
                 });
@@ -135,8 +132,8 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         }, std::plus<int64_t>());
     });
 
-    cm::get_completed_tasks.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return get_cm_stats(ctx, &compaction_manager::stats::completed_tasks);
+    cm::get_completed_tasks.set(r, [&cm] (std::unique_ptr<http::request> req) {
+        return get_cm_stats(cm, &compaction_manager::stats::completed_tasks);
     });
 
     cm::get_total_compactions_completed.set(r, [] (std::unique_ptr<http::request> req) {
@@ -153,14 +150,14 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cm::get_compaction_history.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        std::function<future<>(output_stream<char>&&)> f = [&ctx] (output_stream<char>&& out) -> future<> {
+    cm::get_compaction_history.set(r, [&cm] (std::unique_ptr<http::request> req) {
+        std::function<future<>(output_stream<char>&&)> f = [&cm] (output_stream<char>&& out) -> future<> {
             auto s = std::move(out);
             bool first = true;
             std::exception_ptr ex;
             try {
                 co_await s.write("[");
-                co_await ctx.db.local().get_compaction_manager().get_compaction_history([&s, &first](const db::compaction_history_entry& entry) mutable -> future<> {
+                co_await cm.local().get_compaction_history([&s, &first](const db::compaction_history_entry& entry) mutable -> future<> {
                         cm::history h;
                         h.id = fmt::to_string(entry.id);
                         h.ks = std::move(entry.ks);
@@ -168,7 +165,9 @@ void set_compaction_manager(http_context& ctx, routes& r) {
                         h.compacted_at = entry.compacted_at;
                         h.bytes_in = entry.bytes_in;
                         h.bytes_out =  entry.bytes_out;
-                        for (auto it : entry.rows_merged) {
+
+                        std::map<int32_t, int64_t> items(entry.rows_merged.begin(), entry.rows_merged.end());
+                        for (auto it : items) {
                             httpd::compaction_manager_json::row_merged e;
                             e.key = it.first;
                             e.value = it.second;
@@ -201,6 +200,25 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(res);
     });
 
+    ss::get_compaction_throughput_mb_per_sec.set(r, [&cm](std::unique_ptr<http::request> req) {
+        int value = cm.local().throughput_mbs();
+        return make_ready_future<json::json_return_type>(value);
+    });
+}
+
+void unset_compaction_manager(http_context& ctx, routes& r) {
+    cm::get_compactions.unset(r);
+    cm::get_pending_tasks_by_table.unset(r);
+    cm::force_user_defined_compaction.unset(r);
+    cm::stop_compaction.unset(r);
+    cm::stop_keyspace_compaction.unset(r);
+    cm::get_pending_tasks.unset(r);
+    cm::get_completed_tasks.unset(r);
+    cm::get_total_compactions_completed.unset(r);
+    cm::get_bytes_compacted.unset(r);
+    cm::get_compaction_history.unset(r);
+    cm::get_compaction_info.unset(r);
+    ss::get_compaction_throughput_mb_per_sec.unset(r);
 }
 
 }

api/compaction_manager.hh

@@ -3,17 +3,21 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
+#include <seastar/core/sharded.hh>
 
 namespace seastar::httpd {
 class routes;
 }
 
+class compaction_manager;
+
 namespace api {
 struct http_context;
-void set_compaction_manager(http_context& ctx, seastar::httpd::routes& r);
+void set_compaction_manager(http_context& ctx, seastar::httpd::routes& r, seastar::sharded<compaction_manager>& cm);
+void unset_compaction_manager(http_context& ctx, seastar::httpd::routes& r);
 
 }

api/config.cc

@@ -3,22 +3,25 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include "api/api.hh"
 #include "api/config.hh"
 #include "api/api-doc/config.json.hh"
 #include "api/api-doc/storage_proxy.json.hh"
+#include "api/api-doc/storage_service.json.hh"
 #include "replica/database.hh"
 #include "db/config.hh"
 #include <sstream>
+#include <fmt/ranges.h>
 #include <boost/algorithm/string/replace.hpp>
 #include <seastar/http/exception.hh>
 
 namespace api {
 using namespace seastar::httpd;
 namespace sp = httpd::storage_proxy_json;
+namespace ss = httpd::storage_service_json;
 
 template<class T>
 json::json_return_type get_json_return_type(const T& val) {
@@ -81,7 +84,7 @@ future<> get_config_swagger_entry(std::string_view name, const std::string& desc
 
 namespace cs = httpd::config_json;
 
-void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r, const db::config& cfg, bool first) {
+void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r, db::config& cfg, bool first) {
     rb->register_function(r, [&cfg, first] (output_stream<char>& os) {
         return do_with(first, [&os, &cfg] (bool& first) {
             auto f = make_ready_future();
@@ -183,6 +186,25 @@ void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx
         return make_ready_future<json::json_return_type>(seastar::json::json_void());
     });
 
+    ss::get_all_data_file_locations.set(r, [&cfg](const_req req) {
+        return container_to_vec(cfg.data_file_directories());
+    });
+
+    ss::get_saved_caches_location.set(r, [&cfg](const_req req) {
+        return cfg.saved_caches_directory();
+    });
+
+    ss::set_compaction_throughput_mb_per_sec.set(r, [&cfg](std::unique_ptr<http::request> req) mutable {
+        api::req_param<uint32_t> value(*req, "value", 0);
+        cfg.compaction_throughput_mb_per_sec(value.value, utils::config_file::config_source::API);
+        return make_ready_future<json::json_return_type>(json::json_void());
+    });
+
+    ss::set_stream_throughput_mb_per_sec.set(r, [&cfg](std::unique_ptr<http::request> req) mutable {
+        api::req_param<uint32_t> value(*req, "value", 0);
+        cfg.stream_io_throughput_mb_per_sec(value.value, utils::config_file::config_source::API);
+        return make_ready_future<json::json_return_type>(json::json_void());
+    });
 }
 
 void unset_config(http_context& ctx, routes& r) {
@@ -201,6 +223,10 @@ void unset_config(http_context& ctx, routes& r) {
     sp::set_range_rpc_timeout.unset(r);
     sp::get_truncate_rpc_timeout.unset(r);
     sp::set_truncate_rpc_timeout.unset(r);
+    ss::get_all_data_file_locations.unset(r);
+    ss::get_saved_caches_location.unset(r);
+    ss::set_compaction_throughput_mb_per_sec.unset(r);
+    ss::set_stream_throughput_mb_per_sec.unset(r);
 }
 
 }

api/config.hh

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #pragma once
@@ -13,6 +13,6 @@
 
 namespace api {
 
-void set_config(std::shared_ptr<httpd::api_registry_builder20> rb, http_context& ctx, httpd::routes& r, const db::config& cfg, bool first = false);
+void set_config(std::shared_ptr<httpd::api_registry_builder20> rb, http_context& ctx, httpd::routes& r, db::config& cfg, bool first = false);
 void unset_config(http_context& ctx, httpd::routes& r);
 }

api/cql_server_test.cc

@@ -0,0 +1,75 @@
+/*
+ * Copyright (C) 2024-present ScyllaDB
+ */
+
+/*
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ */
+
+#include "build_mode.hh"
+
+#ifndef SCYLLA_BUILD_MODE_RELEASE
+
+#include <seastar/core/coroutine.hh>
+
+#include "api/api-doc/cql_server_test.json.hh"
+#include "cql_server_test.hh"
+#include "transport/controller.hh"
+#include "transport/server.hh"
+#include "service/qos/qos_common.hh"
+
+namespace api {
+
+namespace cst = httpd::cql_server_test_json;
+using namespace json;
+using namespace seastar::httpd;
+
+struct connection_sl_params : public json::json_base {
+    json::json_element<sstring> _role_name;
+    json::json_element<sstring> _workload_type;
+    json::json_element<sstring> _timeout;
+    json::json_element<sstring> _scheduling_group;
+
+    connection_sl_params(const sstring& role_name, const sstring& workload_type, const sstring& timeout, const sstring& scheduling_group) {
+        _role_name = role_name;
+        _workload_type = workload_type;
+        _timeout = timeout;
+        _scheduling_group = scheduling_group;
+        register_params();
+    }
+
+    connection_sl_params(const connection_sl_params& params)
+        : connection_sl_params(params._role_name(), params._workload_type(), params._timeout(), params._scheduling_group()) {}
+
+    void register_params() {
+        add(&_role_name, "role_name");
+        add(&_workload_type, "workload_type");
+        add(&_timeout, "timeout");
+        add(&_scheduling_group, "scheduling_group");
+    }    
+};
+
+void set_cql_server_test(http_context& ctx, seastar::httpd::routes& r, cql_transport::controller& ctl) {
+    cst::connections_params.set(r, [&ctl] (std::unique_ptr<http::request> req) -> future<json::json_return_type> {
+        auto sl_params = co_await ctl.get_connections_service_level_params();
+
+        std::vector<connection_sl_params> result;
+        std::ranges::transform(std::move(sl_params), std::back_inserter(result), [] (const cql_transport::connection_service_level_params& params) {
+            auto nanos = std::chrono::duration_cast<std::chrono::nanoseconds>(params.timeout_config.read_timeout).count();
+            return connection_sl_params(
+                    std::move(params.role_name), 
+                    sstring(qos::service_level_options::to_string(params.workload_type)), 
+                    to_string(cql_duration(months_counter{0}, days_counter{0}, nanoseconds_counter{nanos})),
+                    std::move(params.scheduling_group_name));
+        });
+        co_return result;
+    });
+}
+
+void unset_cql_server_test(http_context& ctx, seastar::httpd::routes& r) {
+    cst::connections_params.unset(r);
+}
+
+}
+
+#endif

api/cql_server_test.hh

@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2024-present ScyllaDB
+ */
+
+/*
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ */
+
+#ifndef SCYLLA_BUILD_MODE_RELEASE
+
+#pragma once
+
+namespace cql_transport {
+class controller;
+}
+
+namespace seastar::httpd {
+class routes;
+}
+
+namespace api {
+struct http_context;
+
+void set_cql_server_test(http_context& ctx, seastar::httpd::routes& r, cql_transport::controller& ctl);
+void unset_cql_server_test(http_context& ctx, seastar::httpd::routes& r);
+
+}
+
+#endif

api/endpoint_snitch.cc

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

api/endpoint_snitch.hh

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

api/error_injection.cc

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

api/error_injection.hh

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

api/failure_detector.cc

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

api/failure_detector.hh

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

api/gossiper.cc

@@ -3,7 +3,7 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
  */
 
 #include <seastar/core/coroutine.hh>

api/gossiper.hh

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