chore: bump to v0.8.0 (#3971)

* feat: prevent exporting physical table data

* chore: apply suggestions from CR

.cargo/config.toml

@@ -3,13 +3,3 @@ linker = "aarch64-linux-gnu-gcc"
 
 [alias]
 sqlness = "run --bin sqlness-runner --"
-
-
-[build]
-rustflags = [
-    # lints
-    # TODO: use lint configuration in cargo https://github.com/rust-lang/cargo/issues/5034
-    "-Wclippy::print_stdout",
-    "-Wclippy::print_stderr",
-    "-Wclippy::implicit_clone",
-]

.editorconfig

@@ -0,0 +1,10 @@
+root = true
+
+[*]
+end_of_line = lf
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[{Makefile,**.mk}]
+indent_style = tab

.env.example

@@ -21,3 +21,10 @@ GT_GCS_CREDENTIAL_PATH = GCS credential path
 GT_GCS_ENDPOINT = GCS end point
 # Settings for kafka wal test
 GT_KAFKA_ENDPOINTS = localhost:9092
+
+# Setting for fuzz tests
+GT_MYSQL_ADDR = localhost:4002
+
+# Setting for unstable fuzz tests
+GT_FUZZ_BINARY_PATH=/path/to/
+GT_FUZZ_INSTANCE_ROOT_DIR=/tmp/unstable_greptime

.github/CODEOWNERS

@@ -0,0 +1,27 @@
+# GreptimeDB CODEOWNERS
+
+# These owners will be the default owners for everything in the repo.
+
+* @GreptimeTeam/db-approver
+
+## [Module] Databse Engine
+/src/index @zhongzc
+/src/mito2 @evenyag @v0y4g3r @waynexia
+/src/query @evenyag
+
+## [Module] Distributed
+/src/common/meta @MichaelScofield
+/src/common/procedure @MichaelScofield
+/src/meta-client @MichaelScofield
+/src/meta-srv @MichaelScofield
+
+## [Module] Write Ahead Log
+/src/log-store @v0y4g3r
+/src/store-api @v0y4g3r
+
+## [Module] Metrics Engine
+/src/metric-engine @waynexia
+/src/promql @waynexia
+
+## [Module] Flow
+/src/flow @zhongzc @waynexia

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,7 +1,7 @@
 ---
 name: Bug report
 description: Is something not working? Help us fix it!
-labels: [ "bug" ]
+labels: [ "C-bug" ]
 body:
   - type: markdown
     attributes:
@@ -39,7 +39,7 @@ body:
         - Query Engine
         - Table Engine
         - Write Protocols
-        - MetaSrv
+        - Metasrv
         - Frontend
         - Datanode
         - Other

.github/ISSUE_TEMPLATE/config.yml

@@ -4,5 +4,5 @@ contact_links:
     url: https://greptime.com/slack
     about: Get free help from the Greptime community
   - name: Greptime Community Discussion
-    url: https://github.com/greptimeTeam/greptimedb/discussions
+    url: https://github.com/greptimeTeam/discussions
     about: Get free help from the Greptime community

.github/ISSUE_TEMPLATE/enhancement.yml

@@ -1,7 +1,7 @@
 ---
 name: Enhancement
 description: Suggest an enhancement to existing functionality
-labels: [ "enhancement" ]
+labels: [ "C-enhancement" ]
 body:
   - type: dropdown
     id: type

.github/ISSUE_TEMPLATE/feature.yml

@@ -1,7 +1,7 @@
 ---
-name: Feature request
+name: New Feature
 description: Suggest a new feature for GreptimeDB
-labels: [ "feature request" ]
+labels: [ "C-feature" ]
 body:
   - type: markdown
     id: info

.github/actions/build-dev-builder-images/action.yml

@@ -22,15 +22,15 @@ inputs:
   build-dev-builder-ubuntu:
     description: Build dev-builder-ubuntu image
     required: false
-    default: 'true'
+    default: "true"
   build-dev-builder-centos:
     description: Build dev-builder-centos image
     required: false
-    default: 'true'
+    default: "true"
   build-dev-builder-android:
     description: Build dev-builder-android image
     required: false
-    default: 'true'
+    default: "true"
 runs:
   using: composite
   steps:
@@ -47,7 +47,7 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=ubuntu \
-          BUILDX_MULTI_PLATFORM_BUILD=true \
+          BUILDX_MULTI_PLATFORM_BUILD=all \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
           IMAGE_TAG=${{ inputs.version }}
@@ -58,7 +58,7 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=centos \
-          BUILDX_MULTI_PLATFORM_BUILD=true \
+          BUILDX_MULTI_PLATFORM_BUILD=amd64 \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
           IMAGE_TAG=${{ inputs.version }}
@@ -72,5 +72,5 @@ runs:
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
           IMAGE_TAG=${{ inputs.version }} && \
-        
+
         docker push ${{ inputs.dockerhub-image-registry }}/${{ inputs.dockerhub-image-namespace }}/dev-builder-android:${{ inputs.version }}

.github/actions/build-linux-artifacts/action.yml

@@ -16,7 +16,7 @@ inputs:
   dev-mode:
     description: Enable dev mode, only build standard greptime
     required: false
-    default: 'false'
+    default: "false"
   working-dir:
     description: Working directory to build the artifacts
     required: false
@@ -34,7 +34,7 @@ runs:
 
     - name: Upload sqlness logs
       if: ${{ failure() && inputs.disable-run-tests == 'false' }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: sqlness-logs
         path: /tmp/greptime-*.log
@@ -68,7 +68,7 @@ runs:
 
     - name: Build greptime on centos base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build centos7 base image for amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds greptime for centos if the host machine is amd64.
       with:
         base-image: centos
         features: servers/dashboard
@@ -79,7 +79,7 @@ runs:
 
     - name: Build greptime on android base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build android base image on amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds arm64 greptime binary for android if the host machine amd64.
       with:
         base-image: android
         artifacts-dir: greptime-android-arm64-${{ inputs.version }}

.github/actions/build-macos-artifacts/action.yml

@@ -67,7 +67,7 @@ runs:
 
     - name: Upload sqlness logs
       if: ${{ failure() }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: sqlness-logs
         path: /tmp/greptime-*.log

.github/actions/build-windows-artifacts/action.yml

@@ -59,18 +59,21 @@ runs:
       if: ${{ inputs.disable-run-tests == 'false' }}
       shell: pwsh
       run: make test sqlness-test
+      env:
+        RUSTUP_WINDOWS_PATH_ADD_BIN: 1 # Workaround for https://github.com/nextest-rs/nextest/issues/1493
+        RUST_BACKTRACE: 1
 
     - name: Upload sqlness logs
       if: ${{ failure() }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: sqlness-logs
-        path: ${{ runner.temp }}/greptime-*.log
+        path: /tmp/greptime-*.log
         retention-days: 3
 
     - name: Build greptime binary
       shell: pwsh
-      run: cargo build --profile ${{ inputs.cargo-profile }} --features ${{ inputs.features }} --target ${{ inputs.arch }}
+      run: cargo build --profile ${{ inputs.cargo-profile }} --features ${{ inputs.features }} --target ${{ inputs.arch }} --bin greptime
 
     - name: Upload artifacts
       uses: ./.github/actions/upload-artifacts

.github/actions/fuzz-test/action.yaml

@@ -0,0 +1,19 @@
+name: Fuzz Test
+description: 'Fuzz test given setup and service'
+inputs:
+  target:
+    description: "The fuzz target to test"
+    required: true
+  max-total-time:
+    description: "Max total time(secs)"
+    required: true
+  unstable:
+    default: 'false'
+    description: "Enable unstable feature"
+runs:
+  using: composite
+  steps:
+  - name: Run Fuzz Test
+    shell: bash
+    run: cargo fuzz run ${{ inputs.target }} --fuzz-dir tests-fuzz -D -s none ${{ inputs.unstable == 'true' && '--features=unstable' || '' }} -- -max_total_time=${{ inputs.max-total-time }}
+

.github/actions/setup-cyborg/action.yml

@@ -0,0 +1,16 @@
+name: Setup cyborg environment
+description: Setup cyborg environment
+runs:
+  using: composite
+  steps:
+    - uses: actions/setup-node@v4
+      with:
+        node-version: 22
+    - uses: pnpm/action-setup@v3
+      with:
+        package_json_file: 'cyborg/package.json'
+        run_install: true
+    - name: Describe the Environment
+      working-directory: cyborg
+      shell: bash
+      run: pnpm tsx -v

.github/doc-label-config.yml

@@ -1,4 +0,0 @@
-Doc not needed:
-    - '- \[x\]  This PR does not require documentation updates.'
-Doc update required:
-    - '- \[ \]  This PR does not require documentation updates.'

.github/pr-title-breaking-change-label-config.json

@@ -1,13 +0,0 @@
-{
-    "LABEL": {
-        "name": "breaking change",
-        "color": "D93F0B"
-    },
-    "CHECKS": {
-        "regexp": "^(?:(?!!:).)*$",
-        "ignoreLabels": [
-            "ignore-title"
-        ],
-        "alwaysPassCI": true
-    }
-}

.github/pr-title-checker-config.json

@@ -1,12 +0,0 @@
-{
-    "LABEL": {
-        "name": "Invalid PR Title",
-        "color": "B60205"
-    },
-    "CHECKS": {
-        "regexp": "^(feat|fix|test|refactor|chore|style|docs|perf|build|ci|revert)(\\(.*\\))?\\!?:.*",
-        "ignoreLabels": [
-            "ignore-title"
-        ]
-    }
-}

.github/pull_request_template.md

@@ -1,8 +1,10 @@
-I hereby agree to the terms of the [GreptimeDB CLA](https://gist.github.com/xtang/6378857777706e568c1949c7578592cc)
+I hereby agree to the terms of the [GreptimeDB CLA](https://github.com/GreptimeTeam/.github/blob/main/CLA.md).
+
+## Refer to a related PR or issue link (optional)
 
 ## What's changed and what's your intention?
 
-_PLEASE DO NOT LEAVE THIS EMPTY !!!_
+__!!! DO NOT LEAVE THIS BLOCK EMPTY !!!__
 
 Please explain IN DETAIL what the changes are in this PR and why they are needed:
 
@@ -13,8 +15,6 @@ Please explain IN DETAIL what the changes are in this PR and why they are needed
 
 ## Checklist
 
-- [ ]  I have written the necessary rustdoc comments.
-- [ ]  I have added the necessary unit tests and integration tests.
-- [x]  This PR does not require documentation updates.
-
-## Refer to a related PR or issue link (optional)
+- [ ] I have written the necessary rustdoc comments.
+- [ ] I have added the necessary unit tests and integration tests.
+- [ ] This PR requires documentation updates.

.github/workflows/apidoc.yml

@@ -13,7 +13,7 @@ on:
 name: Build API docs
 
 env:
-  RUST_TOOLCHAIN: nightly-2023-12-19
+  RUST_TOOLCHAIN: nightly-2024-04-20
 
 jobs:
   apidoc:
@@ -40,3 +40,4 @@ jobs:
       uses: JamesIves/github-pages-deploy-action@v4
       with:
         folder: target/doc
+        single-commit: true

.github/workflows/develop.yml

@@ -1,7 +1,7 @@
 on:
   merge_group:
   pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
+    types: [ opened, synchronize, reopened, ready_for_review ]
     paths-ignore:
       - 'docs/**'
       - 'config/**'
@@ -30,22 +30,34 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  RUST_TOOLCHAIN: nightly-2023-12-19
+  RUST_TOOLCHAIN: nightly-2024-04-20
 
 jobs:
-  typos:
-    name: Spell Check with Typos
+  check-typos-and-docs:
+    name: Check typos and docs
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
-      - uses: crate-ci/typos@v1.13.10
+      - uses: crate-ci/typos@master
+      - name: Check the config docs
+        run: |
+          make config-docs && \
+          git diff --name-only --exit-code ./config/config.md  \
+          || (echo "'config/config.md' is not up-to-date, please run 'make config-docs'." && exit 1)
+
+  license-header-check:
+    runs-on: ubuntu-20.04
+    name: Check License Header
+    steps:
+      - uses: actions/checkout@v4
+      - uses: korandoru/hawkeye@v5
 
   check:
     name: Check
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ windows-latest, ubuntu-20.04 ]
+        os: [ windows-2022, ubuntu-20.04 ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
@@ -57,7 +69,7 @@ jobs:
           toolchain: ${{ env.RUST_TOOLCHAIN }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with: 
+        with:
           # Shares across multiple jobs
           # Shares with `Clippy` job
           shared-key: "check-lint"
@@ -75,7 +87,7 @@ jobs:
           toolchain: stable
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with: 
+        with:
           # Shares across multiple jobs
           shared-key: "check-toml"
       - name: Install taplo
@@ -93,6 +105,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: arduino/setup-protoc@v3
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
       - uses: dtolnay/rust-toolchain@master
         with:
           toolchain: ${{ env.RUST_TOOLCHAIN }}
@@ -100,9 +114,13 @@ jobs:
         with:
           # Shares across multiple jobs
           shared-key: "build-binaries"
+      - name: Install cargo-gc-bin
+        shell: bash
+        run: cargo install cargo-gc-bin
       - name: Build greptime binaries
         shell: bash
-        run: cargo build
+        # `cargo gc` will invoke `cargo build` with specified args
+        run: cargo gc -- --bin greptime --bin sqlness-runner
       - name: Pack greptime binaries
         shell: bash
         run: |
@@ -117,6 +135,103 @@ jobs:
           artifacts-dir: bins
           version: current
 
+  fuzztest:
+    name: Fuzz Test
+    needs: build
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [ "fuzz_create_table", "fuzz_alter_table", "fuzz_create_database", "fuzz_create_logical_table", "fuzz_alter_logical_table", "fuzz_insert", "fuzz_insert_logical_table" ]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: arduino/setup-protoc@v3
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          # Shares across multiple jobs
+          shared-key: "fuzz-test-targets"
+      - name: Set Rust Fuzz
+        shell: bash
+        run: |
+          sudo apt-get install -y libfuzzer-14-dev
+          rustup install nightly
+          cargo +nightly install cargo-fuzz
+      - name: Download pre-built binaries
+        uses: actions/download-artifact@v4
+        with:
+          name: bins
+          path: .
+      - name: Unzip binaries
+        run: tar -xvf ./bins.tar.gz
+      - name: Run GreptimeDB
+        run: |
+          ./bins/greptime standalone start&
+      - name: Fuzz Test
+        uses: ./.github/actions/fuzz-test
+        env:
+          CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
+          GT_MYSQL_ADDR: 127.0.0.1:4002
+        with:
+          target: ${{ matrix.target }}
+          max-total-time: 120
+
+  unstable-fuzztest:
+    name: Unstable Fuzz Test
+    needs: build
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [ "unstable_fuzz_create_table_standalone" ]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: arduino/setup-protoc@v3
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          # Shares across multiple jobs
+          shared-key: "fuzz-test-targets"
+      - name: Set Rust Fuzz
+        shell: bash
+        run: |
+          sudo apt update && sudo apt install -y libfuzzer-14-dev
+          cargo install cargo-fuzz
+      - name: Download pre-built binaries
+        uses: actions/download-artifact@v4
+        with:
+          name: bins
+          path: .
+      - name: Unzip binaries
+        run: tar -xvf ./bins.tar.gz
+      - name: Fuzz Test
+        uses: ./.github/actions/fuzz-test
+        env:
+          CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
+          GT_MYSQL_ADDR: 127.0.0.1:4002
+          GT_FUZZ_BINARY_PATH: ./bins/greptime
+          GT_FUZZ_INSTANCE_ROOT_DIR: /tmp/unstable-greptime/
+        with:
+          target: ${{ matrix.target }}
+          max-total-time: 120
+          unstable: 'true'
+      - name: Upload unstable fuzz test logs
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: unstable-fuzz-logs
+          path: /tmp/unstable-greptime/
+          retention-days: 3
+
+
   sqlness:
     name: Sqlness Test
     needs: build
@@ -135,14 +250,13 @@ jobs:
       - name: Unzip binaries
         run: tar -xvf ./bins.tar.gz
       - name: Run sqlness
-        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -c ./tests/cases --bins-dir ./bins
-      # FIXME: Logs cannot found be on failure (or even success). Need to figure out the cause.
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -c ./tests/cases --bins-dir ./bins --preserve-state
       - name: Upload sqlness logs
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: sqlness-logs
-          path: ${{ runner.temp }}/greptime-*.log
+          path: /tmp/sqlness*
           retention-days: 3
 
   sqlness-kafka-wal:
@@ -166,14 +280,13 @@ jobs:
         working-directory: tests-integration/fixtures/kafka
         run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Run sqlness
-        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -w kafka -k 127.0.0.1:9092 -c ./tests/cases --bins-dir ./bins
-      # FIXME: Logs cannot be found on failure (or even success). Need to figure out the cause.
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -w kafka -k 127.0.0.1:9092 -c ./tests/cases --bins-dir ./bins --preserve-state
       - name: Upload sqlness logs
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: sqlness-logs
-          path: ${{ runner.temp }}/greptime-*.log
+          name: sqlness-logs-with-kafka-wal
+          path: /tmp/sqlness*
           retention-days: 3
 
   fmt:
@@ -191,7 +304,7 @@ jobs:
           components: rustfmt
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with: 
+        with:
           # Shares across multiple jobs
           shared-key: "check-rust-fmt"
       - name: Run cargo fmt
@@ -212,12 +325,12 @@ jobs:
           components: clippy
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with: 
+        with:
           # Shares across multiple jobs
           # Shares with `Check` job
           shared-key: "check-lint"
       - name: Run cargo clippy
-        run: cargo clippy --workspace --all-targets -- -D warnings
+        run: make clippy
 
   coverage:
     if: github.event.pull_request.draft == false
@@ -241,6 +354,10 @@ jobs:
         with:
           # Shares cross multiple jobs
           shared-key: "coverage-test"
+      - name: Docker Cache
+        uses: ScribeMD/docker-cache@0.3.7
+        with:
+          key: docker-${{ runner.os }}-coverage
       - name: Install latest nextest release
         uses: taiki-e/install-action@nextest
       - name: Install cargo-llvm-cov
@@ -263,18 +380,36 @@ jobs:
           CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
           RUST_BACKTRACE: 1
           CARGO_INCREMENTAL: 0
-          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
-          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
-          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
-          GT_S3_REGION: ${{ secrets.S3_REGION }}
+          GT_S3_BUCKET: ${{ vars.AWS_CI_TEST_BUCKET }}
+          GT_S3_ACCESS_KEY_ID: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
+          GT_S3_ACCESS_KEY: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
+          GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
           GT_ETCD_ENDPOINTS: http://127.0.0.1:2379
           GT_KAFKA_ENDPOINTS: 127.0.0.1:9092
           UNITTEST_LOG_DIR: "__unittest_logs"
       - name: Codecov upload
-        uses: codecov/codecov-action@v2
+        uses: codecov/codecov-action@v4
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./lcov.info
           flags: rust
           fail_ci_if_error: false
           verbose: true
+
+  # compat:
+  #   name: Compatibility Test
+  #   needs: build
+  #   runs-on: ubuntu-20.04
+  #   timeout-minutes: 60
+  #   steps:
+  #     - uses: actions/checkout@v4
+  #     - name: Download pre-built binaries
+  #       uses: actions/download-artifact@v4
+  #       with:
+  #         name: bins
+  #         path: .
+  #     - name: Unzip binaries
+  #       run: |
+  #         mkdir -p ./bins/current
+  #         tar -xvf ./bins.tar.gz --strip-components=1 -C ./bins/current
+  #     - run: ./tests/compat/test-compat.sh 0.6.0

.github/workflows/doc-issue.yml

@@ -1,39 +0,0 @@
-name: Create Issue in downstream repos
-
-on:
-  issues:
-    types:
-      - labeled
-  pull_request_target:
-    types:
-      - labeled
-
-jobs:
-  doc_issue:
-    if: github.event.label.name == 'doc update required'
-    runs-on: ubuntu-20.04
-    steps:
-      - name: create an issue in doc repo
-        uses: dacbd/create-issue-action@v1.2.1
-        with:
-          owner: GreptimeTeam
-          repo: docs
-          token: ${{ secrets.DOCS_REPO_TOKEN }}
-          title: Update docs for ${{ github.event.issue.title || github.event.pull_request.title }}
-          body: |
-            A document change request is generated from
-            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
-  cloud_issue:
-    if: github.event.label.name == 'cloud followup required'
-    runs-on: ubuntu-20.04
-    steps:
-      - name: create an issue in cloud repo
-        uses: dacbd/create-issue-action@v1.2.1
-        with:
-          owner: GreptimeTeam
-          repo: greptimedb-cloud
-          token: ${{ secrets.DOCS_REPO_TOKEN }}
-          title: Followup changes in ${{ github.event.issue.title || github.event.pull_request.title }}
-          body: |
-            A followup request is generated from
-            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}

.github/workflows/doc-label.yml

@@ -1,36 +0,0 @@
-name: "PR Doc Labeler"
-on:
-  pull_request_target:
-    types: [opened, edited, synchronize, ready_for_review, auto_merge_enabled, labeled, unlabeled]
-
-permissions:
-  pull-requests: write
-  contents: read
-
-jobs:
-  triage:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-latest
-    steps:
-    - uses: github/issue-labeler@v3.4
-      with:
-        configuration-path: .github/doc-label-config.yml
-        enable-versioned-regex: false
-        repo-token: ${{ secrets.GITHUB_TOKEN }}
-        sync-labels: 1
-    - name: create an issue in doc repo
-      uses: dacbd/create-issue-action@v1.2.1
-      if: ${{ github.event.action == 'opened' && contains(github.event.pull_request.body, '- [ ]  This PR does not require documentation updates.') }}
-      with:
-        owner: GreptimeTeam
-        repo: docs
-        token: ${{ secrets.DOCS_REPO_TOKEN }}
-        title: Update docs for ${{ github.event.issue.title || github.event.pull_request.title }}
-        body: |
-          A document change request is generated from
-          ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
-    - name: Check doc labels
-      uses: docker://agilepathway/pull-request-label-checker:latest
-      with:
-        one_of: Doc update required,Doc not needed
-        repo_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docbot.yml

@@ -0,0 +1,22 @@
+name: Follow Up Docs
+on:
+  pull_request_target:
+    types: [opened, edited]
+
+permissions:
+  pull-requests: write
+  contents: read
+
+jobs:
+  docbot:
+    runs-on: ubuntu-20.04
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/setup-cyborg
+      - name: Maybe Follow Up Docs Issue
+        working-directory: cyborg
+        run: pnpm tsx bin/follow-up-docs-issue.ts
+        env:
+          DOCS_REPO_TOKEN: ${{ secrets.DOCS_REPO_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs.yml

@@ -34,7 +34,14 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
-      - uses: crate-ci/typos@v1.13.10
+      - uses: crate-ci/typos@master
+
+  license-header-check:
+    runs-on: ubuntu-20.04
+    name: Check License Header
+    steps:
+      - uses: actions/checkout@v4
+      - uses: korandoru/hawkeye@v5
 
   check:
     name: Check
@@ -61,6 +68,18 @@ jobs:
 
   sqlness:
     name: Sqlness Test
-    runs-on: ubuntu-20.04
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-20.04 ]
+    steps:
+      - run: 'echo "No action required"'
+
+  sqlness-kafka-wal:
+    name: Sqlness Test with Kafka Wal
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-20.04 ]
     steps:
       - run: 'echo "No action required"'

.github/workflows/license.yaml

@@ -1,16 +0,0 @@
-name: License checker
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-jobs:
-  license-header-check:
-    runs-on: ubuntu-20.04
-    name: license-header-check
-    steps:
-    - uses: actions/checkout@v4
-    - name: Check License Header
-      uses: korandoru/hawkeye@v4

.github/workflows/nightly-ci.yml

@@ -1,8 +1,6 @@
-# Nightly CI: runs tests every night for our second tier plaforms (Windows)
-
 on:
   schedule:
-    - cron: '0 23 * * 1-5'
+    - cron: "0 23 * * 1-5"
   workflow_dispatch:
 
 name: Nightly CI
@@ -12,16 +10,32 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  RUST_TOOLCHAIN: nightly-2023-12-19
+  RUST_TOOLCHAIN: nightly-2024-04-20
 
 jobs:
-  sqlness:
-    name: Sqlness Test
+  sqlness-test:
+    name: Run sqlness test
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ windows-latest-8-cores ]
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Run sqlness test
+        uses: ./.github/actions/sqlness-test
+        with:
+          data-root: sqlness-test
+          aws-ci-test-bucket: ${{ vars.AWS_CI_TEST_BUCKET }}
+          aws-region: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
+          aws-access-key-id: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
+
+  sqlness-windows:
+    name: Sqlness tests on Windows
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: windows-2022-8-cores
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
@@ -45,15 +59,16 @@ jobs:
             {"text": "Nightly CI failed for sqlness tests"}
       - name: Upload sqlness logs
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: sqlness-logs
-          path: ${{ runner.temp }}/greptime-*.log
+          path: /tmp/greptime-*.log
           retention-days: 3
 
   test-on-windows:
+    name: Run tests on Windows
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: windows-latest-8-cores
+    runs-on: windows-2022-8-cores
     timeout-minutes: 60
     steps:
       - run: git config --global core.autocrlf false
@@ -61,6 +76,9 @@ jobs:
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: KyleMayes/install-llvm-action@v1
+        with:
+          version: "14.0"
       - name: Install Rust toolchain
         uses: dtolnay/rust-toolchain@master
         with:
@@ -73,7 +91,7 @@ jobs:
       - name: Install Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: "3.10"
       - name: Install PyArrow Package
         run: pip install pyarrow
       - name: Install WSL distribution
@@ -83,12 +101,14 @@ jobs:
       - name: Running tests
         run: cargo nextest run -F pyo3_backend,dashboard
         env:
+          CARGO_BUILD_RUSTFLAGS: "-C linker=lld-link"
           RUST_BACKTRACE: 1
           CARGO_INCREMENTAL: 0
-          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
-          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
-          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
-          GT_S3_REGION: ${{ secrets.S3_REGION }}
+          RUSTUP_WINDOWS_PATH_ADD_BIN: 1 # Workaround for https://github.com/nextest-rs/nextest/issues/1493
+          GT_S3_BUCKET: ${{ vars.AWS_CI_TEST_BUCKET }}
+          GT_S3_ACCESS_KEY_ID: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
+          GT_S3_ACCESS_KEY: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
+          GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
           UNITTEST_LOG_DIR: "__unittest_logs"
       - name: Notify slack if failed
         if: failure()

.github/workflows/nightly-funtional-tests.yml

@@ -1,27 +0,0 @@
-name: Nightly functional tests
-
-on:
-  schedule:
-    # At 00:00 on Tuesday.
-    - cron: '0 0 * * 2'
-  workflow_dispatch:
-
-jobs:
-  sqlness-test:
-    name: Run sqlness test
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Run sqlness test
-        uses: ./.github/actions/sqlness-test
-        with:
-          data-root: sqlness-test
-          aws-ci-test-bucket: ${{ vars.AWS_CI_TEST_BUCKET }}
-          aws-region: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
-          aws-access-key-id: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}

.github/workflows/pr-title-checker.yml

@@ -1,29 +0,0 @@
-name: "PR Title Checker"
-on:
-  pull_request_target:
-    types:
-      - opened
-      - edited
-      - synchronize
-      - labeled
-      - unlabeled
-
-jobs:
-  check:
-    runs-on: ubuntu-20.04
-    timeout-minutes: 10
-    steps:
-      - uses: thehanimo/pr-title-checker@v1.4.2
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          pass_on_octokit_error: false
-          configuration_path: ".github/pr-title-checker-config.json"
-  breaking:
-    runs-on: ubuntu-20.04
-    timeout-minutes: 10
-    steps:
-      - uses: thehanimo/pr-title-checker@v1.4.2
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          pass_on_octokit_error: false
-          configuration_path: ".github/pr-title-breaking-change-label-config.json"

.github/workflows/release.yml

@@ -82,7 +82,7 @@ on:
 # Use env variables to control all the release process.
 env:
   # The arguments of building greptime.
-  RUST_TOOLCHAIN: nightly-2023-12-19
+  RUST_TOOLCHAIN: nightly-2024-04-20
   CARGO_PROFILE: nightly
 
   # Controls whether to run tests, include unit-test, integration-test and sqlness.
@@ -91,7 +91,7 @@ env:
   # The scheduled version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD', like v0.2.0-nigthly-20230313;
   NIGHTLY_RELEASE_PREFIX: nightly
   # Note: The NEXT_RELEASE_VERSION should be modified manually by every formal release.
-  NEXT_RELEASE_VERSION: v0.7.0
+  NEXT_RELEASE_VERSION: v0.9.0
 
 jobs:
   allocate-runners:
@@ -102,7 +102,7 @@ jobs:
       linux-amd64-runner: ${{ steps.start-linux-amd64-runner.outputs.label }}
       linux-arm64-runner: ${{ steps.start-linux-arm64-runner.outputs.label }}
       macos-runner: ${{ inputs.macos_runner || vars.DEFAULT_MACOS_RUNNER }}
-      windows-runner: windows-latest-8-cores
+      windows-runner: windows-2022-8-cores
 
       # The following EC2 resource id will be used for resource releasing.
       linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
@@ -221,6 +221,8 @@ jobs:
             arch: x86_64-apple-darwin
             artifacts-dir-prefix: greptime-darwin-amd64-pyo3
     runs-on: ${{ matrix.os }}
+    outputs:
+      build-macos-result: ${{ steps.set-build-macos-result.outputs.build-macos-result }}
     needs: [
       allocate-runners,
     ]
@@ -260,6 +262,8 @@ jobs:
             features: pyo3_backend,servers/dashboard
             artifacts-dir-prefix: greptime-windows-amd64-pyo3
     runs-on: ${{ matrix.os }}
+    outputs:
+      build-windows-result: ${{ steps.set-build-windows-result.outputs.build-windows-result }}
     needs: [
       allocate-runners,
     ]
@@ -284,7 +288,7 @@ jobs:
       - name: Set build windows result
         id: set-build-windows-result
         run: |
-          echo "build-windows-result=success" >> $GITHUB_OUTPUT    
+          echo "build-windows-result=success" >> $Env:GITHUB_OUTPUT
 
   release-images-to-dockerhub:
     name: Build and push images to DockerHub
@@ -295,6 +299,8 @@ jobs:
       build-linux-arm64-artifacts,
     ]
     runs-on: ubuntu-2004-16-cores
+    outputs:
+      build-image-result: ${{ steps.set-build-image-result.outputs.build-image-result }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -310,7 +316,7 @@ jobs:
           version: ${{ needs.allocate-runners.outputs.version }}
 
       - name: Set build image result
-        id: set-image-build-result
+        id: set-build-image-result
         run: |
           echo "build-image-result=success" >> $GITHUB_OUTPUT    
 
@@ -430,7 +436,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
+    if: ${{ always() || github.repository == 'GreptimeTeam/greptimedb' }}
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub,

.github/workflows/schedule.yml

@@ -0,0 +1,24 @@
+name: Schedule Management
+on:
+  schedule:
+    - cron: '4 2 * * *'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  issues: write
+  pull-requests: write
+
+jobs:
+  maintenance:
+    name: Periodic Maintenance
+    runs-on: ubuntu-latest
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/setup-cyborg
+      - name: Do Maintenance
+        working-directory: cyborg
+        run: pnpm tsx bin/schedule.ts
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}

.github/workflows/semantic-pull-request.yml

@@ -0,0 +1,21 @@
+name: "Semantic Pull Request"
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - reopened
+      - edited
+
+jobs:
+  check:
+    runs-on: ubuntu-20.04
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/setup-cyborg
+      - name: Check Pull Request
+        working-directory: cyborg
+        run: pnpm tsx bin/check-pull-request.ts
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -46,3 +46,7 @@ benchmarks/data
 *.code-workspace
 
 venv/
+
+# Fuzz tests 
+tests-fuzz/artifacts/
+tests-fuzz/corpus/

CODE_OF_CONDUCT.md

@@ -1,132 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, caste, color, religion, or sexual
-identity and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the overall
-  community
-
-Examples of unacceptable behavior include:
-
-* The use of sexualized language or imagery, and sexual attention or advances of
-  any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email address,
-  without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-info@greptime.com.
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series of
-actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or permanent
-ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior, harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within the
-community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.1, available at
-[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
-
-Community Impact Guidelines were inspired by
-[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
-
-For answers to common questions about this code of conduct, see the FAQ at
-[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
-[https://www.contributor-covenant.org/translations][translations].
-
-[homepage]: https://www.contributor-covenant.org
-[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
-[Mozilla CoC]: https://github.com/mozilla/diversity
-[FAQ]: https://www.contributor-covenant.org/faq
-[translations]: https://www.contributor-covenant.org/translations

CONTRIBUTING.md

@@ -50,7 +50,7 @@ GreptimeDB uses the [Apache 2.0 license](https://github.com/GreptimeTeam/greptim
 
 - To ensure that community is free and confident in its ability to use your contributions, please sign the Contributor License Agreement (CLA) which will be incorporated in the pull request process.
 - Make sure all files have proper license header (running `docker run --rm -v $(pwd):/github/workspace ghcr.io/korandoru/hawkeye-native:v3 format` from the project root).
-- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/).
+- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/) and [style guide](docs/style-guide.md).
 - Make sure all unit tests are passed (using `cargo test --workspace` or [nextest](https://nexte.st/index.html) `cargo nextest run`).
 - Make sure all clippy warnings are fixed (you can check it locally by running `cargo clippy --workspace --all-targets -- -D warnings`).
 

Cargo.toml

@@ -4,6 +4,7 @@ members = [
     "src/api",
     "src/auth",
     "src/catalog",
+    "src/cache",
     "src/client",
     "src/cmd",
     "src/common/base",
@@ -11,6 +12,7 @@ members = [
     "src/common/config",
     "src/common/datasource",
     "src/common/error",
+    "src/common/frontend",
     "src/common/function",
     "src/common/macro",
     "src/common/greptimedb-telemetry",
@@ -18,6 +20,7 @@ members = [
     "src/common/grpc-expr",
     "src/common/mem-prof",
     "src/common/meta",
+    "src/common/plugins",
     "src/common/procedure",
     "src/common/procedure-test",
     "src/common/query",
@@ -61,18 +64,32 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.6.0"
+version = "0.8.0"
 edition = "2021"
 license = "Apache-2.0"
 
+[workspace.lints]
+clippy.print_stdout = "warn"
+clippy.print_stderr = "warn"
+clippy.implicit_clone = "warn"
+clippy.readonly_write_lock = "allow"
+rust.unknown_lints = "deny"
+# Remove this after https://github.com/PyO3/pyo3/issues/4094
+rust.non_local_definitions = "allow"
+
 [workspace.dependencies]
+# We turn off default-features for some dependencies here so the workspaces which inherit them can
+# selectively turn them on if needed, since we can override default-features = true (from false)
+# for the inherited dependency but cannot do the reverse (override from true to false).
+#
+# See for more detaiils: https://github.com/rust-lang/cargo/issues/11329
 ahash = { version = "0.8", features = ["compile-time-rng"] }
 aquamarine = "0.3"
-arrow = { version = "47.0" }
-arrow-array = "47.0"
-arrow-flight = "47.0"
-arrow-ipc = "47.0"
-arrow-schema = { version = "47.0", features = ["serde"] }
+arrow = { version = "51.0.0", features = ["prettyprint"] }
+arrow-array = { version = "51.0.0", default-features = false, features = ["chrono-tz"] }
+arrow-flight = "51.0"
+arrow-ipc = { version = "51.0.0", default-features = false, features = ["lz4"] }
+arrow-schema = { version = "51.0", features = ["serde"] }
 async-stream = "0.3"
 async-trait = "0.1"
 axum = { version = "0.6", features = ["headers"] }
@@ -83,34 +100,41 @@ bytemuck = "1.12"
 bytes = { version = "1.5", features = ["serde"] }
 chrono = { version = "0.4", features = ["serde"] }
 clap = { version = "4.4", features = ["derive"] }
+config = "0.13.0"
+crossbeam-utils = "0.8"
 dashmap = "5.4"
-datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
+datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-functions = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
 derive_builder = "0.12"
-etcd-client = "0.12"
+dotenv = "0.15"
+# TODO(LFC): Wait for https://github.com/etcdv3/etcd-client/pull/76
+etcd-client = { git = "https://github.com/MichaelScofield/etcd-client.git", rev = "4c371e9b3ea8e0a8ee2f9cbd7ded26e54a45df3b" }
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "96f1f0404f421ee560a4310c73c5071e49168168" }
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "a11db14b8502f55ca5348917fd18e6fcf140f55e" }
+humantime = "2.1"
 humantime-serde = "1.1"
 itertools = "0.10"
 lazy_static = "1.4"
-meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "abbd357c1e193cd270ea65ee7652334a150b628f" }
+meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "80b72716dcde47ec4161478416a5c6c21343364d" }
 mockall = "0.11.4"
 moka = "0.12"
+notify = "6.1"
 num_cpus = "1.16"
 once_cell = "1.18"
-opentelemetry-proto = { git = "https://github.com/waynexia/opentelemetry-rust.git", rev = "33841b38dda79b15f2024952be5f32533325ca02", features = [
+opentelemetry-proto = { version = "0.5", features = [
     "gen-tonic",
     "metrics",
     "trace",
 ] }
-parquet = "47.0"
+parquet = { version = "51.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
@@ -118,36 +142,40 @@ prost = "0.12"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
 regex = "1.8"
-regex-automata = { version = "0.2", features = ["transducer"] }
+regex-automata = { version = "0.4" }
 reqwest = { version = "0.11", default-features = false, features = [
     "json",
     "rustls-tls-native-roots",
     "stream",
+    "multipart",
 ] }
 rskafka = "0.5"
 rust_decimal = "1.33"
+schemars = "0.8"
 serde = { version = "1.0", features = ["derive"] }
-serde_json = "1.0"
+serde_json = { version = "1.0", features = ["float_roundtrip"] }
 serde_with = "3"
 smallvec = { version = "1", features = ["serde"] }
-snafu = "0.7"
+snafu = "0.8"
 sysinfo = "0.30"
-# on branch v0.38.x
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "6a93567ae38d42be5c8d08b13c8ff4dde26502ef", features = [
+# on branch v0.44.x
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "e4e496b8d62416ad50ce70a1b460c7313610cf5d", features = [
     "visitor",
 ] }
 strum = { version = "0.25", features = ["derive"] }
 tempfile = "3"
-tokio = { version = "1.28", features = ["full"] }
+tokio = { version = "1.36", features = ["full"] }
 tokio-stream = { version = "0.1" }
 tokio-util = { version = "0.7", features = ["io-util", "compat"] }
 toml = "0.8.8"
-tonic = { version = "0.10", features = ["tls"] }
-uuid = { version = "1", features = ["serde", "v4", "fast-rng"] }
+tonic = { version = "0.11", features = ["tls"] }
+uuid = { version = "1.7", features = ["serde", "v4", "fast-rng"] }
+zstd = "0.13"
 
 ## workspaces members
 api = { path = "src/api" }
 auth = { path = "src/auth" }
+cache = { path = "src/cache" }
 catalog = { path = "src/catalog" }
 client = { path = "src/client" }
 cmd = { path = "src/cmd" }
@@ -157,6 +185,7 @@ common-config = { path = "src/common/config" }
 common-datasource = { path = "src/common/datasource" }
 common-decimal = { path = "src/common/decimal" }
 common-error = { path = "src/common/error" }
+common-frontend = { path = "src/common/frontend" }
 common-function = { path = "src/common/function" }
 common-greptimedb-telemetry = { path = "src/common/greptimedb-telemetry" }
 common-grpc = { path = "src/common/grpc" }
@@ -164,6 +193,7 @@ common-grpc-expr = { path = "src/common/grpc-expr" }
 common-macro = { path = "src/common/macro" }
 common-mem-prof = { path = "src/common/mem-prof" }
 common-meta = { path = "src/common/meta" }
+common-plugins = { path = "src/common/plugins" }
 common-procedure = { path = "src/common/procedure" }
 common-procedure-test = { path = "src/common/procedure-test" }
 common-query = { path = "src/common/query" }
@@ -177,6 +207,7 @@ common-wal = { path = "src/common/wal" }
 datanode = { path = "src/datanode" }
 datatypes = { path = "src/datatypes" }
 file-engine = { path = "src/file-engine" }
+flow = { path = "src/flow" }
 frontend = { path = "src/frontend" }
 index = { path = "src/index" }
 log-store = { path = "src/log-store" }
@@ -198,10 +229,12 @@ sql = { path = "src/sql" }
 store-api = { path = "src/store-api" }
 substrait = { path = "src/common/substrait" }
 table = { path = "src/table" }
+# TODO some code depends on this
+tests-integration = { path = "tests-integration" }
 
 [workspace.dependencies.meter-macros]
 git = "https://github.com/GreptimeTeam/greptime-meter.git"
-rev = "abbd357c1e193cd270ea65ee7652334a150b628f"
+rev = "80b72716dcde47ec4161478416a5c6c21343364d"
 
 [profile.release]
 debug = 1
@@ -212,3 +245,7 @@ strip = true
 lto = "thin"
 debug = false
 incremental = false
+
+[profile.dev.package.sqlness-runner]
+debug = false
+strip = true

Makefile

@@ -3,6 +3,7 @@ CARGO_PROFILE ?=
 FEATURES ?=
 TARGET_DIR ?=
 TARGET ?=
+BUILD_BIN ?= greptime
 CARGO_BUILD_OPTS := --locked
 IMAGE_REGISTRY ?= docker.io
 IMAGE_NAMESPACE ?= greptime
@@ -45,12 +46,18 @@ ifneq ($(strip $(TARGET)),)
 	CARGO_BUILD_OPTS += --target ${TARGET}
 endif
 
+ifneq ($(strip $(BUILD_BIN)),)
+	CARGO_BUILD_OPTS += --bin ${BUILD_BIN}
+endif
+
 ifneq ($(strip $(RELEASE)),)
 	CARGO_BUILD_OPTS += --release
 endif
 
-ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), true)
+ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), all)
 	BUILDX_MULTI_PLATFORM_BUILD_OPTS := --platform linux/amd64,linux/arm64 --push
+else ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), amd64)
+	BUILDX_MULTI_PLATFORM_BUILD_OPTS := --platform linux/amd64 --push
 else
 	BUILDX_MULTI_PLATFORM_BUILD_OPTS := -o type=docker
 endif
@@ -164,6 +171,10 @@ check: ## Cargo check all the targets.
 clippy: ## Check clippy rules.
 	cargo clippy --workspace --all-targets --all-features -- -D warnings
 
+.PHONY: fix-clippy
+fix-clippy: ## Fix clippy violations.
+	cargo clippy --workspace --all-targets --all-features --fix
+
 .PHONY: fmt-check
 fmt-check: ## Check code format.
 	cargo fmt --all -- --check
@@ -183,6 +194,16 @@ run-it-in-container: start-etcd ## Run integration tests in dev-builder.
 	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:latest \
 	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
 
+##@ Docs
+config-docs: ## Generate configuration documentation from toml files.
+	docker run --rm \
+    -v ${PWD}:/greptimedb \
+    -w /greptimedb/config \
+    toml2docs/toml2docs:latest \
+    -p '##' \
+    -t ./config-docs-template.md \
+    -o ./config.md
+
 ##@ General
 
 # The help target prints out all targets with their descriptions organized

README.md

@@ -6,145 +6,154 @@
   </picture>
 </p>
 
+<h1 align="center">Cloud-scale, Fast and Efficient Time Series Database</h1>
 
+<div align="center">
 <h3 align="center">
-    The next-generation hybrid time-series/analytics processing database in the cloud
-</h3>
+  <a href="https://greptime.com/product/cloud">GreptimeCloud</a> |
+  <a href="https://docs.greptime.com/">User guide</a> |
+  <a href="https://greptimedb.rs/">API Docs</a> |
+  <a href="https://github.com/GreptimeTeam/greptimedb/issues/3412">Roadmap 2024</a>
+</h4>
 
-<p align="center">
-    <a href="https://codecov.io/gh/GrepTimeTeam/greptimedb"><img src="https://codecov.io/gh/GrepTimeTeam/greptimedb/branch/main/graph/badge.svg?token=FITFDI3J3C"></img></a>
-    &nbsp;
-    <a href="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml"><img src="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml/badge.svg" alt="CI"></img></a>
-    &nbsp;
-    <a href="https://github.com/greptimeTeam/greptimedb/blob/main/LICENSE"><img src="https://img.shields.io/github/license/greptimeTeam/greptimedb"></a>
-</p>
+<a href="https://github.com/GreptimeTeam/greptimedb/releases/latest">
+<img src="https://img.shields.io/github/v/release/GreptimeTeam/greptimedb.svg" alt="Version"/>
+</a>
+<a href="https://github.com/GreptimeTeam/greptimedb/releases/latest">
+<img src="https://img.shields.io/github/release-date/GreptimeTeam/greptimedb.svg" alt="Releases"/>
+</a>
+<a href="https://hub.docker.com/r/greptime/greptimedb/">
+<img src="https://img.shields.io/docker/pulls/greptime/greptimedb.svg" alt="Docker Pulls"/>
+</a>
+<a href="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml">
+<img src="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml/badge.svg" alt="GitHub Actions"/>
+</a>
+<a href="https://codecov.io/gh/GrepTimeTeam/greptimedb">
+<img src="https://codecov.io/gh/GrepTimeTeam/greptimedb/branch/main/graph/badge.svg?token=FITFDI3J3C" alt="Codecov"/>
+</a>
+<a href="https://github.com/greptimeTeam/greptimedb/blob/main/LICENSE">
+<img src="https://img.shields.io/github/license/greptimeTeam/greptimedb" alt="License"/>
+</a>
 
-<p align="center">
-    <a href="https://twitter.com/greptime"><img src="https://img.shields.io/badge/twitter-follow_us-1d9bf0.svg"></a>
-    &nbsp;
-    <a href="https://www.linkedin.com/company/greptime/"><img src="https://img.shields.io/badge/linkedin-connect_with_us-0a66c2.svg"></a>
-    &nbsp;
-    <a href="https://greptime.com/slack"><img src="https://img.shields.io/badge/slack-GreptimeDB-0abd59?logo=slack" alt="slack" /></a>
-</p>
+<br/>
 
-## What is GreptimeDB
+<a href="https://greptime.com/slack">
+<img src="https://img.shields.io/badge/slack-GreptimeDB-0abd59?logo=slack&style=for-the-badge" alt="Slack"/>
+</a>
+<a href="https://twitter.com/greptime">
+<img src="https://img.shields.io/badge/twitter-follow_us-1d9bf0.svg?style=for-the-badge" alt="Twitter"/>
+</a>
+<a href="https://www.linkedin.com/company/greptime/">
+<img src="https://img.shields.io/badge/linkedin-connect_with_us-0a66c2.svg?style=for-the-badge" alt="LinkedIn"/>
+</a>
+</div>
 
-GreptimeDB is an open-source time-series database focusing on efficiency, scalability, and analytical capabilities.
-It's designed to work on infrastructure of the cloud era, and users benefit from its elasticity and commodity storage.
+## Introduction
 
-Our core developers have been building time-series data platforms for years. Based on their best-practices, GreptimeDB is born to give you:
+**GreptimeDB** is an open-source time-series database focusing on efficiency, scalability, and analytical capabilities.
+Designed to work on infrastructure of the cloud era, GreptimeDB benefits users with its elasticity and commodity storage, offering a fast and cost-effective **alternative to InfluxDB** and a **long-term storage for Prometheus**.
 
-- Optimized columnar layout for handling time-series data; compacted, compressed, and stored on various storage backends, particularly cloud object storage with 50x cost efficiency.
-- Fully open-source distributed cluster architecture that harnesses the power of cloud-native elastic computing resources.
-- Seamless scalability from a standalone binary at edge to a robust, highly available distributed cluster in cloud, with a transparent experience for both developers and administrators.
-- Native SQL and PromQL for queries, and Python scripting to facilitate complex analytical tasks.
-- Flexible indexing capabilities and distributed, parallel-processing query engine, tackling high cardinality issues down.
-- Widely adopted database protocols and APIs, including MySQL, PostgreSQL, and Prometheus Remote Storage, etc.
+## Why GreptimeDB
 
-## Quick Start
+Our core developers have been building time-series data platforms for years. Based on our best-practices, GreptimeDB is born to give you:
 
-### [GreptimePlay](https://greptime.com/playground)
+* **Easy horizontal scaling**
+
+  Seamless scalability from a standalone binary at edge to a robust, highly available distributed cluster in cloud, with a transparent experience for both developers and administrators.
+
+* **Analyzing time-series data**
+
+  Query your time-series data with SQL and PromQL. Use Python scripts to facilitate complex analytical tasks.
+
+* **Cloud-native distributed database**
+
+  Fully open-source distributed cluster architecture that harnesses the power of cloud-native elastic computing resources.
+
+* **Performance and Cost-effective**
+
+  Flexible indexing capabilities and distributed, parallel-processing query engine, tackling high cardinality issues down. Optimized columnar layout for handling time-series data; compacted, compressed, and stored on various storage backends, particularly cloud object storage with 50x cost efficiency.
+
+* **Compatible with InfluxDB, Prometheus and more protocols**
+
+  Widely adopted database protocols and APIs, including MySQL, PostgreSQL, and Prometheus Remote Storage, etc. [Read more](https://docs.greptime.com/user-guide/clients/overview).
+
+## Try GreptimeDB
+
+### 1. [GreptimePlay](https://greptime.com/playground)
 
 Try out the features of GreptimeDB right from your browser.
 
-### Build
+### 2. [GreptimeCloud](https://console.greptime.cloud/)
 
-#### Build from Source
+Start instantly with a free cluster.
 
-To compile GreptimeDB from source, you'll need:
+### 3. Docker Image
 
-- C/C++ Toolchain: provides basic tools for compiling and linking. This is
-  available as `build-essential` on ubuntu and similar name on other platforms.
-- Rust: the easiest way to install Rust is to use
-  [`rustup`](https://rustup.rs/), which will check our `rust-toolchain` file and
-  install correct Rust version for you.
-- Protobuf: `protoc` is required for compiling `.proto` files. `protobuf` is
-  available from major package manager on macos and linux distributions. You can
-  find an installation instructions [here](https://grpc.io/docs/protoc-installation/).
-  **Note that `protoc` version needs to be >= 3.15** because we have used the `optional`
-  keyword. You can check it with `protoc --version`.
-- python3-dev or python3-devel(Optional feature, only needed if you want to run scripts
-  in CPython, and also need to enable `pyo3_backend` feature when compiling(by `cargo run -F pyo3_backend` or add `pyo3_backend` to src/script/Cargo.toml 's `features.default` like `default = ["python", "pyo3_backend]`)): this install a Python shared library required for running Python
-  scripting engine(In CPython Mode). This is available as `python3-dev` on
-  ubuntu, you can install it with `sudo apt install python3-dev`, or
-  `python3-devel` on RPM based distributions (e.g. Fedora, Red Hat, SuSE). Mac's
-  `Python3` package should have this shared library by default. More detail for compiling with PyO3 can be found in [PyO3](https://pyo3.rs/v0.18.1/building_and_distribution#configuring-the-python-version)'s documentation.
+To install GreptimeDB locally, the recommended way is via Docker:
 
-#### Build with Docker
-
-A docker image with necessary dependencies is provided:
-
-```
-docker build --network host -f docker/Dockerfile -t greptimedb .
+```shell
+docker pull greptime/greptimedb
 ```
 
-### Run
-
-Start GreptimeDB from source code, in standalone mode:
+Start a GreptimeDB container with:
 
+```shell
+docker run --rm --name greptime --net=host greptime/greptimedb standalone start
 ```
+
+Read more about [Installation](https://docs.greptime.com/getting-started/installation/overview) on docs.
+
+## Getting Started
+
+* [Quickstart](https://docs.greptime.com/getting-started/quick-start/overview)
+* [Write Data](https://docs.greptime.com/user-guide/clients/overview)
+* [Query Data](https://docs.greptime.com/user-guide/query-data/overview)
+* [Operations](https://docs.greptime.com/user-guide/operations/overview)
+
+## Build
+
+Check the prerequisite:
+
+* [Rust toolchain](https://www.rust-lang.org/tools/install) (nightly)
+* [Protobuf compiler](https://grpc.io/docs/protoc-installation/) (>= 3.15)
+* Python toolchain (optional): Required only if built with PyO3 backend. More detail for compiling with PyO3 can be found in its [documentation](https://pyo3.rs/v0.18.1/building_and_distribution#configuring-the-python-version).
+
+Build GreptimeDB binary:
+
+```shell
+make
+```
+
+Run a standalone server:
+
+```shell
 cargo run -- standalone start
 ```
 
-Or if you built from docker:
-
-```
-docker run -p 4002:4002 -v "$(pwd):/tmp/greptimedb" greptime/greptimedb standalone start
-```
-
-Please see the online document site for more installation options and [operations info](https://docs.greptime.com/user-guide/operations/overview).
-
-### Get started
-
-Read the [complete getting started guide](https://docs.greptime.com/getting-started/overview) on our [official document site](https://docs.greptime.com/).
-
-To write and query data, GreptimeDB is compatible with multiple [protocols and clients](https://docs.greptime.com/user-guide/clients/overview).
-
-## Resources
-
-### Installation
-
-- [Pre-built Binaries](https://greptime.com/download):
-  For Linux and macOS, you can easily download pre-built binaries including official releases and nightly builds that are ready to use.
-  In most cases, downloading the version without PyO3 is sufficient. However, if you plan to run scripts in CPython (and use Python packages like NumPy and Pandas), you will need to download the version with PyO3 and install a Python with the same version as the Python in the PyO3 version.
-  We recommend using virtualenv for the installation process to manage multiple Python versions.
-- [Docker Images](https://hub.docker.com/r/greptime/greptimedb)(**recommended**): pre-built
-  Docker images, this is the easiest way to try GreptimeDB. By default it runs CPython script with `pyo3_backend` enabled.
-- [`gtctl`](https://github.com/GreptimeTeam/gtctl): the command-line tool for
-  Kubernetes deployment
-
-### Documentation
-
-- GreptimeDB [User Guide](https://docs.greptime.com/user-guide/concepts/overview)
-- GreptimeDB [Developer
-  Guide](https://docs.greptime.com/developer-guide/overview.html)
-- GreptimeDB [internal code document](https://greptimedb.rs)
+## Extension
 
 ### Dashboard
+
 - [The dashboard UI for GreptimeDB](https://github.com/GreptimeTeam/dashboard)
 
 ### SDK
 
-- [GreptimeDB C++ Client](https://github.com/GreptimeTeam/greptimedb-client-cpp)
-- [GreptimeDB Erlang Client](https://github.com/GreptimeTeam/greptimedb-client-erl)
 - [GreptimeDB Go Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-go)
 - [GreptimeDB Java Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-java)
-- [GreptimeDB Python Client](https://github.com/GreptimeTeam/greptimedb-client-py) (WIP)
-- [GreptimeDB Rust Client](https://github.com/GreptimeTeam/greptimedb-client-rust)
-- [GreptimeDB JavaScript Client](https://github.com/GreptimeTeam/greptime-js-sdk)
+- [GreptimeDB C++ Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-cpp)
+- [GreptimeDB Erlang Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-erl)
+- [GreptimeDB Rust Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-rust)
+- [GreptimeDB JavaScript Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-js)
 
 ### Grafana Dashboard
 
-Our official Grafana dashboard is available at [grafana](./grafana/README.md) directory.
+Our official Grafana dashboard is available at [grafana](grafana/README.md) directory.
 
 ## Project Status
 
-This project is in its early stage and under heavy development. We move fast and
-break things. Benchmark on development branch may not represent its potential
-performance. We release pre-built binaries constantly for functional
-evaluation. Do not use it in production at the moment.
-
-For future plans, check out [GreptimeDB roadmap](https://github.com/GreptimeTeam/greptimedb/issues/669).
+The current version has not yet reached General Availability version standards.
+In line with our Greptime 2024 Roadmap, we plan to achieve a production-level
+version with the update to v1.0 in August. [[Join Force]](https://github.com/GreptimeTeam/greptimedb/issues/3412)
 
 ## Community
 
@@ -154,12 +163,12 @@ and what went wrong. If you have any questions or if you would like to get invol
 community, please check out:
 
 - GreptimeDB Community on [Slack](https://greptime.com/slack)
-- GreptimeDB GitHub [Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
-- Greptime official [Website](https://greptime.com)
+- GreptimeDB [GitHub Discussions forum](https://github.com/GreptimeTeam/greptimedb/discussions)
+- Greptime official [website](https://greptime.com)
 
 In addition, you may:
 
-- View our official [Blog](https://greptime.com/blogs/index)
+- View our official [Blog](https://greptime.com/blogs/)
 - Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
 - Follow us on [Twitter](https://twitter.com/greptime)
 
@@ -170,7 +179,7 @@ open contributions and allowing you to use the software however you want.
 
 ## Contributing
 
-Please refer to [contribution guidelines](CONTRIBUTING.md) for more information.
+Please refer to [contribution guidelines](CONTRIBUTING.md) and [internal concepts docs](https://docs.greptime.com/contributor-guide/overview.html) for more information.
 
 ## Acknowledgement
 

benchmarks/Cargo.toml

@@ -4,13 +4,37 @@ version.workspace = true
 edition.workspace = true
 license.workspace = true
 
+[lints]
+workspace = true
+
 [dependencies]
+api.workspace = true
 arrow.workspace = true
 chrono.workspace = true
 clap.workspace = true
 client.workspace = true
+common-base.workspace = true
+common-telemetry.workspace = true
+common-wal.workspace = true
+dotenv.workspace = true
+futures.workspace = true
 futures-util.workspace = true
+humantime.workspace = true
+humantime-serde.workspace = true
 indicatif = "0.17.1"
 itertools.workspace = true
+lazy_static.workspace = true
+log-store.workspace = true
+mito2.workspace = true
+num_cpus.workspace = true
 parquet.workspace = true
+prometheus.workspace = true
+rand.workspace = true
+rskafka.workspace = true
+serde.workspace = true
+store-api.workspace = true
+# TODO depend `Database` client
+tests-integration.workspace = true
 tokio.workspace = true
+toml.workspace = true
+uuid.workspace = true

benchmarks/README.md

@@ -0,0 +1,11 @@
+Benchmarkers for GreptimeDB
+--------------------------------
+
+## Wal Benchmarker
+The wal benchmarker serves to evaluate the performance of GreptimeDB's Write-Ahead Log (WAL) component. It meticulously assesses the read/write performance of the WAL under diverse workloads generated by the benchmarker. 
+
+
+### How to use
+To compile the benchmarker, navigate to the `greptimedb/benchmarks` directory and execute `cargo build --release`. Subsequently, you'll find the compiled target located at `greptimedb/target/release/wal_bench`.
+
+The `./wal_bench -h` command reveals numerous arguments that the target accepts. Among these, a notable one is the `cfg-file` argument. By utilizing a configuration file in the TOML format, you can bypass the need to repeatedly specify cumbersome arguments.

benchmarks/config/wal_bench.example.toml

@@ -0,0 +1,21 @@
+# Refers to the documents of `Args` in benchmarks/src/wal.rs`.
+wal_provider = "kafka"
+bootstrap_brokers = ["localhost:9092"]
+num_workers = 10
+num_topics = 32
+num_regions = 1000
+num_scrapes = 1000
+num_rows = 5
+col_types = "ifs"
+max_batch_size = "512KB"
+linger = "1ms"
+backoff_init = "10ms"
+backoff_max = "1ms"
+backoff_base = 2
+backoff_deadline = "3s"
+compression = "zstd"
+rng_seed = 42
+skip_read = false
+skip_write = false
+random_topics = true
+report_metrics = false

benchmarks/src/bin/nyc-taxi.rs

@@ -1,543 +0,0 @@
-// Copyright 2023 Greptime Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-//! Use the taxi trip records from New York City dataset to bench. You can download the dataset from
-//! [here](https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page).
-
-#![allow(clippy::print_stdout)]
-
-use std::collections::HashMap;
-use std::path::{Path, PathBuf};
-use std::time::Instant;
-
-use arrow::array::{ArrayRef, PrimitiveArray, StringArray, TimestampMicrosecondArray};
-use arrow::datatypes::{DataType, Float64Type, Int64Type};
-use arrow::record_batch::RecordBatch;
-use clap::Parser;
-use client::api::v1::column::Values;
-use client::api::v1::{
-    Column, ColumnDataType, ColumnDef, CreateTableExpr, InsertRequest, InsertRequests, SemanticType,
-};
-use client::{Client, Database, Output, DEFAULT_CATALOG_NAME, DEFAULT_SCHEMA_NAME};
-use futures_util::TryStreamExt;
-use indicatif::{MultiProgress, ProgressBar, ProgressStyle};
-use parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder;
-use tokio::task::JoinSet;
-
-const CATALOG_NAME: &str = "greptime";
-const SCHEMA_NAME: &str = "public";
-
-#[derive(Parser)]
-#[command(name = "NYC benchmark runner")]
-struct Args {
-    /// Path to the dataset
-    #[arg(short, long)]
-    path: Option<String>,
-
-    /// Batch size of insert request.
-    #[arg(short = 's', long = "batch-size", default_value_t = 4096)]
-    batch_size: usize,
-
-    /// Number of client threads on write (parallel on file level)
-    #[arg(short = 't', long = "thread-num", default_value_t = 4)]
-    thread_num: usize,
-
-    /// Number of query iteration
-    #[arg(short = 'i', long = "iter-num", default_value_t = 3)]
-    iter_num: usize,
-
-    #[arg(long = "skip-write")]
-    skip_write: bool,
-
-    #[arg(long = "skip-read")]
-    skip_read: bool,
-
-    #[arg(short, long, default_value_t = String::from("127.0.0.1:4001"))]
-    endpoint: String,
-}
-
-fn get_file_list<P: AsRef<Path>>(path: P) -> Vec<PathBuf> {
-    std::fs::read_dir(path)
-        .unwrap()
-        .map(|dir| dir.unwrap().path().canonicalize().unwrap())
-        .collect()
-}
-
-fn new_table_name() -> String {
-    format!("nyc_taxi_{}", chrono::Utc::now().timestamp())
-}
-
-async fn write_data(
-    table_name: &str,
-    batch_size: usize,
-    db: &Database,
-    path: PathBuf,
-    mpb: MultiProgress,
-    pb_style: ProgressStyle,
-) -> u128 {
-    let file = std::fs::File::open(&path).unwrap();
-    let record_batch_reader_builder = ParquetRecordBatchReaderBuilder::try_new(file).unwrap();
-    let row_num = record_batch_reader_builder
-        .metadata()
-        .file_metadata()
-        .num_rows();
-    let record_batch_reader = record_batch_reader_builder
-        .with_batch_size(batch_size)
-        .build()
-        .unwrap();
-    let progress_bar = mpb.add(ProgressBar::new(row_num as _));
-    progress_bar.set_style(pb_style);
-    progress_bar.set_message(format!("{path:?}"));
-
-    let mut total_rpc_elapsed_ms = 0;
-
-    for record_batch in record_batch_reader {
-        let record_batch = record_batch.unwrap();
-        if !is_record_batch_full(&record_batch) {
-            continue;
-        }
-        let (columns, row_count) = convert_record_batch(record_batch);
-        let request = InsertRequest {
-            table_name: table_name.to_string(),
-            columns,
-            row_count,
-        };
-        let requests = InsertRequests {
-            inserts: vec![request],
-        };
-
-        let now = Instant::now();
-        db.insert(requests).await.unwrap();
-        let elapsed = now.elapsed();
-        total_rpc_elapsed_ms += elapsed.as_millis();
-        progress_bar.inc(row_count as _);
-    }
-
-    progress_bar.finish_with_message(format!("file {path:?} done in {total_rpc_elapsed_ms}ms",));
-    total_rpc_elapsed_ms
-}
-
-fn convert_record_batch(record_batch: RecordBatch) -> (Vec<Column>, u32) {
-    let schema = record_batch.schema();
-    let fields = schema.fields();
-    let row_count = record_batch.num_rows();
-    let mut columns = vec![];
-
-    for (array, field) in record_batch.columns().iter().zip(fields.iter()) {
-        let (values, datatype) = build_values(array);
-        let semantic_type = match field.name().as_str() {
-            "VendorID" => SemanticType::Tag,
-            "tpep_pickup_datetime" => SemanticType::Timestamp,
-            _ => SemanticType::Field,
-        };
-
-        let column = Column {
-            column_name: field.name().clone(),
-            values: Some(values),
-            null_mask: array
-                .to_data()
-                .nulls()
-                .map(|bitmap| bitmap.buffer().as_slice().to_vec())
-                .unwrap_or_default(),
-            datatype: datatype.into(),
-            semantic_type: semantic_type as i32,
-            ..Default::default()
-        };
-        columns.push(column);
-    }
-
-    (columns, row_count as _)
-}
-
-fn build_values(column: &ArrayRef) -> (Values, ColumnDataType) {
-    match column.data_type() {
-        DataType::Int64 => {
-            let array = column
-                .as_any()
-                .downcast_ref::<PrimitiveArray<Int64Type>>()
-                .unwrap();
-            let values = array.values();
-            (
-                Values {
-                    i64_values: values.to_vec(),
-                    ..Default::default()
-                },
-                ColumnDataType::Int64,
-            )
-        }
-        DataType::Float64 => {
-            let array = column
-                .as_any()
-                .downcast_ref::<PrimitiveArray<Float64Type>>()
-                .unwrap();
-            let values = array.values();
-            (
-                Values {
-                    f64_values: values.to_vec(),
-                    ..Default::default()
-                },
-                ColumnDataType::Float64,
-            )
-        }
-        DataType::Timestamp(_, _) => {
-            let array = column
-                .as_any()
-                .downcast_ref::<TimestampMicrosecondArray>()
-                .unwrap();
-            let values = array.values();
-            (
-                Values {
-                    timestamp_microsecond_values: values.to_vec(),
-                    ..Default::default()
-                },
-                ColumnDataType::TimestampMicrosecond,
-            )
-        }
-        DataType::Utf8 => {
-            let array = column.as_any().downcast_ref::<StringArray>().unwrap();
-            let values = array.iter().filter_map(|s| s.map(String::from)).collect();
-            (
-                Values {
-                    string_values: values,
-                    ..Default::default()
-                },
-                ColumnDataType::String,
-            )
-        }
-        DataType::Null
-        | DataType::Boolean
-        | DataType::Int8
-        | DataType::Int16
-        | DataType::Int32
-        | DataType::UInt8
-        | DataType::UInt16
-        | DataType::UInt32
-        | DataType::UInt64
-        | DataType::Float16
-        | DataType::Float32
-        | DataType::Date32
-        | DataType::Date64
-        | DataType::Time32(_)
-        | DataType::Time64(_)
-        | DataType::Duration(_)
-        | DataType::Interval(_)
-        | DataType::Binary
-        | DataType::FixedSizeBinary(_)
-        | DataType::LargeBinary
-        | DataType::LargeUtf8
-        | DataType::List(_)
-        | DataType::FixedSizeList(_, _)
-        | DataType::LargeList(_)
-        | DataType::Struct(_)
-        | DataType::Union(_, _)
-        | DataType::Dictionary(_, _)
-        | DataType::Decimal128(_, _)
-        | DataType::Decimal256(_, _)
-        | DataType::RunEndEncoded(_, _)
-        | DataType::Map(_, _) => todo!(),
-    }
-}
-
-fn is_record_batch_full(batch: &RecordBatch) -> bool {
-    batch.columns().iter().all(|col| col.null_count() == 0)
-}
-
-fn create_table_expr(table_name: &str) -> CreateTableExpr {
-    CreateTableExpr {
-        catalog_name: CATALOG_NAME.to_string(),
-        schema_name: SCHEMA_NAME.to_string(),
-        table_name: table_name.to_string(),
-        desc: String::default(),
-        column_defs: vec![
-            ColumnDef {
-                name: "VendorID".to_string(),
-                data_type: ColumnDataType::Int64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Tag as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "tpep_pickup_datetime".to_string(),
-                data_type: ColumnDataType::TimestampMicrosecond as i32,
-                is_nullable: false,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Timestamp as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "tpep_dropoff_datetime".to_string(),
-                data_type: ColumnDataType::TimestampMicrosecond as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "passenger_count".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "trip_distance".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "RatecodeID".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "store_and_fwd_flag".to_string(),
-                data_type: ColumnDataType::String as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "PULocationID".to_string(),
-                data_type: ColumnDataType::Int64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "DOLocationID".to_string(),
-                data_type: ColumnDataType::Int64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "payment_type".to_string(),
-                data_type: ColumnDataType::Int64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "fare_amount".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "extra".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "mta_tax".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "tip_amount".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "tolls_amount".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "improvement_surcharge".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "total_amount".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "congestion_surcharge".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-            ColumnDef {
-                name: "airport_fee".to_string(),
-                data_type: ColumnDataType::Float64 as i32,
-                is_nullable: true,
-                default_constraint: vec![],
-                semantic_type: SemanticType::Field as i32,
-                comment: String::new(),
-                ..Default::default()
-            },
-        ],
-        time_index: "tpep_pickup_datetime".to_string(),
-        primary_keys: vec!["VendorID".to_string()],
-        create_if_not_exists: true,
-        table_options: Default::default(),
-        table_id: None,
-        engine: "mito".to_string(),
-    }
-}
-
-fn query_set(table_name: &str) -> HashMap<String, String> {
-    HashMap::from([
-        (
-            "count_all".to_string(), 
-            format!("SELECT COUNT(*) FROM {table_name};"),
-        ),
-        (
-            "fare_amt_by_passenger".to_string(),
-            format!("SELECT passenger_count, MIN(fare_amount), MAX(fare_amount), SUM(fare_amount) FROM {table_name} GROUP BY passenger_count"),
-        )
-    ])
-}
-
-async fn do_write(args: &Args, db: &Database, table_name: &str) {
-    let mut file_list = get_file_list(args.path.clone().expect("Specify data path in argument"));
-    let mut write_jobs = JoinSet::new();
-
-    let create_table_result = db.create(create_table_expr(table_name)).await;
-    println!("Create table result: {create_table_result:?}");
-
-    let progress_bar_style = ProgressStyle::with_template(
-        "[{elapsed_precise}] {bar:60.cyan/blue} {pos:>7}/{len:7} {msg}",
-    )
-    .unwrap()
-    .progress_chars("##-");
-    let multi_progress_bar = MultiProgress::new();
-    let file_progress = multi_progress_bar.add(ProgressBar::new(file_list.len() as _));
-    file_progress.inc(0);
-
-    let batch_size = args.batch_size;
-    for _ in 0..args.thread_num {
-        if let Some(path) = file_list.pop() {
-            let db = db.clone();
-            let mpb = multi_progress_bar.clone();
-            let pb_style = progress_bar_style.clone();
-            let table_name = table_name.to_string();
-            let _ = write_jobs.spawn(async move {
-                write_data(&table_name, batch_size, &db, path, mpb, pb_style).await
-            });
-        }
-    }
-    while write_jobs.join_next().await.is_some() {
-        file_progress.inc(1);
-        if let Some(path) = file_list.pop() {
-            let db = db.clone();
-            let mpb = multi_progress_bar.clone();
-            let pb_style = progress_bar_style.clone();
-            let table_name = table_name.to_string();
-            let _ = write_jobs.spawn(async move {
-                write_data(&table_name, batch_size, &db, path, mpb, pb_style).await
-            });
-        }
-    }
-}
-
-async fn do_query(num_iter: usize, db: &Database, table_name: &str) {
-    for (query_name, query) in query_set(table_name) {
-        println!("Running query: {query}");
-        for i in 0..num_iter {
-            let now = Instant::now();
-            let res = db.sql(&query).await.unwrap();
-            match res {
-                Output::AffectedRows(_) | Output::RecordBatches(_) => (),
-                Output::Stream(stream) => {
-                    stream.try_collect::<Vec<_>>().await.unwrap();
-                }
-            }
-            let elapsed = now.elapsed();
-            println!(
-                "query {}, iteration {}: {}ms",
-                query_name,
-                i,
-                elapsed.as_millis(),
-            );
-        }
-    }
-}
-
-fn main() {
-    let args = Args::parse();
-
-    tokio::runtime::Builder::new_multi_thread()
-        .worker_threads(args.thread_num)
-        .enable_all()
-        .build()
-        .unwrap()
-        .block_on(async {
-            let client = Client::with_urls(vec![&args.endpoint]);
-            let db = Database::new(DEFAULT_CATALOG_NAME, DEFAULT_SCHEMA_NAME, client);
-            let table_name = new_table_name();
-
-            if !args.skip_write {
-                do_write(&args, &db, &table_name).await;
-            }
-
-            if !args.skip_read {
-                do_query(args.iter_num, &db, &table_name).await;
-            }
-        })
-}

benchmarks/src/bin/wal_bench.rs

@@ -0,0 +1,326 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+#![feature(int_roundings)]
+
+use std::fs;
+use std::sync::Arc;
+use std::time::Instant;
+
+use api::v1::{ColumnDataType, ColumnSchema, SemanticType};
+use benchmarks::metrics;
+use benchmarks::wal_bench::{Args, Config, Region, WalProvider};
+use clap::Parser;
+use common_telemetry::info;
+use common_wal::config::kafka::common::BackoffConfig;
+use common_wal::config::kafka::DatanodeKafkaConfig as KafkaConfig;
+use common_wal::config::raft_engine::RaftEngineConfig;
+use common_wal::options::{KafkaWalOptions, WalOptions};
+use itertools::Itertools;
+use log_store::kafka::log_store::KafkaLogStore;
+use log_store::raft_engine::log_store::RaftEngineLogStore;
+use mito2::wal::Wal;
+use prometheus::{Encoder, TextEncoder};
+use rand::distributions::{Alphanumeric, DistString};
+use rand::rngs::SmallRng;
+use rand::SeedableRng;
+use rskafka::client::partition::Compression;
+use rskafka::client::ClientBuilder;
+use store_api::logstore::LogStore;
+use store_api::storage::RegionId;
+
+async fn run_benchmarker<S: LogStore>(cfg: &Config, topics: &[String], wal: Arc<Wal<S>>) {
+    let chunk_size = cfg.num_regions.div_ceil(cfg.num_workers);
+    let region_chunks = (0..cfg.num_regions)
+        .map(|id| {
+            build_region(
+                id as u64,
+                topics,
+                &mut SmallRng::seed_from_u64(cfg.rng_seed),
+                cfg,
+            )
+        })
+        .chunks(chunk_size as usize)
+        .into_iter()
+        .map(|chunk| Arc::new(chunk.collect::<Vec<_>>()))
+        .collect::<Vec<_>>();
+
+    let mut write_elapsed = 0;
+    let mut read_elapsed = 0;
+
+    if !cfg.skip_write {
+        info!("Benchmarking write ...");
+
+        let num_scrapes = cfg.num_scrapes;
+        let timer = Instant::now();
+        futures::future::join_all((0..cfg.num_workers).map(|i| {
+            let wal = wal.clone();
+            let regions = region_chunks[i as usize].clone();
+            tokio::spawn(async move {
+                for _ in 0..num_scrapes {
+                    let mut wal_writer = wal.writer();
+                    regions
+                        .iter()
+                        .for_each(|region| region.add_wal_entry(&mut wal_writer));
+                    wal_writer.write_to_wal().await.unwrap();
+                }
+            })
+        }))
+        .await;
+        write_elapsed += timer.elapsed().as_millis();
+    }
+
+    if !cfg.skip_read {
+        info!("Benchmarking read ...");
+
+        let timer = Instant::now();
+        futures::future::join_all((0..cfg.num_workers).map(|i| {
+            let wal = wal.clone();
+            let regions = region_chunks[i as usize].clone();
+            tokio::spawn(async move {
+                for region in regions.iter() {
+                    region.replay(&wal).await;
+                }
+            })
+        }))
+        .await;
+        read_elapsed = timer.elapsed().as_millis();
+    }
+
+    dump_report(cfg, write_elapsed, read_elapsed);
+}
+
+fn build_region(id: u64, topics: &[String], rng: &mut SmallRng, cfg: &Config) -> Region {
+    let wal_options = match cfg.wal_provider {
+        WalProvider::Kafka => {
+            assert!(!topics.is_empty());
+            WalOptions::Kafka(KafkaWalOptions {
+                topic: topics.get(id as usize % topics.len()).cloned().unwrap(),
+            })
+        }
+        WalProvider::RaftEngine => WalOptions::RaftEngine,
+    };
+    Region::new(
+        RegionId::from_u64(id),
+        build_schema(&parse_col_types(&cfg.col_types), rng),
+        wal_options,
+        cfg.num_rows,
+        cfg.rng_seed,
+    )
+}
+
+fn build_schema(col_types: &[ColumnDataType], mut rng: &mut SmallRng) -> Vec<ColumnSchema> {
+    col_types
+        .iter()
+        .map(|col_type| ColumnSchema {
+            column_name: Alphanumeric.sample_string(&mut rng, 5),
+            datatype: *col_type as i32,
+            semantic_type: SemanticType::Field as i32,
+            datatype_extension: None,
+        })
+        .chain(vec![ColumnSchema {
+            column_name: "ts".to_string(),
+            datatype: ColumnDataType::TimestampMillisecond as i32,
+            semantic_type: SemanticType::Tag as i32,
+            datatype_extension: None,
+        }])
+        .collect()
+}
+
+fn dump_report(cfg: &Config, write_elapsed: u128, read_elapsed: u128) {
+    let cost_report = format!(
+        "write costs: {} ms, read costs: {} ms",
+        write_elapsed, read_elapsed,
+    );
+
+    let total_written_bytes = metrics::METRIC_WAL_WRITE_BYTES_TOTAL.get() as u128;
+    let write_throughput = if write_elapsed > 0 {
+        (total_written_bytes * 1000).div_floor(write_elapsed)
+    } else {
+        0
+    };
+    let total_read_bytes = metrics::METRIC_WAL_READ_BYTES_TOTAL.get() as u128;
+    let read_throughput = if read_elapsed > 0 {
+        (total_read_bytes * 1000).div_floor(read_elapsed)
+    } else {
+        0
+    };
+
+    let throughput_report = format!(
+        "total written bytes: {} bytes, total read bytes: {} bytes, write throuput: {} bytes/s ({} mb/s), read throughput: {} bytes/s ({} mb/s)",
+        total_written_bytes,
+        total_read_bytes,
+        write_throughput,
+        write_throughput.div_floor(1 << 20),
+        read_throughput,
+        read_throughput.div_floor(1 << 20),
+    );
+
+    let metrics_report = if cfg.report_metrics {
+        let mut buffer = Vec::new();
+        let encoder = TextEncoder::new();
+        let metrics = prometheus::gather();
+        encoder.encode(&metrics, &mut buffer).unwrap();
+        String::from_utf8(buffer).unwrap()
+    } else {
+        String::new()
+    };
+
+    info!(
+        r#"
+Benchmark config: 
+{cfg:?}
+
+Benchmark report:
+{cost_report}
+{throughput_report}
+{metrics_report}"#
+    );
+}
+
+async fn create_topics(cfg: &Config) -> Vec<String> {
+    // Creates topics.
+    let client = ClientBuilder::new(cfg.bootstrap_brokers.clone())
+        .build()
+        .await
+        .unwrap();
+    let ctrl_client = client.controller_client().unwrap();
+    let (topics, tasks): (Vec<_>, Vec<_>) = (0..cfg.num_topics)
+        .map(|i| {
+            let topic = if cfg.random_topics {
+                format!(
+                    "greptime_wal_bench_topic_{}_{}",
+                    uuid::Uuid::new_v4().as_u128(),
+                    i
+                )
+            } else {
+                format!("greptime_wal_bench_topic_{}", i)
+            };
+            let task = ctrl_client.create_topic(
+                topic.clone(),
+                1,
+                cfg.bootstrap_brokers.len() as i16,
+                2000,
+            );
+            (topic, task)
+        })
+        .unzip();
+    // Must ignore errors since we allow topics being created more than once.
+    let _ = futures::future::try_join_all(tasks).await;
+
+    topics
+}
+
+fn parse_compression(comp: &str) -> Compression {
+    match comp {
+        "no" => Compression::NoCompression,
+        "gzip" => Compression::Gzip,
+        "lz4" => Compression::Lz4,
+        "snappy" => Compression::Snappy,
+        "zstd" => Compression::Zstd,
+        other => unreachable!("Unrecognized compression {other}"),
+    }
+}
+
+fn parse_col_types(col_types: &str) -> Vec<ColumnDataType> {
+    let parts = col_types.split('x').collect::<Vec<_>>();
+    assert!(parts.len() <= 2);
+
+    let pattern = parts[0];
+    let repeat = parts
+        .get(1)
+        .map(|r| r.parse::<usize>().unwrap())
+        .unwrap_or(1);
+
+    pattern
+        .chars()
+        .map(|c| match c {
+            'i' | 'I' => ColumnDataType::Int64,
+            'f' | 'F' => ColumnDataType::Float64,
+            's' | 'S' => ColumnDataType::String,
+            other => unreachable!("Cannot parse {other} as a column data type"),
+        })
+        .cycle()
+        .take(pattern.len() * repeat)
+        .collect()
+}
+
+fn main() {
+    // Sets the global logging to INFO and suppress loggings from rskafka other than ERROR and upper ones.
+    std::env::set_var("UNITTEST_LOG_LEVEL", "info,rskafka=error");
+    common_telemetry::init_default_ut_logging();
+
+    let args = Args::parse();
+    let cfg = if !args.cfg_file.is_empty() {
+        toml::from_str(&fs::read_to_string(&args.cfg_file).unwrap()).unwrap()
+    } else {
+        Config::from(args)
+    };
+
+    // Validates arguments.
+    if cfg.num_regions < cfg.num_workers {
+        panic!("num_regions must be greater than or equal to num_workers");
+    }
+    if cfg
+        .num_workers
+        .min(cfg.num_topics)
+        .min(cfg.num_regions)
+        .min(cfg.num_scrapes)
+        .min(cfg.max_batch_size.as_bytes() as u32)
+        .min(cfg.bootstrap_brokers.len() as u32)
+        == 0
+    {
+        panic!("Invalid arguments");
+    }
+
+    tokio::runtime::Builder::new_multi_thread()
+        .enable_all()
+        .build()
+        .unwrap()
+        .block_on(async {
+            match cfg.wal_provider {
+                WalProvider::Kafka => {
+                    let topics = create_topics(&cfg).await;
+                    let kafka_cfg = KafkaConfig {
+                        broker_endpoints: cfg.bootstrap_brokers.clone(),
+                        max_batch_size: cfg.max_batch_size,
+                        linger: cfg.linger,
+                        backoff: BackoffConfig {
+                            init: cfg.backoff_init,
+                            max: cfg.backoff_max,
+                            base: cfg.backoff_base,
+                            deadline: Some(cfg.backoff_deadline),
+                        },
+                        compression: parse_compression(&cfg.compression),
+                        ..Default::default()
+                    };
+                    let store = Arc::new(KafkaLogStore::try_new(&kafka_cfg).await.unwrap());
+                    let wal = Arc::new(Wal::new(store));
+                    run_benchmarker(&cfg, &topics, wal).await;
+                }
+                WalProvider::RaftEngine => {
+                    // The benchmarker assumes the raft engine directory exists.
+                    let store = RaftEngineLogStore::try_new(
+                        "/tmp/greptimedb/raft-engine-wal".to_string(),
+                        RaftEngineConfig::default(),
+                    )
+                    .await
+                    .map(Arc::new)
+                    .unwrap();
+                    let wal = Arc::new(Wal::new(store));
+                    run_benchmarker(&cfg, &[], wal).await;
+                }
+            }
+        });
+}

benchmarks/src/lib.rs

@@ -0,0 +1,16 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+pub mod metrics;
+pub mod wal_bench;

benchmarks/src/metrics.rs

@@ -0,0 +1,39 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use lazy_static::lazy_static;
+use prometheus::*;
+
+/// Logstore label.
+pub const LOGSTORE_LABEL: &str = "logstore";
+/// Operation type label.
+pub const OPTYPE_LABEL: &str = "optype";
+
+lazy_static! {
+    /// Counters of bytes of each operation on a logstore.
+    pub static ref METRIC_WAL_OP_BYTES_TOTAL: IntCounterVec = register_int_counter_vec!(
+        "greptime_bench_wal_op_bytes_total",
+        "wal operation bytes total",
+        &[OPTYPE_LABEL],
+    )
+    .unwrap();
+    /// Counter of bytes of the append_batch operation.
+    pub static ref METRIC_WAL_WRITE_BYTES_TOTAL: IntCounter = METRIC_WAL_OP_BYTES_TOTAL.with_label_values(
+        &["write"],
+    );
+    /// Counter of bytes of the read operation.
+    pub static ref METRIC_WAL_READ_BYTES_TOTAL: IntCounter = METRIC_WAL_OP_BYTES_TOTAL.with_label_values(
+        &["read"],
+    );
+}

benchmarks/src/wal_bench.rs

@@ -0,0 +1,361 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::mem::size_of;
+use std::sync::atomic::{AtomicI64, AtomicU64, Ordering};
+use std::sync::{Arc, Mutex};
+use std::time::Duration;
+
+use api::v1::value::ValueData;
+use api::v1::{ColumnDataType, ColumnSchema, Mutation, OpType, Row, Rows, Value, WalEntry};
+use clap::{Parser, ValueEnum};
+use common_base::readable_size::ReadableSize;
+use common_wal::options::WalOptions;
+use futures::StreamExt;
+use mito2::wal::{Wal, WalWriter};
+use rand::distributions::{Alphanumeric, DistString, Uniform};
+use rand::rngs::SmallRng;
+use rand::{Rng, SeedableRng};
+use serde::{Deserialize, Serialize};
+use store_api::logstore::LogStore;
+use store_api::storage::RegionId;
+
+use crate::metrics;
+
+/// The wal provider.
+#[derive(Clone, ValueEnum, Default, Debug, PartialEq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum WalProvider {
+    #[default]
+    RaftEngine,
+    Kafka,
+}
+
+#[derive(Parser)]
+pub struct Args {
+    /// The provided configuration file.
+    /// The example configuration file can be found at `greptimedb/benchmarks/config/wal_bench.example.toml`.
+    #[clap(long, short = 'c')]
+    pub cfg_file: String,
+
+    /// The wal provider.
+    #[clap(long, value_enum, default_value_t = WalProvider::default())]
+    pub wal_provider: WalProvider,
+
+    /// The advertised addresses of the kafka brokers.
+    /// If there're multiple bootstrap brokers, their addresses should be separated by comma, for e.g. "localhost:9092,localhost:9093".
+    #[clap(long, short = 'b', default_value = "localhost:9092")]
+    pub bootstrap_brokers: String,
+
+    /// The number of workers each running in a dedicated thread.
+    #[clap(long, default_value_t = num_cpus::get() as u32)]
+    pub num_workers: u32,
+
+    /// The number of kafka topics to be created.
+    #[clap(long, default_value_t = 32)]
+    pub num_topics: u32,
+
+    /// The number of regions.
+    #[clap(long, default_value_t = 1000)]
+    pub num_regions: u32,
+
+    /// The number of times each region is scraped.
+    #[clap(long, default_value_t = 1000)]
+    pub num_scrapes: u32,
+
+    /// The number of rows in each wal entry.
+    /// Each time a region is scraped, a wal entry containing will be produced.
+    #[clap(long, default_value_t = 5)]
+    pub num_rows: u32,
+
+    /// The column types of the schema for each region.
+    /// Currently, three column types are supported:
+    /// - i = ColumnDataType::Int64
+    /// - f = ColumnDataType::Float64
+    /// - s = ColumnDataType::String  
+    /// For e.g., "ifs" will be parsed as three columns: i64, f64, and string.
+    ///
+    /// Additionally, a "x" sign can be provided to repeat the column types for a given number of times.
+    /// For e.g., "iix2" will be parsed as 4 columns: i64, i64, i64, and i64.
+    /// This feature is useful if you want to specify many columns.
+    #[clap(long, default_value = "ifs")]
+    pub col_types: String,
+
+    /// The maximum size of a batch of kafka records.
+    /// The default value is 1mb.
+    #[clap(long, default_value = "512KB")]
+    pub max_batch_size: ReadableSize,
+
+    /// The minimum latency the kafka client issues a batch of kafka records.
+    /// However, a batch of kafka records would be immediately issued if a record cannot be fit into the batch.
+    #[clap(long, default_value = "1ms")]
+    pub linger: String,
+
+    /// The initial backoff delay of the kafka consumer.
+    #[clap(long, default_value = "10ms")]
+    pub backoff_init: String,
+
+    /// The maximum backoff delay of the kafka consumer.
+    #[clap(long, default_value = "1s")]
+    pub backoff_max: String,
+
+    /// The exponential backoff rate of the kafka consumer. The next back off = base * the current backoff.
+    #[clap(long, default_value_t = 2)]
+    pub backoff_base: u32,
+
+    /// The deadline of backoff. The backoff ends if the total backoff delay reaches the deadline.
+    #[clap(long, default_value = "3s")]
+    pub backoff_deadline: String,
+
+    /// The client-side compression algorithm for kafka records.
+    #[clap(long, default_value = "zstd")]
+    pub compression: String,
+
+    /// The seed of random number generators.
+    #[clap(long, default_value_t = 42)]
+    pub rng_seed: u64,
+
+    /// Skips the read phase, aka. region replay, if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_read: bool,
+
+    /// Skips the write phase if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_write: bool,
+
+    /// Randomly generates topic names if set to true.
+    /// Useful when you want to run the benchmarker without worrying about the topics created before.
+    #[clap(long, default_value_t = false)]
+    pub random_topics: bool,
+
+    /// Logs out the gathered prometheus metrics when the benchmarker ends.
+    #[clap(long, default_value_t = false)]
+    pub report_metrics: bool,
+}
+
+/// Benchmarker config.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Config {
+    pub wal_provider: WalProvider,
+    pub bootstrap_brokers: Vec<String>,
+    pub num_workers: u32,
+    pub num_topics: u32,
+    pub num_regions: u32,
+    pub num_scrapes: u32,
+    pub num_rows: u32,
+    pub col_types: String,
+    pub max_batch_size: ReadableSize,
+    #[serde(with = "humantime_serde")]
+    pub linger: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_init: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_max: Duration,
+    pub backoff_base: u32,
+    #[serde(with = "humantime_serde")]
+    pub backoff_deadline: Duration,
+    pub compression: String,
+    pub rng_seed: u64,
+    pub skip_read: bool,
+    pub skip_write: bool,
+    pub random_topics: bool,
+    pub report_metrics: bool,
+}
+
+impl From<Args> for Config {
+    fn from(args: Args) -> Self {
+        let cfg = Self {
+            wal_provider: args.wal_provider,
+            bootstrap_brokers: args
+                .bootstrap_brokers
+                .split(',')
+                .map(ToString::to_string)
+                .collect::<Vec<_>>(),
+            num_workers: args.num_workers.min(num_cpus::get() as u32),
+            num_topics: args.num_topics,
+            num_regions: args.num_regions,
+            num_scrapes: args.num_scrapes,
+            num_rows: args.num_rows,
+            col_types: args.col_types,
+            max_batch_size: args.max_batch_size,
+            linger: humantime::parse_duration(&args.linger).unwrap(),
+            backoff_init: humantime::parse_duration(&args.backoff_init).unwrap(),
+            backoff_max: humantime::parse_duration(&args.backoff_max).unwrap(),
+            backoff_base: args.backoff_base,
+            backoff_deadline: humantime::parse_duration(&args.backoff_deadline).unwrap(),
+            compression: args.compression,
+            rng_seed: args.rng_seed,
+            skip_read: args.skip_read,
+            skip_write: args.skip_write,
+            random_topics: args.random_topics,
+            report_metrics: args.report_metrics,
+        };
+
+        cfg
+    }
+}
+
+/// The region used for wal benchmarker.
+pub struct Region {
+    id: RegionId,
+    schema: Vec<ColumnSchema>,
+    wal_options: WalOptions,
+    next_sequence: AtomicU64,
+    next_entry_id: AtomicU64,
+    next_timestamp: AtomicI64,
+    rng: Mutex<Option<SmallRng>>,
+    num_rows: u32,
+}
+
+impl Region {
+    /// Creates a new region.
+    pub fn new(
+        id: RegionId,
+        schema: Vec<ColumnSchema>,
+        wal_options: WalOptions,
+        num_rows: u32,
+        rng_seed: u64,
+    ) -> Self {
+        Self {
+            id,
+            schema,
+            wal_options,
+            next_sequence: AtomicU64::new(1),
+            next_entry_id: AtomicU64::new(1),
+            next_timestamp: AtomicI64::new(1655276557000),
+            rng: Mutex::new(Some(SmallRng::seed_from_u64(rng_seed))),
+            num_rows,
+        }
+    }
+
+    /// Scrapes the region and adds the generated entry to wal.
+    pub fn add_wal_entry<S: LogStore>(&self, wal_writer: &mut WalWriter<S>) {
+        let mutation = Mutation {
+            op_type: OpType::Put as i32,
+            sequence: self
+                .next_sequence
+                .fetch_add(self.num_rows as u64, Ordering::Relaxed),
+            rows: Some(self.build_rows()),
+        };
+        let entry = WalEntry {
+            mutations: vec![mutation],
+        };
+        metrics::METRIC_WAL_WRITE_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+
+        wal_writer
+            .add_entry(
+                self.id,
+                self.next_entry_id.fetch_add(1, Ordering::Relaxed),
+                &entry,
+                &self.wal_options,
+            )
+            .unwrap();
+    }
+
+    /// Replays the region.
+    pub async fn replay<S: LogStore>(&self, wal: &Arc<Wal<S>>) {
+        let mut wal_stream = wal.scan(self.id, 0, &self.wal_options).unwrap();
+        while let Some(res) = wal_stream.next().await {
+            let (_, entry) = res.unwrap();
+            metrics::METRIC_WAL_READ_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+        }
+    }
+
+    /// Computes the estimated size in bytes of the entry.
+    pub fn entry_estimated_size(entry: &WalEntry) -> usize {
+        let wrapper_size = size_of::<WalEntry>()
+            + entry.mutations.capacity() * size_of::<Mutation>()
+            + size_of::<Rows>();
+
+        let rows = entry.mutations[0].rows.as_ref().unwrap();
+
+        let schema_size = rows.schema.capacity() * size_of::<ColumnSchema>()
+            + rows
+                .schema
+                .iter()
+                .map(|s| s.column_name.capacity())
+                .sum::<usize>();
+        let values_size = (rows.rows.capacity() * size_of::<Row>())
+            + rows
+                .rows
+                .iter()
+                .map(|r| r.values.capacity() * size_of::<Value>())
+                .sum::<usize>();
+
+        wrapper_size + schema_size + values_size
+    }
+
+    fn build_rows(&self) -> Rows {
+        let cols = self
+            .schema
+            .iter()
+            .map(|col_schema| {
+                let col_data_type = ColumnDataType::try_from(col_schema.datatype).unwrap();
+                self.build_col(&col_data_type, self.num_rows)
+            })
+            .collect::<Vec<_>>();
+
+        let rows = (0..self.num_rows)
+            .map(|i| {
+                let values = cols.iter().map(|col| col[i as usize].clone()).collect();
+                Row { values }
+            })
+            .collect();
+
+        Rows {
+            schema: self.schema.clone(),
+            rows,
+        }
+    }
+
+    fn build_col(&self, col_data_type: &ColumnDataType, num_rows: u32) -> Vec<Value> {
+        let mut rng_guard = self.rng.lock().unwrap();
+        let rng = rng_guard.as_mut().unwrap();
+        match col_data_type {
+            ColumnDataType::TimestampMillisecond => (0..num_rows)
+                .map(|_| {
+                    let ts = self.next_timestamp.fetch_add(1000, Ordering::Relaxed);
+                    Value {
+                        value_data: Some(ValueData::TimestampMillisecondValue(ts)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Int64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0, 10_000));
+                    Value {
+                        value_data: Some(ValueData::I64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Float64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0.0, 5000.0));
+                    Value {
+                        value_data: Some(ValueData::F64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::String => (0..num_rows)
+                .map(|_| {
+                    let v = Alphanumeric.sample_string(rng, 10);
+                    Value {
+                        value_data: Some(ValueData::StringValue(v)),
+                    }
+                })
+                .collect(),
+            _ => unreachable!(),
+        }
+    }
+}

cliff.toml

@@ -0,0 +1,127 @@
+# https://git-cliff.org/docs/configuration
+
+[remote.github]
+owner = "GreptimeTeam"
+repo = "greptimedb"
+
+[changelog]
+header = ""
+footer = ""
+# template for the changelog body
+# https://keats.github.io/tera/docs/#introduction
+body = """
+# {{ version }}
+
+Release date: {{ timestamp | date(format="%B %d, %Y") }}
+
+{%- set breakings = commits | filter(attribute="breaking", value=true) -%}
+{%- if breakings | length > 0 %}
+
+## Breaking changes
+    {% for commit in breakings %}
+      * {{ commit.github.pr_title }}\
+        {% if commit.github.username %} by \
+          {% set author = commit.github.username -%}
+          [@{{ author }}](https://github.com/{{ author }})
+        {%- endif -%}
+        {% if commit.github.pr_number %} in \
+          {% set number = commit.github.pr_number -%}
+          [#{{ number }}]({{ self::remote_url() }}/pull/{{ number }})
+        {%- endif %}
+    {%- endfor %}
+{%- endif -%}
+
+{%- set grouped_commits = commits | filter(attribute="breaking", value=false) | group_by(attribute="group") -%}
+{% for group, commits in grouped_commits %}
+
+    ### {{ group | striptags | trim | upper_first }}
+    {% for commit in commits %}
+        * {{ commit.github.pr_title }}\
+            {% if commit.github.username %} by \
+              {% set author = commit.github.username -%}
+              [@{{ author }}](https://github.com/{{ author }})
+            {%- endif -%}
+            {% if commit.github.pr_number %} in \
+              {% set number = commit.github.pr_number -%}
+              [#{{ number }}]({{ self::remote_url() }}/pull/{{ number }})
+            {%- endif %}
+    {%- endfor -%}
+{% endfor %}
+
+{%- if github.contributors | filter(attribute="is_first_time", value=true) | length != 0 %}
+  {% raw %}\n{% endraw -%}
+  ## New Contributors
+{% endif -%}
+{% for contributor in github.contributors | filter(attribute="is_first_time", value=true) %}
+  * [@{{ contributor.username }}](https://github.com/{{ contributor.username }}) made their first contribution
+    {%- if contributor.pr_number %} in \
+      [#{{ contributor.pr_number }}]({{ self::remote_url() }}/pull/{{ contributor.pr_number }}) \
+    {%- endif %}
+{%- endfor -%}
+
+{% if github.contributors | length != 0 %}
+  {% raw %}\n{% endraw -%}
+## All Contributors
+
+We would like to thank the following contributors from the GreptimeDB community:
+
+{%- set contributors = github.contributors | sort(attribute="username") | map(attribute="username") -%}
+{%- set bots = ['dependabot[bot]'] %}
+
+{% for contributor in contributors %}
+{%- if bots is containing(contributor) -%}{% continue %}{%- endif -%}
+{%- if loop.first -%}
+  [@{{ contributor }}](https://github.com/{{ contributor }})
+{%- else -%}
+  , [@{{ contributor }}](https://github.com/{{ contributor }})
+{%- endif -%}
+{%- endfor %}
+{%- endif %}
+{% raw %}\n{% endraw %}
+
+{%- macro remote_url() -%}
+  https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }}
+{%- endmacro -%}
+"""
+trim = true
+
+[git]
+# parse the commits based on https://www.conventionalcommits.org
+conventional_commits = true
+# filter out the commits that are not conventional
+filter_unconventional = true
+# process each line of a commit as an individual commit
+split_commits = false
+# regex for parsing and grouping commits
+commit_parsers = [
+  { message = "^feat", group = "<!-- 0 -->🚀 Features" },
+  { message = "^fix", group = "<!-- 1 -->🐛 Bug Fixes" },
+  { message = "^doc", group = "<!-- 3 -->📚 Documentation" },
+  { message = "^perf", group = "<!-- 4 -->⚡ Performance" },
+  { message = "^refactor", group = "<!-- 2 -->🚜 Refactor" },
+  { message = "^style", group = "<!-- 5 -->🎨 Styling" },
+  { message = "^test", group = "<!-- 6 -->🧪 Testing" },
+  { message = "^chore\\(release\\): prepare for", skip = true },
+  { message = "^chore\\(deps.*\\)", skip = true },
+  { message = "^chore\\(pr\\)", skip = true },
+  { message = "^chore\\(pull\\)", skip = true },
+  { message = "^chore|^ci", group = "<!-- 7 -->⚙️ Miscellaneous Tasks" },
+  { body = ".*security", group = "<!-- 8 -->🛡️ Security" },
+  { message = "^revert", group = "<!-- 9 -->◀️ Revert" },
+]
+# protect breaking changes from being skipped due to matching a skipping commit_parser
+protect_breaking_commits = false
+# filter out the commits that are not matched by commit parsers
+filter_commits = false
+# regex for matching git tags
+# tag_pattern = "v[0-9].*"
+# regex for skipping tags
+# skip_tags = ""
+# regex for ignoring tags
+ignore_tags = ".*-nightly-.*"
+# sort the tags topologically
+topo_order = false
+# sort the commits inside sections by oldest/newest order
+sort_commits = "oldest"
+# limit the number of commits included in the changelog.
+# limit_commits = 42

codecov.yml

@@ -8,5 +8,6 @@ coverage:
 ignore:
   - "**/error*.rs" # ignore all error.rs files
   - "tests/runner/*.rs" # ignore integration test runner
+  - "tests-integration/**/*.rs" # ignore integration tests
 comment:                  # this is a top-level key
   layout: "diff"

config/config-docs-template.md

@@ -0,0 +1,19 @@
+# Configurations
+
+## Standalone Mode
+
+{{ toml2docs "./standalone.example.toml" }}
+
+## Cluster Mode
+
+### Frontend
+
+{{ toml2docs "./frontend.example.toml" }}
+
+### Metasrv
+
+{{ toml2docs "./metasrv.example.toml" }}
+
+### Datanode
+
+{{ toml2docs "./datanode.example.toml" }}

config/config.md

@@ -0,0 +1,379 @@
+# Configurations
+
+## Standalone Mode
+
+| Key | Type | Default | Descriptions |
+| --- | -----| ------- | ----------- |
+| `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
+| `default_timezone` | String | `None` | The default timezone of the server. |
+| `http` | -- | -- | The HTTP server options. |
+| `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
+| `http.timeout` | String | `30s` | HTTP request timeout. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
+| `grpc` | -- | -- | The gRPC server options. |
+| `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
+| `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
+| `mysql` | -- | -- | MySQL server options. |
+| `mysql.enable` | Bool | `true` | Whether to enable. |
+| `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
+| `mysql.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `mysql.tls` | -- | -- | -- |
+| `mysql.tls.mode` | String | `disable` | TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html<br/>- `disable` (default value)<br/>- `prefer`<br/>- `require`<br/>- `verify-ca`<br/>- `verify-full` |
+| `mysql.tls.cert_path` | String | `None` | Certificate file path. |
+| `mysql.tls.key_path` | String | `None` | Private key file path. |
+| `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
+| `postgres` | -- | -- | PostgresSQL server options. |
+| `postgres.enable` | Bool | `true` | Whether to enable |
+| `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
+| `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql_options.tls` section. |
+| `postgres.tls.mode` | String | `disable` | TLS mode. |
+| `postgres.tls.cert_path` | String | `None` | Certificate file path. |
+| `postgres.tls.key_path` | String | `None` | Private key file path. |
+| `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
+| `opentsdb` | -- | -- | OpenTSDB protocol options. |
+| `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
+| `influxdb` | -- | -- | InfluxDB protocol options. |
+| `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
+| `prom_store` | -- | -- | Prometheus remote storage options |
+| `prom_store.enable` | Bool | `true` | Whether to enable Prometheus remote write and read in HTTP API. |
+| `prom_store.with_metric_engine` | Bool | `true` | Whether to store the data from Prometheus remote write in metric engine. |
+| `wal` | -- | -- | The WAL options. |
+| `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
+| `wal.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_base` | Integer | `2` | The exponential backoff rate, i.e. next backoff = base * current backoff.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_deadline` | String | `5mins` | The deadline of retries.<br/>**It's only used when the provider is `kafka`**. |
+| `metadata_store` | -- | -- | Metadata storage options. |
+| `metadata_store.file_size` | String | `256MB` | Kv file size in bytes. |
+| `metadata_store.purge_threshold` | String | `4GB` | Kv purge threshold. |
+| `procedure` | -- | -- | Procedure storage options. |
+| `procedure.max_retry_times` | Integer | `3` | Procedure max retry time. |
+| `procedure.retry_delay` | String | `500ms` | Initial retry delay of procedures, increases exponentially |
+| `storage` | -- | -- | The data storage options. |
+| `storage.data_home` | String | `/tmp/greptimedb/` | The working home directory. |
+| `storage.type` | String | `File` | The storage type used to store the data.<br/>- `File`: the data is stored in the local file system.<br/>- `S3`: the data is stored in the S3 object storage.<br/>- `Gcs`: the data is stored in the Google Cloud Storage.<br/>- `Azblob`: the data is stored in the Azure Blob Storage.<br/>- `Oss`: the data is stored in the Aliyun OSS. |
+| `storage.cache_path` | String | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
+| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
+| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
+| `storage.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
+| `storage.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
+| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.endpoint` | String | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.region` | String | `None` | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `[[region_engine]]` | -- | -- | The region engine options. You can configure multiple region engines. |
+| `region_engine.mito` | -- | -- | The Mito engine options. |
+| `region_engine.mito.num_workers` | Integer | `8` | Number of region workers. |
+| `region_engine.mito.worker_channel_size` | Integer | `128` | Request channel size of each worker. |
+| `region_engine.mito.worker_request_batch_size` | Integer | `64` | Max batch size for a worker to handle requests. |
+| `region_engine.mito.manifest_checkpoint_distance` | Integer | `10` | Number of meta action updated to trigger a new checkpoint for the manifest. |
+| `region_engine.mito.compress_manifest` | Bool | `false` | Whether to compress manifest and checkpoint file by gzip (default false). |
+| `region_engine.mito.max_background_jobs` | Integer | `4` | Max number of running background jobs |
+| `region_engine.mito.auto_flush_interval` | String | `1h` | Interval to auto flush a region if it has not flushed yet. |
+| `region_engine.mito.global_write_buffer_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
+| `region_engine.mito.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
+| `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
+| `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
+| `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
+| `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
+| `region_engine.mito.allow_stale_entries` | Bool | `false` | Whether to allow stale WAL entries read during replay. |
+| `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
+| `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `64M` | Memory threshold for performing an external sort during index creation.<br/>Setting to empty will disable external sorting, forcing all sorting operations to happen in memory. |
+| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`). |
+| `region_engine.mito.memtable` | -- | -- | -- |
+| `region_engine.mito.memtable.type` | String | `time_series` | Memtable type.<br/>- `time_series`: time-series memtable<br/>- `partition_tree`: partition tree memtable (experimental) |
+| `region_engine.mito.memtable.index_max_keys_per_shard` | Integer | `8192` | The max number of keys in one shard.<br/>Only available for `partition_tree` memtable. |
+| `region_engine.mito.memtable.data_freeze_threshold` | Integer | `32768` | The max rows of data inside the actively writing buffer in one shard.<br/>Only available for `partition_tree` memtable. |
+| `region_engine.mito.memtable.fork_dictionary_bytes` | String | `1GiB` | Max dictionary bytes.<br/>Only available for `partition_tree` memtable. |
+| `logging` | -- | -- | The logging options. |
+| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
+| `logging.otlp_endpoint` | String | `None` | The OTLP tracing endpoint. |
+| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
+| `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
+| `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
+| `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
+| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.remote_write` | -- | -- | -- |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
+| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+
+
+## Cluster Mode
+
+### Frontend
+
+| Key | Type | Default | Descriptions |
+| --- | -----| ------- | ----------- |
+| `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
+| `default_timezone` | String | `None` | The default timezone of the server. |
+| `heartbeat` | -- | -- | The heartbeat options. |
+| `heartbeat.interval` | String | `18s` | Interval for sending heartbeat messages to the metasrv. |
+| `heartbeat.retry_interval` | String | `3s` | Interval for retrying to send heartbeat messages to the metasrv. |
+| `http` | -- | -- | The HTTP server options. |
+| `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
+| `http.timeout` | String | `30s` | HTTP request timeout. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
+| `grpc` | -- | -- | The gRPC server options. |
+| `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
+| `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
+| `mysql` | -- | -- | MySQL server options. |
+| `mysql.enable` | Bool | `true` | Whether to enable. |
+| `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
+| `mysql.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `mysql.tls` | -- | -- | -- |
+| `mysql.tls.mode` | String | `disable` | TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html<br/>- `disable` (default value)<br/>- `prefer`<br/>- `require`<br/>- `verify-ca`<br/>- `verify-full` |
+| `mysql.tls.cert_path` | String | `None` | Certificate file path. |
+| `mysql.tls.key_path` | String | `None` | Private key file path. |
+| `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
+| `postgres` | -- | -- | PostgresSQL server options. |
+| `postgres.enable` | Bool | `true` | Whether to enable |
+| `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
+| `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql_options.tls` section. |
+| `postgres.tls.mode` | String | `disable` | TLS mode. |
+| `postgres.tls.cert_path` | String | `None` | Certificate file path. |
+| `postgres.tls.key_path` | String | `None` | Private key file path. |
+| `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
+| `opentsdb` | -- | -- | OpenTSDB protocol options. |
+| `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
+| `influxdb` | -- | -- | InfluxDB protocol options. |
+| `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
+| `prom_store` | -- | -- | Prometheus remote storage options |
+| `prom_store.enable` | Bool | `true` | Whether to enable Prometheus remote write and read in HTTP API. |
+| `prom_store.with_metric_engine` | Bool | `true` | Whether to store the data from Prometheus remote write in metric engine. |
+| `meta_client` | -- | -- | The metasrv client options. |
+| `meta_client.metasrv_addrs` | Array | -- | The addresses of the metasrv. |
+| `meta_client.timeout` | String | `3s` | Operation timeout. |
+| `meta_client.heartbeat_timeout` | String | `500ms` | Heartbeat timeout. |
+| `meta_client.ddl_timeout` | String | `10s` | DDL timeout. |
+| `meta_client.connect_timeout` | String | `1s` | Connect server timeout. |
+| `meta_client.tcp_nodelay` | Bool | `true` | `TCP_NODELAY` option for accepted connections. |
+| `meta_client.metadata_cache_max_capacity` | Integer | `100000` | The configuration about the cache of the metadata. |
+| `meta_client.metadata_cache_ttl` | String | `10m` | TTL of the metadata cache. |
+| `meta_client.metadata_cache_tti` | String | `5m` | -- |
+| `datanode` | -- | -- | Datanode options. |
+| `datanode.client` | -- | -- | Datanode client options. |
+| `datanode.client.connect_timeout` | String | `10s` | -- |
+| `datanode.client.tcp_nodelay` | Bool | `true` | -- |
+| `logging` | -- | -- | The logging options. |
+| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
+| `logging.otlp_endpoint` | String | `None` | The OTLP tracing endpoint. |
+| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
+| `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
+| `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
+| `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
+| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.remote_write` | -- | -- | -- |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
+| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+
+
+### Metasrv
+
+| Key | Type | Default | Descriptions |
+| --- | -----| ------- | ----------- |
+| `data_home` | String | `/tmp/metasrv/` | The working home directory. |
+| `bind_addr` | String | `127.0.0.1:3002` | The bind address of metasrv. |
+| `server_addr` | String | `127.0.0.1:3002` | The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost. |
+| `store_addr` | String | `127.0.0.1:2379` | Etcd server address. |
+| `selector` | String | `lease_based` | Datanode selector type.<br/>- `lease_based` (default value).<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
+| `use_memory_store` | Bool | `false` | Store data in memory. |
+| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. |
+| `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
+| `procedure` | -- | -- | Procedure storage options. |
+| `procedure.max_retry_times` | Integer | `12` | Procedure max retry time. |
+| `procedure.retry_delay` | String | `500ms` | Initial retry delay of procedures, increases exponentially |
+| `procedure.max_metadata_value_size` | String | `1500KiB` | Auto split large value<br/>GreptimeDB procedure uses etcd as the default metadata storage backend.<br/>The etcd the maximum size of any request is 1.5 MiB<br/>1500KiB = 1536KiB (1.5MiB) - 36KiB (reserved size of key)<br/>Comments out the `max_metadata_value_size`, for don't split large value (no limit). |
+| `failure_detector` | -- | -- | -- |
+| `failure_detector.threshold` | Float | `8.0` | -- |
+| `failure_detector.min_std_deviation` | String | `100ms` | -- |
+| `failure_detector.acceptable_heartbeat_pause` | String | `3000ms` | -- |
+| `failure_detector.first_heartbeat_estimate` | String | `1000ms` | -- |
+| `datanode` | -- | -- | Datanode options. |
+| `datanode.client` | -- | -- | Datanode client options. |
+| `datanode.client.timeout` | String | `10s` | -- |
+| `datanode.client.connect_timeout` | String | `10s` | -- |
+| `datanode.client.tcp_nodelay` | Bool | `true` | -- |
+| `wal` | -- | -- | -- |
+| `wal.provider` | String | `raft_engine` | -- |
+| `wal.broker_endpoints` | Array | -- | The broker endpoints of the Kafka cluster. |
+| `wal.num_topics` | Integer | `64` | Number of topics to be created upon start. |
+| `wal.selector_type` | String | `round_robin` | Topic selector type.<br/>Available selector types:<br/>- `round_robin` (default) |
+| `wal.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`. |
+| `wal.replication_factor` | Integer | `1` | Expected number of replicas of each partition. |
+| `wal.create_topic_timeout` | String | `30s` | Above which a topic creation operation will be cancelled. |
+| `wal.backoff_init` | String | `500ms` | The initial backoff for kafka clients. |
+| `wal.backoff_max` | String | `10s` | The maximum backoff for kafka clients. |
+| `wal.backoff_base` | Integer | `2` | Exponential backoff rate, i.e. next backoff = base * current backoff. |
+| `wal.backoff_deadline` | String | `5mins` | Stop reconnecting if the total wait time reaches the deadline. If this config is missing, the reconnecting won't terminate. |
+| `logging` | -- | -- | The logging options. |
+| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
+| `logging.otlp_endpoint` | String | `None` | The OTLP tracing endpoint. |
+| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
+| `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
+| `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
+| `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
+| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.remote_write` | -- | -- | -- |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
+| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+
+
+### Datanode
+
+| Key | Type | Default | Descriptions |
+| --- | -----| ------- | ----------- |
+| `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
+| `node_id` | Integer | `None` | The datanode identifier and should be unique in the cluster. |
+| `require_lease_before_startup` | Bool | `false` | Start services after regions have obtained leases.<br/>It will block the datanode start if it can't receive leases in the heartbeat from metasrv. |
+| `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
+| `rpc_addr` | String | `127.0.0.1:3001` | The gRPC address of the datanode. |
+| `rpc_hostname` | String | `None` | The hostname of the datanode. |
+| `rpc_runtime_size` | Integer | `8` | The number of gRPC server worker threads. |
+| `rpc_max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
+| `rpc_max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
+| `heartbeat` | -- | -- | The heartbeat options. |
+| `heartbeat.interval` | String | `3s` | Interval for sending heartbeat messages to the metasrv. |
+| `heartbeat.retry_interval` | String | `3s` | Interval for retrying to send heartbeat messages to the metasrv. |
+| `meta_client` | -- | -- | The metasrv client options. |
+| `meta_client.metasrv_addrs` | Array | -- | The addresses of the metasrv. |
+| `meta_client.timeout` | String | `3s` | Operation timeout. |
+| `meta_client.heartbeat_timeout` | String | `500ms` | Heartbeat timeout. |
+| `meta_client.ddl_timeout` | String | `10s` | DDL timeout. |
+| `meta_client.connect_timeout` | String | `1s` | Connect server timeout. |
+| `meta_client.tcp_nodelay` | Bool | `true` | `TCP_NODELAY` option for accepted connections. |
+| `meta_client.metadata_cache_max_capacity` | Integer | `100000` | The configuration about the cache of the metadata. |
+| `meta_client.metadata_cache_ttl` | String | `10m` | TTL of the metadata cache. |
+| `meta_client.metadata_cache_tti` | String | `5m` | -- |
+| `wal` | -- | -- | The WAL options. |
+| `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
+| `wal.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_base` | Integer | `2` | The exponential backoff rate, i.e. next backoff = base * current backoff.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.backoff_deadline` | String | `5mins` | The deadline of retries.<br/>**It's only used when the provider is `kafka`**. |
+| `storage` | -- | -- | The data storage options. |
+| `storage.data_home` | String | `/tmp/greptimedb/` | The working home directory. |
+| `storage.type` | String | `File` | The storage type used to store the data.<br/>- `File`: the data is stored in the local file system.<br/>- `S3`: the data is stored in the S3 object storage.<br/>- `Gcs`: the data is stored in the Google Cloud Storage.<br/>- `Azblob`: the data is stored in the Azure Blob Storage.<br/>- `Oss`: the data is stored in the Aliyun OSS. |
+| `storage.cache_path` | String | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
+| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
+| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
+| `storage.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
+| `storage.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
+| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.endpoint` | String | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.region` | String | `None` | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `[[region_engine]]` | -- | -- | The region engine options. You can configure multiple region engines. |
+| `region_engine.mito` | -- | -- | The Mito engine options. |
+| `region_engine.mito.num_workers` | Integer | `8` | Number of region workers. |
+| `region_engine.mito.worker_channel_size` | Integer | `128` | Request channel size of each worker. |
+| `region_engine.mito.worker_request_batch_size` | Integer | `64` | Max batch size for a worker to handle requests. |
+| `region_engine.mito.manifest_checkpoint_distance` | Integer | `10` | Number of meta action updated to trigger a new checkpoint for the manifest. |
+| `region_engine.mito.compress_manifest` | Bool | `false` | Whether to compress manifest and checkpoint file by gzip (default false). |
+| `region_engine.mito.max_background_jobs` | Integer | `4` | Max number of running background jobs |
+| `region_engine.mito.auto_flush_interval` | String | `1h` | Interval to auto flush a region if it has not flushed yet. |
+| `region_engine.mito.global_write_buffer_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
+| `region_engine.mito.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
+| `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
+| `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
+| `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
+| `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
+| `region_engine.mito.allow_stale_entries` | Bool | `false` | Whether to allow stale WAL entries read during replay. |
+| `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
+| `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `64M` | Memory threshold for performing an external sort during index creation.<br/>Setting to empty will disable external sorting, forcing all sorting operations to happen in memory. |
+| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`). |
+| `region_engine.mito.memtable` | -- | -- | -- |
+| `region_engine.mito.memtable.type` | String | `time_series` | Memtable type.<br/>- `time_series`: time-series memtable<br/>- `partition_tree`: partition tree memtable (experimental) |
+| `region_engine.mito.memtable.index_max_keys_per_shard` | Integer | `8192` | The max number of keys in one shard.<br/>Only available for `partition_tree` memtable. |
+| `region_engine.mito.memtable.data_freeze_threshold` | Integer | `32768` | The max rows of data inside the actively writing buffer in one shard.<br/>Only available for `partition_tree` memtable. |
+| `region_engine.mito.memtable.fork_dictionary_bytes` | String | `1GiB` | Max dictionary bytes.<br/>Only available for `partition_tree` memtable. |
+| `logging` | -- | -- | The logging options. |
+| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
+| `logging.otlp_endpoint` | String | `None` | The OTLP tracing endpoint. |
+| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
+| `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
+| `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
+| `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
+| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.remote_write` | -- | -- | -- |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
+| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |

config/datanode.example.toml

@@ -1,159 +1,436 @@
-# Node running mode, see `standalone.example.toml`.
-mode = "distributed"
-# The datanode identifier, should be unique.
+## The running mode of the datanode. It can be `standalone` or `distributed`.
+mode = "standalone"
+
+## The datanode identifier and should be unique in the cluster.
+## +toml2docs:none-default
 node_id = 42
-# gRPC server address, "127.0.0.1:3001" by default.
-rpc_addr = "127.0.0.1:3001"
-# Hostname of this node.
-rpc_hostname = "127.0.0.1"
-# The number of gRPC server worker threads, 8 by default.
-rpc_runtime_size = 8
-# Start services after regions have obtained leases.
-# It will block the datanode start if it can't receive leases in the heartbeat from metasrv.
+
+## Start services after regions have obtained leases.
+## It will block the datanode start if it can't receive leases in the heartbeat from metasrv.
 require_lease_before_startup = false
 
-# Initialize all regions in the background during the startup.
-# By default, it provides services after all regions have been initialized.
+## Initialize all regions in the background during the startup.
+## By default, it provides services after all regions have been initialized.
 init_regions_in_background = false
 
+## The gRPC address of the datanode.
+rpc_addr = "127.0.0.1:3001"
+
+## The hostname of the datanode.
+## +toml2docs:none-default
+rpc_hostname = "127.0.0.1"
+
+## The number of gRPC server worker threads.
+rpc_runtime_size = 8
+
+## The maximum receive message size for gRPC server.
+rpc_max_recv_message_size = "512MB"
+
+## The maximum send message size for gRPC server.
+rpc_max_send_message_size = "512MB"
+
+## Enable telemetry to collect anonymous usage data.
+enable_telemetry = true
+
+## The heartbeat options.
 [heartbeat]
-# Interval for sending heartbeat messages to the Metasrv, 3 seconds by default.
+## Interval for sending heartbeat messages to the metasrv.
 interval = "3s"
 
-# Metasrv client options.
+## Interval for retrying to send heartbeat messages to the metasrv.
+retry_interval = "3s"
+
+## The metasrv client options.
 [meta_client]
-# Metasrv address list.
+## The addresses of the metasrv.
 metasrv_addrs = ["127.0.0.1:3002"]
-# Heartbeat timeout, 500 milliseconds by default.
-heartbeat_timeout = "500ms"
-# Operation timeout, 3 seconds by default.
+
+## Operation timeout.
 timeout = "3s"
-# Connect server timeout, 1 second by default.
+
+## Heartbeat timeout.
+heartbeat_timeout = "500ms"
+
+## DDL timeout.
+ddl_timeout = "10s"
+
+## Connect server timeout.
 connect_timeout = "1s"
-# `TCP_NODELAY` option for accepted connections, true by default.
+
+## `TCP_NODELAY` option for accepted connections.
 tcp_nodelay = true
 
-# WAL options.
+## The configuration about the cache of the metadata.
+metadata_cache_max_capacity = 100000
+
+## TTL of the metadata cache.
+metadata_cache_ttl = "10m"
+
+# TTI of the metadata cache.
+metadata_cache_tti = "5m"
+
+## The WAL options.
 [wal]
+## The provider of the WAL.
+## - `raft_engine`: the wal is stored in the local file system by raft-engine.
+## - `kafka`: it's remote wal that data is stored in Kafka.
 provider = "raft_engine"
 
-# Raft-engine wal options, see `standalone.example.toml`.
-# dir = "/tmp/greptimedb/wal"
+## The directory to store the WAL files.
+## **It's only used when the provider is `raft_engine`**.
+## +toml2docs:none-default
+dir = "/tmp/greptimedb/wal"
+
+## The size of the WAL segment file.
+## **It's only used when the provider is `raft_engine`**.
 file_size = "256MB"
+
+## The threshold of the WAL size to trigger a flush.
+## **It's only used when the provider is `raft_engine`**.
 purge_threshold = "4GB"
+
+## The interval to trigger a flush.
+## **It's only used when the provider is `raft_engine`**.
 purge_interval = "10m"
+
+## The read batch size.
+## **It's only used when the provider is `raft_engine`**.
 read_batch_size = 128
+
+## Whether to use sync write.
+## **It's only used when the provider is `raft_engine`**.
 sync_write = false
 
-# Kafka wal options, see `standalone.example.toml`.
-# broker_endpoints = ["127.0.0.1:9092"]
-# Warning: Kafka has a default limit of 1MB per message in a topic.
-# max_batch_size = "1MB"
-# linger = "200ms"
-# consumer_wait_timeout = "100ms"
-# backoff_init = "500ms"
-# backoff_max = "10s"
-# backoff_base = 2
-# backoff_deadline = "5mins"
+## Whether to reuse logically truncated log files.
+## **It's only used when the provider is `raft_engine`**.
+enable_log_recycle = true
 
-# Storage options, see `standalone.example.toml`.
+## Whether to pre-create log files on start up.
+## **It's only used when the provider is `raft_engine`**.
+prefill_log_files = false
+
+## Duration for fsyncing log files.
+## **It's only used when the provider is `raft_engine`**.
+sync_period = "10s"
+
+## The Kafka broker endpoints.
+## **It's only used when the provider is `kafka`**.
+broker_endpoints = ["127.0.0.1:9092"]
+
+## The max size of a single producer batch.
+## Warning: Kafka has a default limit of 1MB per message in a topic.
+## **It's only used when the provider is `kafka`**.
+max_batch_size = "1MB"
+
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
+
+## The consumer wait timeout.
+## **It's only used when the provider is `kafka`**.
+consumer_wait_timeout = "100ms"
+
+## The initial backoff delay.
+## **It's only used when the provider is `kafka`**.
+backoff_init = "500ms"
+
+## The maximum backoff delay.
+## **It's only used when the provider is `kafka`**.
+backoff_max = "10s"
+
+## The exponential backoff rate, i.e. next backoff = base * current backoff.
+## **It's only used when the provider is `kafka`**.
+backoff_base = 2
+
+## The deadline of retries.
+## **It's only used when the provider is `kafka`**.
+backoff_deadline = "5mins"
+
+# Example of using S3 as the storage.
+# [storage]
+# type = "S3"
+# bucket = "greptimedb"
+# root = "data"
+# access_key_id = "test"
+# secret_access_key = "123456"
+# endpoint = "https://s3.amazonaws.com"
+# region = "us-west-2"
+
+# Example of using Oss as the storage.
+# [storage]
+# type = "Oss"
+# bucket = "greptimedb"
+# root = "data"
+# access_key_id = "test"
+# access_key_secret = "123456"
+# endpoint = "https://oss-cn-hangzhou.aliyuncs.com"
+
+# Example of using Azblob as the storage.
+# [storage]
+# type = "Azblob"
+# container = "greptimedb"
+# root = "data"
+# account_name = "test"
+# account_key = "123456"
+# endpoint = "https://greptimedb.blob.core.windows.net"
+# sas_token = ""
+
+# Example of using Gcs as the storage.
+# [storage]
+# type = "Gcs"
+# bucket = "greptimedb"
+# root = "data"
+# scope = "test"
+# credential_path = "123456"
+# endpoint = "https://storage.googleapis.com"
+
+## The data storage options.
 [storage]
-# The working home directory.
+## The working home directory.
 data_home = "/tmp/greptimedb/"
-# Storage type.
-type = "File"
-# TTL for all tables. Disabled by default.
-# global_ttl = "7d"
 
-# Cache configuration for object storage such as 'S3' etc.
-# The local file cache directory
-# cache_path = "/path/local_cache"
-# The local file cache capacity in bytes.
-# cache_capacity = "256MB"
+## The storage type used to store the data.
+## - `File`: the data is stored in the local file system.
+## - `S3`: the data is stored in the S3 object storage.
+## - `Gcs`: the data is stored in the Google Cloud Storage.
+## - `Azblob`: the data is stored in the Azure Blob Storage.
+## - `Oss`: the data is stored in the Aliyun OSS.
+type = "File"
+
+## Cache configuration for object storage such as 'S3' etc.
+## The local file cache directory.
+## +toml2docs:none-default
+cache_path = "/path/local_cache"
+
+## The local file cache capacity in bytes.
+## +toml2docs:none-default
+cache_capacity = "256MB"
+
+## The S3 bucket name.
+## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
+## +toml2docs:none-default
+bucket = "greptimedb"
+
+## The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.
+## **It's only used when the storage type is `S3`, `Oss` and `Azblob`**.
+## +toml2docs:none-default
+root = "greptimedb"
+
+## The access key id of the aws account.
+## It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.
+## **It's only used when the storage type is `S3` and `Oss`**.
+## +toml2docs:none-default
+access_key_id = "test"
+
+## The secret access key of the aws account.
+## It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.
+## **It's only used when the storage type is `S3`**.
+## +toml2docs:none-default
+secret_access_key = "test"
+
+## The secret access key of the aliyun account.
+## **It's only used when the storage type is `Oss`**.
+## +toml2docs:none-default
+access_key_secret = "test"
+
+## The account key of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+account_name = "test"
+
+## The account key of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+account_key = "test"
+
+## The scope of the google cloud storage.
+## **It's only used when the storage type is `Gcs`**.
+## +toml2docs:none-default
+scope = "test"
+
+## The credential path of the google cloud storage.
+## **It's only used when the storage type is `Gcs`**.
+## +toml2docs:none-default
+credential_path = "test"
+
+## The container of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+container = "greptimedb"
+
+## The sas token of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+sas_token = ""
+
+## The endpoint of the S3 service.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+## +toml2docs:none-default
+endpoint = "https://s3.amazonaws.com"
+
+## The region of the S3 service.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+## +toml2docs:none-default
+region = "us-west-2"
 
 # Custom storage options
-#[[storage.providers]]
-#type = "S3"
-#[[storage.providers]]
-#type = "Gcs"
+# [[storage.providers]]
+# type = "S3"
+# [[storage.providers]]
+# type = "Gcs"
 
-# Mito engine options
+## The region engine options. You can configure multiple region engines.
 [[region_engine]]
+
+## The Mito engine options.
 [region_engine.mito]
-# Number of region workers
+
+## Number of region workers.
 num_workers = 8
-# Request channel size of each worker
+
+## Request channel size of each worker.
 worker_channel_size = 128
-# Max batch size for a worker to handle requests
+
+## Max batch size for a worker to handle requests.
 worker_request_batch_size = 64
-# Number of meta action updated to trigger a new checkpoint for the manifest
+
+## Number of meta action updated to trigger a new checkpoint for the manifest.
 manifest_checkpoint_distance = 10
-# Whether to compress manifest and checkpoint file by gzip (default false).
+
+## Whether to compress manifest and checkpoint file by gzip (default false).
 compress_manifest = false
-# Max number of running background jobs
+
+## Max number of running background jobs
 max_background_jobs = 4
-# Interval to auto flush a region if it has not flushed yet.
+
+## Interval to auto flush a region if it has not flushed yet.
 auto_flush_interval = "1h"
-# Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
+
+## Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
 global_write_buffer_size = "1GB"
-# Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
+
+## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
 global_write_buffer_reject_size = "2GB"
-# Cache size for SST metadata. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
+
+## Cache size for SST metadata. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
 sst_meta_cache_size = "128MB"
-# Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
+
+## Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 vector_cache_size = "512MB"
-# Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
+
+## Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 page_cache_size = "512MB"
-# Buffer size for SST writing.
+
+## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
-# Parallelism to scan a region (default: 1/4 of cpu cores).
-# - 0: using the default value (1/4 of cpu cores).
-# - 1: scan in current thread.
-# - n: scan in parallelism n.
+
+## Parallelism to scan a region (default: 1/4 of cpu cores).
+## - `0`: using the default value (1/4 of cpu cores).
+## - `1`: scan in current thread.
+## - `n`: scan in parallelism n.
 scan_parallelism = 0
-# Capacity of the channel to send data from parallel scan tasks to the main task (default 32).
+
+## Capacity of the channel to send data from parallel scan tasks to the main task.
 parallel_scan_channel_size = 32
-# Whether to allow stale WAL entries read during replay.
+
+## Whether to allow stale WAL entries read during replay.
 allow_stale_entries = false
 
+## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
-# Whether to create the index on flush.
-# - "auto": automatically
-# - "disable": never
+
+## Whether to create the index on flush.
+## - `auto`: automatically
+## - `disable`: never
 create_on_flush = "auto"
-# Whether to create the index on compaction.
-# - "auto": automatically
-# - "disable": never
+
+## Whether to create the index on compaction.
+## - `auto`: automatically
+## - `disable`: never
 create_on_compaction = "auto"
-# Whether to apply the index on query
-# - "auto": automatically
-# - "disable": never
+
+## Whether to apply the index on query
+## - `auto`: automatically
+## - `disable`: never
 apply_on_query = "auto"
-# Memory threshold for performing an external sort during index creation.
-# Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
-mem_threshold_on_create = "64MB"
-# File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`).
+
+## Memory threshold for performing an external sort during index creation.
+## Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
+mem_threshold_on_create = "64M"
+
+## File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`).
 intermediate_path = ""
 
-# Log options, see `standalone.example.toml`
-# [logging]
-# dir = "/tmp/greptimedb/logs"
-# level = "info"
+[region_engine.mito.memtable]
+## Memtable type.
+## - `time_series`: time-series memtable
+## - `partition_tree`: partition tree memtable (experimental)
+type = "time_series"
 
-# Datanode export the metrics generated by itself
-# encoded to Prometheus remote-write format
-# and send to Prometheus remote-write compatible receiver (e.g. send to `greptimedb` itself)
-# This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
-# [export_metrics]
-# whether enable export metrics, default is false
-# enable = false
-# The interval of export metrics
-# write_interval = "30s"
-# [export_metrics.remote_write]
-# The url the metrics send to. The url is empty by default, url example: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`
-# url = ""
-# HTTP headers of Prometheus remote-write carry
-# headers = {}
+## The max number of keys in one shard.
+## Only available for `partition_tree` memtable.
+index_max_keys_per_shard = 8192
+
+## The max rows of data inside the actively writing buffer in one shard.
+## Only available for `partition_tree` memtable.
+data_freeze_threshold = 32768
+
+## Max dictionary bytes.
+## Only available for `partition_tree` memtable.
+fork_dictionary_bytes = "1GiB"
+
+## The logging options.
+[logging]
+## The directory to store the log files.
+dir = "/tmp/greptimedb/logs"
+
+## The log level. Can be `info`/`debug`/`warn`/`error`.
+## +toml2docs:none-default
+level = "info"
+
+## Enable OTLP tracing.
+enable_otlp_tracing = false
+
+## The OTLP tracing endpoint.
+## +toml2docs:none-default
+otlp_endpoint = ""
+
+## Whether to append logs to stdout.
+append_stdout = true
+
+## The percentage of tracing will be sampled and exported.
+## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
+## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
+[logging.tracing_sample_ratio]
+default_ratio = 1.0
+
+## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
+## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
+[export_metrics]
+
+## whether enable export metrics.
+enable = false
+
+## The interval of export metrics.
+write_interval = "30s"
+
+## For `standalone` mode, `self_import` is recommend to collect metrics generated by itself
+[export_metrics.self_import]
+## +toml2docs:none-default
+db = "information_schema"
+
+[export_metrics.remote_write]
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+url = ""
+
+## HTTP headers of Prometheus remote-write carry.
+headers = { }
+
+## The tracing options. Only effect when compiled with `tokio-console` feature.
+[tracing]
+## The tokio console address.
+## +toml2docs:none-default
+tokio_console_addr = "127.0.0.1"

config/frontend.example.toml

@@ -1,104 +1,193 @@
-# Node running mode, see `standalone.example.toml`.
-mode = "distributed"
-# The default timezone of the server
-# default_timezone = "UTC"
+## The running mode of the datanode. It can be `standalone` or `distributed`.
+mode = "standalone"
 
+## The default timezone of the server.
+## +toml2docs:none-default
+default_timezone = "UTC"
+
+## The heartbeat options.
 [heartbeat]
-# Interval for sending heartbeat task to the Metasrv, 5 seconds by default.
-interval = "5s"
-# Interval for retry sending heartbeat task, 5 seconds by default.
-retry_interval = "5s"
+## Interval for sending heartbeat messages to the metasrv.
+interval = "18s"
 
-# HTTP server options, see `standalone.example.toml`.
+## Interval for retrying to send heartbeat messages to the metasrv.
+retry_interval = "3s"
+
+## The HTTP server options.
 [http]
+## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
+## HTTP request timeout.
 timeout = "30s"
+## HTTP request body limit.
+## Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
 body_limit = "64MB"
 
-# gRPC server options, see `standalone.example.toml`.
+## The gRPC server options.
 [grpc]
+## The address to bind the gRPC server.
 addr = "127.0.0.1:4001"
+## The number of server worker threads.
 runtime_size = 8
 
-# MySQL server options, see `standalone.example.toml`.
+## MySQL server options.
 [mysql]
+## Whether to enable.
 enable = true
+## The addr to bind the MySQL server.
 addr = "127.0.0.1:4002"
+## The number of server worker threads.
 runtime_size = 2
 
-# MySQL server TLS options, see `standalone.example.toml`.
+# MySQL server TLS options.
 [mysql.tls]
+
+## TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
+## - `disable` (default value)
+## - `prefer`
+## - `require`
+## - `verify-ca`
+## - `verify-full`
 mode = "disable"
+
+## Certificate file path.
+## +toml2docs:none-default
 cert_path = ""
+
+## Private key file path.
+## +toml2docs:none-default
 key_path = ""
 
-# PostgresSQL server options, see `standalone.example.toml`.
+## Watch for Certificate and key file change and auto reload
+watch = false
+
+## PostgresSQL server options.
 [postgres]
+## Whether to enable
 enable = true
+## The addr to bind the PostgresSQL server.
 addr = "127.0.0.1:4003"
+## The number of server worker threads.
 runtime_size = 2
 
-# PostgresSQL server TLS options, see `standalone.example.toml`.
+## PostgresSQL server TLS options, see `mysql_options.tls` section.
 [postgres.tls]
+## TLS mode.
 mode = "disable"
+
+## Certificate file path.
+## +toml2docs:none-default
 cert_path = ""
+
+## Private key file path.
+## +toml2docs:none-default
 key_path = ""
 
-# OpenTSDB protocol options, see `standalone.example.toml`.
+## Watch for Certificate and key file change and auto reload
+watch = false
+
+## OpenTSDB protocol options.
 [opentsdb]
+## Whether to enable OpenTSDB put in HTTP API.
 enable = true
-addr = "127.0.0.1:4242"
-runtime_size = 2
 
-# InfluxDB protocol options, see `standalone.example.toml`.
+## InfluxDB protocol options.
 [influxdb]
+## Whether to enable InfluxDB protocol in HTTP API.
 enable = true
 
-# Prometheus remote storage options, see `standalone.example.toml`.
+## Prometheus remote storage options
 [prom_store]
+## Whether to enable Prometheus remote write and read in HTTP API.
 enable = true
-# Whether to store the data from Prometheus remote write in metric engine.
-# true by default
+## Whether to store the data from Prometheus remote write in metric engine.
 with_metric_engine = true
 
-# Metasrv client options, see `datanode.example.toml`.
+## The metasrv client options.
 [meta_client]
+## The addresses of the metasrv.
 metasrv_addrs = ["127.0.0.1:3002"]
+
+## Operation timeout.
 timeout = "3s"
-# DDL timeouts options.
+
+## Heartbeat timeout.
+heartbeat_timeout = "500ms"
+
+## DDL timeout.
 ddl_timeout = "10s"
+
+## Connect server timeout.
 connect_timeout = "1s"
+
+## `TCP_NODELAY` option for accepted connections.
 tcp_nodelay = true
-# The configuration about the cache of the Metadata.
-# default: 100000
+
+## The configuration about the cache of the metadata.
 metadata_cache_max_capacity = 100000
-# default: 10m
+
+## TTL of the metadata cache.
 metadata_cache_ttl = "10m"
-# default: 5m
+
+# TTI of the metadata cache.
 metadata_cache_tti = "5m"
 
-# Log options, see `standalone.example.toml`
-# [logging]
-# dir = "/tmp/greptimedb/logs"
-# level = "info"
-
-# Datanode options.
+## Datanode options.
 [datanode]
-# Datanode client options.
+## Datanode client options.
 [datanode.client]
-timeout = "10s"
 connect_timeout = "10s"
 tcp_nodelay = true
 
-# Frontend export the metrics generated by itself
-# encoded to Prometheus remote-write format
-# and send to Prometheus remote-write compatible receiver (e.g. send to `greptimedb` itself)
-# This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
-# [export_metrics]
-# whether enable export metrics, default is false
-# enable = false
-# The interval of export metrics
-# write_interval = "30s"
-# for `frontend`, `self_import` is recommend to collect metrics generated by itself
-# [export_metrics.self_import]
-# db = "information_schema"
+## The logging options.
+[logging]
+## The directory to store the log files.
+dir = "/tmp/greptimedb/logs"
+
+## The log level. Can be `info`/`debug`/`warn`/`error`.
+## +toml2docs:none-default
+level = "info"
+
+## Enable OTLP tracing.
+enable_otlp_tracing = false
+
+## The OTLP tracing endpoint.
+## +toml2docs:none-default
+otlp_endpoint = ""
+
+## Whether to append logs to stdout.
+append_stdout = true
+
+## The percentage of tracing will be sampled and exported.
+## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
+## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
+[logging.tracing_sample_ratio]
+default_ratio = 1.0
+
+## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
+## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
+[export_metrics]
+
+## whether enable export metrics.
+enable = false
+
+## The interval of export metrics.
+write_interval = "30s"
+
+## For `standalone` mode, `self_import` is recommend to collect metrics generated by itself
+[export_metrics.self_import]
+## +toml2docs:none-default
+db = "information_schema"
+
+[export_metrics.remote_write]
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+url = ""
+
+## HTTP headers of Prometheus remote-write carry.
+headers = { }
+
+## The tracing options. Only effect when compiled with `tokio-console` feature.
+[tracing]
+## The tokio console address.
+## +toml2docs:none-default
+tokio_console_addr = "127.0.0.1"

config/metasrv.example.toml

@@ -1,35 +1,46 @@
-# The working home directory.
+## The working home directory.
 data_home = "/tmp/metasrv/"
-# The bind address of metasrv, "127.0.0.1:3002" by default.
+
+## The bind address of metasrv.
 bind_addr = "127.0.0.1:3002"
-# The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost.
+
+## The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost.
 server_addr = "127.0.0.1:3002"
-# Etcd server address, "127.0.0.1:2379" by default.
+
+## Etcd server address.
 store_addr = "127.0.0.1:2379"
-# Datanode selector type.
-# - "lease_based" (default value).
-# - "load_based"
-# For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
+
+## Datanode selector type.
+## - `lease_based` (default value).
+## - `load_based`
+## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
 selector = "lease_based"
-# Store data in memory, false by default.
+
+## Store data in memory.
 use_memory_store = false
-# Whether to enable greptimedb telemetry, true by default.
+
+## Whether to enable greptimedb telemetry.
 enable_telemetry = true
-# If it's not empty, the metasrv will store all data with this key prefix.
+
+## If it's not empty, the metasrv will store all data with this key prefix.
 store_key_prefix = ""
 
-# Log options, see `standalone.example.toml`
-# [logging]
-# dir = "/tmp/greptimedb/logs"
-# level = "info"
-
-# Procedure storage options.
+## Procedure storage options.
 [procedure]
-# Procedure max retry time.
+
+## Procedure max retry time.
 max_retry_times = 12
-# Initial retry delay of procedures, increases exponentially
+
+## Initial retry delay of procedures, increases exponentially
 retry_delay = "500ms"
 
+## Auto split large value
+## GreptimeDB procedure uses etcd as the default metadata storage backend.
+## The etcd the maximum size of any request is 1.5 MiB
+## 1500KiB = 1536KiB (1.5MiB) - 36KiB (reserved size of key)
+## Comments out the `max_metadata_value_size`, for don't split large value (no limit).
+max_metadata_value_size = "1500KiB"
+
 # Failure detectors options.
 [failure_detector]
 threshold = 8.0
@@ -37,57 +48,102 @@ min_std_deviation = "100ms"
 acceptable_heartbeat_pause = "3000ms"
 first_heartbeat_estimate = "1000ms"
 
-# # Datanode options.
-# [datanode]
-# # Datanode client options.
-# [datanode.client_options]
-# timeout = "10s"
-# connect_timeout = "10s"
-# tcp_nodelay = true
+## Datanode options.
+[datanode]
+## Datanode client options.
+[datanode.client]
+timeout = "10s"
+connect_timeout = "10s"
+tcp_nodelay = true
 
 [wal]
 # Available wal providers:
-# - "raft_engine" (default)
-# - "kafka"
+# - `raft_engine` (default): there're none raft-engine wal config since metasrv only involves in remote wal currently.
+# - `kafka`: metasrv **have to be** configured with kafka wal config when using kafka wal provider in datanode.
 provider = "raft_engine"
 
-# There're none raft-engine wal config since meta srv only involves in remote wal currently.
-
 # Kafka wal config.
-# The broker endpoints of the Kafka cluster. ["127.0.0.1:9092"] by default.
-# broker_endpoints = ["127.0.0.1:9092"]
-# Number of topics to be created upon start.
-# num_topics = 64
-# Topic selector type.
-# Available selector types: 
-# - "round_robin" (default)
-# selector_type = "round_robin"
-# A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.
-# topic_name_prefix = "greptimedb_wal_topic"
-# Expected number of replicas of each partition.
-# replication_factor = 1
-# Above which a topic creation operation will be cancelled.
-# create_topic_timeout = "30s"
-# The initial backoff for kafka clients.
-# backoff_init = "500ms"
-# The maximum backoff for kafka clients.
-# backoff_max = "10s"
-# Exponential backoff rate, i.e. next backoff = base * current backoff.
-# backoff_base = 2
-# Stop reconnecting if the total wait time reaches the deadline. If this config is missing, the reconnecting won't terminate.
-# backoff_deadline = "5mins"
 
-# Metasrv export the metrics generated by itself
-# encoded to Prometheus remote-write format
-# and send to Prometheus remote-write compatible receiver (e.g. send to `greptimedb` itself)
-# This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
-# [export_metrics]
-# whether enable export metrics, default is false
-# enable = false
-# The interval of export metrics
-# write_interval = "30s"
-# [export_metrics.remote_write]
-# The url the metrics send to. The url is empty by default, url example: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`
-# url = ""
-# HTTP headers of Prometheus remote-write carry
-# headers = {}
+## The broker endpoints of the Kafka cluster.
+broker_endpoints = ["127.0.0.1:9092"]
+
+## Number of topics to be created upon start.
+num_topics = 64
+
+## Topic selector type.
+## Available selector types:
+## - `round_robin` (default)
+selector_type = "round_robin"
+
+## A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.
+topic_name_prefix = "greptimedb_wal_topic"
+
+## Expected number of replicas of each partition.
+replication_factor = 1
+
+## Above which a topic creation operation will be cancelled.
+create_topic_timeout = "30s"
+## The initial backoff for kafka clients.
+backoff_init = "500ms"
+
+## The maximum backoff for kafka clients.
+backoff_max = "10s"
+
+## Exponential backoff rate, i.e. next backoff = base * current backoff.
+backoff_base = 2
+
+## Stop reconnecting if the total wait time reaches the deadline. If this config is missing, the reconnecting won't terminate.
+backoff_deadline = "5mins"
+
+## The logging options.
+[logging]
+## The directory to store the log files.
+dir = "/tmp/greptimedb/logs"
+
+## The log level. Can be `info`/`debug`/`warn`/`error`.
+## +toml2docs:none-default
+level = "info"
+
+## Enable OTLP tracing.
+enable_otlp_tracing = false
+
+## The OTLP tracing endpoint.
+## +toml2docs:none-default
+otlp_endpoint = ""
+
+## Whether to append logs to stdout.
+append_stdout = true
+
+## The percentage of tracing will be sampled and exported.
+## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
+## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
+[logging.tracing_sample_ratio]
+default_ratio = 1.0
+
+## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
+## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
+[export_metrics]
+
+## whether enable export metrics.
+enable = false
+
+## The interval of export metrics.
+write_interval = "30s"
+
+## For `standalone` mode, `self_import` is recommend to collect metrics generated by itself
+[export_metrics.self_import]
+## +toml2docs:none-default
+db = "information_schema"
+
+[export_metrics.remote_write]
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+url = ""
+
+## HTTP headers of Prometheus remote-write carry.
+headers = { }
+
+## The tracing options. Only effect when compiled with `tokio-console` feature.
+[tracing]
+## The tokio console address.
+## +toml2docs:none-default
+tokio_console_addr = "127.0.0.1"

config/standalone.example.toml

@@ -1,269 +1,479 @@
-# Node running mode, "standalone" or "distributed".
+## The running mode of the datanode. It can be `standalone` or `distributed`.
 mode = "standalone"
-# Whether to enable greptimedb telemetry, true by default.
-enable_telemetry = true
-# The default timezone of the server
-# default_timezone = "UTC"
 
-# HTTP server options.
+## Enable telemetry to collect anonymous usage data.
+enable_telemetry = true
+
+## The default timezone of the server.
+## +toml2docs:none-default
+default_timezone = "UTC"
+
+## The HTTP server options.
 [http]
-# Server address, "127.0.0.1:4000" by default.
+## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-# HTTP request timeout, 30s by default.
+## HTTP request timeout.
 timeout = "30s"
-# HTTP request body limit, 64Mb by default.
-# the following units are supported: B, KB, KiB, MB, MiB, GB, GiB, TB, TiB, PB, PiB
+## HTTP request body limit.
+## Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
 body_limit = "64MB"
 
-# gRPC server options.
+## The gRPC server options.
 [grpc]
-# Server address, "127.0.0.1:4001" by default.
+## The address to bind the gRPC server.
 addr = "127.0.0.1:4001"
-# The number of server worker threads, 8 by default.
+## The number of server worker threads.
 runtime_size = 8
 
-# MySQL server options.
+## MySQL server options.
 [mysql]
-# Whether to enable
+## Whether to enable.
 enable = true
-# Server address, "127.0.0.1:4002" by default.
+## The addr to bind the MySQL server.
 addr = "127.0.0.1:4002"
-# The number of server worker threads, 2 by default.
+## The number of server worker threads.
 runtime_size = 2
 
 # MySQL server TLS options.
 [mysql.tls]
-# TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
-# - "disable" (default value)
-# - "prefer"
-# - "require"
-# - "verify-ca"
-# - "verify-full"
+
+## TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
+## - `disable` (default value)
+## - `prefer`
+## - `require`
+## - `verify-ca`
+## - `verify-full`
 mode = "disable"
-# Certificate file path.
+
+## Certificate file path.
+## +toml2docs:none-default
 cert_path = ""
-# Private key file path.
+
+## Private key file path.
+## +toml2docs:none-default
 key_path = ""
 
-# PostgresSQL server options.
+## Watch for Certificate and key file change and auto reload
+watch = false
+
+## PostgresSQL server options.
 [postgres]
-# Whether to enable
+## Whether to enable
 enable = true
-# Server address, "127.0.0.1:4003" by default.
+## The addr to bind the PostgresSQL server.
 addr = "127.0.0.1:4003"
-# The number of server worker threads, 2 by default.
+## The number of server worker threads.
 runtime_size = 2
 
-# PostgresSQL server TLS options, see `[mysql_options.tls]` section.
+## PostgresSQL server TLS options, see `mysql_options.tls` section.
 [postgres.tls]
-# TLS mode.
+## TLS mode.
 mode = "disable"
-# certificate file path.
+
+## Certificate file path.
+## +toml2docs:none-default
 cert_path = ""
-# private key file path.
+
+## Private key file path.
+## +toml2docs:none-default
 key_path = ""
 
-# OpenTSDB protocol options.
+## Watch for Certificate and key file change and auto reload
+watch = false
+
+## OpenTSDB protocol options.
 [opentsdb]
-# Whether to enable
+## Whether to enable OpenTSDB put in HTTP API.
 enable = true
-# OpenTSDB telnet API server address, "127.0.0.1:4242" by default.
-addr = "127.0.0.1:4242"
-# The number of server worker threads, 2 by default.
-runtime_size = 2
 
-# InfluxDB protocol options.
+## InfluxDB protocol options.
 [influxdb]
-# Whether to enable InfluxDB protocol in HTTP API, true by default.
+## Whether to enable InfluxDB protocol in HTTP API.
 enable = true
 
-# Prometheus remote storage options
+## Prometheus remote storage options
 [prom_store]
-# Whether to enable Prometheus remote write and read in HTTP API, true by default.
+## Whether to enable Prometheus remote write and read in HTTP API.
 enable = true
-# Whether to store the data from Prometheus remote write in metric engine.
-# true by default
+## Whether to store the data from Prometheus remote write in metric engine.
 with_metric_engine = true
 
+## The WAL options.
 [wal]
-# Available wal providers:
-# - "raft_engine" (default)
-# - "kafka"
+## The provider of the WAL.
+## - `raft_engine`: the wal is stored in the local file system by raft-engine.
+## - `kafka`: it's remote wal that data is stored in Kafka.
 provider = "raft_engine"
 
-# Raft-engine wal options.
-# WAL data directory
-# dir = "/tmp/greptimedb/wal"
-# WAL file size in bytes.
+## The directory to store the WAL files.
+## **It's only used when the provider is `raft_engine`**.
+## +toml2docs:none-default
+dir = "/tmp/greptimedb/wal"
+
+## The size of the WAL segment file.
+## **It's only used when the provider is `raft_engine`**.
 file_size = "256MB"
-# WAL purge threshold.
+
+## The threshold of the WAL size to trigger a flush.
+## **It's only used when the provider is `raft_engine`**.
 purge_threshold = "4GB"
-# WAL purge interval in seconds.
+
+## The interval to trigger a flush.
+## **It's only used when the provider is `raft_engine`**.
 purge_interval = "10m"
-# WAL read batch size.
+
+## The read batch size.
+## **It's only used when the provider is `raft_engine`**.
 read_batch_size = 128
-# Whether to sync log file after every write.
+
+## Whether to use sync write.
+## **It's only used when the provider is `raft_engine`**.
 sync_write = false
-# Whether to reuse logically truncated log files.
+
+## Whether to reuse logically truncated log files.
+## **It's only used when the provider is `raft_engine`**.
 enable_log_recycle = true
-# Whether to pre-create log files on start up
+
+## Whether to pre-create log files on start up.
+## **It's only used when the provider is `raft_engine`**.
 prefill_log_files = false
-# Duration for fsyncing log files.
-sync_period = "1000ms"
 
-# Kafka wal options.
-# The broker endpoints of the Kafka cluster. ["127.0.0.1:9092"] by default.
-# broker_endpoints = ["127.0.0.1:9092"]
+## Duration for fsyncing log files.
+## **It's only used when the provider is `raft_engine`**.
+sync_period = "10s"
 
-# Number of topics to be created upon start.
-# num_topics = 64
-# Topic selector type.
-# Available selector types: 
-# - "round_robin" (default)
-# selector_type = "round_robin"
-# The prefix of topic name.
-# topic_name_prefix = "greptimedb_wal_topic"
-# The number of replicas of each partition.
-# Warning: the replication factor must be positive and must not be greater than the number of broker endpoints.
-# replication_factor = 1
+## The Kafka broker endpoints.
+## **It's only used when the provider is `kafka`**.
+broker_endpoints = ["127.0.0.1:9092"]
 
-# The max size of a single producer batch.
-# Warning: Kafka has a default limit of 1MB per message in a topic.
-# max_batch_size = "1MB"
-# The linger duration.
-# linger = "200ms"
-# The consumer wait timeout.
-# consumer_wait_timeout = "100ms"
-# Create topic timeout.
-# create_topic_timeout = "30s"
+## The max size of a single producer batch.
+## Warning: Kafka has a default limit of 1MB per message in a topic.
+## **It's only used when the provider is `kafka`**.
+max_batch_size = "1MB"
 
-# The initial backoff delay.
-# backoff_init = "500ms"
-# The maximum backoff delay.
-# backoff_max = "10s"
-# Exponential backoff rate, i.e. next backoff = base * current backoff.
-# backoff_base = 2
-# The deadline of retries.
-# backoff_deadline = "5mins"
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
 
-# Metadata storage options.
+## The consumer wait timeout.
+## **It's only used when the provider is `kafka`**.
+consumer_wait_timeout = "100ms"
+
+## The initial backoff delay.
+## **It's only used when the provider is `kafka`**.
+backoff_init = "500ms"
+
+## The maximum backoff delay.
+## **It's only used when the provider is `kafka`**.
+backoff_max = "10s"
+
+## The exponential backoff rate, i.e. next backoff = base * current backoff.
+## **It's only used when the provider is `kafka`**.
+backoff_base = 2
+
+## The deadline of retries.
+## **It's only used when the provider is `kafka`**.
+backoff_deadline = "5mins"
+
+## Metadata storage options.
 [metadata_store]
-# Kv file size in bytes.
+## Kv file size in bytes.
 file_size = "256MB"
-# Kv purge threshold.
+## Kv purge threshold.
 purge_threshold = "4GB"
 
-# Procedure storage options.
+## Procedure storage options.
 [procedure]
-# Procedure max retry time.
+## Procedure max retry time.
 max_retry_times = 3
-# Initial retry delay of procedures, increases exponentially
+## Initial retry delay of procedures, increases exponentially
 retry_delay = "500ms"
 
-# Storage options.
+# Example of using S3 as the storage.
+# [storage]
+# type = "S3"
+# bucket = "greptimedb"
+# root = "data"
+# access_key_id = "test"
+# secret_access_key = "123456"
+# endpoint = "https://s3.amazonaws.com"
+# region = "us-west-2"
+
+# Example of using Oss as the storage.
+# [storage]
+# type = "Oss"
+# bucket = "greptimedb"
+# root = "data"
+# access_key_id = "test"
+# access_key_secret = "123456"
+# endpoint = "https://oss-cn-hangzhou.aliyuncs.com"
+
+# Example of using Azblob as the storage.
+# [storage]
+# type = "Azblob"
+# container = "greptimedb"
+# root = "data"
+# account_name = "test"
+# account_key = "123456"
+# endpoint = "https://greptimedb.blob.core.windows.net"
+# sas_token = ""
+
+# Example of using Gcs as the storage.
+# [storage]
+# type = "Gcs"
+# bucket = "greptimedb"
+# root = "data"
+# scope = "test"
+# credential_path = "123456"
+# endpoint = "https://storage.googleapis.com"
+
+## The data storage options.
 [storage]
-# The working home directory.
+## The working home directory.
 data_home = "/tmp/greptimedb/"
-# Storage type.
+
+## The storage type used to store the data.
+## - `File`: the data is stored in the local file system.
+## - `S3`: the data is stored in the S3 object storage.
+## - `Gcs`: the data is stored in the Google Cloud Storage.
+## - `Azblob`: the data is stored in the Azure Blob Storage.
+## - `Oss`: the data is stored in the Aliyun OSS.
 type = "File"
-# TTL for all tables. Disabled by default.
-# global_ttl = "7d"
-# Cache configuration for object storage such as 'S3' etc.
-# cache_path = "/path/local_cache"
-# The local file cache capacity in bytes.
-# cache_capacity = "256MB"
+
+## Cache configuration for object storage such as 'S3' etc.
+## The local file cache directory.
+## +toml2docs:none-default
+cache_path = "/path/local_cache"
+
+## The local file cache capacity in bytes.
+## +toml2docs:none-default
+cache_capacity = "256MB"
+
+## The S3 bucket name.
+## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
+## +toml2docs:none-default
+bucket = "greptimedb"
+
+## The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.
+## **It's only used when the storage type is `S3`, `Oss` and `Azblob`**.
+## +toml2docs:none-default
+root = "greptimedb"
+
+## The access key id of the aws account.
+## It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.
+## **It's only used when the storage type is `S3` and `Oss`**.
+## +toml2docs:none-default
+access_key_id = "test"
+
+## The secret access key of the aws account.
+## It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.
+## **It's only used when the storage type is `S3`**.
+## +toml2docs:none-default
+secret_access_key = "test"
+
+## The secret access key of the aliyun account.
+## **It's only used when the storage type is `Oss`**.
+## +toml2docs:none-default
+access_key_secret = "test"
+
+## The account key of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+account_name = "test"
+
+## The account key of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+account_key = "test"
+
+## The scope of the google cloud storage.
+## **It's only used when the storage type is `Gcs`**.
+## +toml2docs:none-default
+scope = "test"
+
+## The credential path of the google cloud storage.
+## **It's only used when the storage type is `Gcs`**.
+## +toml2docs:none-default
+credential_path = "test"
+
+## The container of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+container = "greptimedb"
+
+## The sas token of the azure account.
+## **It's only used when the storage type is `Azblob`**.
+## +toml2docs:none-default
+sas_token = ""
+
+## The endpoint of the S3 service.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+## +toml2docs:none-default
+endpoint = "https://s3.amazonaws.com"
+
+## The region of the S3 service.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+## +toml2docs:none-default
+region = "us-west-2"
 
 # Custom storage options
-#[[storage.providers]]
-#type = "S3"
-#[[storage.providers]]
-#type = "Gcs"
+# [[storage.providers]]
+# type = "S3"
+# [[storage.providers]]
+# type = "Gcs"
 
-# Mito engine options
+## The region engine options. You can configure multiple region engines.
 [[region_engine]]
+
+## The Mito engine options.
 [region_engine.mito]
-# Number of region workers
+
+## Number of region workers.
 num_workers = 8
-# Request channel size of each worker
+
+## Request channel size of each worker.
 worker_channel_size = 128
-# Max batch size for a worker to handle requests
+
+## Max batch size for a worker to handle requests.
 worker_request_batch_size = 64
-# Number of meta action updated to trigger a new checkpoint for the manifest
+
+## Number of meta action updated to trigger a new checkpoint for the manifest.
 manifest_checkpoint_distance = 10
-# Whether to compress manifest and checkpoint file by gzip (default false).
+
+## Whether to compress manifest and checkpoint file by gzip (default false).
 compress_manifest = false
-# Max number of running background jobs
+
+## Max number of running background jobs
 max_background_jobs = 4
-# Interval to auto flush a region if it has not flushed yet.
+
+## Interval to auto flush a region if it has not flushed yet.
 auto_flush_interval = "1h"
-# Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
+
+## Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
 global_write_buffer_size = "1GB"
-# Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
+
+## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
 global_write_buffer_reject_size = "2GB"
-# Cache size for SST metadata. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
+
+## Cache size for SST metadata. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
 sst_meta_cache_size = "128MB"
-# Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
+
+## Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 vector_cache_size = "512MB"
-# Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
-# If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
+
+## Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 page_cache_size = "512MB"
-# Buffer size for SST writing.
+
+## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
-# Parallelism to scan a region (default: 1/4 of cpu cores).
-# - 0: using the default value (1/4 of cpu cores).
-# - 1: scan in current thread.
-# - n: scan in parallelism n.
+
+## Parallelism to scan a region (default: 1/4 of cpu cores).
+## - `0`: using the default value (1/4 of cpu cores).
+## - `1`: scan in current thread.
+## - `n`: scan in parallelism n.
 scan_parallelism = 0
-# Capacity of the channel to send data from parallel scan tasks to the main task (default 32).
+
+## Capacity of the channel to send data from parallel scan tasks to the main task.
 parallel_scan_channel_size = 32
-# Whether to allow stale WAL entries read during replay.
+
+## Whether to allow stale WAL entries read during replay.
 allow_stale_entries = false
 
+## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
-# Whether to create the index on flush.
-# - "auto": automatically
-# - "disable": never
+
+## Whether to create the index on flush.
+## - `auto`: automatically
+## - `disable`: never
 create_on_flush = "auto"
-# Whether to create the index on compaction.
-# - "auto": automatically
-# - "disable": never
+
+## Whether to create the index on compaction.
+## - `auto`: automatically
+## - `disable`: never
 create_on_compaction = "auto"
-# Whether to apply the index on query
-# - "auto": automatically
-# - "disable": never
+
+## Whether to apply the index on query
+## - `auto`: automatically
+## - `disable`: never
 apply_on_query = "auto"
-# Memory threshold for performing an external sort during index creation.
-# Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
+
+## Memory threshold for performing an external sort during index creation.
+## Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
 mem_threshold_on_create = "64M"
-# File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`).
+
+## File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`).
 intermediate_path = ""
 
-# Log options
-# [logging]
-# Specify logs directory.
-# dir = "/tmp/greptimedb/logs"
-# Specify the log level [info | debug | error | warn]
-# level = "info"
-# whether enable tracing, default is false
-# enable_otlp_tracing = false
-# tracing exporter endpoint with format `ip:port`, we use grpc oltp as exporter, default endpoint is `localhost:4317`
-# otlp_endpoint = "localhost:4317"
-# The percentage of tracing will be sampled and exported. Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1. ratio > 1 are treated as 1. Fractions < 0 are treated as 0
-# tracing_sample_ratio = 1.0
-# Whether to append logs to stdout. Defaults to true.
-# append_stdout = true
+[region_engine.mito.memtable]
+## Memtable type.
+## - `time_series`: time-series memtable
+## - `partition_tree`: partition tree memtable (experimental)
+type = "time_series"
 
-# Standalone export the metrics generated by itself
-# encoded to Prometheus remote-write format
-# and send to Prometheus remote-write compatible receiver (e.g. send to `greptimedb` itself)
-# This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
-# [export_metrics]
-# whether enable export metrics, default is false
-# enable = false
-# The interval of export metrics
-# write_interval = "30s"
-# for `standalone`, `self_import` is recommend to collect metrics generated by itself
-# [export_metrics.self_import]
-# db = "information_schema"
+## The max number of keys in one shard.
+## Only available for `partition_tree` memtable.
+index_max_keys_per_shard = 8192
+
+## The max rows of data inside the actively writing buffer in one shard.
+## Only available for `partition_tree` memtable.
+data_freeze_threshold = 32768
+
+## Max dictionary bytes.
+## Only available for `partition_tree` memtable.
+fork_dictionary_bytes = "1GiB"
+
+## The logging options.
+[logging]
+## The directory to store the log files.
+dir = "/tmp/greptimedb/logs"
+
+## The log level. Can be `info`/`debug`/`warn`/`error`.
+## +toml2docs:none-default
+level = "info"
+
+## Enable OTLP tracing.
+enable_otlp_tracing = false
+
+## The OTLP tracing endpoint.
+## +toml2docs:none-default
+otlp_endpoint = ""
+
+## Whether to append logs to stdout.
+append_stdout = true
+
+## The percentage of tracing will be sampled and exported.
+## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
+## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
+[logging.tracing_sample_ratio]
+default_ratio = 1.0
+
+## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
+## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
+[export_metrics]
+
+## whether enable export metrics.
+enable = false
+
+## The interval of export metrics.
+write_interval = "30s"
+
+## For `standalone` mode, `self_import` is recommend to collect metrics generated by itself
+[export_metrics.self_import]
+## +toml2docs:none-default
+db = "information_schema"
+
+[export_metrics.remote_write]
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+url = ""
+
+## HTTP headers of Prometheus remote-write carry.
+headers = { }
+
+## The tracing options. Only effect when compiled with `tokio-console` feature.
+[tracing]
+## The tokio console address.
+## +toml2docs:none-default
+tokio_console_addr = "127.0.0.1"

cyborg/.gitignore

@@ -0,0 +1,2 @@
+node_modules
+.env

cyborg/bin/check-pull-request.ts

@@ -0,0 +1,79 @@
+/*
+ * Copyright 2023 Greptime Team
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import * as core from '@actions/core'
+import {handleError, obtainClient} from "@/common";
+import {context} from "@actions/github";
+import {PullRequestEvent} from "@octokit/webhooks-types";
+import {Options, sync as conventionalCommitsParser} from 'conventional-commits-parser';
+import conventionalCommitTypes from 'conventional-commit-types';
+import _ from "lodash";
+
+const defaultTypes = Object.keys(conventionalCommitTypes.types)
+const breakingChangeLabel = "breaking-change"
+
+// These options are copied from [1].
+// [1] https://github.com/conventional-changelog/conventional-changelog/blob/3f60b464/packages/conventional-changelog-conventionalcommits/src/parser.js
+export const parserOpts: Options = {
+    headerPattern: /^(\w*)(?:\((.*)\))?!?: (.*)$/,
+    breakingHeaderPattern: /^(\w*)(?:\((.*)\))?!: (.*)$/,
+    headerCorrespondence: [
+        'type',
+        'scope',
+        'subject'
+    ],
+    noteKeywords: ['BREAKING CHANGE', 'BREAKING-CHANGE'],
+    revertPattern: /^(?:Revert|revert:)\s"?([\s\S]+?)"?\s*This reverts commit (\w*)\./i,
+    revertCorrespondence: ['header', 'hash'],
+    issuePrefixes: ['#']
+}
+
+async function main() {
+    if (!context.payload.pull_request) {
+        throw new Error(`Only pull request event supported. ${context.eventName} is unsupported.`)
+    }
+
+    const client = obtainClient("GITHUB_TOKEN")
+    const payload = context.payload as PullRequestEvent
+    const { owner, repo, number } = {
+        owner: payload.pull_request.base.user.login,
+        repo: payload.pull_request.base.repo.name,
+        number: payload.pull_request.number,
+    }
+    const { data: pull_request } = await client.rest.pulls.get({
+        owner, repo, pull_number: number,
+    })
+
+    const commit = conventionalCommitsParser(pull_request.title, parserOpts)
+    core.info(`Receive commit: ${JSON.stringify(commit)}`)
+
+    if (!commit.type) {
+        throw Error(`Malformed commit: ${JSON.stringify(commit)}`)
+    }
+
+    if (!defaultTypes.includes(commit.type)) {
+        throw Error(`Unexpected type ${JSON.stringify(commit.type)} of commit: ${JSON.stringify(commit)}`)
+    }
+
+    const breakingChanges = _.filter(commit.notes, _.matches({ title: 'BREAKING CHANGE'}))
+    if (breakingChanges.length > 0) {
+        await client.rest.issues.addLabels({
+            owner, repo, issue_number: number, labels: [breakingChangeLabel]
+        })
+    }
+}
+
+main().catch(handleError)

cyborg/bin/follow-up-docs-issue.ts

@@ -0,0 +1,106 @@
+/*
+ * Copyright 2023 Greptime Team
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import * as core from '@actions/core'
+import {handleError, obtainClient} from "@/common";
+import {context} from "@actions/github";
+import {PullRequestEditedEvent, PullRequestEvent, PullRequestOpenedEvent} from "@octokit/webhooks-types";
+// @ts-expect-error moduleResolution:nodenext issue 54523
+import {RequestError} from "@octokit/request-error";
+
+const needFollowUpDocs = "[x] This PR requires documentation updates."
+const labelDocsNotRequired = "docs-not-required"
+const labelDocsRequired = "docs-required"
+
+async function main() {
+    if (!context.payload.pull_request) {
+        throw new Error(`Only pull request event supported. ${context.eventName} is unsupported.`)
+    }
+
+    const client = obtainClient("GITHUB_TOKEN")
+    const docsClient = obtainClient("DOCS_REPO_TOKEN")
+    const payload = context.payload as PullRequestEvent
+    const { owner, repo, number, actor, title, html_url } = {
+        owner: payload.pull_request.base.user.login,
+        repo: payload.pull_request.base.repo.name,
+        number: payload.pull_request.number,
+        title: payload.pull_request.title,
+        html_url: payload.pull_request.html_url,
+        actor: payload.pull_request.user.login,
+    }
+    const followUpDocs = checkPullRequestEvent(payload)
+    if (followUpDocs) {
+        core.info("Follow up docs.")
+        await client.rest.issues.removeLabel({
+            owner, repo, issue_number: number, name: labelDocsNotRequired,
+        }).catch((e: RequestError) => {
+            if (e.status != 404) {
+                throw e;
+            }
+            core.debug(`Label ${labelDocsNotRequired} not exist.`)
+        })
+        await client.rest.issues.addLabels({
+            owner, repo, issue_number: number, labels: [labelDocsRequired],
+        })
+        await docsClient.rest.issues.create({
+            owner: 'GreptimeTeam',
+            repo: 'docs',
+            title: `Update docs for ${title}`,
+            body: `A document change request is generated from ${html_url}`,
+            assignee: actor,
+        }).then((res) => {
+            core.info(`Created issue ${res.data}`)
+        })
+    } else {
+        core.info("No need to follow up docs.")
+        await client.rest.issues.removeLabel({
+            owner, repo, issue_number: number, name: labelDocsRequired
+        }).catch((e: RequestError) => {
+            if (e.status != 404) {
+                throw e;
+            }
+            core.debug(`Label ${labelDocsRequired} not exist.`)
+        })
+        await client.rest.issues.addLabels({
+            owner, repo, issue_number: number, labels: [labelDocsNotRequired],
+        })
+    }
+}
+
+function checkPullRequestEvent(payload: PullRequestEvent) {
+    switch (payload.action) {
+        case "opened":
+            return checkPullRequestOpenedEvent(payload as PullRequestOpenedEvent)
+        case "edited":
+            return checkPullRequestEditedEvent(payload as PullRequestEditedEvent)
+        default:
+            throw new Error(`${payload.action} is unsupported.`)
+    }
+}
+
+function checkPullRequestOpenedEvent(event: PullRequestOpenedEvent): boolean {
+    // @ts-ignore
+    return event.pull_request.body?.includes(needFollowUpDocs)
+}
+
+function checkPullRequestEditedEvent(event: PullRequestEditedEvent): boolean {
+    const previous = event.changes.body?.from.includes(needFollowUpDocs)
+    const current = event.pull_request.body?.includes(needFollowUpDocs)
+    // from docs-not-need to docs-required
+    return (!previous) && current
+}
+
+main().catch(handleError)

cyborg/bin/schedule.ts

@@ -0,0 +1,73 @@
+/*
+ * Copyright 2023 Greptime Team
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import * as core from '@actions/core'
+import {GitHub} from "@actions/github/lib/utils"
+import _ from "lodash";
+import dayjs from "dayjs";
+import {handleError, obtainClient} from "@/common";
+
+async function main() {
+    const client = obtainClient("GITHUB_TOKEN")
+    await unassign(client)
+}
+
+async function unassign(client: InstanceType<typeof GitHub>) {
+    const owner = "GreptimeTeam"
+    const repo = "greptimedb"
+
+    const dt = dayjs().subtract(14, 'days');
+    core.info(`Open issues updated before ${dt.toISOString()} will be considered stale.`)
+
+    const members = await client.paginate(client.rest.repos.listCollaborators, {
+        owner,
+        repo,
+        permission: "push",
+        per_page: 100
+    }).then((members) => members.map((member) => member.login))
+    core.info(`Members (${members.length}): ${members}`)
+
+    const issues = await client.paginate(client.rest.issues.listForRepo, {
+        owner,
+        repo,
+        state: "open",
+        sort: "created",
+        direction: "asc",
+        per_page: 100
+    })
+    for (const issue of issues) {
+        let assignees = [];
+        if (issue.assignee) {
+            assignees.push(issue.assignee.login)
+        }
+        for (const assignee of issue.assignees) {
+            assignees.push(assignee.login)
+        }
+        assignees = _.uniq(assignees)
+        assignees = _.difference(assignees, members)
+        if (assignees.length > 0 && dayjs(issue.updated_at).isBefore(dt)) {
+            core.info(`Assignees ${assignees} of issue ${issue.number} will be unassigned.`)
+            await client.rest.issues.removeAssignees({
+                owner,
+                repo,
+                issue_number: issue.number,
+                assignees: assignees,
+            })
+        }
+    }
+}
+
+main().catch(handleError)

cyborg/package.json

@@ -0,0 +1,26 @@
+{
+  "name": "cyborg",
+  "version": "1.0.0",
+  "description": "Automator for GreptimeDB Repository Management",
+  "private": true,
+  "packageManager": "pnpm@8.15.5",
+  "dependencies": {
+    "@actions/core": "^1.10.1",
+    "@actions/github": "^6.0.0",
+    "@octokit/request-error": "^6.1.1",
+    "@octokit/webhooks-types": "^7.5.1",
+    "conventional-commit-types": "^3.0.0",
+    "conventional-commits-parser": "^5.0.0",
+    "dayjs": "^1.11.11",
+    "dotenv": "^16.4.5",
+    "lodash": "^4.17.21"
+  },
+  "devDependencies": {
+    "@types/conventional-commits-parser": "^5.0.0",
+    "@types/lodash": "^4.17.0",
+    "@types/node": "^20.12.7",
+    "tsconfig-paths": "^4.2.0",
+    "tsx": "^4.8.2",
+    "typescript": "^5.4.5"
+  }
+}

cyborg/pnpm-lock.yaml

@@ -0,0 +1,612 @@
+lockfileVersion: '6.0'
+
+settings:
+  autoInstallPeers: true
+  excludeLinksFromLockfile: false
+
+dependencies:
+  '@actions/core':
+    specifier: ^1.10.1
+    version: 1.10.1
+  '@actions/github':
+    specifier: ^6.0.0
+    version: 6.0.0
+  '@octokit/request-error':
+    specifier: ^6.1.1
+    version: 6.1.1
+  '@octokit/webhooks-types':
+    specifier: ^7.5.1
+    version: 7.5.1
+  conventional-commit-types:
+    specifier: ^3.0.0
+    version: 3.0.0
+  conventional-commits-parser:
+    specifier: ^5.0.0
+    version: 5.0.0
+  dayjs:
+    specifier: ^1.11.11
+    version: 1.11.11
+  dotenv:
+    specifier: ^16.4.5
+    version: 16.4.5
+  lodash:
+    specifier: ^4.17.21
+    version: 4.17.21
+
+devDependencies:
+  '@types/conventional-commits-parser':
+    specifier: ^5.0.0
+    version: 5.0.0
+  '@types/lodash':
+    specifier: ^4.17.0
+    version: 4.17.0
+  '@types/node':
+    specifier: ^20.12.7
+    version: 20.12.7
+  tsconfig-paths:
+    specifier: ^4.2.0
+    version: 4.2.0
+  tsx:
+    specifier: ^4.8.2
+    version: 4.8.2
+  typescript:
+    specifier: ^5.4.5
+    version: 5.4.5
+
+packages:
+
+  /@actions/core@1.10.1:
+    resolution: {integrity: sha512-3lBR9EDAY+iYIpTnTIXmWcNbX3T2kCkAEQGIQx4NVQ0575nk2k3GRZDTPQG+vVtS2izSLmINlxXf0uLtnrTP+g==}
+    dependencies:
+      '@actions/http-client': 2.2.1
+      uuid: 8.3.2
+    dev: false
+
+  /@actions/github@6.0.0:
+    resolution: {integrity: sha512-alScpSVnYmjNEXboZjarjukQEzgCRmjMv6Xj47fsdnqGS73bjJNDpiiXmp8jr0UZLdUB6d9jW63IcmddUP+l0g==}
+    dependencies:
+      '@actions/http-client': 2.2.1
+      '@octokit/core': 5.2.0
+      '@octokit/plugin-paginate-rest': 9.2.1(@octokit/core@5.2.0)
+      '@octokit/plugin-rest-endpoint-methods': 10.4.1(@octokit/core@5.2.0)
+    dev: false
+
+  /@actions/http-client@2.2.1:
+    resolution: {integrity: sha512-KhC/cZsq7f8I4LfZSJKgCvEwfkE8o1538VoBeoGzokVLLnbFDEAdFD3UhoMklxo2un9NJVBdANOresx7vTHlHw==}
+    dependencies:
+      tunnel: 0.0.6
+      undici: 5.28.4
+    dev: false
+
+  /@esbuild/aix-ppc64@0.20.2:
+    resolution: {integrity: sha512-D+EBOJHXdNZcLJRBkhENNG8Wji2kgc9AZ9KiPr1JuZjsNtyHzrsfLRrY0tk2H2aoFu6RANO1y1iPPUCDYWkb5g==}
+    engines: {node: '>=12'}
+    cpu: [ppc64]
+    os: [aix]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/android-arm64@0.20.2:
+    resolution: {integrity: sha512-mRzjLacRtl/tWU0SvD8lUEwb61yP9cqQo6noDZP/O8VkwafSYwZ4yWy24kan8jE/IMERpYncRt2dw438LP3Xmg==}
+    engines: {node: '>=12'}
+    cpu: [arm64]
+    os: [android]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/android-arm@0.20.2:
+    resolution: {integrity: sha512-t98Ra6pw2VaDhqNWO2Oph2LXbz/EJcnLmKLGBJwEwXX/JAN83Fym1rU8l0JUWK6HkIbWONCSSatf4sf2NBRx/w==}
+    engines: {node: '>=12'}
+    cpu: [arm]
+    os: [android]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/android-x64@0.20.2:
+    resolution: {integrity: sha512-btzExgV+/lMGDDa194CcUQm53ncxzeBrWJcncOBxuC6ndBkKxnHdFJn86mCIgTELsooUmwUm9FkhSp5HYu00Rg==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [android]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/darwin-arm64@0.20.2:
+    resolution: {integrity: sha512-4J6IRT+10J3aJH3l1yzEg9y3wkTDgDk7TSDFX+wKFiWjqWp/iCfLIYzGyasx9l0SAFPT1HwSCR+0w/h1ES/MjA==}
+    engines: {node: '>=12'}
+    cpu: [arm64]
+    os: [darwin]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/darwin-x64@0.20.2:
+    resolution: {integrity: sha512-tBcXp9KNphnNH0dfhv8KYkZhjc+H3XBkF5DKtswJblV7KlT9EI2+jeA8DgBjp908WEuYll6pF+UStUCfEpdysA==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [darwin]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/freebsd-arm64@0.20.2:
+    resolution: {integrity: sha512-d3qI41G4SuLiCGCFGUrKsSeTXyWG6yem1KcGZVS+3FYlYhtNoNgYrWcvkOoaqMhwXSMrZRl69ArHsGJ9mYdbbw==}
+    engines: {node: '>=12'}
+    cpu: [arm64]
+    os: [freebsd]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/freebsd-x64@0.20.2:
+    resolution: {integrity: sha512-d+DipyvHRuqEeM5zDivKV1KuXn9WeRX6vqSqIDgwIfPQtwMP4jaDsQsDncjTDDsExT4lR/91OLjRo8bmC1e+Cw==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [freebsd]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-arm64@0.20.2:
+    resolution: {integrity: sha512-9pb6rBjGvTFNira2FLIWqDk/uaf42sSyLE8j1rnUpuzsODBq7FvpwHYZxQ/It/8b+QOS1RYfqgGFNLRI+qlq2A==}
+    engines: {node: '>=12'}
+    cpu: [arm64]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-arm@0.20.2:
+    resolution: {integrity: sha512-VhLPeR8HTMPccbuWWcEUD1Az68TqaTYyj6nfE4QByZIQEQVWBB8vup8PpR7y1QHL3CpcF6xd5WVBU/+SBEvGTg==}
+    engines: {node: '>=12'}
+    cpu: [arm]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-ia32@0.20.2:
+    resolution: {integrity: sha512-o10utieEkNPFDZFQm9CoP7Tvb33UutoJqg3qKf1PWVeeJhJw0Q347PxMvBgVVFgouYLGIhFYG0UGdBumROyiig==}
+    engines: {node: '>=12'}
+    cpu: [ia32]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-loong64@0.20.2:
+    resolution: {integrity: sha512-PR7sp6R/UC4CFVomVINKJ80pMFlfDfMQMYynX7t1tNTeivQ6XdX5r2XovMmha/VjR1YN/HgHWsVcTRIMkymrgQ==}
+    engines: {node: '>=12'}
+    cpu: [loong64]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-mips64el@0.20.2:
+    resolution: {integrity: sha512-4BlTqeutE/KnOiTG5Y6Sb/Hw6hsBOZapOVF6njAESHInhlQAghVVZL1ZpIctBOoTFbQyGW+LsVYZ8lSSB3wkjA==}
+    engines: {node: '>=12'}
+    cpu: [mips64el]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-ppc64@0.20.2:
+    resolution: {integrity: sha512-rD3KsaDprDcfajSKdn25ooz5J5/fWBylaaXkuotBDGnMnDP1Uv5DLAN/45qfnf3JDYyJv/ytGHQaziHUdyzaAg==}
+    engines: {node: '>=12'}
+    cpu: [ppc64]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-riscv64@0.20.2:
+    resolution: {integrity: sha512-snwmBKacKmwTMmhLlz/3aH1Q9T8v45bKYGE3j26TsaOVtjIag4wLfWSiZykXzXuE1kbCE+zJRmwp+ZbIHinnVg==}
+    engines: {node: '>=12'}
+    cpu: [riscv64]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-s390x@0.20.2:
+    resolution: {integrity: sha512-wcWISOobRWNm3cezm5HOZcYz1sKoHLd8VL1dl309DiixxVFoFe/o8HnwuIwn6sXre88Nwj+VwZUvJf4AFxkyrQ==}
+    engines: {node: '>=12'}
+    cpu: [s390x]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/linux-x64@0.20.2:
+    resolution: {integrity: sha512-1MdwI6OOTsfQfek8sLwgyjOXAu+wKhLEoaOLTjbijk6E2WONYpH9ZU2mNtR+lZ2B4uwr+usqGuVfFT9tMtGvGw==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [linux]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/netbsd-x64@0.20.2:
+    resolution: {integrity: sha512-K8/DhBxcVQkzYc43yJXDSyjlFeHQJBiowJ0uVL6Tor3jGQfSGHNNJcWxNbOI8v5k82prYqzPuwkzHt3J1T1iZQ==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [netbsd]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/openbsd-x64@0.20.2:
+    resolution: {integrity: sha512-eMpKlV0SThJmmJgiVyN9jTPJ2VBPquf6Kt/nAoo6DgHAoN57K15ZghiHaMvqjCye/uU4X5u3YSMgVBI1h3vKrQ==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [openbsd]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/sunos-x64@0.20.2:
+    resolution: {integrity: sha512-2UyFtRC6cXLyejf/YEld4Hajo7UHILetzE1vsRcGL3earZEW77JxrFjH4Ez2qaTiEfMgAXxfAZCm1fvM/G/o8w==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [sunos]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/win32-arm64@0.20.2:
+    resolution: {integrity: sha512-GRibxoawM9ZCnDxnP3usoUDO9vUkpAxIIZ6GQI+IlVmr5kP3zUq+l17xELTHMWTWzjxa2guPNyrpq1GWmPvcGQ==}
+    engines: {node: '>=12'}
+    cpu: [arm64]
+    os: [win32]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/win32-ia32@0.20.2:
+    resolution: {integrity: sha512-HfLOfn9YWmkSKRQqovpnITazdtquEW8/SoHW7pWpuEeguaZI4QnCRW6b+oZTztdBnZOS2hqJ6im/D5cPzBTTlQ==}
+    engines: {node: '>=12'}
+    cpu: [ia32]
+    os: [win32]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@esbuild/win32-x64@0.20.2:
+    resolution: {integrity: sha512-N49X4lJX27+l9jbLKSqZ6bKNjzQvHaT8IIFUy+YIqmXQdjYCToGWwOItDrfby14c78aDd5NHQl29xingXfCdLQ==}
+    engines: {node: '>=12'}
+    cpu: [x64]
+    os: [win32]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /@fastify/busboy@2.1.1:
+    resolution: {integrity: sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA==}
+    engines: {node: '>=14'}
+    dev: false
+
+  /@octokit/auth-token@4.0.0:
+    resolution: {integrity: sha512-tY/msAuJo6ARbK6SPIxZrPBms3xPbfwBrulZe0Wtr/DIY9lje2HeV1uoebShn6mx7SjCHif6EjMvoREj+gZ+SA==}
+    engines: {node: '>= 18'}
+    dev: false
+
+  /@octokit/core@5.2.0:
+    resolution: {integrity: sha512-1LFfa/qnMQvEOAdzlQymH0ulepxbxnCYAKJZfMci/5XJyIHWgEYnDmgnKakbTh7CH2tFQ5O60oYDvns4i9RAIg==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/auth-token': 4.0.0
+      '@octokit/graphql': 7.1.0
+      '@octokit/request': 8.4.0
+      '@octokit/request-error': 5.1.0
+      '@octokit/types': 13.5.0
+      before-after-hook: 2.2.3
+      universal-user-agent: 6.0.1
+    dev: false
+
+  /@octokit/endpoint@9.0.5:
+    resolution: {integrity: sha512-ekqR4/+PCLkEBF6qgj8WqJfvDq65RH85OAgrtnVp1mSxaXF03u2xW/hUdweGS5654IlC0wkNYC18Z50tSYTAFw==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/types': 13.5.0
+      universal-user-agent: 6.0.1
+    dev: false
+
+  /@octokit/graphql@7.1.0:
+    resolution: {integrity: sha512-r+oZUH7aMFui1ypZnAvZmn0KSqAUgE1/tUXIWaqUCa1758ts/Jio84GZuzsvUkme98kv0WFY8//n0J1Z+vsIsQ==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/request': 8.4.0
+      '@octokit/types': 13.5.0
+      universal-user-agent: 6.0.1
+    dev: false
+
+  /@octokit/openapi-types@20.0.0:
+    resolution: {integrity: sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA==}
+    dev: false
+
+  /@octokit/openapi-types@22.2.0:
+    resolution: {integrity: sha512-QBhVjcUa9W7Wwhm6DBFu6ZZ+1/t/oYxqc2tp81Pi41YNuJinbFRx8B133qVOrAaBbF7D/m0Et6f9/pZt9Rc+tg==}
+    dev: false
+
+  /@octokit/plugin-paginate-rest@9.2.1(@octokit/core@5.2.0):
+    resolution: {integrity: sha512-wfGhE/TAkXZRLjksFXuDZdmGnJQHvtU/joFQdweXUgzo1XwvBCD4o4+75NtFfjfLK5IwLf9vHTfSiU3sLRYpRw==}
+    engines: {node: '>= 18'}
+    peerDependencies:
+      '@octokit/core': '5'
+    dependencies:
+      '@octokit/core': 5.2.0
+      '@octokit/types': 12.6.0
+    dev: false
+
+  /@octokit/plugin-rest-endpoint-methods@10.4.1(@octokit/core@5.2.0):
+    resolution: {integrity: sha512-xV1b+ceKV9KytQe3zCVqjg+8GTGfDYwaT1ATU5isiUyVtlVAO3HNdzpS4sr4GBx4hxQ46s7ITtZrAsxG22+rVg==}
+    engines: {node: '>= 18'}
+    peerDependencies:
+      '@octokit/core': '5'
+    dependencies:
+      '@octokit/core': 5.2.0
+      '@octokit/types': 12.6.0
+    dev: false
+
+  /@octokit/request-error@5.1.0:
+    resolution: {integrity: sha512-GETXfE05J0+7H2STzekpKObFe765O5dlAKUTLNGeH+x47z7JjXHfsHKo5z21D/o/IOZTUEI6nyWyR+bZVP/n5Q==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/types': 13.5.0
+      deprecation: 2.3.1
+      once: 1.4.0
+    dev: false
+
+  /@octokit/request-error@6.1.1:
+    resolution: {integrity: sha512-1mw1gqT3fR/WFvnoVpY/zUM2o/XkMs/2AszUUG9I69xn0JFLv6PGkPhNk5lbfvROs79wiS0bqiJNxfCZcRJJdg==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/types': 13.5.0
+    dev: false
+
+  /@octokit/request@8.4.0:
+    resolution: {integrity: sha512-9Bb014e+m2TgBeEJGEbdplMVWwPmL1FPtggHQRkV+WVsMggPtEkLKPlcVYm/o8xKLkpJ7B+6N8WfQMtDLX2Dpw==}
+    engines: {node: '>= 18'}
+    dependencies:
+      '@octokit/endpoint': 9.0.5
+      '@octokit/request-error': 5.1.0
+      '@octokit/types': 13.5.0
+      universal-user-agent: 6.0.1
+    dev: false
+
+  /@octokit/types@12.6.0:
+    resolution: {integrity: sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw==}
+    dependencies:
+      '@octokit/openapi-types': 20.0.0
+    dev: false
+
+  /@octokit/types@13.5.0:
+    resolution: {integrity: sha512-HdqWTf5Z3qwDVlzCrP8UJquMwunpDiMPt5er+QjGzL4hqr/vBVY/MauQgS1xWxCDT1oMx1EULyqxncdCY/NVSQ==}
+    dependencies:
+      '@octokit/openapi-types': 22.2.0
+    dev: false
+
+  /@octokit/webhooks-types@7.5.1:
+    resolution: {integrity: sha512-1dozxWEP8lKGbtEu7HkRbK1F/nIPuJXNfT0gd96y6d3LcHZTtRtlf8xz3nicSJfesADxJyDh+mWBOsdLkqgzYw==}
+    dev: false
+
+  /@types/conventional-commits-parser@5.0.0:
+    resolution: {integrity: sha512-loB369iXNmAZglwWATL+WRe+CRMmmBPtpolYzIebFaX4YA3x+BEfLqhUAV9WanycKI3TG1IMr5bMJDajDKLlUQ==}
+    dependencies:
+      '@types/node': 20.12.7
+    dev: true
+
+  /@types/lodash@4.17.0:
+    resolution: {integrity: sha512-t7dhREVv6dbNj0q17X12j7yDG4bD/DHYX7o5/DbDxobP0HnGPgpRz2Ej77aL7TZT3DSw13fqUTj8J4mMnqa7WA==}
+    dev: true
+
+  /@types/node@20.12.7:
+    resolution: {integrity: sha512-wq0cICSkRLVaf3UGLMGItu/PtdY7oaXaI/RVU+xliKVOtRna3PRY57ZDfztpDL0n11vfymMUnXv8QwYCO7L1wg==}
+    dependencies:
+      undici-types: 5.26.5
+    dev: true
+
+  /JSONStream@1.3.5:
+    resolution: {integrity: sha512-E+iruNOY8VV9s4JEbe1aNEm6MiszPRr/UfcHMz0TQh1BXSxHK+ASV1R6W4HpjBhSeS+54PIsAMCBmwD06LLsqQ==}
+    hasBin: true
+    dependencies:
+      jsonparse: 1.3.1
+      through: 2.3.8
+    dev: false
+
+  /before-after-hook@2.2.3:
+    resolution: {integrity: sha512-NzUnlZexiaH/46WDhANlyR2bXRopNg4F/zuSA3OpZnllCUgRaOF2znDioDWrmbNVsuZk6l9pMquQB38cfBZwkQ==}
+    dev: false
+
+  /conventional-commit-types@3.0.0:
+    resolution: {integrity: sha512-SmmCYnOniSsAa9GqWOeLqc179lfr5TRu5b4QFDkbsrJ5TZjPJx85wtOr3zn+1dbeNiXDKGPbZ72IKbPhLXh/Lg==}
+    dev: false
+
+  /conventional-commits-parser@5.0.0:
+    resolution: {integrity: sha512-ZPMl0ZJbw74iS9LuX9YIAiW8pfM5p3yh2o/NbXHbkFuZzY5jvdi5jFycEOkmBW5H5I7nA+D6f3UcsCLP2vvSEA==}
+    engines: {node: '>=16'}
+    hasBin: true
+    dependencies:
+      JSONStream: 1.3.5
+      is-text-path: 2.0.0
+      meow: 12.1.1
+      split2: 4.2.0
+    dev: false
+
+  /dayjs@1.11.11:
+    resolution: {integrity: sha512-okzr3f11N6WuqYtZSvm+F776mB41wRZMhKP+hc34YdW+KmtYYK9iqvHSwo2k9FEH3fhGXvOPV6yz2IcSrfRUDg==}
+    dev: false
+
+  /deprecation@2.3.1:
+    resolution: {integrity: sha512-xmHIy4F3scKVwMsQ4WnVaS8bHOx0DmVwRywosKhaILI0ywMDWPtBSku2HNxRvF7jtwDRsoEwYQSfbxj8b7RlJQ==}
+    dev: false
+
+  /dotenv@16.4.5:
+    resolution: {integrity: sha512-ZmdL2rui+eB2YwhsWzjInR8LldtZHGDoQ1ugH85ppHKwpUHL7j7rN0Ti9NCnGiQbhaZ11FpR+7ao1dNsmduNUg==}
+    engines: {node: '>=12'}
+    dev: false
+
+  /esbuild@0.20.2:
+    resolution: {integrity: sha512-WdOOppmUNU+IbZ0PaDiTst80zjnrOkyJNHoKupIcVyU8Lvla3Ugx94VzkQ32Ijqd7UhHJy75gNWDMUekcrSJ6g==}
+    engines: {node: '>=12'}
+    hasBin: true
+    requiresBuild: true
+    optionalDependencies:
+      '@esbuild/aix-ppc64': 0.20.2
+      '@esbuild/android-arm': 0.20.2
+      '@esbuild/android-arm64': 0.20.2
+      '@esbuild/android-x64': 0.20.2
+      '@esbuild/darwin-arm64': 0.20.2
+      '@esbuild/darwin-x64': 0.20.2
+      '@esbuild/freebsd-arm64': 0.20.2
+      '@esbuild/freebsd-x64': 0.20.2
+      '@esbuild/linux-arm': 0.20.2
+      '@esbuild/linux-arm64': 0.20.2
+      '@esbuild/linux-ia32': 0.20.2
+      '@esbuild/linux-loong64': 0.20.2
+      '@esbuild/linux-mips64el': 0.20.2
+      '@esbuild/linux-ppc64': 0.20.2
+      '@esbuild/linux-riscv64': 0.20.2
+      '@esbuild/linux-s390x': 0.20.2
+      '@esbuild/linux-x64': 0.20.2
+      '@esbuild/netbsd-x64': 0.20.2
+      '@esbuild/openbsd-x64': 0.20.2
+      '@esbuild/sunos-x64': 0.20.2
+      '@esbuild/win32-arm64': 0.20.2
+      '@esbuild/win32-ia32': 0.20.2
+      '@esbuild/win32-x64': 0.20.2
+    dev: true
+
+  /fsevents@2.3.3:
+    resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==}
+    engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
+    os: [darwin]
+    requiresBuild: true
+    dev: true
+    optional: true
+
+  /get-tsconfig@4.7.3:
+    resolution: {integrity: sha512-ZvkrzoUA0PQZM6fy6+/Hce561s+faD1rsNwhnO5FelNjyy7EMGJ3Rz1AQ8GYDWjhRs/7dBLOEJvhK8MiEJOAFg==}
+    dependencies:
+      resolve-pkg-maps: 1.0.0
+    dev: true
+
+  /is-text-path@2.0.0:
+    resolution: {integrity: sha512-+oDTluR6WEjdXEJMnC2z6A4FRwFoYuvShVVEGsS7ewc0UTi2QtAKMDJuL4BDEVt+5T7MjFo12RP8ghOM75oKJw==}
+    engines: {node: '>=8'}
+    dependencies:
+      text-extensions: 2.4.0
+    dev: false
+
+  /json5@2.2.3:
+    resolution: {integrity: sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg==}
+    engines: {node: '>=6'}
+    hasBin: true
+    dev: true
+
+  /jsonparse@1.3.1:
+    resolution: {integrity: sha512-POQXvpdL69+CluYsillJ7SUhKvytYjW9vG/GKpnf+xP8UWgYEM/RaMzHHofbALDiKbbP1W8UEYmgGl39WkPZsg==}
+    engines: {'0': node >= 0.2.0}
+    dev: false
+
+  /lodash@4.17.21:
+    resolution: {integrity: sha512-v2kDEe57lecTulaDIuNTPy3Ry4gLGJ6Z1O3vE1krgXZNrsQ+LFTGHVxVjcXPs17LhbZVGedAJv8XZ1tvj5FvSg==}
+    dev: false
+
+  /meow@12.1.1:
+    resolution: {integrity: sha512-BhXM0Au22RwUneMPwSCnyhTOizdWoIEPU9sp0Aqa1PnDMR5Wv2FGXYDjuzJEIX+Eo2Rb8xuYe5jrnm5QowQFkw==}
+    engines: {node: '>=16.10'}
+    dev: false
+
+  /minimist@1.2.8:
+    resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==}
+    dev: true
+
+  /once@1.4.0:
+    resolution: {integrity: sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==}
+    dependencies:
+      wrappy: 1.0.2
+    dev: false
+
+  /resolve-pkg-maps@1.0.0:
+    resolution: {integrity: sha512-seS2Tj26TBVOC2NIc2rOe2y2ZO7efxITtLZcGSOnHHNOQ7CkiUBfw0Iw2ck6xkIhPwLhKNLS8BO+hEpngQlqzw==}
+    dev: true
+
+  /split2@4.2.0:
+    resolution: {integrity: sha512-UcjcJOWknrNkF6PLX83qcHM6KHgVKNkV62Y8a5uYDVv9ydGQVwAHMKqHdJje1VTWpljG0WYpCDhrCdAOYH4TWg==}
+    engines: {node: '>= 10.x'}
+    dev: false
+
+  /strip-bom@3.0.0:
+    resolution: {integrity: sha512-vavAMRXOgBVNF6nyEEmL3DBK19iRpDcoIwW+swQ+CbGiu7lju6t+JklA1MHweoWtadgt4ISVUsXLyDq34ddcwA==}
+    engines: {node: '>=4'}
+    dev: true
+
+  /text-extensions@2.4.0:
+    resolution: {integrity: sha512-te/NtwBwfiNRLf9Ijqx3T0nlqZiQ2XrrtBvu+cLL8ZRrGkO0NHTug8MYFKyoSrv/sHTaSKfilUkizV6XhxMJ3g==}
+    engines: {node: '>=8'}
+    dev: false
+
+  /through@2.3.8:
+    resolution: {integrity: sha512-w89qg7PI8wAdvX60bMDP+bFoD5Dvhm9oLheFp5O4a2QF0cSBGsBX4qZmadPMvVqlLJBBci+WqGGOAPvcDeNSVg==}
+    dev: false
+
+  /tsconfig-paths@4.2.0:
+    resolution: {integrity: sha512-NoZ4roiN7LnbKn9QqE1amc9DJfzvZXxF4xDavcOWt1BPkdx+m+0gJuPM+S0vCe7zTJMYUP0R8pO2XMr+Y8oLIg==}
+    engines: {node: '>=6'}
+    dependencies:
+      json5: 2.2.3
+      minimist: 1.2.8
+      strip-bom: 3.0.0
+    dev: true
+
+  /tsx@4.8.2:
+    resolution: {integrity: sha512-hmmzS4U4mdy1Cnzpl/NQiPUC2k34EcNSTZYVJThYKhdqTwuBeF+4cG9KUK/PFQ7KHaAaYwqlb7QfmsE2nuj+WA==}
+    engines: {node: '>=18.0.0'}
+    hasBin: true
+    dependencies:
+      esbuild: 0.20.2
+      get-tsconfig: 4.7.3
+    optionalDependencies:
+      fsevents: 2.3.3
+    dev: true
+
+  /tunnel@0.0.6:
+    resolution: {integrity: sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg==}
+    engines: {node: '>=0.6.11 <=0.7.0 || >=0.7.3'}
+    dev: false
+
+  /typescript@5.4.5:
+    resolution: {integrity: sha512-vcI4UpRgg81oIRUFwR0WSIHKt11nJ7SAVlYNIu+QpqeyXP+gpQJy/Z4+F0aGxSE4MqwjyXvW/TzgkLAx2AGHwQ==}
+    engines: {node: '>=14.17'}
+    hasBin: true
+    dev: true
+
+  /undici-types@5.26.5:
+    resolution: {integrity: sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==}
+    dev: true
+
+  /undici@5.28.4:
+    resolution: {integrity: sha512-72RFADWFqKmUb2hmmvNODKL3p9hcB6Gt2DOQMis1SEBaV6a4MH8soBvzg+95CYhCKPFedut2JY9bMfrDl9D23g==}
+    engines: {node: '>=14.0'}
+    dependencies:
+      '@fastify/busboy': 2.1.1
+    dev: false
+
+  /universal-user-agent@6.0.1:
+    resolution: {integrity: sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ==}
+    dev: false
+
+  /uuid@8.3.2:
+    resolution: {integrity: sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==}
+    hasBin: true
+    dev: false
+
+  /wrappy@1.0.2:
+    resolution: {integrity: sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==}
+    dev: false

cyborg/src/common.ts

@@ -0,0 +1,30 @@
+/*
+ * Copyright 2023 Greptime Team
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import * as core from "@actions/core";
+import {config} from "dotenv";
+import {getOctokit} from "@actions/github";
+import {GitHub} from "@actions/github/lib/utils";
+
+export function handleError(err: any): void {
+    console.error(err)
+    core.setFailed(`Unhandled error: ${err}`)
+}
+
+export function obtainClient(token: string): InstanceType<typeof GitHub> {
+    config()
+    return getOctokit(process.env[token])
+}

cyborg/tsconfig.json

@@ -0,0 +1,14 @@
+{
+  "ts-node": {
+    "require": ["tsconfig-paths/register"]
+  },
+  "compilerOptions": {
+    "module": "NodeNext",
+    "moduleResolution": "NodeNext",
+    "target": "ES6",
+    "paths": {
+      "@/*": ["./src/*"]
+    },
+    "resolveJsonModule": true,
+  }
+}

docs/benchmarks/tsbs/v0.7.0.md

@@ -0,0 +1,50 @@
+# TSBS benchmark - v0.7.0
+
+## Environment
+
+### Local
+|        |                                    |
+| ------ | ---------------------------------- |
+| CPU    | AMD Ryzen 7 7735HS (8 core 3.2GHz) |
+| Memory | 32GB                               |
+| Disk   | SOLIDIGM SSDPFKNU010TZ             |
+| OS     | Ubuntu 22.04.2 LTS                 |
+
+### Amazon EC2
+
+|         |                |
+| ------- | -------------- |
+| Machine | c5d.2xlarge    |
+| CPU     | 8 core         |
+| Memory  | 16GB           |
+| Disk    | 50GB (GP3)     |
+| OS      | Ubuntu 22.04.1 |
+
+
+## Write performance
+
+| Environment     | Ingest rate (rows/s) |
+| --------------- | -------------------- |
+| Local           | 369581.464           |
+| EC2 c5d.2xlarge | 298716.664           |
+
+
+## Query performance
+
+| Query type            | Local (ms) | EC2 c5d.2xlarge (ms) |
+| --------------------- | ---------- | -------------------- |
+| cpu-max-all-1         | 30.56      | 54.74                |
+| cpu-max-all-8         | 52.69      | 70.50                |
+| double-groupby-1      | 664.30     | 1366.63              |
+| double-groupby-5      | 1391.26    | 2141.71              |
+| double-groupby-all    | 2828.94    | 3389.59              |
+| groupby-orderby-limit | 718.92     | 1213.90              |
+| high-cpu-1            | 29.21      | 52.98                |
+| high-cpu-all          | 5514.12    | 7194.91              |
+| lastpoint             | 7571.40    | 9423.41              |
+| single-groupby-1-1-1  | 19.09      | 7.77                 |
+| single-groupby-1-1-12 | 27.28      | 51.64                |
+| single-groupby-1-8-1  | 31.85      | 11.64                |
+| single-groupby-5-1-1  | 16.14      | 9.67                 |
+| single-groupby-5-1-12 | 27.21      | 53.62                |
+| single-groupby-5-8-1  | 39.62      | 14.96                |

docs/how-to/how-to-write-fuzz-tests.md

@@ -0,0 +1,136 @@
+# How to write fuzz tests
+
+This document introduces how to write fuzz tests in GreptimeDB.
+
+## What is a fuzz test
+Fuzz test is tool that leverage deterministic random generation to assist in finding bugs. The goal of fuzz tests is to identify inputs generated by the fuzzer that cause system panics, crashes, or unexpected behaviors to occur. And we are using the [cargo-fuzz](https://github.com/rust-fuzz/cargo-fuzz) to run our fuzz test targets. 
+
+## Why we need them
+- Find bugs by leveraging random generation
+- Integrate with other tests (e.g., e2e)
+
+## Resources
+All fuzz test-related resources are located in the `/tests-fuzz` directory.
+There are two types of resources: (1) fundamental components and (2) test targets.
+
+### Fundamental components 
+They are located in the `/tests-fuzz/src` directory. The fundamental components define how to generate SQLs (including dialects for different protocols) and validate execution results (e.g., column attribute validation), etc.
+
+### Test targets
+They are located in the `/tests-fuzz/targets` directory, with each file representing an independent fuzz test case. The target utilizes fundamental components to generate SQLs, sends the generated SQLs via specified protocol, and validates the results of SQL execution.
+
+Figure 1 illustrates the fundamental components of the fuzz test provide the ability to generate random SQLs. It utilizes a Random Number Generator (Rng) to generate the Intermediate Representation (IR), then employs a DialectTranslator to produce specified dialects for different protocols. Finally, the fuzz tests send the generated SQL via the specified protocol and verify that the execution results meet expectations.
+```
+                            Rng                                 
+                             |                                  
+                             |                                  
+                             v                                  
+                       ExprGenerator                            
+                             |                                  
+                             |                                  
+                             v                                  
+               Intermediate representation (IR)                 
+                             |                                  
+                             |                                  
+      +----------------------+----------------------+           
+      |                      |                      |           
+      v                      v                      v           
+MySQLTranslator    PostgreSQLTranslator   OtherDialectTranslator
+      |                      |                      |           
+      |                      |                      |           
+      v                      v                      v           
+SQL(MySQL Dialect)         .....                  .....         
+      |
+      |
+      v
+  Fuzz Test
+
+```
+(Figure1: Overview of fuzz tests)
+
+For more details about fuzz targets and fundamental components, please refer to this [tracking issue](https://github.com/GreptimeTeam/greptimedb/issues/3174).
+
+## How to add a fuzz test target
+
+1. Create an empty rust source file under the `/tests-fuzz/targets/<fuzz-target>.rs` directory.
+
+2. Register the fuzz test target in the `/tests-fuzz/Cargo.toml` file.
+
+```toml
+[[bin]]
+name = "<fuzz-target>"
+path = "targets/<fuzz-target>.rs"
+test = false
+bench = false
+doc = false
+```
+
+3. Define the `FuzzInput` in the `/tests-fuzz/targets/<fuzz-target>.rs`.
+
+```rust
+#![no_main]
+use libfuzzer_sys::arbitrary::{Arbitrary, Unstructured};
+
+#[derive(Clone, Debug)]
+struct FuzzInput {
+    seed: u64,
+}
+
+impl Arbitrary<'_> for FuzzInput {
+    fn arbitrary(u: &mut Unstructured<'_>) -> arbitrary::Result<Self> {
+        let seed = u.int_in_range(u64::MIN..=u64::MAX)?;
+        Ok(FuzzInput { seed })
+    }
+}
+```
+
+4. Write your first fuzz test target in the `/tests-fuzz/targets/<fuzz-target>.rs`.
+
+```rust
+use libfuzzer_sys::fuzz_target;
+use rand::{Rng, SeedableRng};
+use rand_chacha::ChaChaRng;
+use snafu::ResultExt;
+use sqlx::{MySql, Pool};
+use tests_fuzz::fake::{
+    merge_two_word_map_fn, random_capitalize_map, uppercase_and_keyword_backtick_map,
+    MappedGenerator, WordGenerator,
+};
+use tests_fuzz::generator::create_expr::CreateTableExprGeneratorBuilder;
+use tests_fuzz::generator::Generator;
+use tests_fuzz::ir::CreateTableExpr;
+use tests_fuzz::translator::mysql::create_expr::CreateTableExprTranslator;
+use tests_fuzz::translator::DslTranslator;
+use tests_fuzz::utils::{init_greptime_connections, Connections};
+
+fuzz_target!(|input: FuzzInput| {
+    common_telemetry::init_default_ut_logging();
+    common_runtime::block_on_write(async {
+        let Connections { mysql } = init_greptime_connections().await;
+            let mut rng = ChaChaRng::seed_from_u64(input.seed);
+            let columns = rng.gen_range(2..30);
+            let create_table_generator = CreateTableExprGeneratorBuilder::default()
+                .name_generator(Box::new(MappedGenerator::new(
+                    WordGenerator,
+                    merge_two_word_map_fn(random_capitalize_map, uppercase_and_keyword_backtick_map),
+                )))
+                .columns(columns)
+                .engine("mito")
+                .if_not_exists(if_not_exists)
+                .build()
+                .unwrap();
+            let ir = create_table_generator.generate(&mut rng);
+            let translator = CreateTableExprTranslator;
+            let sql = translator.translate(&expr).unwrap();
+            mysql.execute(&sql).await
+    })
+});
+```
+
+5. Run your fuzz test target
+
+```bash
+    cargo fuzz run <fuzz-target> --fuzz-dir tests-fuzz
+```
+
+For more details, please refer to this [document](/tests-fuzz/README.md).

docs/rfcs/2023-05-09-distributed-planner.md

@@ -79,7 +79,7 @@ This RFC proposes to add a new expression node `MergeScan` to merge result from
 │               │    │                             │
 └─Frontend──────┘    └─Remote-Sources──────────────┘
 ```
-This merge operation simply chains all the the underlying remote data sources and return `RecordBatch`, just like a coalesce op. And each remote sources is a gRPC query to datanode via the substrait logical plan interface. The plan is transformed and divided from the original query that comes to frontend.
+This merge operation simply chains all the underlying remote data sources and return `RecordBatch`, just like a coalesce op. And each remote sources is a gRPC query to datanode via the substrait logical plan interface. The plan is transformed and divided from the original query that comes to frontend.
 
 ## Commutativity of MergeScan
 

docs/rfcs/2023-07-06-table-engine-refactor.md

@@ -27,8 +27,8 @@ subgraph Frontend["Frontend"]
     end
 end
 
-MyTable --> MetaSrv
-MetaSrv --> ETCD
+MyTable --> Metasrv
+Metasrv --> ETCD
 
 MyTable-->TableEngine0
 MyTable-->TableEngine1
@@ -95,8 +95,8 @@ subgraph Frontend["Frontend"]
     end
 end
 
-MyTable --> MetaSrv
-MetaSrv --> ETCD
+MyTable --> Metasrv
+Metasrv --> ETCD
 
 MyTable-->RegionEngine
 MyTable-->RegionEngine1

docs/rfcs/2024-01-17-dataflow-framework.md

@@ -36,7 +36,7 @@ Hence, we choose the third option, and use a simple logical plan that's anagonis
 ## Deploy mode and protocol
 - Greptime Flow is an independent streaming compute component. It can be used either within a standalone node or as a dedicated node at the same level as frontend in distributed mode.
 - It accepts insert request Rows, which is used between frontend and datanode.
-- New flow job is submitted in the format of modified SQL query like snowflake do, like: `CREATE TASK avg_over_5m WINDOW_SIZE = "5m" AS SELECT avg(value) FROM table WHERE time > now() - 5m GROUP BY time(1m)`. Flow job then got stored in MetaSrv.
+- New flow job is submitted in the format of modified SQL query like snowflake do, like: `CREATE TASK avg_over_5m WINDOW_SIZE = "5m" AS SELECT avg(value) FROM table WHERE time > now() - 5m GROUP BY time(1m)`. Flow job then got stored in Metasrv.
 - It also persists results in the format of Rows to frontend.
 - The query plan uses Substrait as codec format. It's the same with GreptimeDB's query engine.
 - Greptime Flow needs a WAL for recovering. It's possible to reuse datanode's.

docs/rfcs/2024-02-21-multi-dimension-partition-rule/rfc.md

@@ -0,0 +1,101 @@
+---
+Feature Name:  Multi-dimension Partition Rule
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/3351
+Date: 2024-02-21
+Author: "Ruihang Xia <waynestxia@gmail.com>"
+---
+
+# Summary
+
+A new region partition scheme that runs on multiple dimensions of the key space. The partition rule is defined by a set of simple expressions on the partition key columns.
+
+# Motivation
+
+The current partition rule is from MySQL's [`RANGE Partition`](https://dev.mysql.com/doc/refman/8.0/en/partitioning-range.html), which is based on a single dimension. It is sort of a [Hilbert Curve](https://en.wikipedia.org/wiki/Hilbert_curve) and pick several point on the curve to divide the space. It is neither easy to understand how the data get partitioned nor flexible enough to handle complex partitioning requirements.
+
+Considering the future requirements like region repartitioning or autonomous rebalancing, where both workload and partition may change frequently. Here proposes a new region partition scheme that uses a set of simple expressions on the partition key columns to divide the key space.
+
+# Details
+
+## Partition rule
+
+First, we define a simple expression that can be used to define the partition rule. The simple expression is a binary expression expression on the partition key columns that can be evaluated to a boolean value. The binary operator is limited to comparison operators only, like `=`, `!=`, `>`, `>=`, `<`, `<=`. And the operands are limited either literal value or partition column.
+
+Example of valid simple expressions are $`col_A = 10`$, $`col_A \gt 10 \& col_B \gt 20`$ or $`col_A \ne 10`$.
+
+Those expressions can be used as predicates to divide the key space into different regions. The following example have two partition columns `Col A` and `Col B`, and four partitioned regions.
+
+```math
+\left\{\begin{aligned}
+ 
+&col_A \le 10 &Region_1 \\
+&10 \lt col_A \& col_A \le 20 &Region_2 \\
+&20 \lt col_A \space \& \space col_B \lt 100 &Region_3 \\
+&20 \lt col_A \space \& \space col_B \ge 100 &Region_4
+
+\end{aligned}\right\}
+```
+
+An advantage of this scheme is that it is easy to understand how the data get partitioned. The above example can be visualized in a 2D space (two partition column is involved in the example).
+
+![example](2d-example.png)
+
+Here each expression draws a line in the 2D space. Managing data partitioning becomes a matter of drawing lines in the key space.
+
+To make it easy to use, there is a "default region" which catches all the data that doesn't match any of previous expressions. The default region exist by default and do not need to specify. It is also possible to remove this default region if the DB finds it is not necessary.
+
+## SQL interface
+
+The SQL interface is in response to two parts: specifying the partition columns and the partition rule. Thouth we are targeting an autonomous system, it's still allowed to give some bootstrap rules or hints on creating table.
+
+Partition column is specified by `PARTITION ON COLUMNS` sub-clause in `CREATE TABLE`:
+
+```sql
+CREATE TABLE t (...)
+PARTITION ON COLUMNS (...) ();
+```
+
+Two following brackets are for partition columns and partition rule respectively.
+
+Columns provided here are only used as an allow-list of how the partition rule can be defined. Which means (a) the sequence between columns doesn't matter, (b) the columns provided here are not necessarily being used in the partition rule.
+
+The partition rule part is a list of comma-separated simple expressions. Expressions here are not corresponding to region, as they might be changed by system to fit various workload.
+
+A full example of `CREATE TABLE` with partition rule is:
+
+```sql
+CREATE TABLE IF NOT EXISTS demo (
+  a STRING,
+  b STRING,
+  c STRING,
+  d STRING,
+  ts TIMESTAMP,
+  memory DOUBLE,
+  TIME INDEX (ts),
+  PRIMARY KEY (a, b, c, d)
+)
+PARTITION ON COLUMNS (c, b, a) (
+  a < 10,
+  10 >= a AND a < 20,
+  20 >= a AND b < 100,
+  20 >= a AND b > 100
+)
+```
+
+## Combine with storage
+
+Examining columns separately suits our columnar storage very well in two aspects.
+
+1. The simple expression can be pushed down to storage and file format, and is likely to hit existing index. Makes pruning operation very efficient.
+
+2. Columns in columnar storage are not tightly coupled like in the traditional row storages, which means we can easily add or remove columns from partition rule without much impact (like a global reshuffle) on data.
+
+The data file itself can be "projected" to the key space as a polyhedron, it is guaranteed that each plane is in parallel with some coordinate planes (in a 2D scenario, this is saying that all the files can be projected to a rectangle). Thus partition or repartition also only need to consider related columns.
+
+![sst-project](sst-project.png)
+
+An additional limitation is that considering how the index works and how we organize the primary keys at present, the partition columns are limited to be a subset of primary keys for better performance.
+
+# Drawbacks
+
+This is a breaking change.

docs/schema-structs.md

@@ -73,7 +73,7 @@ CREATE TABLE cpu (
     usage_system DOUBLE,
     datacenter STRING,
     TIME INDEX (ts),
-    PRIMARY KEY(datacenter, host)) ENGINE=mito WITH(regions=1);
+    PRIMARY KEY(datacenter, host)) ENGINE=mito;
 ```
 
 Then the table's `TableMeta` may look like this:
@@ -249,7 +249,7 @@ CREATE TABLE cpu (
     usage_system DOUBLE,
     datacenter STRING,
     TIME INDEX (ts),
-    PRIMARY KEY(datacenter, host)) ENGINE=mito WITH(regions=1);
+    PRIMARY KEY(datacenter, host)) ENGINE=mito;
 
 select ts, usage_system from cpu;
 ```

docs/style-guide.md

@@ -0,0 +1,46 @@
+# GreptimeDB Style Guide
+
+This style guide is intended to help contributors to GreptimeDB write code that is consistent with the rest of the codebase. It is a living document and will be updated as the codebase evolves.
+
+It's mainly an complement to the [Rust Style Guide](https://pingcap.github.io/style-guide/rust/).
+
+## Table of Contents
+
+- Formatting
+- Modules
+- Comments
+
+## Formatting
+
+- Place all `mod` declaration before any `use`.
+- Use `unimplemented!()` instead of `todo!()` for things that aren't likely to be implemented.
+- Add an empty line before and after declaration blocks.
+- Place comment before attributes (`#[]`) and derive (`#[derive]`).
+
+## Modules
+
+- Use the file with same name instead of `mod.rs` to define a module. E.g.:
+
+```
+.
+├── cache
+│  ├── cache_size.rs
+│  └── write_cache.rs
+└── cache.rs
+```
+
+## Comments
+
+- Add comments for public functions and structs.
+- Prefer document comment (`///`) over normal comment (`//`) for structs, fields, functions etc.
+- Add link (`[]`) to struct, method, or any other reference. And make sure that link works.
+
+## Error handling
+
+- Define a custom error type for the module if needed.
+- Prefer `with_context()` over `context()` when allocation is needed to construct an error.
+- Use `error!()` or `warn!()` macros in the `common_telemetry` crate to log errors. E.g.:
+
+```rust
+error!(e; "Failed to do something");
+```

grafana/README.md

@@ -7,4 +7,60 @@ Status notify: we are still working on this config. It's expected to change freq
 
 # How to use
 
+## `greptimedb.json`
+
 Open Grafana Dashboard page, choose `New` -> `Import`. And upload `greptimedb.json` file.
+
+## `greptimedb-cluster.json`
+
+This cluster dashboard provides a comprehensive view of incoming requests, response statuses, and internal activities such as flush and compaction, with a layered structure from frontend to datanode. Designed with a focus on alert functionality, its primary aim is to highlight any anomalies in metrics, allowing users to quickly pinpoint the cause of errors.
+
+We use Prometheus to scrape off metrics from nodes in GreptimeDB cluster, Grafana to visualize the diagram. Any compatible stack should work too.
+
+__Note__: This dashboard is still in an early stage of development. Any issue or advice on improvement is welcomed.
+
+### Configuration
+
+Please ensure the following configuration before importing the dashboard into Grafana.
+
+__1. Prometheus scrape config__
+
+Assign `greptime_pod` label to each host target. We use this label to identify each node instance.
+
+```yml
+# example config
+# only to indicate how to assign labels to each target
+# modify yours accordingly
+scrape_configs:
+  - job_name: metasrv
+    static_configs:
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: metasrv
+
+  - job_name: datanode
+    static_configs:
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode1
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode2
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode3
+
+  - job_name: frontend
+    static_configs:
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: frontend
+```
+
+__2. Grafana config__
+
+Create a Prometheus data source in Grafana before using this dashboard. We use `datasource` as a variable in Grafana dashboard so that multiple environments are supported.
+
+### Usage
+
+Use `datasource` or `greptime_pod` on the upper-left corner to filter data from certain node.

grafana/greptimedb.json

@@ -66,7 +66,7 @@
   },
   "editable": true,
   "fiscalYearStartMonth": 0,
-  "graphTooltip": 0,
+  "graphTooltip": 1,
   "id": null,
   "links": [],
   "liveNow": false,
@@ -2116,7 +2116,7 @@
               }
             ]
           },
-          "unit": "bytes"
+          "unit": "none"
         },
         "overrides": []
       },
@@ -2126,7 +2126,7 @@
         "x": 0,
         "y": 61
       },
-      "id": 12,
+      "id": 17,
       "interval": "1s",
       "options": {
         "legend": {
@@ -2147,8 +2147,8 @@
             "uid": "${DS_PROMETHEUS-1}"
           },
           "disableTextWrap": false,
-          "editorMode": "builder",
-          "expr": "histogram_quantile(0.95, sum by(le) (rate(raft_engine_write_size_bucket[$__rate_interval])))",
+          "editorMode": "code",
+          "expr": "rate(raft_engine_sync_log_duration_seconds_count[2s])",
           "fullMetaSearch": false,
           "includeNullMetadata": false,
           "instant": false,
@@ -2158,7 +2158,7 @@
           "useBackend": false
         }
       ],
-      "title": "wal write size",
+      "title": "raft engine sync count",
       "type": "timeseries"
     },
     {
@@ -2378,6 +2378,120 @@
       ],
       "title": "raft engine write duration seconds",
       "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS-1}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 12,
+        "y": 68
+      },
+      "id": 12,
+      "interval": "1s",
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS-1}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum by(le) (rate(raft_engine_write_size_bucket[$__rate_interval])))",
+          "fullMetaSearch": false,
+          "includeNullMetadata": false,
+          "instant": false,
+          "legendFormat": "req-size-p95",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS-1}"
+          },
+          "editorMode": "code",
+          "expr": "rate(raft_engine_write_size_sum[$__rate_interval])",
+          "hide": false,
+          "instant": false,
+          "legendFormat": "throughput",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "wal write size",
+      "type": "timeseries"
     }
   ],
   "refresh": "10s",
@@ -2387,13 +2501,13 @@
     "list": []
   },
   "time": {
-    "from": "now-3h",
+    "from": "now-30m",
     "to": "now"
   },
   "timepicker": {},
   "timezone": "",
   "title": "GreptimeDB",
   "uid": "e7097237-669b-4f8d-b751-13067afbfb68",
-  "version": 9,
+  "version": 12,
   "weekStart": ""
 }

licenserc.toml

@@ -17,6 +17,15 @@ headerPath = "Apache-2.0.txt"
 includes = [
     "*.rs",
     "*.py",
+    "*.ts",
+]
+
+excludes = [
+    # copied sources
+    "src/common/base/src/readable_size.rs",
+    "src/common/base/src/secrets.rs",
+    "src/servers/src/repeated_field.rs",
+    "src/servers/src/http/test_helpers.rs",
 ]
 
 [properties]

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "nightly-2023-12-19"
+channel = "nightly-2024-04-20"

scripts/fetch-dashboard-assets.sh

@@ -1,8 +1,7 @@
 #!/usr/bin/env bash
 
 # This script is used to download built dashboard assets from the "GreptimeTeam/dashboard" repository.
-
-set -e -x
+set -ex
 
 declare -r SCRIPT_DIR=$(cd $(dirname ${0}) >/dev/null 2>&1 && pwd)
 declare -r ROOT_DIR=$(dirname ${SCRIPT_DIR})
@@ -13,13 +12,34 @@ RELEASE_VERSION="$(cat $STATIC_DIR/VERSION | tr -d '\t\r\n ')"
 
 echo "Downloading assets to dir: $OUT_DIR"
 cd $OUT_DIR
+
+if [[ -z "$GITHUB_PROXY_URL" ]]; then
+  GITHUB_URL="https://github.com"
+else
+  GITHUB_URL="${GITHUB_PROXY_URL%/}"
+fi
+
+function retry_fetch() {
+    local url=$1
+    local filename=$2
+
+    curl --connect-timeout 10 --retry 3 -fsSL $url --output $filename || {
+        echo "Failed to download $url"
+        echo "You may try to set http_proxy and https_proxy environment variables."
+        if [[ -z "$GITHUB_PROXY_URL" ]]; then
+          echo "You may try to set GITHUB_PROXY_URL=http://mirror.ghproxy.com/https://github.com/"
+        fi
+        exit 1
+     }
+}
+
 # Download the SHA256 checksum attached to the release. To verify the integrity
 # of the download, this checksum will be used to check the download tar file
 # containing the built dashboard assets.
-curl -Ls https://github.com/GreptimeTeam/dashboard/releases/download/$RELEASE_VERSION/sha256.txt --output sha256.txt
+retry_fetch "${GITHUB_URL}/GreptimeTeam/dashboard/releases/download/${RELEASE_VERSION}/sha256.txt" sha256.txt
 
 # Download the tar file containing the built dashboard assets.
-curl -L https://github.com/GreptimeTeam/dashboard/releases/download/$RELEASE_VERSION/build.tar.gz --output build.tar.gz
+retry_fetch "${GITHUB_URL}/GreptimeTeam/dashboard/releases/download/${RELEASE_VERSION}/build.tar.gz" build.tar.gz
 
 # Verify the checksums match; exit if they don't.
 case "$(uname -s)" in

src/api/Cargo.toml

@@ -4,6 +4,9 @@ version.workspace = true
 edition.workspace = true
 license.workspace = true
 
+[lints]
+workspace = true
+
 [dependencies]
 common-base.workspace = true
 common-decimal.workspace = true
@@ -15,7 +18,6 @@ greptime-proto.workspace = true
 paste = "1.0"
 prost.workspace = true
 snafu.workspace = true
-tonic.workspace = true
 
 [build-dependencies]
 tonic-build = "0.9"

src/api/src/error.rs

@@ -30,6 +30,7 @@ pub enum Error {
     #[snafu(display("Unknown proto column datatype: {}", datatype))]
     UnknownColumnDataType {
         datatype: i32,
+        #[snafu(implicit)]
         location: Location,
         #[snafu(source)]
         error: prost::DecodeError,
@@ -38,12 +39,14 @@ pub enum Error {
     #[snafu(display("Failed to create column datatype from {:?}", from))]
     IntoColumnDataType {
         from: ConcreteDataType,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Failed to convert column default constraint, column: {}", column))]
     ConvertColumnDefaultConstraint {
         column: String,
+        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },
@@ -51,6 +54,7 @@ pub enum Error {
     #[snafu(display("Invalid column default constraint, column: {}", column))]
     InvalidColumnDefaultConstraint {
         column: String,
+        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },

src/api/src/helper.rs

@@ -20,21 +20,20 @@ use common_decimal::Decimal128;
 use common_time::interval::IntervalUnit;
 use common_time::time::Time;
 use common_time::timestamp::TimeUnit;
-use common_time::{Date, DateTime, Duration, Interval, Timestamp};
+use common_time::{Date, DateTime, Interval, Timestamp};
 use datatypes::prelude::{ConcreteDataType, ValueRef};
 use datatypes::scalars::ScalarVector;
 use datatypes::types::{
-    DurationType, Int16Type, Int8Type, IntervalType, TimeType, TimestampType, UInt16Type, UInt8Type,
+    Int16Type, Int8Type, IntervalType, TimeType, TimestampType, UInt16Type, UInt8Type,
 };
 use datatypes::value::{OrderedF32, OrderedF64, Value};
 use datatypes::vectors::{
-    BinaryVector, BooleanVector, DateTimeVector, DateVector, Decimal128Vector,
-    DurationMicrosecondVector, DurationMillisecondVector, DurationNanosecondVector,
-    DurationSecondVector, Float32Vector, Float64Vector, Int32Vector, Int64Vector,
-    IntervalDayTimeVector, IntervalMonthDayNanoVector, IntervalYearMonthVector, PrimitiveVector,
-    StringVector, TimeMicrosecondVector, TimeMillisecondVector, TimeNanosecondVector,
-    TimeSecondVector, TimestampMicrosecondVector, TimestampMillisecondVector,
-    TimestampNanosecondVector, TimestampSecondVector, UInt32Vector, UInt64Vector, VectorRef,
+    BinaryVector, BooleanVector, DateTimeVector, DateVector, Decimal128Vector, Float32Vector,
+    Float64Vector, Int32Vector, Int64Vector, IntervalDayTimeVector, IntervalMonthDayNanoVector,
+    IntervalYearMonthVector, PrimitiveVector, StringVector, TimeMicrosecondVector,
+    TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector, TimestampMicrosecondVector,
+    TimestampMillisecondVector, TimestampNanosecondVector, TimestampSecondVector, UInt32Vector,
+    UInt64Vector, VectorRef,
 };
 use greptime_proto::v1;
 use greptime_proto::v1::column_data_type_extension::TypeExt;
@@ -127,14 +126,6 @@ impl From<ColumnDataTypeWrapper> for ConcreteDataType {
             ColumnDataType::IntervalMonthDayNano => {
                 ConcreteDataType::interval_month_day_nano_datatype()
             }
-            ColumnDataType::DurationSecond => ConcreteDataType::duration_second_datatype(),
-            ColumnDataType::DurationMillisecond => {
-                ConcreteDataType::duration_millisecond_datatype()
-            }
-            ColumnDataType::DurationMicrosecond => {
-                ConcreteDataType::duration_microsecond_datatype()
-            }
-            ColumnDataType::DurationNanosecond => ConcreteDataType::duration_nanosecond_datatype(),
             ColumnDataType::Decimal128 => {
                 if let Some(TypeExt::DecimalType(d)) = datatype_wrapper
                     .datatype_ext
@@ -212,11 +203,7 @@ impl_column_type_functions_with_snake!(
     TimeNanosecond,
     IntervalYearMonth,
     IntervalDayTime,
-    IntervalMonthDayNano,
-    DurationSecond,
-    DurationMillisecond,
-    DurationMicrosecond,
-    DurationNanosecond
+    IntervalMonthDayNano
 );
 
 impl ColumnDataTypeWrapper {
@@ -270,16 +257,11 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
                 IntervalType::DayTime(_) => ColumnDataType::IntervalDayTime,
                 IntervalType::MonthDayNano(_) => ColumnDataType::IntervalMonthDayNano,
             },
-            ConcreteDataType::Duration(d) => match d {
-                DurationType::Second(_) => ColumnDataType::DurationSecond,
-                DurationType::Millisecond(_) => ColumnDataType::DurationMillisecond,
-                DurationType::Microsecond(_) => ColumnDataType::DurationMicrosecond,
-                DurationType::Nanosecond(_) => ColumnDataType::DurationNanosecond,
-            },
             ConcreteDataType::Decimal128(_) => ColumnDataType::Decimal128,
             ConcreteDataType::Null(_)
             | ConcreteDataType::List(_)
-            | ConcreteDataType::Dictionary(_) => {
+            | ConcreteDataType::Dictionary(_)
+            | ConcreteDataType::Duration(_) => {
                 return error::IntoColumnDataTypeSnafu { from: datatype }.fail()
             }
         };
@@ -409,22 +391,6 @@ pub fn values_with_capacity(datatype: ColumnDataType, capacity: usize) -> Values
             interval_month_day_nano_values: Vec::with_capacity(capacity),
             ..Default::default()
         },
-        ColumnDataType::DurationSecond => Values {
-            duration_second_values: Vec::with_capacity(capacity),
-            ..Default::default()
-        },
-        ColumnDataType::DurationMillisecond => Values {
-            duration_millisecond_values: Vec::with_capacity(capacity),
-            ..Default::default()
-        },
-        ColumnDataType::DurationMicrosecond => Values {
-            duration_microsecond_values: Vec::with_capacity(capacity),
-            ..Default::default()
-        },
-        ColumnDataType::DurationNanosecond => Values {
-            duration_nanosecond_values: Vec::with_capacity(capacity),
-            ..Default::default()
-        },
         ColumnDataType::Decimal128 => Values {
             decimal128_values: Vec::with_capacity(capacity),
             ..Default::default()
@@ -476,14 +442,8 @@ pub fn push_vals(column: &mut Column, origin_count: usize, vector: VectorRef) {
                 .interval_month_day_nano_values
                 .push(convert_i128_to_interval(val.to_i128())),
         },
-        Value::Duration(val) => match val.unit() {
-            TimeUnit::Second => values.duration_second_values.push(val.value()),
-            TimeUnit::Millisecond => values.duration_millisecond_values.push(val.value()),
-            TimeUnit::Microsecond => values.duration_microsecond_values.push(val.value()),
-            TimeUnit::Nanosecond => values.duration_nanosecond_values.push(val.value()),
-        },
         Value::Decimal128(val) => values.decimal128_values.push(convert_to_pb_decimal128(val)),
-        Value::List(_) => unreachable!(),
+        Value::List(_) | Value::Duration(_) => unreachable!(),
     });
     column.null_mask = null_mask.into_vec();
 }
@@ -518,6 +478,10 @@ fn ddl_request_type(request: &DdlRequest) -> &'static str {
         Some(Expr::Alter(_)) => "ddl.alter",
         Some(Expr::DropTable(_)) => "ddl.drop_table",
         Some(Expr::TruncateTable(_)) => "ddl.truncate_table",
+        Some(Expr::CreateFlow(_)) => "ddl.create_flow",
+        Some(Expr::DropFlow(_)) => "ddl.drop_flow",
+        Some(Expr::CreateView(_)) => "ddl.create_view",
+        Some(Expr::DropView(_)) => "ddl.drop_view",
         None => "ddl.empty",
     }
 }
@@ -583,10 +547,6 @@ pub fn pb_value_to_value_ref<'a>(
             let interval = Interval::from_month_day_nano(v.months, v.days, v.nanoseconds);
             ValueRef::Interval(interval)
         }
-        ValueData::DurationSecondValue(v) => ValueRef::Duration(Duration::new_second(*v)),
-        ValueData::DurationMillisecondValue(v) => ValueRef::Duration(Duration::new_millisecond(*v)),
-        ValueData::DurationMicrosecondValue(v) => ValueRef::Duration(Duration::new_microsecond(*v)),
-        ValueData::DurationNanosecondValue(v) => ValueRef::Duration(Duration::new_nanosecond(*v)),
         ValueData::Decimal128Value(v) => {
             // get precision and scale from datatype_extension
             if let Some(TypeExt::DecimalType(d)) = datatype_ext
@@ -681,33 +641,21 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
                 ))
             }
         },
-        ConcreteDataType::Duration(unit) => match unit {
-            DurationType::Second(_) => Arc::new(DurationSecondVector::from_vec(
-                values.duration_second_values,
-            )),
-            DurationType::Millisecond(_) => Arc::new(DurationMillisecondVector::from_vec(
-                values.duration_millisecond_values,
-            )),
-            DurationType::Microsecond(_) => Arc::new(DurationMicrosecondVector::from_vec(
-                values.duration_microsecond_values,
-            )),
-            DurationType::Nanosecond(_) => Arc::new(DurationNanosecondVector::from_vec(
-                values.duration_nanosecond_values,
-            )),
-        },
         ConcreteDataType::Decimal128(d) => Arc::new(Decimal128Vector::from_values(
             values.decimal128_values.iter().map(|x| {
                 Decimal128::from_value_precision_scale(x.hi, x.lo, d.precision(), d.scale()).into()
             }),
         )),
-        ConcreteDataType::Null(_) | ConcreteDataType::List(_) | ConcreteDataType::Dictionary(_) => {
+        ConcreteDataType::Null(_)
+        | ConcreteDataType::List(_)
+        | ConcreteDataType::Dictionary(_)
+        | ConcreteDataType::Duration(_) => {
             unreachable!()
         }
     }
 }
 
 pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<Value> {
-    // TODO(fys): use macros to optimize code
     match data_type {
         ConcreteDataType::Int64(_) => values
             .i64_values
@@ -850,26 +798,6 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
                 ))
             })
             .collect(),
-        ConcreteDataType::Duration(DurationType::Second(_)) => values
-            .duration_second_values
-            .into_iter()
-            .map(|v| Value::Duration(Duration::new_second(v)))
-            .collect(),
-        ConcreteDataType::Duration(DurationType::Millisecond(_)) => values
-            .duration_millisecond_values
-            .into_iter()
-            .map(|v| Value::Duration(Duration::new_millisecond(v)))
-            .collect(),
-        ConcreteDataType::Duration(DurationType::Microsecond(_)) => values
-            .duration_microsecond_values
-            .into_iter()
-            .map(|v| Value::Duration(Duration::new_microsecond(v)))
-            .collect(),
-        ConcreteDataType::Duration(DurationType::Nanosecond(_)) => values
-            .duration_nanosecond_values
-            .into_iter()
-            .map(|v| Value::Duration(Duration::new_nanosecond(v)))
-            .collect(),
         ConcreteDataType::Decimal128(d) => values
             .decimal128_values
             .into_iter()
@@ -882,7 +810,10 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
                 ))
             })
             .collect(),
-        ConcreteDataType::Null(_) | ConcreteDataType::List(_) | ConcreteDataType::Dictionary(_) => {
+        ConcreteDataType::Null(_)
+        | ConcreteDataType::List(_)
+        | ConcreteDataType::Dictionary(_)
+        | ConcreteDataType::Duration(_) => {
             unreachable!()
         }
     }
@@ -994,24 +925,10 @@ pub fn to_proto_value(value: Value) -> Option<v1::Value> {
                 )),
             },
         },
-        Value::Duration(v) => match v.unit() {
-            TimeUnit::Second => v1::Value {
-                value_data: Some(ValueData::DurationSecondValue(v.value())),
-            },
-            TimeUnit::Millisecond => v1::Value {
-                value_data: Some(ValueData::DurationMillisecondValue(v.value())),
-            },
-            TimeUnit::Microsecond => v1::Value {
-                value_data: Some(ValueData::DurationMicrosecondValue(v.value())),
-            },
-            TimeUnit::Nanosecond => v1::Value {
-                value_data: Some(ValueData::DurationNanosecondValue(v.value())),
-            },
-        },
         Value::Decimal128(v) => v1::Value {
             value_data: Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
         },
-        Value::List(_) => return None,
+        Value::List(_) | Value::Duration(_) => return None,
     };
 
     Some(proto_value)
@@ -1048,10 +965,6 @@ pub fn proto_value_type(value: &v1::Value) -> Option<ColumnDataType> {
         ValueData::IntervalYearMonthValue(_) => ColumnDataType::IntervalYearMonth,
         ValueData::IntervalDayTimeValue(_) => ColumnDataType::IntervalDayTime,
         ValueData::IntervalMonthDayNanoValue(_) => ColumnDataType::IntervalMonthDayNano,
-        ValueData::DurationSecondValue(_) => ColumnDataType::DurationSecond,
-        ValueData::DurationMillisecondValue(_) => ColumnDataType::DurationMillisecond,
-        ValueData::DurationMicrosecondValue(_) => ColumnDataType::DurationMicrosecond,
-        ValueData::DurationNanosecondValue(_) => ColumnDataType::DurationNanosecond,
         ValueData::Decimal128Value(_) => ColumnDataType::Decimal128,
     };
     Some(value_type)
@@ -1109,14 +1022,8 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
                     ValueData::IntervalMonthDayNanoValue(convert_i128_to_interval(v.to_i128()))
                 }
             }),
-            Value::Duration(v) => Some(match v.unit() {
-                TimeUnit::Second => ValueData::DurationSecondValue(v.value()),
-                TimeUnit::Millisecond => ValueData::DurationMillisecondValue(v.value()),
-                TimeUnit::Microsecond => ValueData::DurationMicrosecondValue(v.value()),
-                TimeUnit::Nanosecond => ValueData::DurationNanosecondValue(v.value()),
-            }),
             Value::Decimal128(v) => Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
-            Value::List(_) => unreachable!(),
+            Value::List(_) | Value::Duration(_) => unreachable!(),
         },
     }
 }
@@ -1126,16 +1033,15 @@ mod tests {
     use std::sync::Arc;
 
     use datatypes::types::{
-        DurationMillisecondType, DurationSecondType, Int32Type, IntervalDayTimeType,
-        IntervalMonthDayNanoType, IntervalYearMonthType, TimeMillisecondType, TimeSecondType,
-        TimestampMillisecondType, TimestampSecondType, UInt32Type,
+        Int32Type, IntervalDayTimeType, IntervalMonthDayNanoType, IntervalYearMonthType,
+        TimeMillisecondType, TimeSecondType, TimestampMillisecondType, TimestampSecondType,
+        UInt32Type,
     };
     use datatypes::vectors::{
-        BooleanVector, DurationMicrosecondVector, DurationMillisecondVector,
-        DurationNanosecondVector, DurationSecondVector, IntervalDayTimeVector,
-        IntervalMonthDayNanoVector, IntervalYearMonthVector, TimeMicrosecondVector,
-        TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector, TimestampMicrosecondVector,
-        TimestampMillisecondVector, TimestampNanosecondVector, TimestampSecondVector, Vector,
+        BooleanVector, IntervalDayTimeVector, IntervalMonthDayNanoVector, IntervalYearMonthVector,
+        TimeMicrosecondVector, TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector,
+        TimestampMicrosecondVector, TimestampMillisecondVector, TimestampNanosecondVector,
+        TimestampSecondVector, Vector,
     };
     use paste::paste;
 
@@ -1211,10 +1117,6 @@ mod tests {
         let values = values.interval_month_day_nano_values;
         assert_eq!(2, values.capacity());
 
-        let values = values_with_capacity(ColumnDataType::DurationMillisecond, 2);
-        let values = values.duration_millisecond_values;
-        assert_eq!(2, values.capacity());
-
         let values = values_with_capacity(ColumnDataType::Decimal128, 2);
         let values = values.decimal128_values;
         assert_eq!(2, values.capacity());
@@ -1302,10 +1204,6 @@ mod tests {
             ConcreteDataType::interval_datatype(IntervalUnit::MonthDayNano),
             ColumnDataTypeWrapper::interval_month_day_nano_datatype().into()
         );
-        assert_eq!(
-            ConcreteDataType::duration_millisecond_datatype(),
-            ColumnDataTypeWrapper::duration_millisecond_datatype().into()
-        );
         assert_eq!(
             ConcreteDataType::decimal128_datatype(10, 2),
             ColumnDataTypeWrapper::decimal128_datatype(10, 2).into()
@@ -1398,12 +1296,6 @@ mod tests {
                 .try_into()
                 .unwrap()
         );
-        assert_eq!(
-            ColumnDataTypeWrapper::duration_millisecond_datatype(),
-            ConcreteDataType::duration_millisecond_datatype()
-                .try_into()
-                .unwrap()
-        );
 
         assert_eq!(
             ColumnDataTypeWrapper::decimal128_datatype(10, 2),
@@ -1557,48 +1449,6 @@ mod tests {
         });
     }
 
-    #[test]
-    fn test_column_put_duration_values() {
-        let mut column = Column {
-            column_name: "test".to_string(),
-            semantic_type: 0,
-            values: Some(Values {
-                ..Default::default()
-            }),
-            null_mask: vec![],
-            datatype: 0,
-            ..Default::default()
-        };
-
-        let vector = Arc::new(DurationNanosecondVector::from_vec(vec![1, 2, 3]));
-        push_vals(&mut column, 3, vector);
-        assert_eq!(
-            vec![1, 2, 3],
-            column.values.as_ref().unwrap().duration_nanosecond_values
-        );
-
-        let vector = Arc::new(DurationMicrosecondVector::from_vec(vec![7, 8, 9]));
-        push_vals(&mut column, 3, vector);
-        assert_eq!(
-            vec![7, 8, 9],
-            column.values.as_ref().unwrap().duration_microsecond_values
-        );
-
-        let vector = Arc::new(DurationMillisecondVector::from_vec(vec![4, 5, 6]));
-        push_vals(&mut column, 3, vector);
-        assert_eq!(
-            vec![4, 5, 6],
-            column.values.as_ref().unwrap().duration_millisecond_values
-        );
-
-        let vector = Arc::new(DurationSecondVector::from_vec(vec![10, 11, 12]));
-        push_vals(&mut column, 3, vector);
-        assert_eq!(
-            vec![10, 11, 12],
-            column.values.as_ref().unwrap().duration_second_values
-        );
-    }
-
     #[test]
     fn test_column_put_vector() {
         use crate::v1::SemanticType;
@@ -1700,39 +1550,6 @@ mod tests {
         assert_eq!(expect, actual);
     }
 
-    #[test]
-    fn test_convert_duration_values() {
-        // second
-        let actual = pb_values_to_values(
-            &ConcreteDataType::Duration(DurationType::Second(DurationSecondType)),
-            Values {
-                duration_second_values: vec![1_i64, 2_i64, 3_i64],
-                ..Default::default()
-            },
-        );
-        let expect = vec![
-            Value::Duration(Duration::new_second(1_i64)),
-            Value::Duration(Duration::new_second(2_i64)),
-            Value::Duration(Duration::new_second(3_i64)),
-        ];
-        assert_eq!(expect, actual);
-
-        // millisecond
-        let actual = pb_values_to_values(
-            &ConcreteDataType::Duration(DurationType::Millisecond(DurationMillisecondType)),
-            Values {
-                duration_millisecond_values: vec![1_i64, 2_i64, 3_i64],
-                ..Default::default()
-            },
-        );
-        let expect = vec![
-            Value::Duration(Duration::new_millisecond(1_i64)),
-            Value::Duration(Duration::new_millisecond(2_i64)),
-            Value::Duration(Duration::new_millisecond(3_i64)),
-        ];
-        assert_eq!(expect, actual);
-    }
-
     #[test]
     fn test_convert_interval_values() {
         // year_month

src/api/src/lib.rs

@@ -21,6 +21,7 @@ pub mod prom_store {
     }
 }
 
+pub mod region;
 pub mod v1;
 
 pub use greptime_proto;

src/api/src/region.rs

@@ -0,0 +1,42 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::collections::HashMap;
+
+use common_base::AffectedRows;
+use greptime_proto::v1::region::RegionResponse as RegionResponseV1;
+
+/// This result struct is derived from [RegionResponseV1]
+#[derive(Debug)]
+pub struct RegionResponse {
+    pub affected_rows: AffectedRows,
+    pub extension: HashMap<String, Vec<u8>>,
+}
+
+impl RegionResponse {
+    pub fn from_region_response(region_response: RegionResponseV1) -> Self {
+        Self {
+            affected_rows: region_response.affected_rows as _,
+            extension: region_response.extension,
+        }
+    }
+
+    /// Creates one response without extension
+    pub fn new(affected_rows: AffectedRows) -> Self {
+        Self {
+            affected_rows,
+            extension: Default::default(),
+        }
+    }
+}

src/auth/Cargo.toml

@@ -8,14 +8,18 @@ license.workspace = true
 default = []
 testing = []
 
+[lints]
+workspace = true
+
 [dependencies]
 api.workspace = true
 async-trait.workspace = true
+common-base.workspace = true
 common-error.workspace = true
 common-macro.workspace = true
+common-telemetry.workspace = true
 digest = "0.10"
-hex = { version = "0.4" }
-secrecy = { version = "0.8", features = ["serde", "alloc"] }
+notify.workspace = true
 sha1 = "0.10"
 snafu.workspace = true
 sql.workspace = true

src/auth/src/common.rs

@@ -14,14 +14,17 @@
 
 use std::sync::Arc;
 
+use common_base::secrets::SecretString;
 use digest::Digest;
-use secrecy::SecretString;
 use sha1::Sha1;
 use snafu::{ensure, OptionExt};
 
 use crate::error::{IllegalParamSnafu, InvalidConfigSnafu, Result, UserPasswordMismatchSnafu};
 use crate::user_info::DefaultUserInfo;
 use crate::user_provider::static_user_provider::{StaticUserProvider, STATIC_USER_PROVIDER};
+use crate::user_provider::watch_file_user_provider::{
+    WatchFileUserProvider, WATCH_FILE_USER_PROVIDER,
+};
 use crate::{UserInfoRef, UserProviderRef};
 
 pub(crate) const DEFAULT_USERNAME: &str = "greptime";
@@ -40,9 +43,12 @@ pub fn user_provider_from_option(opt: &String) -> Result<UserProviderRef> {
     match name {
         STATIC_USER_PROVIDER => {
             let provider =
-                StaticUserProvider::try_from(content).map(|p| Arc::new(p) as UserProviderRef)?;
+                StaticUserProvider::new(content).map(|p| Arc::new(p) as UserProviderRef)?;
             Ok(provider)
         }
+        WATCH_FILE_USER_PROVIDER => {
+            WatchFileUserProvider::new(content).map(|p| Arc::new(p) as UserProviderRef)
+        }
         _ => InvalidConfigSnafu {
             value: name.to_string(),
             msg: "Invalid UserProviderOption",

src/auth/src/error.rs

@@ -34,11 +34,13 @@ pub enum Error {
     Io {
         #[snafu(source)]
         error: std::io::Error,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Auth failed"))]
     AuthBackend {
+        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
@@ -64,8 +66,18 @@ pub enum Error {
         username: String,
     },
 
+    #[snafu(display("Failed to initialize a watcher for file {}", path))]
+    FileWatch {
+        path: String,
+        #[snafu(source)]
+        error: notify::Error,
+    },
+
     #[snafu(display("User is not authorized to perform this action"))]
-    PermissionDenied { location: Location },
+    PermissionDenied {
+        #[snafu(implicit)]
+        location: Location,
+    },
 }
 
 impl ErrorExt for Error {
@@ -73,6 +85,7 @@ impl ErrorExt for Error {
         match self {
             Error::InvalidConfig { .. } => StatusCode::InvalidArguments,
             Error::IllegalParam { .. } => StatusCode::InvalidArguments,
+            Error::FileWatch { .. } => StatusCode::InvalidArguments,
             Error::InternalState { .. } => StatusCode::Unexpected,
             Error::Io { .. } => StatusCode::Internal,
             Error::AuthBackend { .. } => StatusCode::Internal,

src/auth/src/tests.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use secrecy::ExposeSecret;
+use common_base::secrets::ExposeSecret;
 
 use crate::error::{
     AccessDeniedSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
@@ -45,9 +45,9 @@ impl Default for MockUserProvider {
 
 impl MockUserProvider {
     pub fn set_authorization_info(&mut self, info: DatabaseAuthInfo) {
-        self.catalog = info.catalog.to_owned();
-        self.schema = info.schema.to_owned();
-        self.username = info.username.to_owned();
+        info.catalog.clone_into(&mut self.catalog);
+        info.schema.clone_into(&mut self.schema);
+        info.username.clone_into(&mut self.username);
     }
 }
 

src/auth/src/user_provider.rs

@@ -13,10 +13,24 @@
 // limitations under the License.
 
 pub(crate) mod static_user_provider;
+pub(crate) mod watch_file_user_provider;
+
+use std::collections::HashMap;
+use std::fs::File;
+use std::io;
+use std::io::BufRead;
+use std::path::Path;
+
+use common_base::secrets::ExposeSecret;
+use snafu::{ensure, OptionExt, ResultExt};
 
 use crate::common::{Identity, Password};
-use crate::error::Result;
-use crate::UserInfoRef;
+use crate::error::{
+    IllegalParamSnafu, InvalidConfigSnafu, IoSnafu, Result, UnsupportedPasswordTypeSnafu,
+    UserNotFoundSnafu, UserPasswordMismatchSnafu,
+};
+use crate::user_info::DefaultUserInfo;
+use crate::{auth_mysql, UserInfoRef};
 
 #[async_trait::async_trait]
 pub trait UserProvider: Send + Sync {
@@ -44,3 +58,88 @@ pub trait UserProvider: Send + Sync {
         Ok(user_info)
     }
 }
+
+fn load_credential_from_file(filepath: &str) -> Result<Option<HashMap<String, Vec<u8>>>> {
+    // check valid path
+    let path = Path::new(filepath);
+    if !path.exists() {
+        return Ok(None);
+    }
+
+    ensure!(
+        path.is_file(),
+        InvalidConfigSnafu {
+            value: filepath,
+            msg: "UserProvider file must be a file",
+        }
+    );
+    let file = File::open(path).context(IoSnafu)?;
+    let credential = io::BufReader::new(file)
+        .lines()
+        .map_while(std::result::Result::ok)
+        .filter_map(|line| {
+            if let Some((k, v)) = line.split_once('=') {
+                Some((k.to_string(), v.as_bytes().to_vec()))
+            } else {
+                None
+            }
+        })
+        .collect::<HashMap<String, Vec<u8>>>();
+
+    ensure!(
+        !credential.is_empty(),
+        InvalidConfigSnafu {
+            value: filepath,
+            msg: "UserProvider's file must contains at least one valid credential",
+        }
+    );
+
+    Ok(Some(credential))
+}
+
+fn authenticate_with_credential(
+    users: &HashMap<String, Vec<u8>>,
+    input_id: Identity<'_>,
+    input_pwd: Password<'_>,
+) -> Result<UserInfoRef> {
+    match input_id {
+        Identity::UserId(username, _) => {
+            ensure!(
+                !username.is_empty(),
+                IllegalParamSnafu {
+                    msg: "blank username"
+                }
+            );
+            let save_pwd = users.get(username).context(UserNotFoundSnafu {
+                username: username.to_string(),
+            })?;
+
+            match input_pwd {
+                Password::PlainText(pwd) => {
+                    ensure!(
+                        !pwd.expose_secret().is_empty(),
+                        IllegalParamSnafu {
+                            msg: "blank password"
+                        }
+                    );
+                    if save_pwd == pwd.expose_secret().as_bytes() {
+                        Ok(DefaultUserInfo::with_name(username))
+                    } else {
+                        UserPasswordMismatchSnafu {
+                            username: username.to_string(),
+                        }
+                        .fail()
+                    }
+                }
+                Password::MysqlNativePassword(auth_data, salt) => {
+                    auth_mysql(auth_data, salt, username, save_pwd)
+                        .map(|_| DefaultUserInfo::with_name(username))
+                }
+                Password::PgMD5(_, _) => UnsupportedPasswordTypeSnafu {
+                    password_type: "pg_md5",
+                }
+                .fail(),
+            }
+        }
+    }
+}

src/auth/src/user_provider/static_user_provider.rs

@@ -13,60 +13,34 @@
 // limitations under the License.
 
 use std::collections::HashMap;
-use std::fs::File;
-use std::io;
-use std::io::BufRead;
-use std::path::Path;
 
 use async_trait::async_trait;
-use secrecy::ExposeSecret;
-use snafu::{ensure, OptionExt, ResultExt};
+use snafu::OptionExt;
 
-use crate::error::{
-    Error, IllegalParamSnafu, InvalidConfigSnafu, IoSnafu, Result, UnsupportedPasswordTypeSnafu,
-    UserNotFoundSnafu, UserPasswordMismatchSnafu,
-};
-use crate::user_info::DefaultUserInfo;
-use crate::{auth_mysql, Identity, Password, UserInfoRef, UserProvider};
+use crate::error::{InvalidConfigSnafu, Result};
+use crate::user_provider::{authenticate_with_credential, load_credential_from_file};
+use crate::{Identity, Password, UserInfoRef, UserProvider};
 
 pub(crate) const STATIC_USER_PROVIDER: &str = "static_user_provider";
 
-impl TryFrom<&str> for StaticUserProvider {
-    type Error = Error;
+pub(crate) struct StaticUserProvider {
+    users: HashMap<String, Vec<u8>>,
+}
 
-    fn try_from(value: &str) -> Result<Self> {
+impl StaticUserProvider {
+    pub(crate) fn new(value: &str) -> Result<Self> {
         let (mode, content) = value.split_once(':').context(InvalidConfigSnafu {
             value: value.to_string(),
             msg: "StaticUserProviderOption must be in format `<option>:<value>`",
         })?;
         return match mode {
             "file" => {
-                // check valid path
-                let path = Path::new(content);
-                ensure!(path.exists() && path.is_file(), InvalidConfigSnafu {
-                    value: content.to_string(),
-                    msg: "StaticUserProviderOption file must be a valid file path",
-                });
-
-                let file = File::open(path).context(IoSnafu)?;
-                let credential = io::BufReader::new(file)
-                    .lines()
-                    .map_while(std::result::Result::ok)
-                    .filter_map(|line| {
-                        if let Some((k, v)) = line.split_once('=') {
-                            Some((k.to_string(), v.as_bytes().to_vec()))
-                        } else {
-                            None
-                        }
-                    })
-                    .collect::<HashMap<String, Vec<u8>>>();
-
-                ensure!(!credential.is_empty(), InvalidConfigSnafu {
-                    value: content.to_string(),
-                    msg: "StaticUserProviderOption file must contains at least one valid credential",
-                });
-
-                Ok(StaticUserProvider { users: credential, })
+                let users = load_credential_from_file(content)?
+                    .context(InvalidConfigSnafu {
+                        value: content.to_string(),
+                        msg: "StaticFileUserProvider must be a valid file path",
+                    })?;
+                Ok(StaticUserProvider { users })
             }
             "cmd" => content
                 .split(',')
@@ -83,66 +57,19 @@ impl TryFrom<&str> for StaticUserProvider {
                 value: mode.to_string(),
                 msg: "StaticUserProviderOption must be in format `file:<path>` or `cmd:<values>`",
             }
-            .fail(),
+                .fail(),
         };
     }
 }
 
-pub(crate) struct StaticUserProvider {
-    users: HashMap<String, Vec<u8>>,
-}
-
 #[async_trait]
 impl UserProvider for StaticUserProvider {
     fn name(&self) -> &str {
         STATIC_USER_PROVIDER
     }
 
-    async fn authenticate(
-        &self,
-        input_id: Identity<'_>,
-        input_pwd: Password<'_>,
-    ) -> Result<UserInfoRef> {
-        match input_id {
-            Identity::UserId(username, _) => {
-                ensure!(
-                    !username.is_empty(),
-                    IllegalParamSnafu {
-                        msg: "blank username"
-                    }
-                );
-                let save_pwd = self.users.get(username).context(UserNotFoundSnafu {
-                    username: username.to_string(),
-                })?;
-
-                match input_pwd {
-                    Password::PlainText(pwd) => {
-                        ensure!(
-                            !pwd.expose_secret().is_empty(),
-                            IllegalParamSnafu {
-                                msg: "blank password"
-                            }
-                        );
-                        return if save_pwd == pwd.expose_secret().as_bytes() {
-                            Ok(DefaultUserInfo::with_name(username))
-                        } else {
-                            UserPasswordMismatchSnafu {
-                                username: username.to_string(),
-                            }
-                            .fail()
-                        };
-                    }
-                    Password::MysqlNativePassword(auth_data, salt) => {
-                        auth_mysql(auth_data, salt, username, save_pwd)
-                            .map(|_| DefaultUserInfo::with_name(username))
-                    }
-                    Password::PgMD5(_, _) => UnsupportedPasswordTypeSnafu {
-                        password_type: "pg_md5",
-                    }
-                    .fail(),
-                }
-            }
-        }
+    async fn authenticate(&self, id: Identity<'_>, pwd: Password<'_>) -> Result<UserInfoRef> {
+        authenticate_with_credential(&self.users, id, pwd)
     }
 
     async fn authorize(
@@ -181,7 +108,7 @@ pub mod test {
     #[tokio::test]
     async fn test_authorize() {
         let user_info = DefaultUserInfo::with_name("root");
-        let provider = StaticUserProvider::try_from("cmd:root=123456,admin=654321").unwrap();
+        let provider = StaticUserProvider::new("cmd:root=123456,admin=654321").unwrap();
         provider
             .authorize("catalog", "schema", &user_info)
             .await
@@ -190,7 +117,7 @@ pub mod test {
 
     #[tokio::test]
     async fn test_inline_provider() {
-        let provider = StaticUserProvider::try_from("cmd:root=123456,admin=654321").unwrap();
+        let provider = StaticUserProvider::new("cmd:root=123456,admin=654321").unwrap();
         test_authenticate(&provider, "root", "123456").await;
         test_authenticate(&provider, "admin", "654321").await;
     }
@@ -214,7 +141,7 @@ admin=654321",
         }
 
         let param = format!("file:{file_path}");
-        let provider = StaticUserProvider::try_from(param.as_str()).unwrap();
+        let provider = StaticUserProvider::new(param.as_str()).unwrap();
         test_authenticate(&provider, "root", "123456").await;
         test_authenticate(&provider, "admin", "654321").await;
     }

src/auth/src/user_provider/watch_file_user_provider.rs

@@ -0,0 +1,215 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::collections::HashMap;
+use std::path::Path;
+use std::sync::mpsc::channel;
+use std::sync::{Arc, Mutex};
+
+use async_trait::async_trait;
+use common_telemetry::{info, warn};
+use notify::{EventKind, RecursiveMode, Watcher};
+use snafu::{ensure, ResultExt};
+
+use crate::error::{FileWatchSnafu, InvalidConfigSnafu, Result};
+use crate::user_info::DefaultUserInfo;
+use crate::user_provider::{authenticate_with_credential, load_credential_from_file};
+use crate::{Identity, Password, UserInfoRef, UserProvider};
+
+pub(crate) const WATCH_FILE_USER_PROVIDER: &str = "watch_file_user_provider";
+
+type WatchedCredentialRef = Arc<Mutex<Option<HashMap<String, Vec<u8>>>>>;
+
+/// A user provider that reads user credential from a file and watches the file for changes.
+///
+/// Empty file is invalid; but file not exist means every user can be authenticated.
+pub(crate) struct WatchFileUserProvider {
+    users: WatchedCredentialRef,
+}
+
+impl WatchFileUserProvider {
+    pub fn new(filepath: &str) -> Result<Self> {
+        let credential = load_credential_from_file(filepath)?;
+        let users = Arc::new(Mutex::new(credential));
+        let this = WatchFileUserProvider {
+            users: users.clone(),
+        };
+
+        let (tx, rx) = channel::<notify::Result<notify::Event>>();
+        let mut debouncer =
+            notify::recommended_watcher(tx).context(FileWatchSnafu { path: "<none>" })?;
+        let mut dir = Path::new(filepath).to_path_buf();
+        ensure!(
+            dir.pop(),
+            InvalidConfigSnafu {
+                value: filepath,
+                msg: "UserProvider path must be a file path",
+            }
+        );
+        debouncer
+            .watch(&dir, RecursiveMode::NonRecursive)
+            .context(FileWatchSnafu { path: filepath })?;
+
+        let filepath = filepath.to_string();
+        std::thread::spawn(move || {
+            let filename = Path::new(&filepath).file_name();
+            let _hold = debouncer;
+            while let Ok(res) = rx.recv() {
+                if let Ok(event) = res {
+                    let is_this_file = event.paths.iter().any(|p| p.file_name() == filename);
+                    let is_relevant_event = matches!(
+                        event.kind,
+                        EventKind::Modify(_) | EventKind::Create(_) | EventKind::Remove(_)
+                    );
+                    if is_this_file && is_relevant_event {
+                        info!(?event.kind, "User provider file {} changed", &filepath);
+                        match load_credential_from_file(&filepath) {
+                            Ok(credential) => {
+                                let mut users =
+                                    users.lock().expect("users credential must be valid");
+                                #[cfg(not(test))]
+                                info!("User provider file {filepath} reloaded");
+                                #[cfg(test)]
+                                info!("User provider file {filepath} reloaded: {credential:?}");
+                                *users = credential;
+                            }
+                            Err(err) => {
+                                warn!(
+                                    ?err,
+                                    "Fail to load credential from file {filepath}; keep the old one",
+                                )
+                            }
+                        }
+                    }
+                }
+            }
+        });
+
+        Ok(this)
+    }
+}
+
+#[async_trait]
+impl UserProvider for WatchFileUserProvider {
+    fn name(&self) -> &str {
+        WATCH_FILE_USER_PROVIDER
+    }
+
+    async fn authenticate(&self, id: Identity<'_>, password: Password<'_>) -> Result<UserInfoRef> {
+        let users = self.users.lock().expect("users credential must be valid");
+        if let Some(users) = users.as_ref() {
+            authenticate_with_credential(users, id, password)
+        } else {
+            match id {
+                Identity::UserId(id, _) => {
+                    warn!(id, "User provider file not exist, allow all users");
+                    Ok(DefaultUserInfo::with_name(id))
+                }
+            }
+        }
+    }
+
+    async fn authorize(&self, _: &str, _: &str, _: &UserInfoRef) -> Result<()> {
+        // default allow all
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+pub mod test {
+    use std::time::{Duration, Instant};
+
+    use common_test_util::temp_dir::create_temp_dir;
+    use tokio::time::sleep;
+
+    use crate::user_provider::watch_file_user_provider::WatchFileUserProvider;
+    use crate::user_provider::{Identity, Password};
+    use crate::UserProvider;
+
+    async fn test_authenticate(
+        provider: &dyn UserProvider,
+        username: &str,
+        password: &str,
+        ok: bool,
+        timeout: Option<Duration>,
+    ) {
+        if let Some(timeout) = timeout {
+            let deadline = Instant::now().checked_add(timeout).unwrap();
+            loop {
+                let re = provider
+                    .authenticate(
+                        Identity::UserId(username, None),
+                        Password::PlainText(password.to_string().into()),
+                    )
+                    .await;
+                if re.is_ok() == ok {
+                    break;
+                } else if Instant::now() < deadline {
+                    sleep(Duration::from_millis(100)).await;
+                } else {
+                    panic!("timeout (username: {username}, password: {password}, expected: {ok})");
+                }
+            }
+        } else {
+            let re = provider
+                .authenticate(
+                    Identity::UserId(username, None),
+                    Password::PlainText(password.to_string().into()),
+                )
+                .await;
+            assert_eq!(
+                re.is_ok(),
+                ok,
+                "username: {}, password: {}",
+                username,
+                password
+            );
+        }
+    }
+
+    #[tokio::test]
+    async fn test_file_provider() {
+        common_telemetry::init_default_ut_logging();
+
+        let dir = create_temp_dir("test_file_provider");
+        let file_path = format!("{}/test_file_provider", dir.path().to_str().unwrap());
+
+        // write a tmp file
+        assert!(std::fs::write(&file_path, "root=123456\nadmin=654321\n").is_ok());
+        let provider = WatchFileUserProvider::new(file_path.as_str()).unwrap();
+        let timeout = Duration::from_secs(60);
+
+        test_authenticate(&provider, "root", "123456", true, None).await;
+        test_authenticate(&provider, "admin", "654321", true, None).await;
+        test_authenticate(&provider, "root", "654321", false, None).await;
+
+        // update the tmp file
+        assert!(std::fs::write(&file_path, "root=654321\n").is_ok());
+        test_authenticate(&provider, "root", "123456", false, Some(timeout)).await;
+        test_authenticate(&provider, "root", "654321", true, Some(timeout)).await;
+        test_authenticate(&provider, "admin", "654321", false, Some(timeout)).await;
+
+        // remove the tmp file
+        assert!(std::fs::remove_file(&file_path).is_ok());
+        test_authenticate(&provider, "root", "123456", true, Some(timeout)).await;
+        test_authenticate(&provider, "root", "654321", true, Some(timeout)).await;
+        test_authenticate(&provider, "admin", "654321", true, Some(timeout)).await;
+
+        // recreate the tmp file
+        assert!(std::fs::write(&file_path, "root=123456\n").is_ok());
+        test_authenticate(&provider, "root", "123456", true, Some(timeout)).await;
+        test_authenticate(&provider, "root", "654321", false, Some(timeout)).await;
+        test_authenticate(&provider, "admin", "654321", false, Some(timeout)).await;
+    }
+}

src/cache/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "cache"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+catalog.workspace = true
+common-error.workspace = true
+common-macro.workspace = true
+common-meta.workspace = true
+moka.workspace = true
+snafu.workspace = true

src/cache/src/error.rs

@@ -0,0 +1,44 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use common_error::ext::ErrorExt;
+use common_error::status_code::StatusCode;
+use common_macro::stack_trace_debug;
+use snafu::{Location, Snafu};
+
+#[derive(Snafu)]
+#[snafu(visibility(pub))]
+#[stack_trace_debug]
+pub enum Error {
+    #[snafu(display("Failed to get cache from cache registry: {}", name))]
+    CacheRequired {
+        #[snafu(implicit)]
+        location: Location,
+        name: String,
+    },
+}
+
+pub type Result<T> = std::result::Result<T, Error>;
+
+impl ErrorExt for Error {
+    fn status_code(&self) -> StatusCode {
+        match self {
+            Error::CacheRequired { .. } => StatusCode::Internal,
+        }
+    }
+
+    fn as_any(&self) -> &dyn std::any::Any {
+        self
+    }
+}

src/cache/src/lib.rs

@@ -0,0 +1,122 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+pub mod error;
+
+use std::sync::Arc;
+use std::time::Duration;
+
+use catalog::kvbackend::new_table_cache;
+use common_meta::cache::{
+    new_table_flownode_set_cache, new_table_info_cache, new_table_name_cache,
+    new_table_route_cache, CacheRegistry, CacheRegistryBuilder, LayeredCacheRegistryBuilder,
+};
+use common_meta::kv_backend::KvBackendRef;
+use moka::future::CacheBuilder;
+use snafu::OptionExt;
+
+use crate::error::Result;
+
+const DEFAULT_CACHE_MAX_CAPACITY: u64 = 65536;
+const DEFAULT_CACHE_TTL: Duration = Duration::from_secs(10 * 60);
+const DEFAULT_CACHE_TTI: Duration = Duration::from_secs(5 * 60);
+
+pub const TABLE_INFO_CACHE_NAME: &str = "table_info_cache";
+pub const TABLE_NAME_CACHE_NAME: &str = "table_name_cache";
+pub const TABLE_CACHE_NAME: &str = "table_cache";
+pub const TABLE_FLOWNODE_SET_CACHE_NAME: &str = "table_flownode_set_cache";
+pub const TABLE_ROUTE_CACHE_NAME: &str = "table_route_cache";
+
+pub fn build_fundamental_cache_registry(kv_backend: KvBackendRef) -> CacheRegistry {
+    // Builds table info cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let table_info_cache = Arc::new(new_table_info_cache(
+        TABLE_INFO_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    // Builds table name cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let table_name_cache = Arc::new(new_table_name_cache(
+        TABLE_NAME_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    // Builds table route cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let table_route_cache = Arc::new(new_table_route_cache(
+        TABLE_ROUTE_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    // Builds table flownode set cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let table_flownode_set_cache = Arc::new(new_table_flownode_set_cache(
+        TABLE_FLOWNODE_SET_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    CacheRegistryBuilder::default()
+        .add_cache(table_info_cache)
+        .add_cache(table_name_cache)
+        .add_cache(table_route_cache)
+        .add_cache(table_flownode_set_cache)
+        .build()
+}
+
+// TODO(weny): Make the cache configurable.
+pub fn with_default_composite_cache_registry(
+    builder: LayeredCacheRegistryBuilder,
+) -> Result<LayeredCacheRegistryBuilder> {
+    let table_info_cache = builder.get().context(error::CacheRequiredSnafu {
+        name: TABLE_INFO_CACHE_NAME,
+    })?;
+    let table_name_cache = builder.get().context(error::CacheRequiredSnafu {
+        name: TABLE_NAME_CACHE_NAME,
+    })?;
+
+    // Builds table cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let table_cache = Arc::new(new_table_cache(
+        TABLE_CACHE_NAME.to_string(),
+        cache,
+        table_info_cache,
+        table_name_cache,
+    ));
+
+    let registry = CacheRegistryBuilder::default()
+        .add_cache(table_cache)
+        .build();
+
+    Ok(builder.add_cache_registry(registry))
+}

src/catalog/Cargo.toml

@@ -7,21 +7,22 @@ license.workspace = true
 [features]
 testing = []
 
+[lints]
+workspace = true
+
 [dependencies]
 api.workspace = true
-arc-swap = "1.0"
 arrow.workspace = true
 arrow-schema.workspace = true
 async-stream.workspace = true
 async-trait = "0.1"
 common-catalog.workspace = true
+common-config.workspace = true
 common-error.workspace = true
-common-grpc.workspace = true
 common-macro.workspace = true
 common-meta.workspace = true
 common-query.workspace = true
 common-recordbatch.workspace = true
-common-runtime.workspace = true
 common-telemetry.workspace = true
 common-time.workspace = true
 common-version.workspace = true
@@ -30,19 +31,18 @@ datafusion.workspace = true
 datatypes.workspace = true
 futures = "0.3"
 futures-util.workspace = true
+humantime.workspace = true
 itertools.workspace = true
 lazy_static.workspace = true
 meta-client.workspace = true
 moka = { workspace = true, features = ["future", "sync"] }
-parking_lot = "0.12"
 partition.workspace = true
 paste = "1.0"
 prometheus.workspace = true
-regex.workspace = true
-serde.workspace = true
 serde_json.workspace = true
 session.workspace = true
 snafu.workspace = true
+sql.workspace = true
 store-api.workspace = true
 table.workspace = true
 tokio.workspace = true

src/catalog/src/error.rs

@@ -30,12 +30,14 @@ use tokio::task::JoinError;
 pub enum Error {
     #[snafu(display("Failed to list catalogs"))]
     ListCatalogs {
+        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
 
     #[snafu(display("Failed to list {}'s schemas", catalog))]
     ListSchemas {
+        #[snafu(implicit)]
         location: Location,
         catalog: String,
         source: BoxedError,
@@ -43,25 +45,36 @@ pub enum Error {
 
     #[snafu(display("Failed to list {}.{}'s tables", catalog, schema))]
     ListTables {
+        #[snafu(implicit)]
         location: Location,
         catalog: String,
         schema: String,
         source: BoxedError,
     },
 
+    #[snafu(display("Failed to list nodes in cluster: {source}"))]
+    ListNodes {
+        #[snafu(implicit)]
+        location: Location,
+        source: BoxedError,
+    },
+
     #[snafu(display("Failed to re-compile script due to internal error"))]
     CompileScriptInternal {
+        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
     #[snafu(display("Failed to open system catalog table"))]
     OpenSystemCatalog {
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("Failed to create system catalog table"))]
     CreateSystemCatalog {
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
@@ -69,12 +82,17 @@ pub enum Error {
     #[snafu(display("Failed to create table, table info: {}", table_info))]
     CreateTable {
         table_info: String,
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("System catalog is not valid: {}", msg))]
-    SystemCatalog { msg: String, location: Location },
+    SystemCatalog {
+        msg: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display(
         "System catalog table type mismatch, expected: binary, found: {:?}",
@@ -82,34 +100,42 @@ pub enum Error {
     ))]
     SystemCatalogTypeMismatch {
         data_type: ConcreteDataType,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Invalid system catalog entry type: {:?}", entry_type))]
     InvalidEntryType {
         entry_type: Option<u8>,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Invalid system catalog key: {:?}", key))]
     InvalidKey {
         key: Option<String>,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Catalog value is not present"))]
-    EmptyValue { location: Location },
+    EmptyValue {
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Failed to deserialize value"))]
     ValueDeserialize {
         #[snafu(source)]
         error: serde_json::error::Error,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Table engine not found: {}", engine_name))]
     TableEngineNotFound {
         engine_name: String,
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
@@ -117,6 +143,7 @@ pub enum Error {
     #[snafu(display("Cannot find catalog by name: {}", catalog_name))]
     CatalogNotFound {
         catalog_name: String,
+        #[snafu(implicit)]
         location: Location,
     },
 
@@ -124,30 +151,49 @@ pub enum Error {
     SchemaNotFound {
         catalog: String,
         schema: String,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Table `{}` already exists", table))]
-    TableExists { table: String, location: Location },
+    TableExists {
+        table: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Table not found: {}", table))]
-    TableNotExist { table: String, location: Location },
+    TableNotExist {
+        table: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Schema {} already exists", schema))]
-    SchemaExists { schema: String, location: Location },
+    SchemaExists {
+        schema: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Operation {} not implemented yet", operation))]
     Unimplemented {
         operation: String,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Operation {} not supported", op))]
-    NotSupported { op: String, location: Location },
+    NotSupported {
+        op: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Failed to open table {table_id}"))]
     OpenTable {
         table_id: TableId,
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
@@ -161,71 +207,81 @@ pub enum Error {
     #[snafu(display("Table not found while opening table, table info: {}", table_info))]
     TableNotFound {
         table_info: String,
+        #[snafu(implicit)]
         location: Location,
     },
 
-    #[snafu(display("Failed to find table partitions: #{table}"))]
-    FindPartitions {
-        source: partition::error::Error,
-        table: String,
-    },
+    #[snafu(display("Failed to find table partitions"))]
+    FindPartitions { source: partition::error::Error },
 
     #[snafu(display("Failed to find region routes"))]
     FindRegionRoutes { source: partition::error::Error },
 
     #[snafu(display("Failed to read system catalog table records"))]
     ReadSystemCatalog {
+        #[snafu(implicit)]
         location: Location,
         source: common_recordbatch::error::Error,
     },
 
     #[snafu(display("Failed to create recordbatch"))]
     CreateRecordBatch {
+        #[snafu(implicit)]
         location: Location,
         source: common_recordbatch::error::Error,
     },
 
     #[snafu(display("Failed to insert table creation record to system catalog"))]
     InsertCatalogRecord {
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("Failed to scan system catalog table"))]
     SystemCatalogTableScan {
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("Internal error"))]
     Internal {
+        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
 
     #[snafu(display("Failed to upgrade weak catalog manager reference"))]
-    UpgradeWeakCatalogManagerRef { location: Location },
+    UpgradeWeakCatalogManagerRef {
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Failed to execute system catalog table scan"))]
     SystemCatalogTableScanExec {
+        #[snafu(implicit)]
         location: Location,
         source: common_query::error::Error,
     },
 
     #[snafu(display("Cannot parse catalog value"))]
     InvalidCatalogValue {
+        #[snafu(implicit)]
         location: Location,
         source: common_catalog::error::Error,
     },
 
     #[snafu(display("Failed to perform metasrv operation"))]
-    MetaSrv {
+    Metasrv {
+        #[snafu(implicit)]
         location: Location,
         source: meta_client::error::Error,
     },
 
     #[snafu(display("Invalid table info in catalog"))]
     InvalidTableInfoInCatalog {
+        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },
@@ -237,21 +293,35 @@ pub enum Error {
     Datafusion {
         #[snafu(source)]
         error: DataFusionError,
+        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Table schema mismatch"))]
     TableSchemaMismatch {
+        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("A generic error has occurred, msg: {}", msg))]
-    Generic { msg: String, location: Location },
+    Generic {
+        msg: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
 
     #[snafu(display("Table metadata manager error"))]
     TableMetadataManager {
         source: common_meta::error::Error,
+        #[snafu(implicit)]
+        location: Location,
+    },
+
+    #[snafu(display("Failed to get table cache"))]
+    GetTableCache {
+        source: common_meta::error::Error,
+        #[snafu(implicit)]
         location: Location,
     },
 }
@@ -291,6 +361,7 @@ impl ErrorExt for Error {
             }
 
             Error::ListCatalogs { source, .. }
+            | Error::ListNodes { source, .. }
             | Error::ListSchemas { source, .. }
             | Error::ListTables { source, .. } => source.status_code(),
 
@@ -301,7 +372,7 @@ impl ErrorExt for Error {
             | Error::CreateTable { source, .. }
             | Error::TableSchemaMismatch { source, .. } => source.status_code(),
 
-            Error::MetaSrv { source, .. } => source.status_code(),
+            Error::Metasrv { source, .. } => source.status_code(),
             Error::SystemCatalogTableScan { source, .. } => source.status_code(),
             Error::SystemCatalogTableScanExec { source, .. } => source.status_code(),
             Error::InvalidTableInfoInCatalog { source, .. } => source.status_code(),
@@ -314,6 +385,7 @@ impl ErrorExt for Error {
             Error::QueryAccessDenied { .. } => StatusCode::AccessDenied,
             Error::Datafusion { .. } => StatusCode::EngineExecuteQuery,
             Error::TableMetadataManager { source, .. } => source.status_code(),
+            Error::GetTableCache { .. } => StatusCode::Internal,
         }
     }
 

src/catalog/src/information_schema.rs

@@ -12,16 +12,19 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-mod columns;
-mod key_column_usage;
+mod cluster_info;
+pub mod columns;
+pub mod key_column_usage;
 mod memory_table;
 mod partitions;
 mod predicate;
 mod region_peers;
 mod runtime_metrics;
-mod schemata;
+pub mod schemata;
+mod table_constraints;
 mod table_names;
-mod tables;
+pub mod tables;
+pub(crate) mod utils;
 
 use std::collections::HashMap;
 use std::sync::{Arc, Weak};
@@ -41,18 +44,19 @@ use table::error::{SchemaConversionSnafu, TablesRecordBatchSnafu};
 use table::metadata::{
     FilterPushDownType, TableInfoBuilder, TableInfoRef, TableMetaBuilder, TableType,
 };
-use table::thin_table::{ThinTable, ThinTableAdapter};
-use table::TableRef;
+use table::{Table, TableRef};
 pub use table_names::*;
 
 use self::columns::InformationSchemaColumns;
 use crate::error::Result;
+use crate::information_schema::cluster_info::InformationSchemaClusterInfo;
 use crate::information_schema::key_column_usage::InformationSchemaKeyColumnUsage;
 use crate::information_schema::memory_table::{get_schema_columns, MemoryTable};
 use crate::information_schema::partitions::InformationSchemaPartitions;
 use crate::information_schema::region_peers::InformationSchemaRegionPeers;
 use crate::information_schema::runtime_metrics::InformationSchemaMetrics;
 use crate::information_schema::schemata::InformationSchemaSchemata;
+use crate::information_schema::table_constraints::InformationSchemaTableConstraints;
 use crate::information_schema::tables::InformationSchemaTables;
 use crate::CatalogManager;
 
@@ -149,6 +153,7 @@ impl InformationSchemaProvider {
     fn build_tables(&mut self) {
         let mut tables = HashMap::new();
 
+        // SECURITY NOTE:
         // Carefully consider the tables that may expose sensitive cluster configurations,
         // authentication details, and other critical information.
         // Only put these tables under `greptime` catalog to prevent info leak.
@@ -165,6 +170,10 @@ impl InformationSchemaProvider {
                 REGION_PEERS.to_string(),
                 self.build_table(REGION_PEERS).unwrap(),
             );
+            tables.insert(
+                CLUSTER_INFO.to_string(),
+                self.build_table(CLUSTER_INFO).unwrap(),
+            );
         }
 
         tables.insert(TABLES.to_string(), self.build_table(TABLES).unwrap());
@@ -174,6 +183,10 @@ impl InformationSchemaProvider {
             KEY_COLUMN_USAGE.to_string(),
             self.build_table(KEY_COLUMN_USAGE).unwrap(),
         );
+        tables.insert(
+            TABLE_CONSTRAINTS.to_string(),
+            self.build_table(TABLE_CONSTRAINTS).unwrap(),
+        );
 
         // Add memory tables
         for name in MEMORY_TABLES.iter() {
@@ -187,10 +200,9 @@ impl InformationSchemaProvider {
         self.information_table(name).map(|table| {
             let table_info = Self::table_info(self.catalog_name.clone(), &table);
             let filter_pushdown = FilterPushDownType::Inexact;
-            let thin_table = ThinTable::new(table_info, filter_pushdown);
-
             let data_source = Arc::new(InformationTableDataSource::new(table));
-            Arc::new(ThinTableAdapter::new(thin_table, data_source)) as _
+            let table = Table::new(table_info, filter_pushdown, data_source);
+            Arc::new(table)
         })
     }
 
@@ -243,6 +255,13 @@ impl InformationSchemaProvider {
                 self.catalog_name.clone(),
                 self.catalog_manager.clone(),
             )) as _),
+            TABLE_CONSTRAINTS => Some(Arc::new(InformationSchemaTableConstraints::new(
+                self.catalog_name.clone(),
+                self.catalog_manager.clone(),
+            )) as _),
+            CLUSTER_INFO => Some(Arc::new(InformationSchemaClusterInfo::new(
+                self.catalog_manager.clone(),
+            )) as _),
             _ => None,
         }
     }

src/catalog/src/information_schema/cluster_info.rs

@@ -0,0 +1,317 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::sync::{Arc, Weak};
+use std::time::Duration;
+
+use arrow_schema::SchemaRef as ArrowSchemaRef;
+use common_catalog::consts::INFORMATION_SCHEMA_CLUSTER_INFO_TABLE_ID;
+use common_config::Mode;
+use common_error::ext::BoxedError;
+use common_meta::cluster::{ClusterInfo, NodeInfo, NodeStatus};
+use common_meta::peer::Peer;
+use common_recordbatch::adapter::RecordBatchStreamAdapter;
+use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
+use common_telemetry::warn;
+use common_time::timestamp::Timestamp;
+use datafusion::execution::TaskContext;
+use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
+use datafusion::physical_plan::streaming::PartitionStream as DfPartitionStream;
+use datafusion::physical_plan::SendableRecordBatchStream as DfSendableRecordBatchStream;
+use datatypes::prelude::{ConcreteDataType, ScalarVectorBuilder, VectorRef};
+use datatypes::schema::{ColumnSchema, Schema, SchemaRef};
+use datatypes::timestamp::TimestampMillisecond;
+use datatypes::value::Value;
+use datatypes::vectors::{
+    Int64VectorBuilder, StringVectorBuilder, TimestampMillisecondVectorBuilder,
+};
+use snafu::ResultExt;
+use store_api::storage::{ScanRequest, TableId};
+
+use super::CLUSTER_INFO;
+use crate::error::{CreateRecordBatchSnafu, InternalSnafu, ListNodesSnafu, Result};
+use crate::information_schema::{utils, InformationTable, Predicates};
+use crate::CatalogManager;
+
+const PEER_ID: &str = "peer_id";
+const PEER_TYPE: &str = "peer_type";
+const PEER_ADDR: &str = "peer_addr";
+const VERSION: &str = "version";
+const GIT_COMMIT: &str = "git_commit";
+const START_TIME: &str = "start_time";
+const UPTIME: &str = "uptime";
+const ACTIVE_TIME: &str = "active_time";
+
+const INIT_CAPACITY: usize = 42;
+
+/// The `CLUSTER_INFO` table provides information about the current topology information of the cluster.
+///
+/// - `peer_id`: the peer server id.
+/// - `peer_type`: the peer type, such as `datanode`, `frontend`, `metasrv` etc.
+/// - `peer_addr`: the peer gRPC address.
+/// - `version`: the build package version of the peer.
+/// - `git_commit`: the build git commit hash of the peer.
+/// - `start_time`: the starting time of the peer.
+/// - `uptime`: the uptime of the peer.
+/// - `active_time`: the time since the last activity of the peer.
+///
+pub(super) struct InformationSchemaClusterInfo {
+    schema: SchemaRef,
+    catalog_manager: Weak<dyn CatalogManager>,
+    start_time_ms: u64,
+}
+
+impl InformationSchemaClusterInfo {
+    pub(super) fn new(catalog_manager: Weak<dyn CatalogManager>) -> Self {
+        Self {
+            schema: Self::schema(),
+            catalog_manager,
+            start_time_ms: common_time::util::current_time_millis() as u64,
+        }
+    }
+
+    pub(crate) fn schema() -> SchemaRef {
+        Arc::new(Schema::new(vec![
+            ColumnSchema::new(PEER_ID, ConcreteDataType::int64_datatype(), false),
+            ColumnSchema::new(PEER_TYPE, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(PEER_ADDR, ConcreteDataType::string_datatype(), true),
+            ColumnSchema::new(VERSION, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(GIT_COMMIT, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(
+                START_TIME,
+                ConcreteDataType::timestamp_millisecond_datatype(),
+                true,
+            ),
+            ColumnSchema::new(UPTIME, ConcreteDataType::string_datatype(), true),
+            ColumnSchema::new(ACTIVE_TIME, ConcreteDataType::string_datatype(), true),
+        ]))
+    }
+
+    fn builder(&self) -> InformationSchemaClusterInfoBuilder {
+        InformationSchemaClusterInfoBuilder::new(
+            self.schema.clone(),
+            self.catalog_manager.clone(),
+            self.start_time_ms,
+        )
+    }
+}
+
+impl InformationTable for InformationSchemaClusterInfo {
+    fn table_id(&self) -> TableId {
+        INFORMATION_SCHEMA_CLUSTER_INFO_TABLE_ID
+    }
+
+    fn table_name(&self) -> &'static str {
+        CLUSTER_INFO
+    }
+
+    fn schema(&self) -> SchemaRef {
+        self.schema.clone()
+    }
+
+    fn to_stream(&self, request: ScanRequest) -> Result<SendableRecordBatchStream> {
+        let schema = self.schema.arrow_schema().clone();
+        let mut builder = self.builder();
+        let stream = Box::pin(DfRecordBatchStreamAdapter::new(
+            schema,
+            futures::stream::once(async move {
+                builder
+                    .make_cluster_info(Some(request))
+                    .await
+                    .map(|x| x.into_df_record_batch())
+                    .map_err(Into::into)
+            }),
+        ));
+        Ok(Box::pin(
+            RecordBatchStreamAdapter::try_new(stream)
+                .map_err(BoxedError::new)
+                .context(InternalSnafu)?,
+        ))
+    }
+}
+
+struct InformationSchemaClusterInfoBuilder {
+    schema: SchemaRef,
+    start_time_ms: u64,
+    catalog_manager: Weak<dyn CatalogManager>,
+
+    peer_ids: Int64VectorBuilder,
+    peer_types: StringVectorBuilder,
+    peer_addrs: StringVectorBuilder,
+    versions: StringVectorBuilder,
+    git_commits: StringVectorBuilder,
+    start_times: TimestampMillisecondVectorBuilder,
+    uptimes: StringVectorBuilder,
+    active_times: StringVectorBuilder,
+}
+
+impl InformationSchemaClusterInfoBuilder {
+    fn new(
+        schema: SchemaRef,
+        catalog_manager: Weak<dyn CatalogManager>,
+        start_time_ms: u64,
+    ) -> Self {
+        Self {
+            schema,
+            catalog_manager,
+            peer_ids: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            peer_types: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            peer_addrs: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            versions: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            git_commits: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            start_times: TimestampMillisecondVectorBuilder::with_capacity(INIT_CAPACITY),
+            uptimes: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            active_times: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            start_time_ms,
+        }
+    }
+
+    /// Construct the `information_schema.cluster_info` virtual table
+    async fn make_cluster_info(&mut self, request: Option<ScanRequest>) -> Result<RecordBatch> {
+        let predicates = Predicates::from_scan_request(&request);
+        let mode = utils::running_mode(&self.catalog_manager)?.unwrap_or(Mode::Standalone);
+
+        match mode {
+            Mode::Standalone => {
+                let build_info = common_version::build_info();
+
+                self.add_node_info(
+                    &predicates,
+                    NodeInfo {
+                        // For the standalone:
+                        // - id always 0
+                        // - empty string for peer_addr
+                        peer: Peer {
+                            id: 0,
+                            addr: "".to_string(),
+                        },
+                        last_activity_ts: -1,
+                        status: NodeStatus::Standalone,
+                        version: build_info.version.to_string(),
+                        git_commit: build_info.commit_short.to_string(),
+                        // Use `self.start_time_ms` instead.
+                        // It's not precise but enough.
+                        start_time_ms: self.start_time_ms,
+                    },
+                );
+            }
+            Mode::Distributed => {
+                if let Some(meta_client) = utils::meta_client(&self.catalog_manager)? {
+                    let node_infos = meta_client
+                        .list_nodes(None)
+                        .await
+                        .map_err(BoxedError::new)
+                        .context(ListNodesSnafu)?;
+
+                    for node_info in node_infos {
+                        self.add_node_info(&predicates, node_info);
+                    }
+                } else {
+                    warn!("Could not find meta client in distributed mode.");
+                }
+            }
+        }
+
+        self.finish()
+    }
+
+    fn add_node_info(&mut self, predicates: &Predicates, node_info: NodeInfo) {
+        let peer_type = node_info.status.role_name();
+
+        let row = [
+            (PEER_ID, &Value::from(node_info.peer.id)),
+            (PEER_TYPE, &Value::from(peer_type)),
+            (PEER_ADDR, &Value::from(node_info.peer.addr.as_str())),
+            (VERSION, &Value::from(node_info.version.as_str())),
+            (GIT_COMMIT, &Value::from(node_info.git_commit.as_str())),
+        ];
+
+        if !predicates.eval(&row) {
+            return;
+        }
+
+        if peer_type == "FRONTEND" || peer_type == "METASRV" {
+            // Always set peer_id to be -1 for frontends and metasrvs
+            self.peer_ids.push(Some(-1));
+        } else {
+            self.peer_ids.push(Some(node_info.peer.id as i64));
+        }
+
+        self.peer_types.push(Some(peer_type));
+        self.peer_addrs.push(Some(&node_info.peer.addr));
+        self.versions.push(Some(&node_info.version));
+        self.git_commits.push(Some(&node_info.git_commit));
+        if node_info.start_time_ms > 0 {
+            self.start_times
+                .push(Some(TimestampMillisecond(Timestamp::new_millisecond(
+                    node_info.start_time_ms as i64,
+                ))));
+            self.uptimes.push(Some(
+                Self::format_duration_since(node_info.start_time_ms).as_str(),
+            ));
+        } else {
+            self.start_times.push(None);
+            self.uptimes.push(None);
+        }
+
+        if node_info.last_activity_ts > 0 {
+            self.active_times.push(Some(
+                Self::format_duration_since(node_info.last_activity_ts as u64).as_str(),
+            ));
+        } else {
+            self.active_times.push(None);
+        }
+    }
+
+    fn format_duration_since(ts: u64) -> String {
+        let now = common_time::util::current_time_millis() as u64;
+        let duration_since = now - ts;
+        humantime::format_duration(Duration::from_millis(duration_since)).to_string()
+    }
+
+    fn finish(&mut self) -> Result<RecordBatch> {
+        let columns: Vec<VectorRef> = vec![
+            Arc::new(self.peer_ids.finish()),
+            Arc::new(self.peer_types.finish()),
+            Arc::new(self.peer_addrs.finish()),
+            Arc::new(self.versions.finish()),
+            Arc::new(self.git_commits.finish()),
+            Arc::new(self.start_times.finish()),
+            Arc::new(self.uptimes.finish()),
+            Arc::new(self.active_times.finish()),
+        ];
+        RecordBatch::new(self.schema.clone(), columns).context(CreateRecordBatchSnafu)
+    }
+}
+
+impl DfPartitionStream for InformationSchemaClusterInfo {
+    fn schema(&self) -> &ArrowSchemaRef {
+        self.schema.arrow_schema()
+    }
+
+    fn execute(&self, _: Arc<TaskContext>) -> DfSendableRecordBatchStream {
+        let schema = self.schema.arrow_schema().clone();
+        let mut builder = self.builder();
+        Box::pin(DfRecordBatchStreamAdapter::new(
+            schema,
+            futures::stream::once(async move {
+                builder
+                    .make_cluster_info(None)
+                    .await
+                    .map(|x| x.into_df_record_batch())
+                    .map_err(Into::into)
+            }),
+        ))
+    }
+}

src/catalog/src/information_schema/columns.rs

@@ -20,19 +20,22 @@ use common_catalog::consts::{
     SEMANTIC_TYPE_TIME_INDEX,
 };
 use common_error::ext::BoxedError;
-use common_query::physical_plan::TaskContext;
 use common_recordbatch::adapter::RecordBatchStreamAdapter;
 use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
+use datafusion::execution::TaskContext;
 use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
 use datafusion::physical_plan::streaming::PartitionStream as DfPartitionStream;
 use datafusion::physical_plan::SendableRecordBatchStream as DfSendableRecordBatchStream;
-use datatypes::prelude::{ConcreteDataType, DataType};
+use datatypes::prelude::{ConcreteDataType, DataType, MutableVector};
 use datatypes::scalars::ScalarVectorBuilder;
 use datatypes::schema::{ColumnSchema, Schema, SchemaRef};
 use datatypes::value::Value;
-use datatypes::vectors::{StringVectorBuilder, VectorRef};
+use datatypes::vectors::{
+    ConstantVector, Int64Vector, Int64VectorBuilder, StringVector, StringVectorBuilder, VectorRef,
+};
 use futures::TryStreamExt;
 use snafu::{OptionExt, ResultExt};
+use sql::statements;
 use store_api::storage::{ScanRequest, TableId};
 
 use super::{InformationTable, COLUMNS};
@@ -48,18 +51,42 @@ pub(super) struct InformationSchemaColumns {
     catalog_manager: Weak<dyn CatalogManager>,
 }
 
-const TABLE_CATALOG: &str = "table_catalog";
-const TABLE_SCHEMA: &str = "table_schema";
-const TABLE_NAME: &str = "table_name";
-const COLUMN_NAME: &str = "column_name";
-const DATA_TYPE: &str = "data_type";
-const SEMANTIC_TYPE: &str = "semantic_type";
-const COLUMN_DEFAULT: &str = "column_default";
-const IS_NULLABLE: &str = "is_nullable";
+pub const TABLE_CATALOG: &str = "table_catalog";
+pub const TABLE_SCHEMA: &str = "table_schema";
+pub const TABLE_NAME: &str = "table_name";
+pub const COLUMN_NAME: &str = "column_name";
+const ORDINAL_POSITION: &str = "ordinal_position";
+const CHARACTER_MAXIMUM_LENGTH: &str = "character_maximum_length";
+const CHARACTER_OCTET_LENGTH: &str = "character_octet_length";
+const NUMERIC_PRECISION: &str = "numeric_precision";
+const NUMERIC_SCALE: &str = "numeric_scale";
+const DATETIME_PRECISION: &str = "datetime_precision";
+const CHARACTER_SET_NAME: &str = "character_set_name";
+pub const COLLATION_NAME: &str = "collation_name";
+pub const COLUMN_KEY: &str = "column_key";
+pub const EXTRA: &str = "extra";
+pub const PRIVILEGES: &str = "privileges";
+const GENERATION_EXPRESSION: &str = "generation_expression";
+// Extension field to keep greptime data type name
+pub const GREPTIME_DATA_TYPE: &str = "greptime_data_type";
+pub const DATA_TYPE: &str = "data_type";
+pub const SEMANTIC_TYPE: &str = "semantic_type";
+pub const COLUMN_DEFAULT: &str = "column_default";
+pub const IS_NULLABLE: &str = "is_nullable";
 const COLUMN_TYPE: &str = "column_type";
-const COLUMN_COMMENT: &str = "column_comment";
+pub const COLUMN_COMMENT: &str = "column_comment";
+const SRS_ID: &str = "srs_id";
 const INIT_CAPACITY: usize = 42;
 
+// The maximum length of string type
+const MAX_STRING_LENGTH: i64 = 2147483647;
+const UTF8_CHARSET_NAME: &str = "utf8";
+const UTF8_COLLATE_NAME: &str = "utf8_bin";
+const PRI_COLUMN_KEY: &str = "PRI";
+const TIME_INDEX_COLUMN_KEY: &str = "TIME INDEX";
+const DEFAULT_PRIVILEGES: &str = "select,insert";
+const EMPTY_STR: &str = "";
+
 impl InformationSchemaColumns {
     pub(super) fn new(catalog_name: String, catalog_manager: Weak<dyn CatalogManager>) -> Self {
         Self {
@@ -75,12 +102,46 @@ impl InformationSchemaColumns {
             ColumnSchema::new(TABLE_SCHEMA, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(TABLE_NAME, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(COLUMN_NAME, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(ORDINAL_POSITION, ConcreteDataType::int64_datatype(), false),
+            ColumnSchema::new(
+                CHARACTER_MAXIMUM_LENGTH,
+                ConcreteDataType::int64_datatype(),
+                true,
+            ),
+            ColumnSchema::new(
+                CHARACTER_OCTET_LENGTH,
+                ConcreteDataType::int64_datatype(),
+                true,
+            ),
+            ColumnSchema::new(NUMERIC_PRECISION, ConcreteDataType::int64_datatype(), true),
+            ColumnSchema::new(NUMERIC_SCALE, ConcreteDataType::int64_datatype(), true),
+            ColumnSchema::new(DATETIME_PRECISION, ConcreteDataType::int64_datatype(), true),
+            ColumnSchema::new(
+                CHARACTER_SET_NAME,
+                ConcreteDataType::string_datatype(),
+                true,
+            ),
+            ColumnSchema::new(COLLATION_NAME, ConcreteDataType::string_datatype(), true),
+            ColumnSchema::new(COLUMN_KEY, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(EXTRA, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(PRIVILEGES, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(
+                GENERATION_EXPRESSION,
+                ConcreteDataType::string_datatype(),
+                false,
+            ),
+            ColumnSchema::new(
+                GREPTIME_DATA_TYPE,
+                ConcreteDataType::string_datatype(),
+                false,
+            ),
             ColumnSchema::new(DATA_TYPE, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(SEMANTIC_TYPE, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(COLUMN_DEFAULT, ConcreteDataType::string_datatype(), true),
             ColumnSchema::new(IS_NULLABLE, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(COLUMN_TYPE, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(COLUMN_COMMENT, ConcreteDataType::string_datatype(), true),
+            ColumnSchema::new(SRS_ID, ConcreteDataType::int64_datatype(), true),
         ]))
     }
 
@@ -136,9 +197,18 @@ struct InformationSchemaColumnsBuilder {
     schema_names: StringVectorBuilder,
     table_names: StringVectorBuilder,
     column_names: StringVectorBuilder,
+    ordinal_positions: Int64VectorBuilder,
+    character_maximum_lengths: Int64VectorBuilder,
+    character_octet_lengths: Int64VectorBuilder,
+    numeric_precisions: Int64VectorBuilder,
+    numeric_scales: Int64VectorBuilder,
+    datetime_precisions: Int64VectorBuilder,
+    character_set_names: StringVectorBuilder,
+    collation_names: StringVectorBuilder,
+    column_keys: StringVectorBuilder,
+    greptime_data_types: StringVectorBuilder,
     data_types: StringVectorBuilder,
     semantic_types: StringVectorBuilder,
-
     column_defaults: StringVectorBuilder,
     is_nullables: StringVectorBuilder,
     column_types: StringVectorBuilder,
@@ -159,6 +229,16 @@ impl InformationSchemaColumnsBuilder {
             schema_names: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             table_names: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             column_names: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            ordinal_positions: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            character_maximum_lengths: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            character_octet_lengths: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            numeric_precisions: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            numeric_scales: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            datetime_precisions: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
+            character_set_names: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            collation_names: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            column_keys: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            greptime_data_types: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             data_types: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             semantic_types: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             column_defaults: StringVectorBuilder::with_capacity(INIT_CAPACITY),
@@ -178,7 +258,7 @@ impl InformationSchemaColumnsBuilder {
         let predicates = Predicates::from_scan_request(&request);
 
         for schema_name in catalog_manager.schema_names(&catalog_name).await? {
-            let mut stream = catalog_manager.tables(&catalog_name, &schema_name).await;
+            let mut stream = catalog_manager.tables(&catalog_name, &schema_name);
 
             while let Some(table) = stream.try_next().await? {
                 let keys = &table.table_info().meta.primary_key_indices;
@@ -195,6 +275,7 @@ impl InformationSchemaColumnsBuilder {
 
                     self.add_column(
                         &predicates,
+                        idx,
                         &catalog_name,
                         &schema_name,
                         &table.table_info().name,
@@ -208,16 +289,27 @@ impl InformationSchemaColumnsBuilder {
         self.finish()
     }
 
+    #[allow(clippy::too_many_arguments)]
     fn add_column(
         &mut self,
         predicates: &Predicates,
+        index: usize,
         catalog_name: &str,
         schema_name: &str,
         table_name: &str,
         semantic_type: &str,
         column_schema: &ColumnSchema,
     ) {
-        let data_type = &column_schema.data_type.name();
+        // Use sql data type name
+        let data_type = statements::concrete_data_type_to_sql_data_type(&column_schema.data_type)
+            .map(|dt| dt.to_string().to_lowercase())
+            .unwrap_or_else(|_| column_schema.data_type.name());
+
+        let column_key = match semantic_type {
+            SEMANTIC_TYPE_PRIMARY_KEY => PRI_COLUMN_KEY,
+            SEMANTIC_TYPE_TIME_INDEX => TIME_INDEX_COLUMN_KEY,
+            _ => EMPTY_STR,
+        };
 
         let row = [
             (TABLE_CATALOG, &Value::from(catalog_name)),
@@ -226,6 +318,8 @@ impl InformationSchemaColumnsBuilder {
             (COLUMN_NAME, &Value::from(column_schema.name.as_str())),
             (DATA_TYPE, &Value::from(data_type.as_str())),
             (SEMANTIC_TYPE, &Value::from(semantic_type)),
+            (ORDINAL_POSITION, &Value::from((index + 1) as i64)),
+            (COLUMN_KEY, &Value::from(column_key)),
         ];
 
         if !predicates.eval(&row) {
@@ -236,7 +330,63 @@ impl InformationSchemaColumnsBuilder {
         self.schema_names.push(Some(schema_name));
         self.table_names.push(Some(table_name));
         self.column_names.push(Some(&column_schema.name));
-        self.data_types.push(Some(data_type));
+        // Starts from 1
+        self.ordinal_positions.push(Some((index + 1) as i64));
+
+        if column_schema.data_type.is_string() {
+            self.character_maximum_lengths.push(Some(MAX_STRING_LENGTH));
+            self.character_octet_lengths.push(Some(MAX_STRING_LENGTH));
+            self.numeric_precisions.push(None);
+            self.numeric_scales.push(None);
+            self.datetime_precisions.push(None);
+            self.character_set_names.push(Some(UTF8_CHARSET_NAME));
+            self.collation_names.push(Some(UTF8_COLLATE_NAME));
+        } else if column_schema.data_type.is_numeric() || column_schema.data_type.is_decimal() {
+            self.character_maximum_lengths.push(None);
+            self.character_octet_lengths.push(None);
+
+            self.numeric_precisions.push(
+                column_schema
+                    .data_type
+                    .numeric_precision()
+                    .map(|x| x as i64),
+            );
+            self.numeric_scales
+                .push(column_schema.data_type.numeric_scale().map(|x| x as i64));
+
+            self.datetime_precisions.push(None);
+            self.character_set_names.push(None);
+            self.collation_names.push(None);
+        } else {
+            self.character_maximum_lengths.push(None);
+            self.character_octet_lengths.push(None);
+            self.numeric_precisions.push(None);
+            self.numeric_scales.push(None);
+
+            match &column_schema.data_type {
+                ConcreteDataType::DateTime(datetime_type) => {
+                    self.datetime_precisions
+                        .push(Some(datetime_type.precision() as i64));
+                }
+                ConcreteDataType::Timestamp(ts_type) => {
+                    self.datetime_precisions
+                        .push(Some(ts_type.precision() as i64));
+                }
+                ConcreteDataType::Time(time_type) => {
+                    self.datetime_precisions
+                        .push(Some(time_type.precision() as i64));
+                }
+                _ => self.datetime_precisions.push(None),
+            }
+
+            self.character_set_names.push(None);
+            self.collation_names.push(None);
+        }
+
+        self.column_keys.push(Some(column_key));
+        self.greptime_data_types
+            .push(Some(&column_schema.data_type.name()));
+        self.data_types.push(Some(&data_type));
         self.semantic_types.push(Some(semantic_type));
         self.column_defaults.push(
             column_schema
@@ -249,23 +399,52 @@ impl InformationSchemaColumnsBuilder {
         } else {
             self.is_nullables.push(Some("No"));
         }
-        self.column_types.push(Some(data_type));
+        self.column_types.push(Some(&data_type));
         self.column_comments
             .push(column_schema.column_comment().map(|x| x.as_ref()));
     }
 
     fn finish(&mut self) -> Result<RecordBatch> {
+        let rows_num = self.collation_names.len();
+
+        let privileges = Arc::new(ConstantVector::new(
+            Arc::new(StringVector::from(vec![DEFAULT_PRIVILEGES])),
+            rows_num,
+        ));
+        let empty_string = Arc::new(ConstantVector::new(
+            Arc::new(StringVector::from(vec![EMPTY_STR])),
+            rows_num,
+        ));
+        let srs_ids = Arc::new(ConstantVector::new(
+            Arc::new(Int64Vector::from(vec![None])),
+            rows_num,
+        ));
+
         let columns: Vec<VectorRef> = vec![
             Arc::new(self.catalog_names.finish()),
             Arc::new(self.schema_names.finish()),
             Arc::new(self.table_names.finish()),
             Arc::new(self.column_names.finish()),
+            Arc::new(self.ordinal_positions.finish()),
+            Arc::new(self.character_maximum_lengths.finish()),
+            Arc::new(self.character_octet_lengths.finish()),
+            Arc::new(self.numeric_precisions.finish()),
+            Arc::new(self.numeric_scales.finish()),
+            Arc::new(self.datetime_precisions.finish()),
+            Arc::new(self.character_set_names.finish()),
+            Arc::new(self.collation_names.finish()),
+            Arc::new(self.column_keys.finish()),
+            empty_string.clone(),
+            privileges,
+            empty_string,
+            Arc::new(self.greptime_data_types.finish()),
             Arc::new(self.data_types.finish()),
             Arc::new(self.semantic_types.finish()),
             Arc::new(self.column_defaults.finish()),
             Arc::new(self.is_nullables.finish()),
             Arc::new(self.column_types.finish()),
             Arc::new(self.column_comments.finish()),
+            srs_ids,
         ];
 
         RecordBatch::new(self.schema.clone(), columns).context(CreateRecordBatchSnafu)

src/catalog/src/information_schema/key_column_usage.rs

@@ -17,9 +17,9 @@ use std::sync::{Arc, Weak};
 use arrow_schema::SchemaRef as ArrowSchemaRef;
 use common_catalog::consts::INFORMATION_SCHEMA_KEY_COLUMN_USAGE_TABLE_ID;
 use common_error::ext::BoxedError;
-use common_query::physical_plan::TaskContext;
 use common_recordbatch::adapter::RecordBatchStreamAdapter;
 use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
+use datafusion::execution::TaskContext;
 use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
 use datafusion::physical_plan::streaming::PartitionStream as DfPartitionStream;
 use datafusion::physical_plan::SendableRecordBatchStream as DfSendableRecordBatchStream;
@@ -37,15 +37,23 @@ use crate::error::{
 use crate::information_schema::{InformationTable, Predicates};
 use crate::CatalogManager;
 
-const CONSTRAINT_SCHEMA: &str = "constraint_schema";
-const CONSTRAINT_NAME: &str = "constraint_name";
-const TABLE_CATALOG: &str = "table_catalog";
-const TABLE_SCHEMA: &str = "table_schema";
-const TABLE_NAME: &str = "table_name";
-const COLUMN_NAME: &str = "column_name";
-const ORDINAL_POSITION: &str = "ordinal_position";
+pub const CONSTRAINT_SCHEMA: &str = "constraint_schema";
+pub const CONSTRAINT_NAME: &str = "constraint_name";
+// It's always `def` in MySQL
+pub const TABLE_CATALOG: &str = "table_catalog";
+// The real catalog name for this key column.
+pub const REAL_TABLE_CATALOG: &str = "real_table_catalog";
+pub const TABLE_SCHEMA: &str = "table_schema";
+pub const TABLE_NAME: &str = "table_name";
+pub const COLUMN_NAME: &str = "column_name";
+pub const ORDINAL_POSITION: &str = "ordinal_position";
 const INIT_CAPACITY: usize = 42;
 
+/// Primary key constraint name
+pub(crate) const PRI_CONSTRAINT_NAME: &str = "PRIMARY";
+/// Time index constraint name
+pub(crate) const TIME_INDEX_CONSTRAINT_NAME: &str = "TIME INDEX";
+
 /// The virtual table implementation for `information_schema.KEY_COLUMN_USAGE`.
 pub(super) struct InformationSchemaKeyColumnUsage {
     schema: SchemaRef,
@@ -76,6 +84,11 @@ impl InformationSchemaKeyColumnUsage {
             ),
             ColumnSchema::new(CONSTRAINT_NAME, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(TABLE_CATALOG, ConcreteDataType::string_datatype(), false),
+            ColumnSchema::new(
+                REAL_TABLE_CATALOG,
+                ConcreteDataType::string_datatype(),
+                false,
+            ),
             ColumnSchema::new(TABLE_SCHEMA, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(TABLE_NAME, ConcreteDataType::string_datatype(), false),
             ColumnSchema::new(COLUMN_NAME, ConcreteDataType::string_datatype(), false),
@@ -158,6 +171,7 @@ struct InformationSchemaKeyColumnUsageBuilder {
     constraint_schema: StringVectorBuilder,
     constraint_name: StringVectorBuilder,
     table_catalog: StringVectorBuilder,
+    real_table_catalog: StringVectorBuilder,
     table_schema: StringVectorBuilder,
     table_name: StringVectorBuilder,
     column_name: StringVectorBuilder,
@@ -179,6 +193,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
             constraint_schema: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             constraint_name: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             table_catalog: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            real_table_catalog: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             table_schema: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             table_name: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             column_name: StringVectorBuilder::with_capacity(INIT_CAPACITY),
@@ -222,7 +237,8 @@ impl InformationSchemaKeyColumnUsageBuilder {
                             self.add_key_column_usage(
                                 &predicates,
                                 &schema_name,
-                                "TIME INDEX",
+                                TIME_INDEX_CONSTRAINT_NAME,
+                                &catalog_name,
                                 &schema_name,
                                 &table_name,
                                 &column.name,
@@ -231,6 +247,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
                         }
                         if keys.contains(&idx) {
                             primary_constraints.push((
+                                catalog_name.clone(),
                                 schema_name.clone(),
                                 table_name.clone(),
                                 column.name.clone(),
@@ -244,13 +261,14 @@ impl InformationSchemaKeyColumnUsageBuilder {
             }
         }
 
-        for (i, (schema_name, table_name, column_name)) in
+        for (i, (catalog_name, schema_name, table_name, column_name)) in
             primary_constraints.into_iter().enumerate()
         {
             self.add_key_column_usage(
                 &predicates,
                 &schema_name,
-                "PRIMARY",
+                PRI_CONSTRAINT_NAME,
+                &catalog_name,
                 &schema_name,
                 &table_name,
                 &column_name,
@@ -269,6 +287,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
         predicates: &Predicates,
         constraint_schema: &str,
         constraint_name: &str,
+        table_catalog: &str,
         table_schema: &str,
         table_name: &str,
         column_name: &str,
@@ -277,6 +296,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
         let row = [
             (CONSTRAINT_SCHEMA, &Value::from(constraint_schema)),
             (CONSTRAINT_NAME, &Value::from(constraint_name)),
+            (REAL_TABLE_CATALOG, &Value::from(table_catalog)),
             (TABLE_SCHEMA, &Value::from(table_schema)),
             (TABLE_NAME, &Value::from(table_name)),
             (COLUMN_NAME, &Value::from(column_name)),
@@ -291,6 +311,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
         self.constraint_schema.push(Some(constraint_schema));
         self.constraint_name.push(Some(constraint_name));
         self.table_catalog.push(Some("def"));
+        self.real_table_catalog.push(Some(table_catalog));
         self.table_schema.push(Some(table_schema));
         self.table_name.push(Some(table_name));
         self.column_name.push(Some(column_name));
@@ -310,6 +331,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
             Arc::new(self.constraint_schema.finish()),
             Arc::new(self.constraint_name.finish()),
             Arc::new(self.table_catalog.finish()),
+            Arc::new(self.real_table_catalog.finish()),
             Arc::new(self.table_schema.finish()),
             Arc::new(self.table_name.finish()),
             Arc::new(self.column_name.finish()),

src/catalog/src/information_schema/memory_table.rs

@@ -17,9 +17,9 @@ use std::sync::Arc;
 
 use arrow_schema::SchemaRef as ArrowSchemaRef;
 use common_error::ext::BoxedError;
-use common_query::physical_plan::TaskContext;
 use common_recordbatch::adapter::RecordBatchStreamAdapter;
 use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
+use datafusion::execution::TaskContext;
 use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
 use datafusion::physical_plan::streaming::PartitionStream as DfPartitionStream;
 use datafusion::physical_plan::SendableRecordBatchStream as DfSendableRecordBatchStream;