fix: some cr comments

.cargo/config.toml

@@ -3,3 +3,13 @@ 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",
+]

.coderabbit.yaml

@@ -1,15 +0,0 @@
-# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
-language: "en-US"
-early_access: false
-reviews:
-  profile: "chill"
-  request_changes_workflow: false
-  high_level_summary: true
-  poem: true
-  review_status: true
-  collapse_walkthrough: false
-  auto_review:
-    enabled: false
-    drafts: false
-chat:
-  auto_reply: true

.editorconfig

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

.env.example

@@ -14,23 +14,10 @@ GT_AZBLOB_CONTAINER=AZBLOB container
 GT_AZBLOB_ACCOUNT_NAME=AZBLOB account name
 GT_AZBLOB_ACCOUNT_KEY=AZBLOB account key
 GT_AZBLOB_ENDPOINT=AZBLOB endpoint
-# Settings for gcs test
-GT_GCS_BUCKET = GCS bucket
+# Settings for gcs test 
+GT_GCS_BUCKET = GCS bucket 
 GT_GCS_SCOPE  = GCS scope
-GT_GCS_CREDENTIAL_PATH = GCS credential path
-GT_GCS_CREDENTIAL = GCS credential
+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
-GT_FUZZ_INPUT_MAX_ROWS=2048
-GT_FUZZ_INPUT_MAX_TABLES=32
-GT_FUZZ_INPUT_MAX_COLUMNS=32
-GT_FUZZ_INPUT_MAX_ALTER_ACTIONS=256
-GT_FUZZ_INPUT_MAX_INSERT_ACTIONS=8

.github/CODEOWNERS

@@ -1,27 +0,0 @@
-# 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: [ "C-bug" ]
+labels: [ "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/discussions
+    url: https://github.com/greptimeTeam/greptimedb/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: [ "C-enhancement" ]
+labels: [ "enhancement" ]
 body:
   - type: dropdown
     id: type

.github/ISSUE_TEMPLATE/feature_request.yml

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

.github/actions/build-and-push-ci-image/action.yml

@@ -1,18 +0,0 @@
-name: Build and push CI Docker image
-description: Build and push CI Docker image to local registry
-inputs:
-  binary_path:
-    default: "./bin"
-    description: "Binary path"
-runs:
-  using: composite
-  steps: 
-    - name: Build and push to local registry
-      uses: docker/build-push-action@v5
-      with:
-        context: .
-        file: ./docker/ci/ubuntu/Dockerfile.fuzztests
-        push: true
-        tags: localhost:5001/greptime/greptimedb:latest
-        build-args: |
-          BINARY_PATH=${{ inputs.binary_path }}

.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:
@@ -47,10 +47,10 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=ubuntu \
-          BUILDX_MULTI_PLATFORM_BUILD=all \
+          BUILDX_MULTI_PLATFORM_BUILD=true \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          DEV_BUILDER_IMAGE_TAG=${{ inputs.version }}
+          IMAGE_TAG=${{ inputs.version }}
 
     - name: Build and push dev-builder-centos image
       shell: bash
@@ -58,10 +58,10 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=centos \
-          BUILDX_MULTI_PLATFORM_BUILD=amd64 \
+          BUILDX_MULTI_PLATFORM_BUILD=true \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          DEV_BUILDER_IMAGE_TAG=${{ inputs.version }}
+          IMAGE_TAG=${{ inputs.version }}
 
     - name: Build and push dev-builder-android image # Only build image for amd64 platform.
       shell: bash
@@ -71,6 +71,6 @@ runs:
           BASE_IMAGE=android \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          DEV_BUILDER_IMAGE_TAG=${{ inputs.version }} && \
-
+          IMAGE_TAG=${{ inputs.version }} && \
+        
         docker push ${{ inputs.dockerhub-image-registry }}/${{ inputs.dockerhub-image-namespace }}/dev-builder-android:${{ inputs.version }}

.github/actions/build-greptime-binary/action.yml

@@ -24,14 +24,6 @@ inputs:
     description: Build android artifacts
     required: false
     default: 'false'
-  image-namespace:
-    description: Image Namespace
-    required: false
-    default: 'greptime'
-  image-registry:
-    description: Image Registry
-    required: false
-    default: 'docker.io'
 runs:
   using: composite
   steps:
@@ -43,9 +35,7 @@ runs:
         make build-by-dev-builder \
           CARGO_PROFILE=${{ inputs.cargo-profile }} \
           FEATURES=${{ inputs.features }} \
-          BASE_IMAGE=${{ inputs.base-image }} \
-          IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-          IMAGE_REGISTRY=${{ inputs.image-registry }}
+          BASE_IMAGE=${{ inputs.base-image }}
 
     - name: Upload artifacts
       uses: ./.github/actions/upload-artifacts
@@ -63,9 +53,7 @@ runs:
       shell: bash
       if: ${{ inputs.build-android-artifacts == 'true' }}
       run: |
-        cd ${{ inputs.working-dir }} && make strip-android-bin \
-          IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-          IMAGE_REGISTRY=${{ inputs.image-registry }}
+        cd ${{ inputs.working-dir }} && make strip-android-bin
 
     - name: Upload android artifacts
       uses: ./.github/actions/upload-artifacts

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

@@ -16,13 +16,7 @@ inputs:
   dev-mode:
     description: Enable dev mode, only build standard greptime
     required: false
-    default: "false"
-  image-namespace:
-    description: Image Namespace
-    required: true
-  image-registry:
-    description: Image Registry
-    required: true
+    default: 'false'
   working-dir:
     description: Working directory to build the artifacts
     required: false
@@ -36,13 +30,11 @@ runs:
       # NOTE: If the BUILD_JOBS > 4, it's always OOM in EC2 instance.
       run: |
         cd ${{ inputs.working-dir }} && \
-        make run-it-in-container BUILD_JOBS=4 \
-        IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-        IMAGE_REGISTRY=${{ inputs.image-registry }}
+        make run-it-in-container BUILD_JOBS=4
 
     - name: Upload sqlness logs
       if: ${{ failure() && inputs.disable-run-tests == 'false' }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v3
       with:
         name: sqlness-logs
         path: /tmp/greptime-*.log
@@ -57,8 +49,6 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-pyo3-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: ${{ inputs.image-registry }}
-        image-namespace: ${{ inputs.image-namespace }}
 
     - name: Build greptime without pyo3
       if: ${{ inputs.dev-mode == 'false' }}
@@ -70,8 +60,6 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: ${{ inputs.image-registry }}
-        image-namespace: ${{ inputs.image-namespace }}
 
     - name: Clean up the target directory # Clean up the target directory for the centos7 base image, or it will still use the objects of last build.
       shell: bash
@@ -80,7 +68,7 @@ runs:
 
     - name: Build greptime on centos base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds greptime for centos if the host machine is amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build centos7 base image for amd64.
       with:
         base-image: centos
         features: servers/dashboard
@@ -88,17 +76,13 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-centos-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: ${{ inputs.image-registry }}
-        image-namespace: ${{ inputs.image-namespace }}
 
     - name: Build greptime on android base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds arm64 greptime binary for android if the host machine amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build android base image on amd64.
       with:
         base-image: android
         artifacts-dir: greptime-android-arm64-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
         build-android-artifacts: true
-        image-registry: ${{ inputs.image-registry }}
-        image-namespace: ${{ inputs.image-namespace }}

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

@@ -4,6 +4,9 @@ inputs:
   arch:
     description: Architecture to build
     required: true
+  rust-toolchain:
+    description: Rust toolchain to use
+    required: true
   cargo-profile:
     description: Cargo profile to build
     required: true
@@ -40,9 +43,10 @@ runs:
         brew install protobuf
 
     - name: Install rust toolchain
-      uses: actions-rust-lang/setup-rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
-        target: ${{ inputs.arch }}
+        toolchain: ${{ inputs.rust-toolchain }}
+        targets: ${{ inputs.arch }}
 
     - name: Start etcd # For integration tests.
       if: ${{ inputs.disable-run-tests == 'false' }}
@@ -55,22 +59,15 @@ runs:
       if: ${{ inputs.disable-run-tests == 'false' }}
       uses: taiki-e/install-action@nextest
 
-    # Get proper backtraces in mac Sonoma. Currently there's an issue with the new
-    # linker that prevents backtraces from getting printed correctly.
-    #
-    # <https://github.com/rust-lang/rust/issues/113783>
     - name: Run integration tests
       if: ${{ inputs.disable-run-tests == 'false' }}
       shell: bash
-      env:
-        CARGO_BUILD_RUSTFLAGS: "-Clink-arg=-Wl,-ld_classic"
-        SQLNESS_OPTS: "--preserve-state"
       run: |
         make test sqlness-test
 
     - name: Upload sqlness logs
       if: ${{ failure() }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v3
       with:
         name: sqlness-logs
         path: /tmp/greptime-*.log
@@ -78,8 +75,6 @@ runs:
 
     - name: Build greptime binary
       shell: bash
-      env:
-        CARGO_BUILD_RUSTFLAGS: "-Clink-arg=-Wl,-ld_classic"
       run: |
         make build \
         CARGO_PROFILE=${{ inputs.cargo-profile }} \

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

@@ -4,6 +4,9 @@ inputs:
   arch:
     description: Architecture to build
     required: true
+  rust-toolchain:
+    description: Rust toolchain to use
+    required: true
   cargo-profile:
     description: Cargo profile to build
     required: true
@@ -25,9 +28,10 @@ runs:
     - uses: arduino/setup-protoc@v3
 
     - name: Install rust toolchain
-      uses: actions-rust-lang/setup-rust-toolchain@v1
+      uses: dtolnay/rust-toolchain@master
       with:
-        target: ${{ inputs.arch }}
+        toolchain: ${{ inputs.rust-toolchain }}
+        targets: ${{ inputs.arch }}
         components: llvm-tools-preview
 
     - name: Rust Cache
@@ -36,11 +40,11 @@ runs:
     - name: Install Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.10"
+        python-version: '3.10'
 
     - name: Install PyArrow Package
       shell: pwsh
-      run: pip install pyarrow numpy
+      run: pip install pyarrow
 
     - name: Install WSL distribution
       uses: Vampire/setup-wsl@v2
@@ -55,22 +59,18 @@ 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
-        SQLNESS_OPTS: "--preserve-state"
 
     - name: Upload sqlness logs
       if: ${{ failure() }} # Only upload logs when the integration tests failed.
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v3
       with:
         name: sqlness-logs
-        path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
+        path: ${{ runner.temp }}/greptime-*.log
         retention-days: 3
 
     - name: Build greptime binary
       shell: pwsh
-      run: cargo build --profile ${{ inputs.cargo-profile }} --features ${{ inputs.features }} --target ${{ inputs.arch }} --bin greptime
+      run: cargo build --profile ${{ inputs.cargo-profile }} --features ${{ inputs.features }} --target ${{ inputs.arch }}
 
     - name: Upload artifacts
       uses: ./.github/actions/upload-artifacts

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

@@ -1,19 +0,0 @@
-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/release-cn-artifacts/action.yaml

@@ -123,10 +123,10 @@ runs:
         DST_REGISTRY_PASSWORD: ${{ inputs.dst-image-registry-password }}
       run: |
         ./.github/scripts/copy-image.sh \
-         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}-centos:${{ inputs.version }} \
+         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}-centos:latest \
          ${{ inputs.dst-image-registry }}/${{ inputs.dst-image-namespace }}
 
-    - name: Push latest greptimedb-centos image from DockerHub to ACR
+    - name: Push greptimedb-centos image from DockerHub to ACR
       shell: bash
       if: ${{ inputs.dev-mode == 'false' && inputs.push-latest-tag == 'true' }}
       env:

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

@@ -1,17 +0,0 @@
-name: Setup Kind
-description: Deploy Kind
-runs:
-  using: composite
-  steps:
-  - uses: actions/checkout@v4
-  - name: Create kind cluster
-    shell: bash
-    run: |
-      helm repo add chaos-mesh https://charts.chaos-mesh.org
-      kubectl create ns chaos-mesh
-      helm install chaos-mesh chaos-mesh/chaos-mesh -n=chaos-mesh --version 2.6.3
-  - name: Print Chaos-mesh
-    if: always()
-    shell: bash
-    run: | 
-      kubectl get po -n chaos-mesh

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

@@ -1,16 +0,0 @@
-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/actions/setup-etcd-cluster/action.yml

@@ -1,27 +0,0 @@
-name: Setup Etcd cluster
-description: Deploy Etcd cluster on Kubernetes
-inputs:
-  etcd-replicas:
-    default: 1
-    description: "Etcd replicas"
-  namespace:
-    default: "etcd-cluster"
-
-runs:
-  using: composite
-  steps:
-  - name: Install Etcd cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install etcd oci://registry-1.docker.io/bitnamicharts/etcd \
-        --set replicaCount=${{ inputs.etcd-replicas }} \
-        --set resources.requests.cpu=50m \
-        --set resources.requests.memory=128Mi \
-        --set resources.limits.cpu=1500m \
-        --set resources.limits.memory=2Gi \
-        --set auth.rbac.create=false \
-        --set auth.rbac.token.enabled=false \
-        --set persistence.size=2Gi \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

.github/actions/setup-greptimedb-cluster/action.yml

@@ -1,95 +0,0 @@
-name: Setup GreptimeDB cluster
-description: Deploy GreptimeDB cluster on Kubernetes
-inputs:
-  frontend-replicas:
-    default: 2
-    description: "Number of Frontend replicas"
-  datanode-replicas:
-    default: 2
-    description: "Number of Datanode replicas"
-  meta-replicas:
-    default: 1
-    description: "Number of Metasrv replicas"
-  image-registry: 
-    default: "docker.io"
-    description: "Image registry"
-  image-repository: 
-    default: "greptime/greptimedb"
-    description: "Image repository"
-  image-tag: 
-    default: "latest"
-    description: 'Image tag'
-  etcd-endpoints:
-    default: "etcd.etcd-cluster.svc.cluster.local:2379"
-    description: "Etcd endpoints"
-  values-filename:
-    default: "with-minio.yaml"
-  enable-region-failover:
-    default: false
-
-runs:
-  using: composite
-  steps:
-  - name: Install GreptimeDB operator
-    uses: nick-fields/retry@v3
-    with: 
-      timeout_minutes: 3
-      max_attempts: 3
-      shell: bash
-      command: |
-        helm repo add greptime https://greptimeteam.github.io/helm-charts/ 
-        helm repo update
-        helm upgrade \
-          --install \
-          --create-namespace \
-          greptimedb-operator greptime/greptimedb-operator \
-          -n greptimedb-admin \
-          --wait \
-          --wait-for-jobs
-  - name: Install GreptimeDB cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install my-greptimedb \
-        --set meta.etcdEndpoints=${{ inputs.etcd-endpoints }} \
-        --set meta.enableRegionFailover=${{ inputs.enable-region-failover }} \
-        --set image.registry=${{ inputs.image-registry }} \
-        --set image.repository=${{ inputs.image-repository }}  \
-        --set image.tag=${{ inputs.image-tag }} \
-        --set base.podTemplate.main.resources.requests.cpu=50m \
-        --set base.podTemplate.main.resources.requests.memory=256Mi \
-        --set base.podTemplate.main.resources.limits.cpu=2000m \
-        --set base.podTemplate.main.resources.limits.memory=2Gi \
-        --set frontend.replicas=${{ inputs.frontend-replicas }} \
-        --set datanode.replicas=${{ inputs.datanode-replicas }} \
-        --set meta.replicas=${{ inputs.meta-replicas }} \
-        greptime/greptimedb-cluster \
-        --create-namespace \
-        -n my-greptimedb \
-        --values ./.github/actions/setup-greptimedb-cluster/${{ inputs.values-filename }} \
-        --wait \
-        --wait-for-jobs
-  - name: Wait for GreptimeDB
-    shell: bash
-    run: |
-      while true; do 
-        PHASE=$(kubectl -n my-greptimedb get gtc my-greptimedb -o jsonpath='{.status.clusterPhase}')
-        if [ "$PHASE" == "Running" ]; then
-          echo "Cluster is ready"
-          break
-        else
-          echo "Cluster is not ready yet: Current phase: $PHASE"
-          kubectl get pods -n my-greptimedb
-          sleep 5 # wait for 5 seconds before check again.
-        fi
-      done
-  - name: Print GreptimeDB info
-    if: always()
-    shell: bash
-    run: | 
-      kubectl get all --show-labels -n my-greptimedb
-  - name: Describe Nodes
-    if: always()
-    shell: bash
-    run: | 
-      kubectl describe nodes

.github/actions/setup-greptimedb-cluster/with-disk.yaml

@@ -1,13 +0,0 @@
-meta:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-datanode:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    compact_rt_size = 2
-frontend:
-  configData: |-
-    [runtime]
-    global_rt_size = 4

.github/actions/setup-greptimedb-cluster/with-minio-and-cache.yaml

@@ -1,33 +0,0 @@
-meta:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    compact_rt_size = 2
-    
-    [storage]
-    cache_path = "/data/greptimedb/s3cache"
-    cache_capacity = "256MB"
-frontend:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123

.github/actions/setup-greptimedb-cluster/with-minio.yaml

@@ -1,29 +0,0 @@
-meta:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    compact_rt_size = 2
-frontend:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123

.github/actions/setup-greptimedb-cluster/with-remote-wal.yaml

@@ -1,45 +0,0 @@
-meta:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    
-    [wal]
-    provider = "kafka"
-    broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
-    num_topics = 3
-
-        
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-    compact_rt_size = 2
-
-    [wal]
-    provider = "kafka"
-    broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
-    linger = "2ms"
-frontend:
-  configData: |-
-    [runtime]
-    global_rt_size = 4
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123
-remoteWal:
-   enabled: true
-   kafka:
-     brokerEndpoints: 
-      - "kafka.kafka-cluster.svc.cluster.local:9092"

.github/actions/setup-kafka-cluster/action.yml

@@ -1,26 +0,0 @@
-name: Setup Kafka cluster
-description: Deploy Kafka cluster on Kubernetes
-inputs:
-  controller-replicas:
-    default: 3
-    description: "Kafka controller replicas"
-  namespace:
-    default: "kafka-cluster"
-
-runs:
-  using: composite
-  steps:
-  - name: Install Kafka cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install kafka oci://registry-1.docker.io/bitnamicharts/kafka \
-        --set controller.replicaCount=${{ inputs.controller-replicas }} \
-        --set controller.resources.requests.cpu=50m \
-        --set controller.resources.requests.memory=128Mi \
-        --set controller.resources.limits.cpu=2000m \
-        --set controller.resources.limits.memory=2Gi \
-        --set listeners.controller.protocol=PLAINTEXT \
-        --set listeners.client.protocol=PLAINTEXT \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

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

@@ -1,10 +0,0 @@
-name: Setup Kind
-description: Deploy Kind
-runs:
-  using: composite
-  steps:
-  - uses: actions/checkout@v4
-  - name: Create kind cluster
-    shell: bash
-    run: |
-      ./.github/scripts/kind-with-registry.sh

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

@@ -1,24 +0,0 @@
-name: Setup Minio cluster
-description: Deploy Minio cluster on Kubernetes
-inputs:
-  replicas:
-    default: 1
-    description: "replicas"
-
-runs:
-  using: composite
-  steps:
-  - name: Install Etcd cluster
-    shell: bash
-    run: | 
-      helm repo add minio https://charts.min.io/
-      helm upgrade --install minio \
-      --set resources.requests.memory=128Mi \
-      --set replicas=${{ inputs.replicas }} \
-      --set mode=standalone \
-      --set rootUser=rootuser,rootPassword=rootpass123 \
-      --set buckets[0].name=default \
-      --set service.port=80,service.targetPort=9000 \
-      minio/minio \
-      --create-namespace \
-      -n minio

.github/actions/setup-postgres-cluster/action.yml

@@ -1,30 +0,0 @@
-name: Setup PostgreSQL
-description: Deploy PostgreSQL on Kubernetes
-inputs:
-  postgres-replicas:
-    default: 1
-    description: "Number of PostgreSQL replicas"
-  namespace:
-    default: "postgres-namespace"
-  postgres-version:
-    default: "14.2"
-    description: "PostgreSQL version"
-  storage-size:
-    default: "1Gi"
-    description: "Storage size for PostgreSQL"
-
-runs:
-  using: composite
-  steps:
-  - name: Install PostgreSQL
-    shell: bash
-    run: |
-      helm upgrade \
-        --install postgresql oci://registry-1.docker.io/bitnamicharts/postgresql \
-        --set replicaCount=${{ inputs.postgres-replicas }} \
-        --set image.tag=${{ inputs.postgres-version }} \
-        --set persistence.size=${{ inputs.storage-size }} \
-        --set postgresql.username=greptimedb \
-        --set postgresql.password=admin \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

.github/actions/sqlness-test/action.yml

@@ -57,14 +57,3 @@ runs:
         AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-secret-access-key }}
       run: |
         aws s3 rm s3://${{ inputs.aws-ci-test-bucket }}/${{ inputs.data-root }} --recursive
-    - name: Export kind logs
-      if: failure()
-      shell: bash
-      run: kind export logs -n greptimedb-operator-e2e /tmp/kind
-    - name: Upload logs
-      if: failure()
-      uses: actions/upload-artifact@v4
-      with:
-        name: kind-logs
-        path: /tmp/kind
-        retention-days: 3

.github/actions/start-runner/action.yml

@@ -38,7 +38,7 @@ runs:
   steps:
     - name: Configure AWS credentials
       if: startsWith(inputs.runner, 'ec2')
-      uses: aws-actions/configure-aws-credentials@v4
+      uses: aws-actions/configure-aws-credentials@v2
       with:
         aws-access-key-id: ${{ inputs.aws-access-key-id }}
         aws-secret-access-key: ${{ inputs.aws-secret-access-key }}

.github/actions/stop-runner/action.yml

@@ -25,7 +25,7 @@ runs:
   steps:
     - name: Configure AWS credentials
       if: ${{ inputs.label && inputs.ec2-instance-id }}
-      uses: aws-actions/configure-aws-credentials@v4
+      uses: aws-actions/configure-aws-credentials@v2
       with:
         aws-access-key-id: ${{ inputs.aws-access-key-id }}
         aws-secret-access-key: ${{ inputs.aws-secret-access-key }}

.github/cargo-blacklist.txt

@@ -1,3 +0,0 @@
-native-tls
-openssl
-aws-lc-sys

.github/doc-label-config.yml

@@ -0,0 +1,4 @@
+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

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

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

@@ -0,0 +1,12 @@
+{
+    "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

@@ -1,11 +1,8 @@
-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)
+I hereby agree to the terms of the [GreptimeDB CLA](https://gist.github.com/xtang/6378857777706e568c1949c7578592cc)
 
 ## What's changed and what's your intention?
 
-<!--    
- __!!! DO NOT LEAVE THIS BLOCK EMPTY !!!__
+_PLEASE DO NOT LEAVE THIS EMPTY !!!_
 
 Please explain IN DETAIL what the changes are in this PR and why they are needed:
 
@@ -13,14 +10,11 @@ Please explain IN DETAIL what the changes are in this PR and why they are needed
 - How does this PR work? Need a brief introduction for the changed logic (optional)
 - Describe clearly one logical change and avoid lazy messages (optional)
 - Describe any limitations of the current code (optional)
-- Describe if this PR will break **API or data compatibility**  (optional)
--->
 
-## PR Checklist
-Please convert it to a draft if some of the following conditions are not met.
+## Checklist
 
-- [ ] I have written the necessary rustdoc comments.
-- [ ] I have added the necessary unit tests and integration tests.
-- [ ] This PR requires documentation updates.
-- [ ] API changes are backward compatible.
-- [ ] Schema or data changes are backward compatible.
+- [ ]  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)

.github/scripts/check-install-script.sh

@@ -1,14 +0,0 @@
-#!/bin/sh
-
-set -e
-
-# Get the latest version of github.com/GreptimeTeam/greptimedb
-VERSION=$(curl -s https://api.github.com/repos/GreptimeTeam/greptimedb/releases/latest | jq -r '.tag_name')
-
-echo "Downloading the latest version: $VERSION"
-
-# Download the install script
-curl -fsSL https://raw.githubusercontent.com/greptimeteam/greptimedb/main/scripts/install.sh | sh -s $VERSION
-
-# Execute the `greptime` command
-./greptime --version

.github/scripts/kind-with-registry.sh

@@ -1,66 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-set -o pipefail
-
-# 1. Create registry container unless it already exists
-reg_name='kind-registry'
-reg_port='5001'
-if [ "$(docker inspect -f '{{.State.Running}}' "${reg_name}" 2>/dev/null || true)" != 'true' ]; then
-  docker run \
-    -d --restart=always -p "127.0.0.1:${reg_port}:5000" --network bridge --name "${reg_name}" \
-    registry:2
-fi
-
-# 2. Create kind cluster with containerd registry config dir enabled
-# TODO: kind will eventually enable this by default and this patch will
-# be unnecessary.
-#
-# See:
-# https://github.com/kubernetes-sigs/kind/issues/2875
-# https://github.com/containerd/containerd/blob/main/docs/cri/config.md#registry-configuration
-# See: https://github.com/containerd/containerd/blob/main/docs/hosts.md
-cat <<EOF | kind create cluster --wait 2m --config=-
-kind: Cluster
-apiVersion: kind.x-k8s.io/v1alpha4
-containerdConfigPatches:
-- |-
-  [plugins."io.containerd.grpc.v1.cri".registry]
-    config_path = "/etc/containerd/certs.d"
-EOF
-
-# 3. Add the registry config to the nodes
-#
-# This is necessary because localhost resolves to loopback addresses that are
-# network-namespace local.
-# In other words: localhost in the container is not localhost on the host.
-#
-# We want a consistent name that works from both ends, so we tell containerd to
-# alias localhost:${reg_port} to the registry container when pulling images
-REGISTRY_DIR="/etc/containerd/certs.d/localhost:${reg_port}"
-for node in $(kind get nodes); do
-  docker exec "${node}" mkdir -p "${REGISTRY_DIR}"
-  cat <<EOF | docker exec -i "${node}" cp /dev/stdin "${REGISTRY_DIR}/hosts.toml"
-[host."http://${reg_name}:5000"]
-EOF
-done
-
-# 4. Connect the registry to the cluster network if not already connected
-# This allows kind to bootstrap the network but ensures they're on the same network
-if [ "$(docker inspect -f='{{json .NetworkSettings.Networks.kind}}' "${reg_name}")" = 'null' ]; then
-  docker network connect "kind" "${reg_name}"
-fi
-
-# 5. Document the local registry
-# https://github.com/kubernetes/enhancements/tree/master/keps/sig-cluster-lifecycle/generic/1755-communicating-a-local-registry
-cat <<EOF | kubectl apply -f -
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: local-registry-hosting
-  namespace: kube-public
-data:
-  localRegistryHosting.v1: |
-    host: "localhost:${reg_port}"
-    help: "https://kind.sigs.k8s.io/docs/user/local-registry/"
-EOF

.github/workflows/apidoc.yml

@@ -12,6 +12,9 @@ on:
 
 name: Build API docs
 
+env:
+  RUST_TOOLCHAIN: nightly-2023-12-19
+
 jobs:
   apidoc:
     runs-on: ubuntu-20.04
@@ -20,7 +23,9 @@ jobs:
     - uses: arduino/setup-protoc@v3
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
-    - uses: actions-rust-lang/setup-rust-toolchain@v1
+    - uses: dtolnay/rust-toolchain@master
+      with:
+        toolchain: ${{ env.RUST_TOOLCHAIN }}
     - run: cargo doc --workspace --no-deps --document-private-items
     - run: |
         cat <<EOF > target/doc/index.html
@@ -35,4 +40,3 @@ jobs:
       uses: JamesIves/github-pages-deploy-action@v4
       with:
         folder: target/doc
-        single-commit: true

.github/workflows/dependency-check.yml

@@ -1,36 +0,0 @@
-name: Check Dependencies
-
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-    branches:
-      - main
-
-jobs:
-  check-dependencies:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-
-    - name: Set up Rust
-      uses: actions-rust-lang/setup-rust-toolchain@v1
-
-    - name: Run cargo tree
-      run: cargo tree --prefix none > dependencies.txt
-
-    - name: Extract dependency names
-      run: awk '{print $1}' dependencies.txt > dependency_names.txt
-
-    - name: Check for blacklisted crates
-      run: |
-        while read -r dep; do
-          if grep -qFx "$dep" dependency_names.txt; then
-            echo "Blacklisted crate '$dep' found in dependencies."
-            exit 1
-          fi
-        done < .github/cargo-blacklist.txt
-        echo "No blacklisted crates found."

.github/workflows/dev-build.yml

@@ -29,7 +29,7 @@ on:
       linux_arm64_runner:
         type: choice
         description: The runner uses to build linux-arm64 artifacts
-        default: ec2-c6g.8xlarge-arm64
+        default: ec2-c6g.4xlarge-arm64
         options:
           - ec2-c6g.xlarge-arm64 # 4C8G
           - ec2-c6g.2xlarge-arm64 # 8C16G
@@ -82,9 +82,6 @@ env:
   # The source code will check out in the following path: '${WORKING_DIR}/dev/greptime'.
   CHECKOUT_GREPTIMEDB_PATH: dev/greptimedb
 
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -177,8 +174,6 @@ jobs:
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
           dev-mode: true # Only build the standard greptime binary.
           working-dir: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   build-linux-arm64-artifacts:
     name: Build linux-arm64 artifacts
@@ -208,8 +203,6 @@ jobs:
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
           dev-mode: true # Only build the standard greptime binary.
           working-dir: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   release-images-to-dockerhub:
     name: Build and push images to DockerHub
@@ -328,7 +321,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub
@@ -337,25 +330,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.build-result == 'success' }}
-      - name: Notify dev build successful result
+      - name: Notifiy dev build successful result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
 
-      - name: Notify dev build failed result
+      - name: Notifiy dev build failed result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

.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/**'
@@ -29,42 +29,35 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
-jobs:
-  check-typos-and-docs:
-    name: Check typos and docs
-    runs-on: ubuntu-20.04
-    steps:
-      - uses: actions/checkout@v4
-      - 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)
+env:
+  RUST_TOOLCHAIN: nightly-2023-12-19
 
-  license-header-check:
+jobs:
+  typos:
+    name: Spell Check with Typos
     runs-on: ubuntu-20.04
-    name: Check License Header
     steps:
       - uses: actions/checkout@v4
-      - uses: korandoru/hawkeye@v5
+      - uses: crate-ci/typos@v1.13.10
 
   check:
     name: Check
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ windows-2022, ubuntu-20.04 ]
+        os: [ windows-latest, ubuntu-20.04 ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          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"
@@ -77,10 +70,12 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: stable
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with:
+        with: 
           # Shares across multiple jobs
           shared-key: "check-toml"
       - name: Install taplo
@@ -98,20 +93,16 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: arduino/setup-protoc@v3
+      - uses: dtolnay/rust-toolchain@master
         with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
       - uses: Swatinem/rust-cache@v2
         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
-        # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc -- --bin greptime --bin sqlness-runner
+        run: cargo build
       - name: Pack greptime binaries
         shell: bash
         run: |
@@ -126,471 +117,16 @@ jobs:
           artifacts-dir: bins
           version: current
 
-  fuzztest:
-    name: Fuzz Test
-    needs: build
-    runs-on: ubuntu-latest
-    timeout-minutes: 60
-    strategy:
-      fail-fast: false
-      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:
-      - name: Remove unused software
-        run: |
-          echo "Disk space before:"
-          df -h
-          [[ -d /usr/share/dotnet ]] && sudo rm -rf /usr/share/dotnet
-          [[ -d /usr/local/lib/android ]] && sudo rm -rf /usr/local/lib/android
-          [[ -d /opt/ghc ]] && sudo rm -rf /opt/ghc
-          [[ -d /opt/hostedtoolcache/CodeQL ]] && sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo docker image prune --all --force
-          sudo docker builder prune -a
-          echo "Disk space after:"
-          df -h
-      - uses: actions/checkout@v4
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - 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 cargo-gc-bin
-      - name: Download pre-built binaries
-        uses: actions/download-artifact@v4
-        with:
-          name: bins
-          path: .
-      - name: Unzip binaries
-        run: |
-          tar -xvf ./bins.tar.gz
-          rm ./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-greptime-ci
-    runs-on: ubuntu-latest
-    timeout-minutes: 60
-    strategy:
-      matrix:
-        target: [ "unstable_fuzz_create_table_standalone" ]
-    steps:
-      - name: Remove unused software
-        run: |
-          echo "Disk space before:"
-          df -h
-          [[ -d /usr/share/dotnet ]] && sudo rm -rf /usr/share/dotnet
-          [[ -d /usr/local/lib/android ]] && sudo rm -rf /usr/local/lib/android
-          [[ -d /opt/ghc ]] && sudo rm -rf /opt/ghc
-          [[ -d /opt/hostedtoolcache/CodeQL ]] && sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo docker image prune --all --force
-          sudo docker builder prune -a
-          echo "Disk space after:"
-          df -h
-      - uses: actions/checkout@v4
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - 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 cargo-gc-bin
-      - name: Download pre-built binariy
-        uses: actions/download-artifact@v4
-        with:
-          name: bin
-          path: .
-      - name: Unzip bianry
-        run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Run 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: ./bin/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
-
-  build-greptime-ci:
-    name: Build GreptimeDB binary (profile-CI)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ ubuntu-20.04 ]
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v4
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "build-greptime-ci"
-      - name: Install cargo-gc-bin
-        shell: bash
-        run: cargo install cargo-gc-bin
-      - name: Build greptime bianry
-        shell: bash
-        # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc --profile ci -- --bin greptime
-      - name: Pack greptime binary
-        shell: bash
-        run: |
-          mkdir bin && \
-          mv ./target/ci/greptime bin
-      - name: Print greptime binaries info
-        run: ls -lh bin
-      - name: Upload artifacts
-        uses: ./.github/actions/upload-artifacts
-        with:
-          artifacts-dir: bin
-          version: current
-
-  distributed-fuzztest:
-    name: Fuzz Test (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
-    runs-on: ubuntu-latest
-    needs:  build-greptime-ci
-    timeout-minutes: 60
-    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" ]
-        mode:
-          - name: "Remote WAL"
-            minio: true
-            kafka: true
-            values: "with-remote-wal.yaml"
-    steps:
-      - name: Remove unused software
-        run: |
-          echo "Disk space before:"
-          df -h
-          [[ -d /usr/share/dotnet ]] && sudo rm -rf /usr/share/dotnet
-          [[ -d /usr/local/lib/android ]] && sudo rm -rf /usr/local/lib/android
-          [[ -d /opt/ghc ]] && sudo rm -rf /opt/ghc
-          [[ -d /opt/hostedtoolcache/CodeQL ]] && sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo docker image prune --all --force
-          sudo docker builder prune -a
-          echo "Disk space after:"
-          df -h
-      - uses: actions/checkout@v4
-      - name: Setup Kind
-        uses: ./.github/actions/setup-kind
-      - if: matrix.mode.minio
-        name: Setup Minio
-        uses: ./.github/actions/setup-minio
-      - if: matrix.mode.kafka
-        name: Setup Kafka cluser
-        uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluser
-        uses: ./.github/actions/setup-etcd-cluster
-      # Prepares for fuzz tests
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - 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 cargo-gc-bin
-      # Downloads ci image
-      - name: Download pre-built binariy
-        uses: actions/download-artifact@v4
-        with:
-          name: bin
-          path: .
-      - name: Unzip binary
-        run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Build and push GreptimeDB image
-        uses: ./.github/actions/build-and-push-ci-image
-      - name: Wait for etcd
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=etcd \
-            --timeout=120s \
-            -n etcd-cluster
-      - if: matrix.mode.minio
-        name: Wait for minio
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app=minio \
-            --timeout=120s \
-            -n minio
-      - if: matrix.mode.kafka
-        name: Wait for kafka
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=kafka \
-            --timeout=120s \
-            -n kafka-cluster
-      - name: Print etcd info
-        shell: bash
-        run: kubectl get all --show-labels -n etcd-cluster
-      # Setup cluster for test
-      - name: Setup GreptimeDB cluster
-        uses: ./.github/actions/setup-greptimedb-cluster
-        with:
-          image-registry: localhost:5001
-          values-filename: ${{ matrix.mode.values }}
-      - name: Port forward (mysql)
-        run: |
-          kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
-      - 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: ${{ matrix.target }}
-          max-total-time: 120
-      - name: Describe Nodes
-        if: failure()
-        shell: bash
-        run: |
-          kubectl describe nodes
-      - name: Export kind logs
-        if: failure()
-        shell: bash
-        run: |
-          kind export logs /tmp/kind
-      - name: Upload logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: fuzz-tests-kind-logs-${{ matrix.mode.name }}-${{ matrix.target }}
-          path: /tmp/kind
-          retention-days: 3
-      - name: Delete cluster
-        if: success()
-        shell: bash
-        run: |
-          kind delete cluster
-          docker stop $(docker ps -a -q)
-          docker rm $(docker ps -a -q)
-          docker system prune -f
-
-  distributed-fuzztest-with-chaos:
-    name: Fuzz Test with Chaos (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
-    runs-on: ubuntu-latest
-    needs:  build-greptime-ci
-    timeout-minutes: 60
-    strategy:
-      matrix:
-        target: ["fuzz_migrate_mito_regions", "fuzz_migrate_metric_regions", "fuzz_failover_mito_regions", "fuzz_failover_metric_regions"]
-        mode:
-          - name: "Remote WAL"
-            minio: true
-            kafka: true
-            values: "with-remote-wal.yaml"
-        include:
-          - target: "fuzz_migrate_mito_regions"
-            mode:
-              name: "Local WAL"
-              minio: true
-              kafka: false
-              values: "with-minio.yaml"
-          - target: "fuzz_migrate_metric_regions"
-            mode:
-              name: "Local WAL"
-              minio: true
-              kafka: false
-              values: "with-minio.yaml"
-    steps:
-      - name: Remove unused software
-        run: |
-          echo "Disk space before:"
-          df -h
-          [[ -d /usr/share/dotnet ]] && sudo rm -rf /usr/share/dotnet
-          [[ -d /usr/local/lib/android ]] && sudo rm -rf /usr/local/lib/android
-          [[ -d /opt/ghc ]] && sudo rm -rf /opt/ghc
-          [[ -d /opt/hostedtoolcache/CodeQL ]] && sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo docker image prune --all --force
-          sudo docker builder prune -a
-          echo "Disk space after:"
-          df -h
-      - uses: actions/checkout@v4
-      - name: Setup Kind
-        uses: ./.github/actions/setup-kind
-      - name: Setup Chaos Mesh
-        uses: ./.github/actions/setup-chaos
-      - if: matrix.mode.minio
-        name: Setup Minio
-        uses: ./.github/actions/setup-minio
-      - if: matrix.mode.kafka
-        name: Setup Kafka cluser
-        uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluser
-        uses: ./.github/actions/setup-etcd-cluster
-      # Prepares for fuzz tests
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - 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 cargo-gc-bin
-      # Downloads ci image
-      - name: Download pre-built binariy
-        uses: actions/download-artifact@v4
-        with:
-          name: bin
-          path: .
-      - name: Unzip binary
-        run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Build and push GreptimeDB image
-        uses: ./.github/actions/build-and-push-ci-image
-      - name: Wait for etcd
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=etcd \
-            --timeout=120s \
-            -n etcd-cluster
-      - if: matrix.mode.minio
-        name: Wait for minio
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app=minio \
-            --timeout=120s \
-            -n minio
-      - if: matrix.mode.kafka
-        name: Wait for kafka
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=kafka \
-            --timeout=120s \
-            -n kafka-cluster
-      - name: Print etcd info
-        shell: bash
-        run: kubectl get all --show-labels -n etcd-cluster
-      # Setup cluster for test
-      - name: Setup GreptimeDB cluster
-        uses: ./.github/actions/setup-greptimedb-cluster
-        with:
-          image-registry: localhost:5001
-          values-filename: ${{ matrix.mode.values }}
-          enable-region-failover: ${{ matrix.mode.kafka }}
-      - name: Port forward (mysql)
-        run: |
-          kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
-      - 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: ${{ matrix.target }}
-          max-total-time: 120
-      - name: Describe Nodes
-        if: failure()
-        shell: bash
-        run: |
-          kubectl describe nodes
-      - name: Export kind logs
-        if: failure()
-        shell: bash
-        run: |
-          kind export logs /tmp/kind
-      - name: Upload logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: fuzz-tests-kind-logs-${{ matrix.mode.name }}-${{ matrix.target }}
-          path: /tmp/kind
-          retention-days: 3
-      - name: Delete cluster
-        if: success()
-        shell: bash
-        run: |
-          kind delete cluster
-          docker stop $(docker ps -a -q)
-          docker rm $(docker ps -a -q)
-          docker system prune -f
-
   sqlness:
-    name: Sqlness Test (${{ matrix.mode.name }})
+    name: Sqlness Test
     needs: build
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ ubuntu-20.04 ]
-        mode:
-          - name: "Basic"
-            opts: ""
-            kafka: false
-          - name: "Remote WAL"
-            opts: "-w kafka -k 127.0.0.1:9092"
-            kafka: true
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
-      - if: matrix.mode.kafka
-        name: Setup kafka server
-        working-directory: tests-integration/fixtures/kafka
-        run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
@@ -599,13 +135,45 @@ jobs:
       - name: Unzip binaries
         run: tar -xvf ./bins.tar.gz
       - name: Run sqlness
-        run: RUST_BACKTRACE=1 ./bins/sqlness-runner ${{ matrix.mode.opts }} -c ./tests/cases --bins-dir ./bins --preserve-state
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -c ./tests/cases --bins-dir ./bins
+      # FIXME: Logs cannot found be on failure (or even success). Need to figure out the cause.
       - name: Upload sqlness logs
-        if: failure()
-        uses: actions/upload-artifact@v4
+        if: always()
+        uses: actions/upload-artifact@v3
         with:
-          name: sqlness-logs-${{ matrix.mode.name }}
-          path: /tmp/sqlness*
+          name: sqlness-logs
+          path: ${{ runner.temp }}/greptime-*.log
+          retention-days: 3
+
+  sqlness-kafka-wal:
+    name: Sqlness Test with Kafka Wal
+    needs: build
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ 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: tar -xvf ./bins.tar.gz
+      - name: Setup kafka server
+        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.
+      - name: Upload sqlness logs
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: sqlness-logs
+          path: ${{ runner.temp }}/greptime-*.log
           retention-days: 3
 
   fmt:
@@ -617,16 +185,17 @@ jobs:
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - uses: dtolnay/rust-toolchain@master
         with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
           components: rustfmt
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
-        with:
+        with: 
           # Shares across multiple jobs
           shared-key: "check-rust-fmt"
-      - name: Check format
-        run: make fmt-check
+      - name: Run cargo fmt
+        run: cargo fmt --all -- --check
 
   clippy:
     name: Clippy
@@ -637,17 +206,18 @@ jobs:
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - uses: dtolnay/rust-toolchain@master
         with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
           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: make clippy
+        run: cargo clippy --workspace --all-targets -- -D warnings
 
   coverage:
     if: github.event.pull_request.draft == false
@@ -662,18 +232,15 @@ jobs:
         with:
           version: "14.0"
       - name: Install toolchain
-        uses: actions-rust-lang/setup-rust-toolchain@v1
+        uses: dtolnay/rust-toolchain@master
         with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
           components: llvm-tools-preview
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
           # Shares cross multiple jobs
           shared-key: "coverage-test"
-      - name: Docker Cache
-        uses: ScribeMD/docker-cache@0.3.7
-        with:
-          key: docker-${{ runner.os }}-coverage
       - name: Install latest nextest release
         uses: taiki-e/install-action@nextest
       - name: Install cargo-llvm-cov
@@ -683,62 +250,31 @@ jobs:
         with:
           python-version: '3.10'
       - name: Install PyArrow Package
-        run: pip install pyarrow numpy
+        run: pip install pyarrow
       - name: Setup etcd server
         working-directory: tests-integration/fixtures/etcd
         run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Setup kafka server
         working-directory: tests-integration/fixtures/kafka
         run: docker compose -f docker-compose-standalone.yml up -d --wait
-      - name: Setup minio
-        working-directory: tests-integration/fixtures/minio
-        run: docker compose -f docker-compose-standalone.yml up -d --wait
-      - name: Setup postgres server
-        working-directory: tests-integration/fixtures/postgres
-        run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Run nextest cases
         run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F pyo3_backend -F dashboard
         env:
           CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
           RUST_BACKTRACE: 1
           CARGO_INCREMENTAL: 0
-          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_MINIO_BUCKET: greptime
-          GT_MINIO_ACCESS_KEY_ID: superpower_ci_user
-          GT_MINIO_ACCESS_KEY: superpower_password
-          GT_MINIO_REGION: us-west-2
-          GT_MINIO_ENDPOINT_URL: http://127.0.0.1:9000
+          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_ETCD_ENDPOINTS: http://127.0.0.1:2379
-          GT_POSTGRES_ENDPOINTS: postgres://greptimedb:admin@127.0.0.1:5432/postgres
           GT_KAFKA_ENDPOINTS: 127.0.0.1:9092
-          GT_KAFKA_SASL_ENDPOINTS: 127.0.0.1:9093
           UNITTEST_LOG_DIR: "__unittest_logs"
       - name: Codecov upload
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v2
         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

@@ -0,0 +1,39 @@
+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

@@ -0,0 +1,36 @@
+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

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

@@ -34,14 +34,7 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
-      - 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
+      - uses: crate-ci/typos@v1.13.10
 
   check:
     name: Check
@@ -67,13 +60,7 @@ jobs:
       - run: 'echo "No action required"'
 
   sqlness:
-    name: Sqlness Test (${{ matrix.mode.name }})
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ ubuntu-20.04 ]
-        mode:
-          - name: "Basic"
-          - name: "Remote WAL"
+    name: Sqlness Test
+    runs-on: ubuntu-20.04
     steps:
       - run: 'echo "No action required"'

.github/workflows/license.yaml

@@ -0,0 +1,16 @@
+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-build.yml

@@ -12,7 +12,7 @@ on:
       linux_amd64_runner:
         type: choice
         description: The runner uses to build linux-amd64 artifacts
-        default: ec2-c6i.4xlarge-amd64
+        default: ec2-c6i.2xlarge-amd64
         options:
           - ubuntu-20.04
           - ubuntu-20.04-8-cores
@@ -27,7 +27,7 @@ on:
       linux_arm64_runner:
         type: choice
         description: The runner uses to build linux-arm64 artifacts
-        default: ec2-c6g.8xlarge-arm64
+        default: ec2-c6g.2xlarge-arm64
         options:
           - ec2-c6g.xlarge-arm64 # 4C8G
           - ec2-c6g.2xlarge-arm64 # 8C16G
@@ -66,13 +66,6 @@ env:
 
   NIGHTLY_RELEASE_PREFIX: nightly
 
-  # Use the different image name to avoid conflict with the release images.
-  # The DockerHub image will be greptime/greptimedb-nightly.
-  IMAGE_NAME: greptimedb-nightly
-
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -154,8 +147,6 @@ jobs:
           cargo-profile: ${{ env.CARGO_PROFILE }}
           version: ${{ needs.allocate-runners.outputs.version }}
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   build-linux-arm64-artifacts:
     name: Build linux-arm64 artifacts
@@ -175,8 +166,6 @@ jobs:
           cargo-profile: ${{ env.CARGO_PROFILE }}
           version: ${{ needs.allocate-runners.outputs.version }}
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   release-images-to-dockerhub:
     name: Build and push images to DockerHub
@@ -199,11 +188,10 @@ jobs:
         with:
           image-registry: docker.io
           image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          image-name: ${{ env.IMAGE_NAME }}
           image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
           version: ${{ needs.allocate-runners.outputs.version }}
-          push-latest-tag: true
+          push-latest-tag: false # Don't push the latest tag to registry.
 
       - name: Set nightly build result
         id: set-nightly-build-result
@@ -232,7 +220,7 @@ jobs:
         with:
           src-image-registry: docker.io
           src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: ${{ env.IMAGE_NAME }}
+          src-image-name: greptimedb
           dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
           dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
           dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
@@ -244,7 +232,7 @@ jobs:
           aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
           dev-mode: false
           update-version-info: false  # Don't update version info in S3.
-          push-latest-tag: true
+          push-latest-tag: false      # Don't push the latest tag to registry.
 
   stop-linux-amd64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
     name: Stop linux-amd64 runner
@@ -297,7 +285,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub
@@ -306,25 +294,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result == 'success' }}
-      - name: Notify nightly build successful result
+      - name: Notifiy nightly build successful result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
 
-      - name: Notify nightly build failed result
+      - name: Notifiy nightly build failed result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

.github/workflows/nightly-ci.yml

@@ -1,6 +1,8 @@
+# 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
@@ -9,83 +11,60 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
-permissions:
-  issues: write
+env:
+  RUST_TOOLCHAIN: nightly-2023-12-19
 
 jobs:
-  sqlness-test:
-    name: Run sqlness test
+  sqlness:
+    name: Sqlness Test
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Check install.sh
-        run: ./.github/scripts/check-install-script.sh
-
-      - 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 }}
-      - name: Upload sqlness logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: sqlness-logs-kind
-          path: /tmp/kind/
-          retention-days: 3
-
-  sqlness-windows:
-    name: Sqlness tests on Windows
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: windows-2022-8-cores
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ windows-latest-8-cores ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Run sqlness
-        run: make sqlness-test
-        env:
-          SQLNESS_OPTS: "--preserve-state"
-      - name: Upload sqlness logs
+        run: cargo sqlness
+      - name: Notify slack if failed
         if: failure()
-        uses: actions/upload-artifact@v4
+        uses: slackapi/slack-github-action@v1.23.0
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
+        with:
+          payload: |
+            {"text": "Nightly CI failed for sqlness tests"}
+      - name: Upload sqlness logs
+        if: always()
+        uses: actions/upload-artifact@v3
         with:
           name: sqlness-logs
-          path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
+          path: ${{ runner.temp }}/greptime-*.log
           retention-days: 3
 
   test-on-windows:
-    name: Run tests on Windows
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: windows-2022-8-cores
+    runs-on: windows-latest-8-cores
     timeout-minutes: 60
     steps:
       - run: git config --global core.autocrlf false
       - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
       - 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: actions-rust-lang/setup-rust-toolchain@v1
+        uses: dtolnay/rust-toolchain@master
         with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
           components: llvm-tools-preview
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
@@ -94,9 +73,9 @@ 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 numpy
+        run: pip install pyarrow
       - name: Install WSL distribution
         uses: Vampire/setup-wsl@v2
         with:
@@ -104,67 +83,18 @@ 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
-          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 }}
+          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 }}
           UNITTEST_LOG_DIR: "__unittest_logs"
-
-  cleanbuild-linux-nix:
-    runs-on: ubuntu-latest-8-cores
-    timeout-minutes: 60
-    needs: [coverage, fmt, clippy, check]
-    steps:
-      - uses: actions/checkout@v4
-      - uses: cachix/install-nix-action@v27
-        with:
-          nix_path: nixpkgs=channel:nixos-unstable
-      - run: nix-shell --pure --run "cargo build"
-
-  check-status:
-    name: Check status
-    needs: [sqlness-test, sqlness-windows, test-on-windows]
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-20.04
-    outputs:
-      check-result: ${{ steps.set-check-result.outputs.check-result }}
-    steps:
-      - name: Set check result
-        id: set-check-result
-        run: |
-          echo "check-result=success" >> $GITHUB_OUTPUT
-
-  notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
-    name: Send notification to Greptime team
-    needs: [check-status]
-    runs-on: ubuntu-20.04
-    env:
-      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
+      - name: Notify slack if failed
+        if: failure()
+        uses: slackapi/slack-github-action@v1.23.0
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.check-status.outputs.check-result == 'success' }}
-      - name: Notify dev build successful result
-        uses: slackapi/slack-github-action@v1.23.0
-        if: ${{ needs.check-status.outputs.check-result == 'success' }}
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
         with:
           payload: |
-            {"text": "Nightly CI has completed successfully."}
-
-      - name: Notify dev build failed result
-        uses: slackapi/slack-github-action@v1.23.0
-        if: ${{ needs.check-status.outputs.check-result != 'success' }}
-        with:
-          payload: |
-            {"text": "Nightly CI failed has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "Nightly CI failed for cargo test"}

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

@@ -0,0 +1,27 @@
+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

@@ -0,0 +1,29 @@
+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-dev-builder-images.yaml

@@ -1,14 +1,12 @@
 name: Release dev-builder images
 
 on:
-  push:
-    branches:
-      - main
-    paths:
-      - rust-toolchain.toml
-      - 'docker/dev-builder/**'
   workflow_dispatch: # Allows you to run this workflow manually.
     inputs:
+      version:
+        description: Version of the dev-builder
+        required: false
+        default: latest
       release_dev_builder_ubuntu_image:
         type: boolean
         description: Release dev-builder-ubuntu image
@@ -30,103 +28,22 @@ jobs:
     name: Release dev builder images
     if: ${{ inputs.release_dev_builder_ubuntu_image || inputs.release_dev_builder_centos_image || inputs.release_dev_builder_android_image }} # Only manually trigger this job.
     runs-on: ubuntu-20.04-16-cores
-    outputs:
-      version: ${{ steps.set-version.outputs.version }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - name: Configure build image version
-        id: set-version
-        shell: bash
-        run: |
-          commitShortSHA=`echo ${{ github.sha }} | cut -c1-8`
-          buildTime=`date +%Y%m%d%H%M%S`
-          BUILD_VERSION="$commitShortSHA-$buildTime"
-          RUST_TOOLCHAIN_VERSION=$(cat rust-toolchain.toml | grep -Eo '[0-9]{4}-[0-9]{2}-[0-9]{2}')
-          IMAGE_VERSION="${RUST_TOOLCHAIN_VERSION}-${BUILD_VERSION}"
-          echo "VERSION=${IMAGE_VERSION}" >> $GITHUB_ENV
-          echo "version=$IMAGE_VERSION" >> $GITHUB_OUTPUT
-
       - name: Build and push dev builder images
         uses: ./.github/actions/build-dev-builder-images
         with:
-          version: ${{ env.VERSION }}
+          version: ${{ inputs.version }}
           dockerhub-image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           dockerhub-image-registry-token: ${{ secrets.DOCKERHUB_TOKEN }}
           build-dev-builder-ubuntu: ${{ inputs.release_dev_builder_ubuntu_image }}
           build-dev-builder-centos: ${{ inputs.release_dev_builder_centos_image }}
           build-dev-builder-android: ${{ inputs.release_dev_builder_android_image }}
 
-  release-dev-builder-images-ecr:
-    name: Release dev builder images to AWS ECR
-    runs-on: ubuntu-20.04
-    needs: [
-      release-dev-builder-images
-    ]
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ECR_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_ECR_SECRET_ACCESS_KEY }}
-          aws-region: ${{ vars.ECR_REGION }}
-
-      - name: Login to Amazon ECR
-        id: login-ecr-public
-        uses: aws-actions/amazon-ecr-login@v2
-        env:
-          AWS_REGION: ${{ vars.ECR_REGION }}
-        with:
-          registry-type: public
-
-      - name: Push dev-builder-ubuntu image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_ubuntu_image }}
-        run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ needs.release-dev-builder-images.outputs.version }}
-
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:latest \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-ubuntu:latest
-      - name: Push dev-builder-centos image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_centos_image }}
-        run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-centos:${{ needs.release-dev-builder-images.outputs.version }}
-
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:latest \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-centos:latest
-      - name: Push dev-builder-android image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_android_image }}
-        run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-android:${{ needs.release-dev-builder-images.outputs.version }}
-
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:latest \
-            docker://${{ vars.ECR_IMAGE_REGISTRY }}/${{ vars.ECR_IMAGE_NAMESPACE }}/dev-builder-android:latest
   release-dev-builder-images-cn: # Note: Be careful issue: https://github.com/containers/skopeo/issues/1874 and we decide to use the latest stable skopeo container.
     name: Release dev builder images to CN region
     runs-on: ubuntu-20.04
@@ -134,39 +51,35 @@ jobs:
       release-dev-builder-images
     ]
     steps:
-      - name: Login to AliCloud Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ vars.ACR_IMAGE_REGISTRY }}
-          username: ${{ secrets.ALICLOUD_USERNAME }}
-          password: ${{ secrets.ALICLOUD_PASSWORD }}
-
       - name: Push dev-builder-ubuntu image
         shell: bash
         if: ${{ inputs.release_dev_builder_ubuntu_image }}
+        env:
+          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
+          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
         run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ needs.release-dev-builder-images.outputs.version }}
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }} \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }}
 
       - name: Push dev-builder-centos image
         shell: bash
         if: ${{ inputs.release_dev_builder_centos_image }}
+        env:
+          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
+          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
         run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ needs.release-dev-builder-images.outputs.version }}
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }} \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }}
 
       - name: Push dev-builder-android image
         shell: bash
         if: ${{ inputs.release_dev_builder_android_image }}
+        env:
+          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
+          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
         run: |
-          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
-            quay.io/skopeo/stable:latest \
-            copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ needs.release-dev-builder-images.outputs.version }} \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ needs.release-dev-builder-images.outputs.version }}
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }} \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }}

.github/workflows/release.yml

@@ -31,9 +31,8 @@ on:
       linux_arm64_runner:
         type: choice
         description: The runner uses to build linux-arm64 artifacts
-        default: ec2-c6g.8xlarge-arm64
+        default: ec2-c6g.4xlarge-arm64
         options:
-          - ubuntu-2204-32-cores-arm
           - ec2-c6g.xlarge-arm64 # 4C8G
           - ec2-c6g.2xlarge-arm64 # 8C16G
           - ec2-c6g.4xlarge-arm64 # 16C32G
@@ -83,6 +82,7 @@ on:
 # Use env variables to control all the release process.
 env:
   # The arguments of building greptime.
+  RUST_TOOLCHAIN: nightly-2023-12-19
   CARGO_PROFILE: nightly
 
   # Controls whether to run tests, include unit-test, integration-test and sqlness.
@@ -91,12 +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: v0.11.0
-
-# Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
-permissions:
-  issues: write # Allows the action to create issues for cyborg.
-  contents: write # Allows the action to create a release.
+  NEXT_RELEASE_VERSION: v0.7.0
 
 jobs:
   allocate-runners:
@@ -107,7 +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-2022-8-cores
+      windows-runner: windows-latest-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 }}
@@ -123,11 +118,6 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Check Rust toolchain version
-        shell: bash
-        run: |
-          ./scripts/check-builder-rust-version.sh
-
       # The create-version will create a global variable named 'version' in the global workflows.
       # - If it's a tag push release, the version is the tag name(${{ github.ref_name }});
       # - If it's a scheduled release, the version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-$buildTime', like v0.2.0-nigthly-20230313;
@@ -188,8 +178,6 @@ jobs:
           cargo-profile: ${{ env.CARGO_PROFILE }}
           version: ${{ needs.allocate-runners.outputs.version }}
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   build-linux-arm64-artifacts:
     name: Build linux-arm64 artifacts
@@ -209,8 +197,6 @@ jobs:
           cargo-profile: ${{ env.CARGO_PROFILE }}
           version: ${{ needs.allocate-runners.outputs.version }}
           disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          image-registry: ${{ vars.ECR_IMAGE_REGISTRY }}
-          image-namespace: ${{ vars.ECR_IMAGE_NAMESPACE }}
 
   build-macos-artifacts:
     name: Build macOS artifacts
@@ -235,8 +221,6 @@ 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,
     ]
@@ -249,17 +233,17 @@ jobs:
       - uses: ./.github/actions/build-macos-artifacts
         with:
           arch: ${{ matrix.arch }}
+          rust-toolchain: ${{ env.RUST_TOOLCHAIN }}
           cargo-profile: ${{ env.CARGO_PROFILE }}
           features: ${{ matrix.features }}
           version: ${{ needs.allocate-runners.outputs.version }}
-          # We decide to disable the integration tests on macOS because it's unnecessary and time-consuming.
-          disable-run-tests: true
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
           artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
 
       - name: Set build macos result
         id: set-build-macos-result
         run: |
-          echo "build-macos-result=success" >> $GITHUB_OUTPUT
+          echo "build-macos-result=success" >> $GITHUB_OUTPUT    
 
   build-windows-artifacts:
     name: Build Windows artifacts
@@ -276,8 +260,6 @@ 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,
     ]
@@ -292,6 +274,7 @@ jobs:
       - uses: ./.github/actions/build-windows-artifacts
         with:
           arch: ${{ matrix.arch }}
+          rust-toolchain: ${{ env.RUST_TOOLCHAIN }}
           cargo-profile: ${{ env.CARGO_PROFILE }}
           features: ${{ matrix.features }}
           version: ${{ needs.allocate-runners.outputs.version }}
@@ -301,7 +284,7 @@ jobs:
       - name: Set build windows result
         id: set-build-windows-result
         run: |
-          echo "build-windows-result=success" >> $Env:GITHUB_OUTPUT
+          echo "build-windows-result=success" >> $GITHUB_OUTPUT    
 
   release-images-to-dockerhub:
     name: Build and push images to DockerHub
@@ -312,8 +295,6 @@ 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:
@@ -329,9 +310,9 @@ jobs:
           version: ${{ needs.allocate-runners.outputs.version }}
 
       - name: Set build image result
-        id: set-build-image-result
+        id: set-image-build-result
         run: |
-          echo "build-image-result=success" >> $GITHUB_OUTPUT
+          echo "build-image-result=success" >> $GITHUB_OUTPUT    
 
   release-cn-artifacts:
     name: Release artifacts to CN region
@@ -449,7 +430,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && (github.event_name == 'push' || github.event_name == 'schedule') && always() }}
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub,
@@ -460,25 +441,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.build-image-result == 'success' && needs.build-windows-artifacts.outputs.build-windows-result == 'success' && needs.build-macos-artifacts.outputs.build-macos-result == 'success' }}
-      - name: Notify release successful result
+      - name: Notifiy release successful result
         uses: slackapi/slack-github-action@v1.25.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-image-result == 'success' && needs.build-windows-artifacts.outputs.build-windows-result == 'success' && needs.build-macos-artifacts.outputs.build-macos-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's release version has completed successfully."}
 
-      - name: Notify release failed result
+      - name: Notifiy release failed result
         uses: slackapi/slack-github-action@v1.25.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-image-result != 'success' || needs.build-windows-artifacts.outputs.build-windows-result != 'success' || needs.build-macos-artifacts.outputs.build-macos-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's release version has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's release version has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/release.yml'."}

.github/workflows/schedule.yml

@@ -1,24 +0,0 @@
-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

@@ -1,21 +0,0 @@
-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

@@ -46,11 +46,3 @@ benchmarks/data
 *.code-workspace
 
 venv/
-
-# Fuzz tests
-tests-fuzz/artifacts/
-tests-fuzz/corpus/
-
-# Nix
-.direnv
-.envrc

.pre-commit-config.yaml

@@ -16,7 +16,6 @@ repos:
     hooks:
     -    id: fmt
     -    id: clippy
-         args: ["--workspace", "--all-targets", "--all-features", "--", "-D", "warnings"]
-         stages: [pre-push]
+         args: ["--workspace", "--all-targets", "--", "-D", "warnings", "-D", "clippy::print_stdout", "-D", "clippy::print_stderr"]
+         stages: [push]
     -    id: cargo-check
-         args: ["--workspace", "--all-targets", "--all-features"]

AUTHOR.md

@@ -1,44 +0,0 @@
-# GreptimeDB Authors
-
-## Individual Committers (in alphabetical order)
-
-* [CookiePieWw](https://github.com/CookiePieWw)
-* [KKould](https://github.com/KKould)
-* [NiwakaDev](https://github.com/NiwakaDev)
-* [etolbakov](https://github.com/etolbakov)
-* [irenjj](https://github.com/irenjj)
-* [tisonkun](https://github.com/tisonkun)
-* [Lanqing Yang](https://github.com/lyang24)
-
-## Team Members (in alphabetical order)
-
-* [Breeze-P](https://github.com/Breeze-P)
-* [GrepTime](https://github.com/GrepTime)
-* [MichaelScofield](https://github.com/MichaelScofield)
-* [Wenjie0329](https://github.com/Wenjie0329)
-* [WenyXu](https://github.com/WenyXu)
-* [ZonaHex](https://github.com/ZonaHex)
-* [apdong2022](https://github.com/apdong2022)
-* [beryl678](https://github.com/beryl678)
-* [daviderli614](https://github.com/daviderli614)
-* [discord9](https://github.com/discord9)
-* [evenyag](https://github.com/evenyag)
-* [fengjiachun](https://github.com/fengjiachun)
-* [fengys1996](https://github.com/fengys1996)
-* [holalengyu](https://github.com/holalengyu)
-* [killme2008](https://github.com/killme2008)
-* [nicecui](https://github.com/nicecui)
-* [paomian](https://github.com/paomian)
-* [shuiyisong](https://github.com/shuiyisong)
-* [sunchanglong](https://github.com/sunchanglong)
-* [sunng87](https://github.com/sunng87)
-* [v0y4g3r](https://github.com/v0y4g3r)
-* [waynexia](https://github.com/waynexia)
-* [xtang](https://github.com/xtang)
-* [zhaoyingnan01](https://github.com/zhaoyingnan01)
-* [zhongzc](https://github.com/zhongzc)
-* [zyy17](https://github.com/zyy17)
-
-## All Contributors
-
-[![All Contributors](https://contrib.rocks/image?repo=GreptimeTeam/greptimedb)](https://github.com/GreptimeTeam/greptimedb/graphs/contributors)

CODE_OF_CONDUCT.md

@@ -0,0 +1,132 @@
+# 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

@@ -2,11 +2,7 @@
 
 Thanks a lot for considering contributing to GreptimeDB. We believe people like you would make GreptimeDB a great product. We intend to build a community where individuals can have open talks, show respect for one another, and speak with true ❤️. Meanwhile, we are to keep transparency and make your effort count here.
 
-You can find our contributors at https://github.com/GreptimeTeam/greptimedb/graphs/contributors. When you dedicate to GreptimeDB for a few months and keep bringing high-quality contributions (code, docs, advocate, etc.), you will be a candidate of a committer.
-
-A committer will be granted both read & write access to GreptimeDB repos. Check the [AUTHOR.md](AUTHOR.md) file for all current individual committers.
-
-Please read the guidelines, and they can help you get started. Communicate respectfully with the developers maintaining and developing the project. In return, they should reciprocate that respect by addressing your issue, reviewing changes, as well as helping finalize and merge your pull requests.
+Please read the guidelines, and they can help you get started. Communicate with respect to developers maintaining and developing the project. In return, they should reciprocate that respect by addressing your issue, reviewing changes, as well as helping finalize and merge your pull requests.
 
 Follow our [README](https://github.com/GreptimeTeam/greptimedb#readme) to get the whole picture of the project. To learn about the design of GreptimeDB, please refer to the [design docs](https://github.com/GrepTimeTeam/docs).
 
@@ -14,7 +10,7 @@ Follow our [README](https://github.com/GreptimeTeam/greptimedb#readme) to get th
 
 It can feel intimidating to contribute to a complex project, but it can also be exciting and fun. These general notes will help everyone participate in this communal activity.
 
-- Follow the [Code of Conduct](https://github.com/GreptimeTeam/.github/blob/main/.github/CODE_OF_CONDUCT.md)
+- Follow the [Code of Conduct](https://github.com/GreptimeTeam/greptimedb/blob/main/CODE_OF_CONDUCT.md)
 - Small changes make huge differences. We will happily accept a PR making a single character change if it helps move forward. Don't wait to have everything working.
 - Check the closed issues before opening your issue.
 - Try to follow the existing style of the code.
@@ -30,7 +26,7 @@ Pull requests are great, but we accept all kinds of other help if you like. Such
 
 ## Code of Conduct
 
-Also, there are things that we are not looking for because they don't match the goals of the product or benefit the community. Please read [Code of Conduct](https://github.com/GreptimeTeam/.github/blob/main/.github/CODE_OF_CONDUCT.md); we hope everyone can keep good manners and become an honored member.
+Also, there are things that we are not looking for because they don't match the goals of the product or benefit the community. Please read [Code of Conduct](https://github.com/GreptimeTeam/greptimedb/blob/main/CODE_OF_CONDUCT.md); we hope everyone can keep good manners and become an honored member.
 
 ## License
 
@@ -54,8 +50,8 @@ 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/) and [style guide](docs/style-guide.md).
-- Make sure all unit tests are passed using [nextest](https://nexte.st/index.html) `cargo nextest run`.
+- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/).
+- 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`).
 
 #### `pre-commit` Hooks

Cargo.toml

@@ -1,29 +1,23 @@
 [workspace]
 members = [
+    "benchmarks",
     "src/api",
     "src/auth",
-    "src/cache",
     "src/catalog",
-    "src/cli",
     "src/client",
     "src/cmd",
     "src/common/base",
     "src/common/catalog",
     "src/common/config",
     "src/common/datasource",
-    "src/common/decimal",
     "src/common/error",
-    "src/common/frontend",
     "src/common/function",
+    "src/common/macro",
     "src/common/greptimedb-telemetry",
     "src/common/grpc",
     "src/common/grpc-expr",
-    "src/common/macro",
     "src/common/mem-prof",
     "src/common/meta",
-    "src/common/options",
-    "src/common/plugins",
-    "src/common/pprof",
     "src/common/procedure",
     "src/common/procedure-test",
     "src/common/query",
@@ -33,6 +27,7 @@ members = [
     "src/common/telemetry",
     "src/common/test-util",
     "src/common/time",
+    "src/common/decimal",
     "src/common/version",
     "src/common/wal",
     "src/datanode",
@@ -40,8 +35,6 @@ members = [
     "src/file-engine",
     "src/flow",
     "src/frontend",
-    "src/index",
-    "src/log-query",
     "src/log-store",
     "src/meta-client",
     "src/meta-srv",
@@ -50,7 +43,6 @@ members = [
     "src/object-store",
     "src/operator",
     "src/partition",
-    "src/pipeline",
     "src/plugins",
     "src/promql",
     "src/puffin",
@@ -61,6 +53,7 @@ members = [
     "src/sql",
     "src/store-api",
     "src/table",
+    "src/index",
     "tests-fuzz",
     "tests-integration",
     "tests/runner",
@@ -68,34 +61,18 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.11.1"
+version = "0.6.0"
 edition = "2021"
 license = "Apache-2.0"
 
-[workspace.lints]
-clippy.print_stdout = "warn"
-clippy.print_stderr = "warn"
-clippy.dbg_macro = "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"
-rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
-
 [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 = "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", "zstd"] }
-arrow-schema = { version = "51.0", features = ["serde"] }
+arrow = { version = "47.0" }
+arrow-array = "47.0"
+arrow-flight = "47.0"
+arrow-ipc = "47.0"
+arrow-schema = { version = "47.0", features = ["serde"] }
 async-stream = "0.3"
 async-trait = "0.1"
 axum = { version = "0.6", features = ["headers"] }
@@ -103,115 +80,83 @@ base64 = "0.21"
 bigdecimal = "0.4.2"
 bitflags = "2.4.1"
 bytemuck = "1.12"
-bytes = { version = "1.7", features = ["serde"] }
+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/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+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" }
 derive_builder = "0.12"
-dotenv = "0.15"
-etcd-client = "0.13"
+etcd-client = "0.12"
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "a875e976441188028353f7274a46a7e6e065c5d4" }
-hex = "0.4"
-humantime = "2.1"
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "96f1f0404f421ee560a4310c73c5071e49168168" }
 humantime-serde = "1.1"
 itertools = "0.10"
-jsonb = { git = "https://github.com/databendlabs/jsonb.git", rev = "8c8d2fc294a39f3ff08909d60f718639cfba3875", default-features = false }
 lazy_static = "1.4"
-meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "a10facb353b41460eeb98578868ebf19c2084fac" }
+meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "abbd357c1e193cd270ea65ee7652334a150b628f" }
 mockall = "0.11.4"
 moka = "0.12"
-notify = "6.1"
 num_cpus = "1.16"
 once_cell = "1.18"
-opentelemetry-proto = { version = "0.5", features = [
+opentelemetry-proto = { git = "https://github.com/waynexia/opentelemetry-rust.git", rev = "33841b38dda79b15f2024952be5f32533325ca02", features = [
     "gen-tonic",
     "metrics",
     "trace",
-    "with-serde",
-    "logs",
 ] }
-parking_lot = "0.12"
-parquet = { version = "51.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
+parquet = "47.0"
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-promql-parser = { version = "0.4.3", features = ["ser"] }
 prost = "0.12"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
-ratelimit = "0.9"
 regex = "1.8"
-regex-automata = "0.4"
-reqwest = { version = "0.12", default-features = false, features = [
+regex-automata = { version = "0.2", features = ["transducer"] }
+reqwest = { version = "0.11", default-features = false, features = [
     "json",
     "rustls-tls-native-roots",
     "stream",
-    "multipart",
 ] }
-rskafka = { git = "https://github.com/influxdata/rskafka.git", rev = "75535b5ad9bae4a5dbb582c82e44dfd81ec10105", features = [
-    "transport-tls",
-] }
-rstest = "0.21"
-rstest_reuse = "0.7"
+rskafka = "0.5"
 rust_decimal = "1.33"
-rustc-hash = "2.0"
 serde = { version = "1.0", features = ["derive"] }
-serde_json = { version = "1.0", features = ["float_roundtrip"] }
+serde_json = "1.0"
 serde_with = "3"
-shadow-rs = "0.35"
-similar-asserts = "1.6.0"
 smallvec = { version = "1", features = ["serde"] }
-snafu = "0.8"
+snafu = "0.7"
 sysinfo = "0.30"
-# on branch v0.44.x
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "54a267ac89c09b11c0c88934690530807185d3e7", features = [
+# on branch v0.38.x
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "6a93567ae38d42be5c8d08b13c8ff4dde26502ef", features = [
     "visitor",
-    "serde",
 ] }
 strum = { version = "0.25", features = ["derive"] }
 tempfile = "3"
-tokio = { version = "1.40", features = ["full"] }
-tokio-postgres = "0.7"
-tokio-stream = "0.1"
+tokio = { version = "1.28", features = ["full"] }
+tokio-stream = { version = "0.1" }
 tokio-util = { version = "0.7", features = ["io-util", "compat"] }
 toml = "0.8.8"
-tonic = { version = "0.11", features = ["tls", "gzip", "zstd"] }
-tower = "0.4"
-tracing-appender = "0.2"
-tracing-subscriber = { version = "0.3", features = ["env-filter", "json", "fmt"] }
-typetag = "0.2"
-uuid = { version = "1.7", features = ["serde", "v4", "fast-rng"] }
-zstd = "0.13"
+tonic = { version = "0.10", features = ["tls"] }
+uuid = { version = "1", features = ["serde", "v4", "fast-rng"] }
 
 ## workspaces members
 api = { path = "src/api" }
 auth = { path = "src/auth" }
-cache = { path = "src/cache" }
 catalog = { path = "src/catalog" }
-cli = { path = "src/cli" }
 client = { path = "src/client" }
-cmd = { path = "src/cmd", default-features = false }
+cmd = { path = "src/cmd" }
 common-base = { path = "src/common/base" }
 common-catalog = { path = "src/common/catalog" }
 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" }
@@ -219,9 +164,6 @@ 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-options = { path = "src/common/options" }
-common-plugins = { path = "src/common/plugins" }
-common-pprof = { path = "src/common/pprof" }
 common-procedure = { path = "src/common/procedure" }
 common-procedure-test = { path = "src/common/procedure-test" }
 common-query = { path = "src/common/query" }
@@ -235,8 +177,7 @@ 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", default-features = false }
+frontend = { path = "src/frontend" }
 index = { path = "src/index" }
 log-store = { path = "src/log-store" }
 meta-client = { path = "src/meta-client" }
@@ -246,7 +187,6 @@ mito2 = { path = "src/mito2" }
 object-store = { path = "src/object-store" }
 operator = { path = "src/operator" }
 partition = { path = "src/partition" }
-pipeline = { path = "src/pipeline" }
 plugins = { path = "src/plugins" }
 promql = { path = "src/promql" }
 puffin = { path = "src/puffin" }
@@ -259,39 +199,16 @@ store-api = { path = "src/store-api" }
 substrait = { path = "src/common/substrait" }
 table = { path = "src/table" }
 
-[patch.crates-io]
-# change all rustls dependencies to use our fork to default to `ring` to make it "just work"
-hyper-rustls = { git = "https://github.com/GreptimeTeam/hyper-rustls" }
-rustls = { git = "https://github.com/GreptimeTeam/rustls" }
-tokio-rustls = { git = "https://github.com/GreptimeTeam/tokio-rustls" }
-# This is commented, since we are not using aws-lc-sys, if we need to use it, we need to uncomment this line or use a release after this commit, or it wouldn't compile with gcc < 8.1
-# see https://github.com/aws/aws-lc-rs/pull/526
-# aws-lc-sys = { git ="https://github.com/aws/aws-lc-rs", rev = "556558441e3494af4b156ae95ebc07ebc2fd38aa" }
-# Apply a fix for pprof for unaligned pointer access
-pprof = { git = "https://github.com/GreptimeTeam/pprof-rs", rev = "1bd1e21" }
-
 [workspace.dependencies.meter-macros]
 git = "https://github.com/GreptimeTeam/greptime-meter.git"
-rev = "a10facb353b41460eeb98578868ebf19c2084fac"
+rev = "abbd357c1e193cd270ea65ee7652334a150b628f"
 
 [profile.release]
 debug = 1
 
 [profile.nightly]
 inherits = "release"
-strip = "debuginfo"
+strip = true
 lto = "thin"
 debug = false
 incremental = false
-
-[profile.ci]
-inherits = "dev"
-strip = true
-
-[profile.dev.package.sqlness-runner]
-debug = false
-strip = true
-
-[profile.dev.package.tests-fuzz]
-debug = false
-strip = true

Makefile

@@ -3,12 +3,10 @@ CARGO_PROFILE ?=
 FEATURES ?=
 TARGET_DIR ?=
 TARGET ?=
-BUILD_BIN ?= greptime
 CARGO_BUILD_OPTS := --locked
 IMAGE_REGISTRY ?= docker.io
 IMAGE_NAMESPACE ?= greptime
 IMAGE_TAG ?= latest
-DEV_BUILDER_IMAGE_TAG ?= 2024-10-19-a5c00e85-20241024184445
 BUILDX_MULTI_PLATFORM_BUILD ?= false
 BUILDX_BUILDER_NAME ?= gtbuilder
 BASE_IMAGE ?= ubuntu
@@ -16,7 +14,6 @@ RUST_TOOLCHAIN ?= $(shell cat rust-toolchain.toml | grep channel | cut -d'"' -f2
 CARGO_REGISTRY_CACHE ?= ${HOME}/.cargo/registry
 ARCH := $(shell uname -m | sed 's/x86_64/amd64/' | sed 's/aarch64/arm64/')
 OUTPUT_DIR := $(shell if [ "$(RELEASE)" = "true" ]; then echo "release"; elif [ ! -z "$(CARGO_PROFILE)" ]; then echo "$(CARGO_PROFILE)" ; else echo "debug"; fi)
-SQLNESS_OPTS ?=
 
 # The arguments for running integration tests.
 ETCD_VERSION ?= v3.5.9
@@ -48,18 +45,12 @@ 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 ($(BUILDX_MULTI_PLATFORM_BUILD), all)
+ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), true)
 	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
@@ -78,7 +69,7 @@ build: ## Build debug version greptime.
 build-by-dev-builder: ## Build greptime by dev-builder.
 	docker run --network=host \
 	-v ${PWD}:/greptimedb -v ${CARGO_REGISTRY_CACHE}:/root/.cargo/registry \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:latest \
 	make build \
 	CARGO_EXTENSION="${CARGO_EXTENSION}" \
 	CARGO_PROFILE=${CARGO_PROFILE} \
@@ -92,7 +83,7 @@ build-by-dev-builder: ## Build greptime by dev-builder.
 build-android-bin: ## Build greptime binary for android.
 	docker run --network=host \
 	-v ${PWD}:/greptimedb -v ${CARGO_REGISTRY_CACHE}:/root/.cargo/registry \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:${DEV_BUILDER_IMAGE_TAG} \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:latest \
 	make build \
 	CARGO_EXTENSION="ndk --platform 23 -t aarch64-linux-android" \
 	CARGO_PROFILE=release \
@@ -106,8 +97,8 @@ build-android-bin: ## Build greptime binary for android.
 strip-android-bin: build-android-bin ## Strip greptime binary for android.
 	docker run --network=host \
 	-v ${PWD}:/greptimedb \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:${DEV_BUILDER_IMAGE_TAG} \
-	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip --strip-debug /greptimedb/target/aarch64-linux-android/release/greptime'
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:latest \
+	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip /greptimedb/target/aarch64-linux-android/release/greptime'
 
 .PHONY: clean
 clean: ## Clean the project.
@@ -146,7 +137,7 @@ dev-builder: multi-platform-buildx ## Build dev-builder image.
 	docker buildx build --builder ${BUILDX_BUILDER_NAME} \
 	--build-arg="RUST_TOOLCHAIN=${RUST_TOOLCHAIN}" \
 	-f docker/dev-builder/${BASE_IMAGE}/Dockerfile \
-	-t ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} ${BUILDX_MULTI_PLATFORM_BUILD_OPTS} .
+	-t ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${IMAGE_TAG} ${BUILDX_MULTI_PLATFORM_BUILD_OPTS} .
 
 .PHONY: multi-platform-buildx
 multi-platform-buildx: ## Create buildx multi-platform builder.
@@ -163,18 +154,7 @@ nextest: ## Install nextest tools.
 
 .PHONY: sqlness-test
 sqlness-test: ## Run sqlness test.
-	cargo sqlness ${SQLNESS_OPTS}
-
-# Run fuzz test ${FUZZ_TARGET}.
-RUNS ?= 1
-FUZZ_TARGET ?= fuzz_alter_table
-.PHONY: fuzz
-fuzz:
-	cargo fuzz run ${FUZZ_TARGET} --fuzz-dir tests-fuzz -D -s none -- -runs=${RUNS}
-
-.PHONY: fuzz-ls
-fuzz-ls:
-	cargo fuzz list --fuzz-dir tests-fuzz
+	cargo sqlness
 
 .PHONY: check
 check: ## Cargo check all the targets.
@@ -184,14 +164,9 @@ 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
-	python3 scripts/check-snafu.py
 
 .PHONY: start-etcd
 start-etcd: ## Start single node etcd for testing purpose.
@@ -205,27 +180,9 @@ stop-etcd: ## Stop single node etcd for testing purpose.
 run-it-in-container: start-etcd ## Run integration tests in dev-builder.
 	docker run --network=host \
 	-v ${PWD}:/greptimedb -v ${CARGO_REGISTRY_CACHE}:/root/.cargo/registry -v /tmp:/tmp \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:latest \
 	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
 
-.PHONY: start-cluster
-start-cluster: ## Start the greptimedb cluster with etcd by using docker compose.
-	 docker compose -f ./docker/docker-compose/cluster-with-etcd.yaml up
-
-.PHONY: stop-cluster
-stop-cluster: ## Stop the greptimedb cluster that created by docker compose.
-	docker compose -f ./docker/docker-compose/cluster-with-etcd.yaml stop
-
-##@ Docs
-config-docs: ## Generate configuration documentation from toml files.
-	docker run --rm \
-    -v ${PWD}:/greptimedb \
-    -w /greptimedb/config \
-    toml2docs/toml2docs:v0.1.3 \
-    -p '##' \
-    -t ./config-docs-template.md \
-    -o ./config.md
-
 ##@ General
 
 # The help target prints out all targets with their descriptions organized

README.md

@@ -6,182 +6,145 @@
   </picture>
 </p>
 
-<h2 align="center">Unified & Cost-Effective Time Series Database for Metrics, Logs, and Events</h2>
 
-<div align="center">
 <h3 align="center">
-  <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>
+    The next-generation hybrid time-series/analytics processing database in the cloud
+</h3>
 
-<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://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>
 
-<br/>
+<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>
 
-<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>
+## What is GreptimeDB
 
-- [Introduction](#introduction)
-- [**Features: Why GreptimeDB**](#why-greptimedb)
-- [Architecture](https://docs.greptime.com/contributor-guide/overview/#architecture)
-- [Try it for free](#try-greptimedb)
-- [Getting Started](#getting-started)
-- [Project Status](#project-status)
-- [Join the community](#community)
-  - [Contributing](#contributing)
-- [Tools & Extensions](#tools--extensions)
-- [License](#license)
-- [Acknowledgement](#acknowledgement)
+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 unified & cost-effective time-series database for **Metrics**, **Logs**, and **Events** (also **Traces** in plan). You can gain real-time insights from Edge to Cloud at Any Scale.
+- 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 was born to give you:
-
-* **Unified Processing of Metrics, Logs, and Events**
-
-GreptimeDB unifies time series data processing by treating all data - whether metrics, logs, or events - as timestamped events with context. Users can analyze this data using either [SQL](https://docs.greptime.com/user-guide/query-data/sql) or [PromQL](https://docs.greptime.com/user-guide/query-data/promql) and leverage stream processing ([Flow](https://docs.greptime.com/user-guide/continuous-aggregation/overview)) to enable continuous aggregation. [Read more](https://docs.greptime.com/user-guide/concepts/data-model).
-
-* **Cloud-native Distributed Database**
-
-Built for [Kubernetes](https://docs.greptime.com/user-guide/deployments/deploy-on-kubernetes/greptimedb-operator-management). GreptimeDB achieves seamless scalability with its [cloud-native architecture](https://docs.greptime.com/user-guide/concepts/architecture) of separated compute and storage, built on object storage (AWS S3, Azure Blob Storage, etc.) while enabling cross-cloud deployment through a unified data access layer.
-
-* **Performance and Cost-effective**
-
-Written in pure Rust for superior performance and reliability. GreptimeDB features a distributed query engine with intelligent indexing to handle high cardinality data efficiently. Its optimized columnar storage achieves 50x cost efficiency on cloud object storage through advanced compression. [Benchmark reports](https://www.greptime.com/blogs/2024-09-09-report-summary).
-
-* **Cloud-Edge Collaboration**
-
-GreptimeDB seamlessly operates across cloud and edge (ARM/Android/Linux), providing consistent APIs and control plane for unified data management and efficient synchronization. [Learn how to run on Android](https://docs.greptime.com/user-guide/deployments/run-on-android/).
-
-* **Multi-protocol Ingestion, SQL & PromQL Ready**
-
-Widely adopted database protocols and APIs, including MySQL, PostgreSQL, InfluxDB, OpenTelemetry, Loki and Prometheus, etc.  Effortless Adoption & Seamless Migration. [Supported Protocols Overview](https://docs.greptime.com/user-guide/protocols/overview).
-
-For more detailed info please read  [Why GreptimeDB](https://docs.greptime.com/user-guide/concepts/why-greptimedb).
-
-## Try GreptimeDB
-
-### 1. [Live Demo](https://greptime.com/playground)
+### [GreptimePlay](https://greptime.com/playground)
 
 Try out the features of GreptimeDB right from your browser.
 
-### 2. [GreptimeCloud](https://console.greptime.cloud/)
+### Build
 
-Start instantly with a free cluster.
+#### Build from Source
 
-### 3. Docker Image
+To compile GreptimeDB from source, you'll need:
 
-To install GreptimeDB locally, the recommended way is via Docker:
+- 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.
 
-```shell
-docker pull greptime/greptimedb
+#### Build with Docker
+
+A docker image with necessary dependencies is provided:
+
+```
+docker build --network host -f docker/Dockerfile -t greptimedb .
 ```
 
-Start a GreptimeDB container with:
+### Run
+
+Start GreptimeDB from source code, in standalone mode:
 
-```shell
-docker run -p 127.0.0.1:4000-4003:4000-4003 \
-  -v "$(pwd)/greptimedb:/tmp/greptimedb" \
-  --name greptime --rm \
-  greptime/greptimedb:latest standalone start \
-  --http-addr 0.0.0.0:4000 \
-  --rpc-addr 0.0.0.0:4001 \
-  --mysql-addr 0.0.0.0:4002 \
-  --postgres-addr 0.0.0.0:4003
 ```
-
-Access the dashboard via `http://localhost:4000/dashboard`.
-
-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)
-* [User Guide](https://docs.greptime.com/user-guide/overview)
-* [Demos](https://github.com/GreptimeTeam/demo-scene)
-* [FAQ](https://docs.greptime.com/faq-and-others/faq)
-
-## 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
 ```
 
-## Tools & Extensions
+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)
 
 ### 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 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)
+- [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)
 
 ### Grafana Dashboard
 
-Our official Grafana dashboard for monitoring GreptimeDB is available at [grafana](grafana/README.md) directory.
+Our official Grafana dashboard is available at [grafana](./grafana/README.md) directory.
 
 ## Project Status
 
-GreptimeDB is currently in Beta. We are targeting GA (General Availability) with v1.0 release by Early 2025. 
+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.
 
-While in Beta, GreptimeDB is already:
-
-* Being used in production by early adopters
-* Actively maintained with regular releases, [about version number](https://docs.greptime.com/nightly/reference/about-greptimedb-version)
-* Suitable for testing and evaluation
-
-For production use, we recommend using the latest stable release.
+For future plans, check out [GreptimeDB roadmap](https://github.com/GreptimeTeam/greptimedb/issues/669).
 
 ## Community
 
@@ -191,22 +154,15 @@ 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 forum](https://github.com/GreptimeTeam/greptimedb/discussions)
-- Greptime official [website](https://greptime.com)
+- GreptimeDB GitHub [Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
+- Greptime official [Website](https://greptime.com)
 
 In addition, you may:
 
-- View our official [Blog](https://greptime.com/blogs/)
+- View our official [Blog](https://greptime.com/blogs/index)
 - Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
 - Follow us on [Twitter](https://twitter.com/greptime)
 
-## Commercial Support
-
-If you are running GreptimeDB OSS in your organization, we offer additional
-enterprise add-ons, installation services, training, and consulting. [Contact
-us](https://greptime.com/contactus) and we will reach out to you with more
-detail of our commercial license.
-
 ## License
 
 GreptimeDB uses the [Apache License 2.0](https://apache.org/licenses/LICENSE-2.0.txt) to strike a balance between
@@ -214,12 +170,10 @@ open contributions and allowing you to use the software however you want.
 
 ## Contributing
 
-Please refer to [contribution guidelines](CONTRIBUTING.md) and [internal concepts docs](https://docs.greptime.com/contributor-guide/overview.html) for more information.
+Please refer to [contribution guidelines](CONTRIBUTING.md) for more information.
 
 ## Acknowledgement
 
-Special thanks to all the contributors who have propelled GreptimeDB forward. For a complete list of contributors, please refer to [AUTHOR.md](AUTHOR.md).
-
 - GreptimeDB uses [Apache Arrow™](https://arrow.apache.org/) as the memory model and [Apache Parquet™](https://parquet.apache.org/) as the persistent file format.
 - GreptimeDB's query engine is powered by [Apache Arrow DataFusion™](https://arrow.apache.org/datafusion/).
 - [Apache OpenDAL™](https://opendal.apache.org) gives GreptimeDB a very general and elegant data access abstraction layer.

benchmarks/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "benchmarks"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+arrow.workspace = true
+chrono.workspace = true
+clap.workspace = true
+client.workspace = true
+futures-util.workspace = true
+indicatif = "0.17.1"
+itertools.workspace = true
+parquet.workspace = true
+tokio.workspace = true

benchmarks/src/bin/nyc-taxi.rs

@@ -0,0 +1,543 @@
+// 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;
+            }
+        })
+}

cliff.toml

@@ -1,127 +0,0 @@
-# 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

@@ -8,6 +8,5 @@ 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

@@ -1,31 +0,0 @@
-# Configurations
-
-- [Configurations](#configurations)
-  - [Standalone Mode](#standalone-mode)
-  - [Distributed Mode](#distributed-mode)
-    - [Frontend](#frontend)
-    - [Metasrv](#metasrv)
-    - [Datanode](#datanode)
-    - [Flownode](#flownode)
-
-## Standalone Mode
-
-{{ toml2docs "./standalone.example.toml" }}
-
-## Distributed Mode
-
-### Frontend
-
-{{ toml2docs "./frontend.example.toml" }}
-
-### Metasrv
-
-{{ toml2docs "./metasrv.example.toml" }}
-
-### Datanode
-
-{{ toml2docs "./datanode.example.toml" }}
-
-### Flownode
-
-{{ toml2docs "./flownode.example.toml"}}

config/config.md

@@ -1,559 +0,0 @@
-# Configurations
-
-- [Configurations](#configurations)
-  - [Standalone Mode](#standalone-mode)
-  - [Distributed Mode](#distributed-mode)
-    - [Frontend](#frontend)
-    - [Metasrv](#metasrv)
-    - [Datanode](#datanode)
-    - [Flownode](#flownode)
-
-## Standalone Mode
-
-| Key | Type | Default | Descriptions |
-| --- | -----| ------- | ----------- |
-| `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
-| `default_timezone` | String | Unset | The default timezone of the server. |
-| `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. |
-| `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
-| `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
-| `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. Set to 0 to disable timeout. |
-| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
-| `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. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | Unset | Certificate file path. |
-| `grpc.tls.key_path` | String | Unset | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
-| `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 | Unset | Certificate file path. |
-| `mysql.tls.key_path` | String | Unset | 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.tls` section. |
-| `postgres.tls.mode` | String | `disable` | TLS mode. |
-| `postgres.tls.cert_path` | String | Unset | Certificate file path. |
-| `postgres.tls.key_path` | String | Unset | 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 | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `1GB` | 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 | `1m` | 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.recovery_parallelism` | Integer | `2` | Parallelism during WAL recovery. |
-| `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.auto_create_topics` | Bool | `true` | Automatically create topics for WAL.<br/>Set to `true` to automatically create topics for WAL.<br/>Otherwise, use topics named `topic_name_prefix_[0..num_topics)` |
-| `wal.num_topics` | Integer | `64` | Number of topics.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.selector_type` | String | `round_robin` | Topic selector type.<br/>Available selector types:<br/>- `round_robin` (default)<br/>**It's only used when the provider is `kafka`**. |
-| `wal.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.<br/>i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.replication_factor` | Integer | `1` | Expected number of replicas of each partition.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.create_topic_timeout` | String | `30s` | Above which a topic creation operation will be cancelled.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.max_batch_bytes` | 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.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`**. |
-| `wal.overwrite_entry_start_id` | Bool | `false` | Ignore missing entries during read WAL.<br/>**It's only used when the provider is `kafka`**.<br/><br/>This option ensures that when Kafka messages are deleted, the system<br/>can still successfully replay memtable data without throwing an<br/>out-of-range error.<br/>However, enabling this option might lead to unexpected data loss,<br/>as the system will skip over missing entries instead of treating<br/>them as critical errors. |
-| `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 | Unset | Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.<br/>A local file directory, defaults to `{data_home}/object_cache/read`. An empty string means disabling. |
-| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger. |
-| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | Unset | 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 | Unset | 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 | Unset | 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 | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.sas_token` | String | Unset | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.endpoint` | String | Unset | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.region` | String | Unset | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.http_client` | -- | -- | The http client options to the storage.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.http_client.pool_max_idle_per_host` | Integer | `1024` | The maximum idle connection per host allowed in the pool. |
-| `storage.http_client.connect_timeout` | String | `30s` | The timeout for only the connect phase of a http client. |
-| `storage.http_client.timeout` | String | `30s` | The total request timeout, applied from when the request starts connecting until the response body has finished.<br/>Also considered a total deadline. |
-| `storage.http_client.pool_idle_timeout` | String | `90s` | The timeout for idle sockets being kept-alive. |
-| `[[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_flushes` | Integer | Auto | Max number of running background flush jobs (default: 1/2 of cpu cores). |
-| `region_engine.mito.max_background_compactions` | Integer | Auto | Max number of running background compaction jobs (default: 1/4 of cpu cores). |
-| `region_engine.mito.max_background_purges` | Integer | Auto | Max number of running background purge jobs (default: number of cpu cores). |
-| `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 | Auto | 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 | Auto | 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 | Auto | 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 | Auto | 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 | Auto | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/8 of OS memory. |
-| `region_engine.mito.selector_result_cache_size` | String | Auto | Cache size for time series selector (e.g. `last_value()`). 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.enable_experimental_write_cache` | Bool | `false` | Whether to enable the experimental write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance. |
-| `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/object_cache/write`. |
-| `region_engine.mito.experimental_write_cache_size` | String | `5GiB` | Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | Unset | TTL for write cache. |
-| `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
-| `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.min_compaction_interval` | String | `0m` | Minimum time interval between two compactions.<br/>To align with the old behavior, the default value is 0 (no restrictions). |
-| `region_engine.mito.index` | -- | -- | The options for index in Mito engine. |
-| `region_engine.mito.index.aux_path` | String | `""` | Auxiliary directory path for the index in filesystem, used to store intermediate files for<br/>creating the index and staging files for searching the index, defaults to `{data_home}/index_intermediate`.<br/>The default name for this directory is `index_intermediate` for backward compatibility.<br/><br/>This path contains two subdirectories:<br/>- `__intm`: for storing intermediate files used during creating index.<br/>- `staging`: for storing staging files used during searching index. |
-| `region_engine.mito.index.staging_size` | String | `2GB` | The max capacity of the staging directory. |
-| `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 (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `auto` | Memory threshold for performing an external sort during index creation.<br/>- `auto`: automatically determine the threshold based on the system memory size (default)<br/>- `unlimited`: no memory limit<br/>- `[size]` e.g. `64MB`: fixed memory threshold |
-| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | Deprecated, use `region_engine.mito.index.aux_path` instead. |
-| `region_engine.mito.inverted_index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
-| `region_engine.mito.inverted_index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
-| `region_engine.mito.inverted_index.content_cache_page_size` | String | `8MiB` | Page size for inverted index content cache. |
-| `region_engine.mito.fulltext_index` | -- | -- | The options for full-text index in Mito engine. |
-| `region_engine.mito.fulltext_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.mem_threshold_on_create` | String | `auto` | Memory threshold for index creation.<br/>- `auto`: automatically determine the threshold based on the system memory size (default)<br/>- `unlimited`: no memory limit<br/>- `[size]` e.g. `64MB`: fixed memory threshold |
-| `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. |
-| `region_engine.file` | -- | -- | Enable the file engine. |
-| `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. If set to empty, logs will not be written to files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
-| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
-| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
-| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
-| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
-| `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` | -- |
-| `logging.slow_query` | -- | -- | The slow query log options. |
-| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
-| `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 recommended to collect metrics generated by itself<br/>You must create the database before enabling it. |
-| `export_metrics.self_import.db` | String | Unset | -- |
-| `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=greptime_metrics`. |
-| `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 | Unset | The tokio console address. |
-
-
-## Distributed Mode
-
-### Frontend
-
-| Key | Type | Default | Descriptions |
-| --- | -----| ------- | ----------- |
-| `default_timezone` | String | Unset | The default timezone of the server. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
-| `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. Set to 0 to disable timeout. |
-| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
-| `grpc` | -- | -- | The gRPC server options. |
-| `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
-| `grpc.hostname` | String | `127.0.0.1` | The hostname advertised to the metasrv,<br/>and used for connections from outside the host |
-| `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | Unset | Certificate file path. |
-| `grpc.tls.key_path` | String | Unset | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
-| `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 | Unset | Certificate file path. |
-| `mysql.tls.key_path` | String | Unset | 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.tls` section. |
-| `postgres.tls.mode` | String | `disable` | TLS mode. |
-| `postgres.tls.cert_path` | String | Unset | Certificate file path. |
-| `postgres.tls.key_path` | String | Unset | 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. If set to empty, logs will not be written to files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
-| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
-| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
-| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
-| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
-| `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` | -- |
-| `logging.slow_query` | -- | -- | The slow query log options. |
-| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
-| `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<br/>You must create the database before enabling it. |
-| `export_metrics.self_import.db` | String | Unset | -- |
-| `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=greptime_metrics`. |
-| `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 | Unset | 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_addrs` | Array | -- | Store server address default to etcd store. |
-| `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
-| `backend` | String | `EtcdStore` | The datastore for meta server. |
-| `selector` | String | `round_robin` | Datanode selector type.<br/>- `round_robin` (default value)<br/>- `lease_based`<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_region_failover` | Bool | `false` | Whether to enable region failover.<br/>This feature is only available on GreptimeDB running on cluster mode and<br/>- Using Remote WAL<br/>- Using shared storage (e.g., s3). |
-| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. Enabled by default. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
-| `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` | The threshold value used by the failure detector to determine failure conditions. |
-| `failure_detector.min_std_deviation` | String | `100ms` | The minimum standard deviation of the heartbeat intervals, used to calculate acceptable variations. |
-| `failure_detector.acceptable_heartbeat_pause` | String | `10000ms` | The acceptable pause duration between heartbeats, used to determine if a heartbeat interval is acceptable. |
-| `failure_detector.first_heartbeat_estimate` | String | `1000ms` | The initial estimate of the heartbeat interval used by the failure detector. |
-| `datanode` | -- | -- | Datanode options. |
-| `datanode.client` | -- | -- | Datanode client options. |
-| `datanode.client.timeout` | String | `10s` | Operation timeout. |
-| `datanode.client.connect_timeout` | String | `10s` | Connect server timeout. |
-| `datanode.client.tcp_nodelay` | Bool | `true` | `TCP_NODELAY` option for accepted connections. |
-| `wal` | -- | -- | -- |
-| `wal.provider` | String | `raft_engine` | -- |
-| `wal.broker_endpoints` | Array | -- | The broker endpoints of the Kafka cluster. |
-| `wal.auto_create_topics` | Bool | `true` | Automatically create topics for WAL.<br/>Set to `true` to automatically create topics for WAL.<br/>Otherwise, use topics named `topic_name_prefix_[0..num_topics)` |
-| `wal.num_topics` | Integer | `64` | Number of topics. |
-| `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`.<br/>i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1. |
-| `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. If set to empty, logs will not be written to files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
-| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
-| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
-| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
-| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
-| `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` | -- |
-| `logging.slow_query` | -- | -- | The slow query log options. |
-| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
-| `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<br/>You must create the database before enabling it. |
-| `export_metrics.self_import.db` | String | Unset | -- |
-| `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=greptime_metrics`. |
-| `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 | Unset | 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 | Unset | 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. |
-| `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
-| `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
-| `rpc_addr` | String | Unset | Deprecated, use `grpc.addr` instead. |
-| `rpc_hostname` | String | Unset | Deprecated, use `grpc.hostname` instead. |
-| `rpc_runtime_size` | Integer | Unset | Deprecated, use `grpc.runtime_size` instead. |
-| `rpc_max_recv_message_size` | String | Unset | Deprecated, use `grpc.rpc_max_recv_message_size` instead. |
-| `rpc_max_send_message_size` | String | Unset | Deprecated, use `grpc.rpc_max_send_message_size` instead. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
-| `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. Set to 0 to disable timeout. |
-| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
-| `grpc` | -- | -- | The gRPC server options. |
-| `grpc.addr` | String | `127.0.0.1:3001` | The address to bind the gRPC server. |
-| `grpc.hostname` | String | `127.0.0.1` | The hostname advertised to the metasrv,<br/>and used for connections from outside the host |
-| `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
-| `grpc.max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
-| `grpc.max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | Unset | Certificate file path. |
-| `grpc.tls.key_path` | String | Unset | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
-| `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 | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `1GB` | 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 | `1m` | 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.recovery_parallelism` | Integer | `2` | Parallelism during WAL recovery. |
-| `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.max_batch_bytes` | 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.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`**. |
-| `wal.create_index` | Bool | `true` | Whether to enable WAL index creation.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.dump_index_interval` | String | `60s` | The interval for dumping WAL indexes.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.overwrite_entry_start_id` | Bool | `false` | Ignore missing entries during read WAL.<br/>**It's only used when the provider is `kafka`**.<br/><br/>This option ensures that when Kafka messages are deleted, the system<br/>can still successfully replay memtable data without throwing an<br/>out-of-range error.<br/>However, enabling this option might lead to unexpected data loss,<br/>as the system will skip over missing entries instead of treating<br/>them as critical errors. |
-| `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 | Unset | Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.<br/>A local file directory, defaults to `{data_home}/object_cache/read`. An empty string means disabling. |
-| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger. |
-| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | Unset | 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 | Unset | 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 | Unset | 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 | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.sas_token` | String | Unset | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.endpoint` | String | Unset | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.region` | String | Unset | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.http_client` | -- | -- | The http client options to the storage.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.http_client.pool_max_idle_per_host` | Integer | `1024` | The maximum idle connection per host allowed in the pool. |
-| `storage.http_client.connect_timeout` | String | `30s` | The timeout for only the connect phase of a http client. |
-| `storage.http_client.timeout` | String | `30s` | The total request timeout, applied from when the request starts connecting until the response body has finished.<br/>Also considered a total deadline. |
-| `storage.http_client.pool_idle_timeout` | String | `90s` | The timeout for idle sockets being kept-alive. |
-| `[[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_flushes` | Integer | Auto | Max number of running background flush jobs (default: 1/2 of cpu cores). |
-| `region_engine.mito.max_background_compactions` | Integer | Auto | Max number of running background compaction jobs (default: 1/4 of cpu cores). |
-| `region_engine.mito.max_background_purges` | Integer | Auto | Max number of running background purge jobs (default: number of cpu cores). |
-| `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 | Auto | 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 | Auto | 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 | Auto | 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 | Auto | 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 | Auto | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/8 of OS memory. |
-| `region_engine.mito.selector_result_cache_size` | String | Auto | Cache size for time series selector (e.g. `last_value()`). 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.enable_experimental_write_cache` | Bool | `false` | Whether to enable the experimental write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance. |
-| `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/object_cache/write`. |
-| `region_engine.mito.experimental_write_cache_size` | String | `5GiB` | Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | Unset | TTL for write cache. |
-| `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
-| `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.min_compaction_interval` | String | `0m` | Minimum time interval between two compactions.<br/>To align with the old behavior, the default value is 0 (no restrictions). |
-| `region_engine.mito.index` | -- | -- | The options for index in Mito engine. |
-| `region_engine.mito.index.aux_path` | String | `""` | Auxiliary directory path for the index in filesystem, used to store intermediate files for<br/>creating the index and staging files for searching the index, defaults to `{data_home}/index_intermediate`.<br/>The default name for this directory is `index_intermediate` for backward compatibility.<br/><br/>This path contains two subdirectories:<br/>- `__intm`: for storing intermediate files used during creating index.<br/>- `staging`: for storing staging files used during searching index. |
-| `region_engine.mito.index.staging_size` | String | `2GB` | The max capacity of the staging directory. |
-| `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 (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `auto` | Memory threshold for performing an external sort during index creation.<br/>- `auto`: automatically determine the threshold based on the system memory size (default)<br/>- `unlimited`: no memory limit<br/>- `[size]` e.g. `64MB`: fixed memory threshold |
-| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | Deprecated, use `region_engine.mito.index.aux_path` instead. |
-| `region_engine.mito.inverted_index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
-| `region_engine.mito.inverted_index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
-| `region_engine.mito.inverted_index.content_cache_page_size` | String | `8MiB` | Page size for inverted index content cache. |
-| `region_engine.mito.fulltext_index` | -- | -- | The options for full-text index in Mito engine. |
-| `region_engine.mito.fulltext_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
-| `region_engine.mito.fulltext_index.mem_threshold_on_create` | String | `auto` | Memory threshold for index creation.<br/>- `auto`: automatically determine the threshold based on the system memory size (default)<br/>- `unlimited`: no memory limit<br/>- `[size]` e.g. `64MB`: fixed memory threshold |
-| `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. |
-| `region_engine.file` | -- | -- | Enable the file engine. |
-| `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. If set to empty, logs will not be written to files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
-| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
-| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
-| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
-| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
-| `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` | -- |
-| `logging.slow_query` | -- | -- | The slow query log options. |
-| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
-| `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<br/>You must create the database before enabling it. |
-| `export_metrics.self_import.db` | String | Unset | -- |
-| `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=greptime_metrics`. |
-| `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 | Unset | The tokio console address. |
-
-
-### Flownode
-
-| Key | Type | Default | Descriptions |
-| --- | -----| ------- | ----------- |
-| `mode` | String | `distributed` | The running mode of the flownode. It can be `standalone` or `distributed`. |
-| `node_id` | Integer | Unset | The flownode identifier and should be unique in the cluster. |
-| `grpc` | -- | -- | The gRPC server options. |
-| `grpc.addr` | String | `127.0.0.1:6800` | The address to bind the gRPC server. |
-| `grpc.hostname` | String | `127.0.0.1` | The hostname advertised to the metasrv,<br/>and used for connections from outside the host |
-| `grpc.runtime_size` | Integer | `2` | The number of server worker threads. |
-| `grpc.max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
-| `grpc.max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
-| `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` | -- |
-| `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. |
-| `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. If set to empty, logs will not be written to files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
-| `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
-| `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
-| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
-| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
-| `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` | -- |
-| `logging.slow_query` | -- | -- | The slow query log options. |
-| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
-| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |

config/datanode.example.toml

@@ -1,671 +1,159 @@
-## 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 running mode, see `standalone.example.toml`.
+mode = "distributed"
+# The datanode identifier, should be unique.
 node_id = 42
-
-## Start services after regions have obtained leases.
-## It will block the datanode start if it can't receive leases in the heartbeat from metasrv.
+# 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.
 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
 
-## Parallelism of initializing regions.
-init_regions_parallelism = 16
-
-## The maximum current queries allowed to be executed. Zero means unlimited.
-max_concurrent_queries = 0
-
-## Deprecated, use `grpc.addr` instead.
-## @toml2docs:none-default
-rpc_addr = "127.0.0.1:3001"
-
-## Deprecated, use `grpc.hostname` instead.
-## @toml2docs:none-default
-rpc_hostname = "127.0.0.1"
-
-## Deprecated, use `grpc.runtime_size` instead.
-## @toml2docs:none-default
-rpc_runtime_size = 8
-
-## Deprecated, use `grpc.rpc_max_recv_message_size` instead.
-## @toml2docs:none-default
-rpc_max_recv_message_size = "512MB"
-
-## Deprecated, use `grpc.rpc_max_send_message_size` instead.
-## @toml2docs:none-default
-rpc_max_send_message_size = "512MB"
-
-## Enable telemetry to collect anonymous usage data. Enabled by default.
-#+ enable_telemetry = true
-
-## The HTTP server options.
-[http]
-## The address to bind the HTTP server.
-addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
-timeout = "30s"
-## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
-body_limit = "64MB"
-
-## The gRPC server options.
-[grpc]
-## The address to bind the gRPC server.
-addr = "127.0.0.1:3001"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
-## The number of server worker threads.
-runtime_size = 8
-## The maximum receive message size for gRPC server.
-max_recv_message_size = "512MB"
-## The maximum send message size for gRPC server.
-max_send_message_size = "512MB"
-
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## @toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
-## The runtime options.
-#+ [runtime]
-## The number of threads to execute the runtime for global read operations.
-#+ global_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-#+ compact_rt_size = 4
-
-## The heartbeat options.
 [heartbeat]
-## Interval for sending heartbeat messages to the metasrv.
+# Interval for sending heartbeat messages to the Metasrv, 3 seconds by default.
 interval = "3s"
 
-## Interval for retrying to send heartbeat messages to the metasrv.
-retry_interval = "3s"
-
-## The metasrv client options.
+# Metasrv client options.
 [meta_client]
-## The addresses of the metasrv.
+# Metasrv address list.
 metasrv_addrs = ["127.0.0.1:3002"]
-
-## Operation timeout.
-timeout = "3s"
-
-## Heartbeat timeout.
+# Heartbeat timeout, 500 milliseconds by default.
 heartbeat_timeout = "500ms"
-
-## DDL timeout.
-ddl_timeout = "10s"
-
-## Connect server timeout.
+# Operation timeout, 3 seconds by default.
+timeout = "3s"
+# Connect server timeout, 1 second by default.
 connect_timeout = "1s"
-
-## `TCP_NODELAY` option for accepted connections.
+# `TCP_NODELAY` option for accepted connections, true by default.
 tcp_nodelay = true
 
-## 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 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"
 
-## 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 = "128MB"
-
-## The threshold of the WAL size to trigger a flush.
-## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "1GB"
-
-## The interval to trigger a flush.
-## **It's only used when the provider is `raft_engine`**.
-purge_interval = "1m"
-
-## The read batch size.
-## **It's only used when the provider is `raft_engine`**.
+# Raft-engine wal options, see `standalone.example.toml`.
+# dir = "/tmp/greptimedb/wal"
+file_size = "256MB"
+purge_threshold = "4GB"
+purge_interval = "10m"
 read_batch_size = 128
-
-## 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.
-## **It's only used when the provider is `raft_engine`**.
-enable_log_recycle = true
+# 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 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"
-
-## Parallelism during WAL recovery.
-recovery_parallelism = 2
-
-## 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_bytes = "1MB"
-
-## 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"
-
-## Whether to enable WAL index creation.
-## **It's only used when the provider is `kafka`**.
-create_index = true
-
-## The interval for dumping WAL indexes.
-## **It's only used when the provider is `kafka`**.
-dump_index_interval = "60s"
-
-## Ignore missing entries during read WAL.
-## **It's only used when the provider is `kafka`**.
-##
-## This option ensures that when Kafka messages are deleted, the system
-## can still successfully replay memtable data without throwing an
-## out-of-range error.
-## However, enabling this option might lead to unexpected data loss,
-## as the system will skip over missing entries instead of treating
-## them as critical errors.
-overwrite_entry_start_id = false
-
-# The Kafka SASL configuration.
-# **It's only used when the provider is `kafka`**.
-# Available SASL mechanisms:
-# - `PLAIN`
-# - `SCRAM-SHA-256`
-# - `SCRAM-SHA-512`
-# [wal.sasl]
-# type = "SCRAM-SHA-512"
-# username = "user_kafka"
-# password = "secret"
-
-# The Kafka TLS configuration.
-# **It's only used when the provider is `kafka`**.
-# [wal.tls]
-# server_ca_cert_path = "/path/to/server_cert"
-# client_cert_path = "/path/to/client_cert"
-# client_key_path = "/path/to/key"
-
-# 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"
-# credential = "base64-credential"
-# endpoint = "https://storage.googleapis.com"
-
-## The data storage options.
+# Storage options, see `standalone.example.toml`.
 [storage]
-## The working home directory.
+# The working home directory.
 data_home = "/tmp/greptimedb/"
-
-## 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.
+# Storage type.
 type = "File"
+# TTL for all tables. Disabled by default.
+# global_ttl = "7d"
 
-## Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.
-## A local file directory, defaults to `{data_home}/object_cache/read`. An empty string means disabling.
-## @toml2docs:none-default
-#+ cache_path = ""
-
-## The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger.
-## @toml2docs:none-default
-cache_capacity = "5GiB"
-
-## 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 credential of the google cloud storage.
-## **It's only used when the storage type is `Gcs`**.
-## @toml2docs:none-default
-credential = "base64-credential"
-
-## 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"
-
-## The http client options to the storage.
-## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
-[storage.http_client]
-
-## The maximum idle connection per host allowed in the pool.
-pool_max_idle_per_host = 1024
-
-## The timeout for only the connect phase of a http client.
-connect_timeout = "30s"
-
-## The total request timeout, applied from when the request starts connecting until the response body has finished.
-## Also considered a total deadline.
-timeout = "30s"
-
-## The timeout for idle sockets being kept-alive.
-pool_idle_timeout = "90s"
+# 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"
 
 # Custom storage options
-# [[storage.providers]]
-# name = "S3"
-# type = "S3"
-# bucket = "greptimedb"
-# root = "data"
-# access_key_id = "test"
-# secret_access_key = "123456"
-# endpoint = "https://s3.amazonaws.com"
-# region = "us-west-2"
-# [[storage.providers]]
-# name = "Gcs"
-# type = "Gcs"
-# bucket = "greptimedb"
-# root = "data"
-# scope = "test"
-# credential_path = "123456"
-# credential = "base64-credential"
-# endpoint = "https://storage.googleapis.com"
+#[[storage.providers]]
+#type = "S3"
+#[[storage.providers]]
+#type = "Gcs"
 
-## The region engine options. You can configure multiple region engines.
+# Mito engine options
 [[region_engine]]
-
-## The Mito engine options.
 [region_engine.mito]
-
-## Number of region workers.
-#+ num_workers = 8
-
-## Request channel size of each worker.
+# Number of region workers
+num_workers = 8
+# 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 flush jobs (default: 1/2 of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_flushes = 4
-
-## Max number of running background compaction jobs (default: 1/4 of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_compactions = 2
-
-## Max number of running background purge jobs (default: number of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_purges = 8
-
-## Interval to auto flush a region if it has not flushed yet.
+# Max number of running background jobs
+max_background_jobs = 4
+# 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.
-## @toml2docs:none-default="Auto"
-#+ 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`
-## @toml2docs:none-default="Auto"
-#+ 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.
-## @toml2docs:none-default="Auto"
-#+ 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.
-## @toml2docs:none-default="Auto"
-#+ 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 1/8 of OS memory.
-## @toml2docs:none-default="Auto"
-#+ page_cache_size = "512MB"
-
-## Cache size for time series selector (e.g. `last_value()`). 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.
-## @toml2docs:none-default="Auto"
-#+ selector_result_cache_size = "512MB"
-
-## Whether to enable the experimental write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance.
-enable_experimental_write_cache = false
-
-## File system path for write cache, defaults to `{data_home}/object_cache/write`.
-experimental_write_cache_path = ""
-
-## Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger.
-experimental_write_cache_size = "5GiB"
-
-## TTL for write cache.
-## @toml2docs:none-default
-experimental_write_cache_ttl = "8h"
-
-## Buffer size for SST writing.
+# 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_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.
+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.
+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.
+page_cache_size = "512MB"
+# Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
-
-## Capacity of the channel to send data from parallel scan tasks to the main task.
+# 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).
 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
 
-## Minimum time interval between two compactions.
-## To align with the old behavior, the default value is 0 (no restrictions).
-min_compaction_interval = "0m"
-
-## The options for index in Mito engine.
-[region_engine.mito.index]
-
-## Auxiliary directory path for the index in filesystem, used to store intermediate files for
-## creating the index and staging files for searching the index, defaults to `{data_home}/index_intermediate`.
-## The default name for this directory is `index_intermediate` for backward compatibility.
-##
-## This path contains two subdirectories:
-## - `__intm`: for storing intermediate files used during creating index.
-## - `staging`: for storing staging files used during searching index.
-aux_path = ""
-
-## The max capacity of the staging directory.
-staging_size = "2GB"
-
-## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
-
-## Whether to create the index on flush.
-## - `auto`: automatically (default)
-## - `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 (default)
-## - `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 (default)
-## - `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.
-## - `auto`: automatically determine the threshold based on the system memory size (default)
-## - `unlimited`: no memory limit
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
-
-## Deprecated, use `region_engine.mito.index.aux_path` instead.
+# 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`).
 intermediate_path = ""
 
-## Cache size for inverted index metadata.
-metadata_cache_size = "64MiB"
+# Log options, see `standalone.example.toml`
+# [logging]
+# dir = "/tmp/greptimedb/logs"
+# level = "info"
 
-## Cache size for inverted index content.
-content_cache_size = "128MiB"
-
-## Page size for inverted index content cache.
-content_cache_page_size = "8MiB"
-
-## The options for full-text index in Mito engine.
-[region_engine.mito.fulltext_index]
-
-## Whether to create the index on flush.
-## - `auto`: automatically (default)
-## - `disable`: never
-create_on_flush = "auto"
-
-## Whether to create the index on compaction.
-## - `auto`: automatically (default)
-## - `disable`: never
-create_on_compaction = "auto"
-
-## Whether to apply the index on query
-## - `auto`: automatically (default)
-## - `disable`: never
-apply_on_query = "auto"
-
-## Memory threshold for index creation.
-## - `auto`: automatically determine the threshold based on the system memory size (default)
-## - `unlimited`: no memory limit
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
-
-[region_engine.mito.memtable]
-## Memtable type.
-## - `time_series`: time-series memtable
-## - `partition_tree`: partition tree memtable (experimental)
-type = "time_series"
-
-## 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"
-
-[[region_engine]]
-## Enable the file engine.
-[region_engine.file]
-
-## The logging options.
-[logging]
-## The directory to store the log files. If set to empty, logs will not be written to 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.
-otlp_endpoint = "http://localhost:4317"
-
-## Whether to append logs to stdout.
-append_stdout = true
-
-## The log format. Can be `text`/`json`.
-log_format = "text"
-
-## The maximum amount of log files.
-max_log_files = 720
-
-## 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 slow query log options.
-[logging.slow_query]
-## Whether to enable slow query log.
-enable = false
-
-## The threshold of slow query.
-## @toml2docs:none-default
-threshold = "10s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1].
-## @toml2docs:none-default
-sample_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
-## You must create the database before enabling it.
-[export_metrics.self_import]
-## @toml2docs:none-default
-db = "greptime_metrics"
-
-[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=greptime_metrics`.
-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"
+# 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 = {}

config/flownode.example.toml

@@ -1,108 +0,0 @@
-## The running mode of the flownode. It can be `standalone` or `distributed`.
-mode = "distributed"
-
-## The flownode identifier and should be unique in the cluster.
-## @toml2docs:none-default
-node_id = 14
-
-## The gRPC server options.
-[grpc]
-## The address to bind the gRPC server.
-addr = "127.0.0.1:6800"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
-## The number of server worker threads.
-runtime_size = 2
-## The maximum receive message size for gRPC server.
-max_recv_message_size = "512MB"
-## The maximum send message size for gRPC server.
-max_send_message_size = "512MB"
-
-
-## The metasrv client options.
-[meta_client]
-## The addresses of the metasrv.
-metasrv_addrs = ["127.0.0.1:3002"]
-
-## Operation timeout.
-timeout = "3s"
-
-## 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.
-metadata_cache_max_capacity = 100000
-
-## TTL of the metadata cache.
-metadata_cache_ttl = "10m"
-
-# TTI of the metadata cache.
-metadata_cache_tti = "5m"
-
-## The heartbeat options.
-[heartbeat]
-## Interval for sending heartbeat messages to the metasrv.
-interval = "3s"
-
-## Interval for retrying to send heartbeat messages to the metasrv.
-retry_interval = "3s"
-
-## The logging options.
-[logging]
-## The directory to store the log files. If set to empty, logs will not be written to 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.
-otlp_endpoint = "http://localhost:4317"
-
-## Whether to append logs to stdout.
-append_stdout = true
-
-## The log format. Can be `text`/`json`.
-log_format = "text"
-
-## The maximum amount of log files.
-max_log_files = 720
-
-## 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 slow query log options.
-[logging.slow_query]
-## Whether to enable slow query log.
-enable = false
-
-## The threshold of slow query.
-## @toml2docs:none-default
-threshold = "10s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1].
-## @toml2docs:none-default
-sample_ratio = 1.0
-
-## 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

@@ -1,237 +1,104 @@
-## The default timezone of the server.
-## @toml2docs:none-default
-default_timezone = "UTC"
+# Node running mode, see `standalone.example.toml`.
+mode = "distributed"
+# The default timezone of the server
+# default_timezone = "UTC"
 
-## The runtime options.
-#+ [runtime]
-## The number of threads to execute the runtime for global read operations.
-#+ global_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-#+ compact_rt_size = 4
-
-## The heartbeat options.
 [heartbeat]
-## Interval for sending heartbeat messages to the metasrv.
-interval = "18s"
+# 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 retrying to send heartbeat messages to the metasrv.
-retry_interval = "3s"
-
-## The HTTP server options.
+# HTTP server options, see `standalone.example.toml`.
 [http]
-## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
 timeout = "30s"
-## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
 body_limit = "64MB"
 
-## The gRPC server options.
+# gRPC server options, see `standalone.example.toml`.
 [grpc]
-## The address to bind the gRPC server.
 addr = "127.0.0.1:4001"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
-## The number of server worker threads.
 runtime_size = 8
 
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## @toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
-## MySQL server options.
+# MySQL server options, see `standalone.example.toml`.
 [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.
+# MySQL server TLS options, see `standalone.example.toml`.
 [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 = ""
 
-## Watch for Certificate and key file change and auto reload
-watch = false
-
-## PostgresSQL server options.
+# PostgresSQL server options, see `standalone.example.toml`.
 [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 `mysql.tls` section.
+# PostgresSQL server TLS options, see `standalone.example.toml`.
 [postgres.tls]
-## TLS mode.
 mode = "disable"
-
-## Certificate file path.
-## @toml2docs:none-default
 cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
 key_path = ""
 
-## Watch for Certificate and key file change and auto reload
-watch = false
-
-## OpenTSDB protocol options.
+# OpenTSDB protocol options, see `standalone.example.toml`.
 [opentsdb]
-## Whether to enable OpenTSDB put in HTTP API.
 enable = true
+addr = "127.0.0.1:4242"
+runtime_size = 2
 
-## InfluxDB protocol options.
+# InfluxDB protocol options, see `standalone.example.toml`.
 [influxdb]
-## Whether to enable InfluxDB protocol in HTTP API.
 enable = true
 
-## Prometheus remote storage options
+# Prometheus remote storage options, see `standalone.example.toml`.
 [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.
+# Whether to store the data from Prometheus remote write in metric engine.
+# true by default
 with_metric_engine = true
 
-## The metasrv client options.
+# Metasrv client options, see `datanode.example.toml`.
 [meta_client]
-## The addresses of the metasrv.
 metasrv_addrs = ["127.0.0.1:3002"]
-
-## Operation timeout.
 timeout = "3s"
-
-## Heartbeat timeout.
-heartbeat_timeout = "500ms"
-
-## DDL timeout.
+# DDL timeouts options.
 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.
+# The configuration about the cache of the Metadata.
+# default: 100000
 metadata_cache_max_capacity = 100000
-
-## TTL of the metadata cache.
+# default: 10m
 metadata_cache_ttl = "10m"
-
-# TTI of the metadata cache.
+# default: 5m
 metadata_cache_tti = "5m"
 
-## Datanode options.
+# Log options, see `standalone.example.toml`
+# [logging]
+# dir = "/tmp/greptimedb/logs"
+# level = "info"
+
+# Datanode options.
 [datanode]
-## Datanode client options.
+# Datanode client options.
 [datanode.client]
+timeout = "10s"
 connect_timeout = "10s"
 tcp_nodelay = true
 
-## The logging options.
-[logging]
-## The directory to store the log files. If set to empty, logs will not be written to 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.
-otlp_endpoint = "http://localhost:4317"
-
-## Whether to append logs to stdout.
-append_stdout = true
-
-## The log format. Can be `text`/`json`.
-log_format = "text"
-
-## The maximum amount of log files.
-max_log_files = 720
-
-## 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 slow query log options.
-[logging.slow_query]
-## Whether to enable slow query log.
-enable = false
-
-## The threshold of slow query.
-## @toml2docs:none-default
-threshold = "10s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1].
-## @toml2docs:none-default
-sample_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
-## You must create the database before enabling it.
-[export_metrics.self_import]
-## @toml2docs:none-default
-db = "greptime_metrics"
-
-[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=greptime_metrics`.
-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"
+# 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"

config/metasrv.example.toml

@@ -1,224 +1,93 @@
-## The working home directory.
+# The working home directory.
 data_home = "/tmp/metasrv/"
-
-## The bind address of metasrv.
+# The bind address of metasrv, "127.0.0.1:3002" by default.
 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"
-
-## Store server address default to etcd store.
-store_addrs = ["127.0.0.1:2379"]
-
-## If it's not empty, the metasrv will store all data with this key prefix.
+# Etcd server address, "127.0.0.1:2379" by default.
+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".
+selector = "lease_based"
+# Store data in memory, false by default.
+use_memory_store = false
+# Whether to enable greptimedb telemetry, true by default.
+enable_telemetry = true
+# If it's not empty, the metasrv will store all data with this key prefix.
 store_key_prefix = ""
 
-## The datastore for meta server.
-backend = "EtcdStore"
+# Log options, see `standalone.example.toml`
+# [logging]
+# dir = "/tmp/greptimedb/logs"
+# level = "info"
 
-## Datanode selector type.
-## - `round_robin` (default value)
-## - `lease_based`
-## - `load_based`
-## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
-selector = "round_robin"
-
-## Store data in memory.
-use_memory_store = false
-
-## Whether to enable region failover.
-## This feature is only available on GreptimeDB running on cluster mode and
-## - Using Remote WAL
-## - Using shared storage (e.g., s3).
-enable_region_failover = false
-
-## Whether to enable greptimedb telemetry. Enabled by default.
-#+ enable_telemetry = true
-
-## The runtime options.
-#+ [runtime]
-## The number of threads to execute the runtime for global read operations.
-#+ global_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-#+ compact_rt_size = 4
-
-## 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]
-
-## The threshold value used by the failure detector to determine failure conditions.
 threshold = 8.0
-
-## The minimum standard deviation of the heartbeat intervals, used to calculate acceptable variations.
 min_std_deviation = "100ms"
-
-## The acceptable pause duration between heartbeats, used to determine if a heartbeat interval is acceptable.
-acceptable_heartbeat_pause = "10000ms"
-
-## The initial estimate of the heartbeat interval used by the failure detector.
+acceptable_heartbeat_pause = "3000ms"
 first_heartbeat_estimate = "1000ms"
 
-## Datanode options.
-[datanode]
-
-## Datanode client options.
-[datanode.client]
-
-## Operation timeout.
-timeout = "10s"
-
-## Connect server timeout.
-connect_timeout = "10s"
-
-## `TCP_NODELAY` option for accepted connections.
-tcp_nodelay = true
+# # Datanode options.
+# [datanode]
+# # Datanode client options.
+# [datanode.client_options]
+# timeout = "10s"
+# connect_timeout = "10s"
+# tcp_nodelay = true
 
 [wal]
 # Available wal providers:
-# - `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.
+# - "raft_engine" (default)
+# - "kafka"
 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"
 
-## The broker endpoints of the Kafka cluster.
-broker_endpoints = ["127.0.0.1:9092"]
-
-## Automatically create topics for WAL.
-## Set to `true` to automatically create topics for WAL.
-## Otherwise, use topics named `topic_name_prefix_[0..num_topics)`
-auto_create_topics = true
-
-## Number of topics.
-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`.
-## i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.
-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 Kafka SASL configuration.
-# **It's only used when the provider is `kafka`**.
-# Available SASL mechanisms:
-# - `PLAIN`
-# - `SCRAM-SHA-256`
-# - `SCRAM-SHA-512`
-# [wal.sasl]
-# type = "SCRAM-SHA-512"
-# username = "user_kafka"
-# password = "secret"
-
-# The Kafka TLS configuration.
-# **It's only used when the provider is `kafka`**.
-# [wal.tls]
-# server_ca_cert_path = "/path/to/server_cert"
-# client_cert_path = "/path/to/client_cert"
-# client_key_path = "/path/to/key"
-
-## The logging options.
-[logging]
-## The directory to store the log files. If set to empty, logs will not be written to 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.
-otlp_endpoint = "http://localhost:4317"
-
-## Whether to append logs to stdout.
-append_stdout = true
-
-## The log format. Can be `text`/`json`.
-log_format = "text"
-
-## The maximum amount of log files.
-max_log_files = 720
-
-## 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 slow query log options.
-[logging.slow_query]
-## Whether to enable slow query log.
-enable = false
-
-## The threshold of slow query.
-## @toml2docs:none-default
-threshold = "10s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1].
-## @toml2docs:none-default
-sample_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
-## You must create the database before enabling it.
-[export_metrics.self_import]
-## @toml2docs:none-default
-db = "greptime_metrics"
-
-[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=greptime_metrics`.
-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"
+# 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 = {}

config/standalone.example.toml

@@ -1,710 +1,269 @@
-## The running mode of the datanode. It can be `standalone` or `distributed`.
+# Node running mode, "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"
 
-## The default timezone of the server.
-## @toml2docs:none-default
-default_timezone = "UTC"
-
-## 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
-
-## Parallelism of initializing regions.
-init_regions_parallelism = 16
-
-## The maximum current queries allowed to be executed. Zero means unlimited.
-max_concurrent_queries = 0
-
-## Enable telemetry to collect anonymous usage data. Enabled by default.
-#+ enable_telemetry = true
-
-## The runtime options.
-#+ [runtime]
-## The number of threads to execute the runtime for global read operations.
-#+ global_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-#+ compact_rt_size = 4
-
-## The HTTP server options.
+# HTTP server options.
 [http]
-## The address to bind the HTTP server.
+# Server address, "127.0.0.1:4000" by default.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
+# HTTP request timeout, 30s by default.
 timeout = "30s"
-## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
+# HTTP request body limit, 64Mb by default.
+# the following units are supported: B, KB, KiB, MB, MiB, GB, GiB, TB, TiB, PB, PiB
 body_limit = "64MB"
 
-## The gRPC server options.
+# gRPC server options.
 [grpc]
-## The address to bind the gRPC server.
+# Server address, "127.0.0.1:4001" by default.
 addr = "127.0.0.1:4001"
-## The number of server worker threads.
+# The number of server worker threads, 8 by default.
 runtime_size = 8
 
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## @toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
-## MySQL server options.
+# MySQL server options.
 [mysql]
-## Whether to enable.
+# Whether to enable
 enable = true
-## The addr to bind the MySQL server.
+# Server address, "127.0.0.1:4002" by default.
 addr = "127.0.0.1:4002"
-## The number of server worker threads.
+# The number of server worker threads, 2 by default.
 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.
-## @toml2docs:none-default
+# Certificate file path.
 cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
+# Private key file path.
 key_path = ""
 
-## Watch for Certificate and key file change and auto reload
-watch = false
-
-## PostgresSQL server options.
+# PostgresSQL server options.
 [postgres]
-## Whether to enable
+# Whether to enable
 enable = true
-## The addr to bind the PostgresSQL server.
+# Server address, "127.0.0.1:4003" by default.
 addr = "127.0.0.1:4003"
-## The number of server worker threads.
+# The number of server worker threads, 2 by default.
 runtime_size = 2
 
-## PostgresSQL server TLS options, see `mysql.tls` section.
+# PostgresSQL server TLS options, see `[mysql_options.tls]` section.
 [postgres.tls]
-## TLS mode.
+# TLS mode.
 mode = "disable"
-
-## Certificate file path.
-## @toml2docs:none-default
+# certificate file path.
 cert_path = ""
-
-## Private key file path.
-## @toml2docs:none-default
+# private key file path.
 key_path = ""
 
-## Watch for Certificate and key file change and auto reload
-watch = false
-
-## OpenTSDB protocol options.
+# OpenTSDB protocol options.
 [opentsdb]
-## Whether to enable OpenTSDB put in HTTP API.
+# Whether to enable
 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.
+# Whether to enable InfluxDB protocol in HTTP API, true by default.
 enable = true
 
-## Prometheus remote storage options
+# Prometheus remote storage options
 [prom_store]
-## Whether to enable Prometheus remote write and read in HTTP API.
+# Whether to enable Prometheus remote write and read in HTTP API, true by default.
 enable = true
-## Whether to store the data from Prometheus remote write in metric engine.
+# Whether to store the data from Prometheus remote write in metric engine.
+# true by default
 with_metric_engine = true
 
-## 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.
+# Available wal providers:
+# - "raft_engine" (default)
+# - "kafka"
 provider = "raft_engine"
 
-## 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 = "128MB"
-
-## The threshold of the WAL size to trigger a flush.
-## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "1GB"
-
-## The interval to trigger a flush.
-## **It's only used when the provider is `raft_engine`**.
-purge_interval = "1m"
-
-## 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
-
-## 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.
-## **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"
-
-## Parallelism during WAL recovery.
-recovery_parallelism = 2
-
-## The Kafka broker endpoints.
-## **It's only used when the provider is `kafka`**.
-broker_endpoints = ["127.0.0.1:9092"]
-
-## Automatically create topics for WAL.
-## Set to `true` to automatically create topics for WAL.
-## Otherwise, use topics named `topic_name_prefix_[0..num_topics)`
-auto_create_topics = true
-
-## Number of topics.
-## **It's only used when the provider is `kafka`**.
-num_topics = 64
-
-## Topic selector type.
-## Available selector types:
-## - `round_robin` (default)
-## **It's only used when the provider is `kafka`**.
-selector_type = "round_robin"
-
-## A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.
-## i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.
-## **It's only used when the provider is `kafka`**.
-topic_name_prefix = "greptimedb_wal_topic"
-
-## Expected number of replicas of each partition.
-## **It's only used when the provider is `kafka`**.
-replication_factor = 1
-
-## Above which a topic creation operation will be cancelled.
-## **It's only used when the provider is `kafka`**.
-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_bytes = "1MB"
-
-## 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"
-
-## Ignore missing entries during read WAL.
-## **It's only used when the provider is `kafka`**.
-##
-## This option ensures that when Kafka messages are deleted, the system
-## can still successfully replay memtable data without throwing an
-## out-of-range error.
-## However, enabling this option might lead to unexpected data loss,
-## as the system will skip over missing entries instead of treating
-## them as critical errors.
-overwrite_entry_start_id = false
-
-# The Kafka SASL configuration.
-# **It's only used when the provider is `kafka`**.
-# Available SASL mechanisms:
-# - `PLAIN`
-# - `SCRAM-SHA-256`
-# - `SCRAM-SHA-512`
-# [wal.sasl]
-# type = "SCRAM-SHA-512"
-# username = "user_kafka"
-# password = "secret"
-
-# The Kafka TLS configuration.
-# **It's only used when the provider is `kafka`**.
-# [wal.tls]
-# server_ca_cert_path = "/path/to/server_cert"
-# client_cert_path = "/path/to/client_cert"
-# client_key_path = "/path/to/key"
-
-## Metadata storage options.
-[metadata_store]
-## Kv file size in bytes.
+# Raft-engine wal options.
+# WAL data directory
+# dir = "/tmp/greptimedb/wal"
+# WAL file size in bytes.
 file_size = "256MB"
-## Kv purge threshold.
+# WAL purge threshold.
+purge_threshold = "4GB"
+# WAL purge interval in seconds.
+purge_interval = "10m"
+# WAL read batch size.
+read_batch_size = 128
+# Whether to sync log file after every write.
+sync_write = false
+# Whether to reuse logically truncated log files.
+enable_log_recycle = true
+# Whether to pre-create log files on start up
+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"]
+
+# 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 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 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"
+
+# Metadata storage options.
+[metadata_store]
+# Kv file size in bytes.
+file_size = "256MB"
+# 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"
 
-# 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"
-# credential = "base64-credential"
-# endpoint = "https://storage.googleapis.com"
-
-## The data storage options.
+# Storage options.
 [storage]
-## The working home directory.
+# The working home directory.
 data_home = "/tmp/greptimedb/"
-
-## 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.
+# Storage type.
 type = "File"
-
-## Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.
-## A local file directory, defaults to `{data_home}/object_cache/read`. An empty string means disabling.
-## @toml2docs:none-default
-#+ cache_path = ""
-
-## The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger.
-## @toml2docs:none-default
-cache_capacity = "5GiB"
-
-## 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 credential of the google cloud storage.
-## **It's only used when the storage type is `Gcs`**.
-## @toml2docs:none-default
-credential = "base64-credential"
-
-## 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"
-
-## The http client options to the storage.
-## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
-[storage.http_client]
-
-## The maximum idle connection per host allowed in the pool.
-pool_max_idle_per_host = 1024
-
-## The timeout for only the connect phase of a http client.
-connect_timeout = "30s"
-
-## The total request timeout, applied from when the request starts connecting until the response body has finished.
-## Also considered a total deadline.
-timeout = "30s"
-
-## The timeout for idle sockets being kept-alive.
-pool_idle_timeout = "90s"
+# 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"
 
 # Custom storage options
-# [[storage.providers]]
-# name = "S3"
-# type = "S3"
-# bucket = "greptimedb"
-# root = "data"
-# access_key_id = "test"
-# secret_access_key = "123456"
-# endpoint = "https://s3.amazonaws.com"
-# region = "us-west-2"
-# [[storage.providers]]
-# name = "Gcs"
-# type = "Gcs"
-# bucket = "greptimedb"
-# root = "data"
-# scope = "test"
-# credential_path = "123456"
-# credential = "base64-credential"
-# endpoint = "https://storage.googleapis.com"
+#[[storage.providers]]
+#type = "S3"
+#[[storage.providers]]
+#type = "Gcs"
 
-## The region engine options. You can configure multiple region engines.
+# Mito engine options
 [[region_engine]]
-
-## The Mito engine options.
 [region_engine.mito]
-
-## Number of region workers.
-#+ num_workers = 8
-
-## Request channel size of each worker.
+# Number of region workers
+num_workers = 8
+# 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 flush jobs (default: 1/2 of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_flushes = 4
-
-## Max number of running background compaction jobs (default: 1/4 of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_compactions = 2
-
-## Max number of running background purge jobs (default: number of cpu cores).
-## @toml2docs:none-default="Auto"
-#+ max_background_purges = 8
-
-## Interval to auto flush a region if it has not flushed yet.
+# Max number of running background jobs
+max_background_jobs = 4
+# 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.
-## @toml2docs:none-default="Auto"
-#+ 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`.
-## @toml2docs:none-default="Auto"
-#+ 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.
-## @toml2docs:none-default="Auto"
-#+ 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.
-## @toml2docs:none-default="Auto"
-#+ 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 1/8 of OS memory.
-## @toml2docs:none-default="Auto"
-#+ page_cache_size = "512MB"
-
-## Cache size for time series selector (e.g. `last_value()`). 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.
-## @toml2docs:none-default="Auto"
-#+ selector_result_cache_size = "512MB"
-
-## Whether to enable the experimental write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance.
-enable_experimental_write_cache = false
-
-## File system path for write cache, defaults to `{data_home}/object_cache/write`.
-experimental_write_cache_path = ""
-
-## Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger.
-experimental_write_cache_size = "5GiB"
-
-## TTL for write cache.
-## @toml2docs:none-default
-experimental_write_cache_ttl = "8h"
-
-## Buffer size for SST writing.
+# 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_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.
+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.
+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.
+page_cache_size = "512MB"
+# Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
-
-## Capacity of the channel to send data from parallel scan tasks to the main task.
+# 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).
 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
 
-## Minimum time interval between two compactions.
-## To align with the old behavior, the default value is 0 (no restrictions).
-min_compaction_interval = "0m"
-
-## The options for index in Mito engine.
-[region_engine.mito.index]
-
-## Auxiliary directory path for the index in filesystem, used to store intermediate files for
-## creating the index and staging files for searching the index, defaults to `{data_home}/index_intermediate`.
-## The default name for this directory is `index_intermediate` for backward compatibility.
-##
-## This path contains two subdirectories:
-## - `__intm`: for storing intermediate files used during creating index.
-## - `staging`: for storing staging files used during searching index.
-aux_path = ""
-
-## The max capacity of the staging directory.
-staging_size = "2GB"
-
-## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
-
-## Whether to create the index on flush.
-## - `auto`: automatically (default)
-## - `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 (default)
-## - `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 (default)
-## - `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.
-## - `auto`: automatically determine the threshold based on the system memory size (default)
-## - `unlimited`: no memory limit
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
-
-## Deprecated, use `region_engine.mito.index.aux_path` instead.
+# 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 = ""
 
-## Cache size for inverted index metadata.
-metadata_cache_size = "64MiB"
+# 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
 
-## Cache size for inverted index content.
-content_cache_size = "128MiB"
-
-## Page size for inverted index content cache.
-content_cache_page_size = "8MiB"
-
-## The options for full-text index in Mito engine.
-[region_engine.mito.fulltext_index]
-
-## Whether to create the index on flush.
-## - `auto`: automatically (default)
-## - `disable`: never
-create_on_flush = "auto"
-
-## Whether to create the index on compaction.
-## - `auto`: automatically (default)
-## - `disable`: never
-create_on_compaction = "auto"
-
-## Whether to apply the index on query
-## - `auto`: automatically (default)
-## - `disable`: never
-apply_on_query = "auto"
-
-## Memory threshold for index creation.
-## - `auto`: automatically determine the threshold based on the system memory size (default)
-## - `unlimited`: no memory limit
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
-
-[region_engine.mito.memtable]
-## Memtable type.
-## - `time_series`: time-series memtable
-## - `partition_tree`: partition tree memtable (experimental)
-type = "time_series"
-
-## 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"
-
-[[region_engine]]
-## Enable the file engine.
-[region_engine.file]
-
-## The logging options.
-[logging]
-## The directory to store the log files. If set to empty, logs will not be written to 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.
-otlp_endpoint = "http://localhost:4317"
-
-## Whether to append logs to stdout.
-append_stdout = true
-
-## The log format. Can be `text`/`json`.
-log_format = "text"
-
-## The maximum amount of log files.
-max_log_files = 720
-
-## 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 slow query log options.
-[logging.slow_query]
-## Whether to enable slow query log.
-enable = false
-
-## The threshold of slow query.
-## @toml2docs:none-default
-threshold = "10s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1].
-## @toml2docs:none-default
-sample_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 recommended to collect metrics generated by itself
-## You must create the database before enabling it.
-[export_metrics.self_import]
-## @toml2docs:none-default
-db = "greptime_metrics"
-
-[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=greptime_metrics`.
-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"
+# 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"

cyborg/.gitignore

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

cyborg/bin/check-pull-request.ts

@@ -1,79 +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.
- */
-
-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

@@ -1,106 +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.
- */
-
-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/report-ci-failure.ts

@@ -1,83 +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.
- */
-
-import * as core from '@actions/core'
-import {handleError, obtainClient} from "@/common"
-import {context} from "@actions/github"
-import _ from "lodash"
-
-async function main() {
-    const success = process.env["CI_REPORT_STATUS"] === "true"
-    core.info(`CI_REPORT_STATUS=${process.env["CI_REPORT_STATUS"]}, resolved to ${success}`)
-
-    const client = obtainClient("GITHUB_TOKEN")
-    const title = `Workflow run '${context.workflow}' failed`
-    const url = `${process.env["GITHUB_SERVER_URL"]}/${process.env["GITHUB_REPOSITORY"]}/actions/runs/${process.env["GITHUB_RUN_ID"]}`
-    const failure_comment = `@GreptimeTeam/db-approver\nNew failure: ${url} `
-    const success_comment = `@GreptimeTeam/db-approver\nBack to success: ${url}`
-
-    const {owner, repo} = context.repo
-    const labels = ['O-ci-failure']
-
-    const issues = await client.paginate(client.rest.issues.listForRepo, {
-        owner,
-        repo,
-        labels: labels.join(','),
-        state: "open",
-        sort: "created",
-        direction: "desc",
-    });
-    const issue = _.find(issues, (i) => i.title === title);
-
-    if (issue) { // exist issue
-        core.info(`Found previous issue ${issue.html_url}`)
-        if (!success) {
-            await client.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: issue.number,
-                body: failure_comment,
-            })
-        } else {
-            await client.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: issue.number,
-                body: success_comment,
-            })
-            await client.rest.issues.update({
-                owner,
-                repo,
-                issue_number: issue.number,
-                state: "closed",
-                state_reason: "completed",
-            })
-        }
-        core.setOutput("html_url", issue.html_url)
-    } else if (!success) { // create new issue for failure
-        const issue = await client.rest.issues.create({
-            owner,
-            repo,
-            title,
-            labels,
-            body: failure_comment,
-        })
-        core.info(`Created issue ${issue.data.html_url}`)
-        core.setOutput("html_url", issue.data.html_url)
-    }
-}
-
-main().catch(handleError)

cyborg/bin/schedule.ts

@@ -1,73 +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.
- */
-
-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

@@ -1,26 +0,0 @@
-{
-  "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

@@ -1,612 +0,0 @@
-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

@@ -1,30 +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.
- */
-
-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

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

docker/ci/centos/Dockerfile

@@ -1,9 +1,5 @@
 FROM centos:7
 
-# Note: CentOS 7 has reached EOL since 2024-07-01 thus `mirror.centos.org` is no longer available and we need to use `vault.centos.org` instead.
-RUN sed -i s/mirror.centos.org/vault.centos.org/g /etc/yum.repos.d/*.repo
-RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
-
 RUN yum install -y epel-release \
     openssl \
     openssl-devel  \

docker/ci/ubuntu/Dockerfile.fuzztests

@@ -1,16 +0,0 @@
-FROM ubuntu:22.04
-
-# The binary name of GreptimeDB executable.
-# Defaults to "greptime", but sometimes in other projects it might be different.
-ARG TARGET_BIN=greptime
-
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-    ca-certificates \
-    curl
-
-ARG BINARY_PATH
-ADD $BINARY_PATH/$TARGET_BIN /greptime/bin/
-
-ENV PATH /greptime/bin/:$PATH
-
-ENTRYPOINT ["greptime"]

docker/dev-builder/android/Dockerfile

@@ -34,7 +34,7 @@ RUN rustup toolchain install ${RUST_TOOLCHAIN}
 RUN rustup target add aarch64-linux-android
 
 # Install cargo-ndk
-RUN cargo install cargo-ndk@3.5.4
+RUN cargo install cargo-ndk
 ENV ANDROID_NDK_HOME $NDK_ROOT
 
 # Builder entrypoint.

docker/dev-builder/binstall/pull_binstall.sh

@@ -1,50 +0,0 @@
-#!/bin/bash
-
-set -euxo pipefail
-
-cd "$(mktemp -d)"
-# Fix version to v1.6.6, this is different than the latest version in original install script in
-# https://raw.githubusercontent.com/cargo-bins/cargo-binstall/main/install-from-binstall-release.sh
-base_url="https://github.com/cargo-bins/cargo-binstall/releases/download/v1.6.6/cargo-binstall-"
-
-os="$(uname -s)"
-if [ "$os" == "Darwin" ]; then
-    url="${base_url}universal-apple-darwin.zip"
-    curl -LO --proto '=https' --tlsv1.2 -sSf "$url"
-    unzip cargo-binstall-universal-apple-darwin.zip
-elif [ "$os" == "Linux" ]; then
-    machine="$(uname -m)"
-    if [ "$machine" == "armv7l" ]; then
-        machine="armv7"
-    fi
-    target="${machine}-unknown-linux-musl"
-    if [ "$machine" == "armv7" ]; then
-        target="${target}eabihf"
-    fi
-
-    url="${base_url}${target}.tgz"
-    curl -L --proto '=https' --tlsv1.2 -sSf "$url" | tar -xvzf -
-elif [ "${OS-}" = "Windows_NT" ]; then
-    machine="$(uname -m)"
-    target="${machine}-pc-windows-msvc"
-    url="${base_url}${target}.zip"
-    curl -LO --proto '=https' --tlsv1.2 -sSf "$url"
-    unzip "cargo-binstall-${target}.zip"
-else
-    echo "Unsupported OS ${os}"
-    exit 1
-fi
-
-./cargo-binstall -y --force cargo-binstall
-
-CARGO_HOME="${CARGO_HOME:-$HOME/.cargo}"
-
-if ! [[ ":$PATH:" == *":$CARGO_HOME/bin:"* ]]; then
-    if [ -n "${CI:-}" ] && [ -n "${GITHUB_PATH:-}" ]; then
-        echo "$CARGO_HOME/bin" >> "$GITHUB_PATH"
-    else
-        echo
-        printf "\033[0;31mYour path is missing %s, you might want to add it.\033[0m\n" "$CARGO_HOME/bin"
-        echo
-    fi
-fi

docker/dev-builder/centos/Dockerfile

@@ -2,10 +2,6 @@ FROM centos:7 as builder
 
 ENV LANG en_US.utf8
 
-# Note: CentOS 7 has reached EOL since 2024-07-01 thus `mirror.centos.org` is no longer available and we need to use `vault.centos.org` instead.
-RUN sed -i s/mirror.centos.org/vault.centos.org/g /etc/yum.repos.d/*.repo
-RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
-
 # Install dependencies
 RUN ulimit -n 1024000 && yum groupinstall -y 'Development Tools'
 RUN yum install -y epel-release  \
@@ -29,12 +25,6 @@ ENV PATH /opt/rh/rh-python38/root/usr/bin:/usr/local/bin:/root/.cargo/bin/:$PATH
 ARG RUST_TOOLCHAIN
 RUN rustup toolchain install ${RUST_TOOLCHAIN}
 
-
-# Install cargo-binstall with a specific version to adapt the current rust toolchain.
-# Note: if we use the latest version, we may encounter the following `use of unstable library feature 'io_error_downcast'` error.
-# compile from source take too long, so we use the precompiled binary instead
-COPY $DOCKER_BUILD_ROOT/docker/dev-builder/binstall/pull_binstall.sh /usr/local/bin/pull_binstall.sh
-RUN chmod +x /usr/local/bin/pull_binstall.sh && /usr/local/bin/pull_binstall.sh
-
 # Install nextest.
+RUN cargo install cargo-binstall --locked
 RUN cargo binstall cargo-nextest --no-confirm

docker/dev-builder/ubuntu/Dockerfile

@@ -15,8 +15,8 @@ RUN apt-get update && \
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     libssl-dev \
     tzdata \
+    protobuf-compiler \
     curl \
-    unzip \
     ca-certificates \
     git \
     build-essential \
@@ -24,29 +24,6 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     python3.10 \
     python3.10-dev
 
-ARG TARGETPLATFORM
-RUN echo "target platform: $TARGETPLATFORM"
-
-# Install protobuf, because the one in the apt is too old (v3.12).
-RUN if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v29.1/protoc-29.1-linux-aarch_64.zip && \
-    unzip protoc-29.1-linux-aarch_64.zip -d protoc3; \
-elif [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
-    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v29.1/protoc-29.1-linux-x86_64.zip && \
-    unzip protoc-29.1-linux-x86_64.zip -d protoc3; \
-fi
-RUN mv protoc3/bin/* /usr/local/bin/
-RUN mv protoc3/include/* /usr/local/include/
-
-# https://github.com/GreptimeTeam/greptimedb/actions/runs/10935485852/job/30357457188#step:3:7106
-# `aws-lc-sys` require gcc >= 10.3.0 to work, hence alias to use gcc-10
-RUN apt-get remove -y gcc-9 g++-9 cpp-9 && \
-    apt-get install -y gcc-10 g++-10 cpp-10 make cmake && \
-    ln -sf /usr/bin/gcc-10 /usr/bin/gcc && ln -sf /usr/bin/g++-10 /usr/bin/g++ && \
-    ln -sf /usr/bin/gcc-10 /usr/bin/cc && \
-    ln -sf /usr/bin/g++-10 /usr/bin/cpp && ln -sf /usr/bin/g++-10 /usr/bin/c++ && \
-    cc --version && gcc --version && g++ --version && cpp --version && c++ --version
-
 # Remove Python 3.8 and install pip.
 RUN apt-get -y purge python3.8 && \
     apt-get -y autoremove && \
@@ -63,7 +40,7 @@ RUN apt-get -y purge python3.8 && \
 # wildcard here. However, that requires the git's config files and the submodules all owned by the very same user.
 # It's troublesome to do this since the dev build runs in Docker, which is under user "root"; while outside the Docker,
 # it can be a different user that have prepared the submodules.
-RUN git config --global --add safe.directory '*'
+RUN git config --global --add safe.directory *
 
 # Install Python dependencies.
 COPY $DOCKER_BUILD_ROOT/docker/python/requirements.txt /etc/greptime/requirements.txt
@@ -78,11 +55,6 @@ ENV PATH /root/.cargo/bin/:$PATH
 ARG RUST_TOOLCHAIN
 RUN rustup toolchain install ${RUST_TOOLCHAIN}
 
-# Install cargo-binstall with a specific version to adapt the current rust toolchain.
-# Note: if we use the latest version, we may encounter the following `use of unstable library feature 'io_error_downcast'` error.
-# compile from source take too long, so we use the precompiled binary instead
-COPY $DOCKER_BUILD_ROOT/docker/dev-builder/binstall/pull_binstall.sh /usr/local/bin/pull_binstall.sh
-RUN chmod +x /usr/local/bin/pull_binstall.sh && /usr/local/bin/pull_binstall.sh
-
 # Install nextest.
+RUN cargo install cargo-binstall --locked
 RUN cargo binstall cargo-nextest --no-confirm

docker/dev-builder/ubuntu/Dockerfile-18.10

@@ -43,9 +43,6 @@ ENV PATH /root/.cargo/bin/:$PATH
 ARG RUST_TOOLCHAIN
 RUN rustup toolchain install ${RUST_TOOLCHAIN}
 
-# Install cargo-binstall with a specific version to adapt the current rust toolchain.
-# Note: if we use the latest version, we may encounter the following `use of unstable library feature 'io_error_downcast'` error.
-RUN cargo install cargo-binstall --version 1.6.6 --locked
-
 # Install nextest.
+RUN cargo install cargo-binstall --locked
 RUN cargo binstall cargo-nextest --no-confirm

docker/docker-compose/cluster-with-etcd.yaml

@@ -1,133 +0,0 @@
-x-custom:
-  etcd_initial_cluster_token: &etcd_initial_cluster_token "--initial-cluster-token=etcd-cluster"
-  etcd_common_settings: &etcd_common_settings
-    image: "${ETCD_REGISTRY:-quay.io}/${ETCD_NAMESPACE:-coreos}/etcd:${ETCD_VERSION:-v3.5.10}"
-    entrypoint: /usr/local/bin/etcd
-  greptimedb_image: &greptimedb_image "${GREPTIMEDB_REGISTRY:-docker.io}/${GREPTIMEDB_NAMESPACE:-greptime}/greptimedb:${GREPTIMEDB_VERSION:-latest}"
-
-services:
-  etcd0:
-    <<: *etcd_common_settings
-    container_name: etcd0
-    ports:
-      - 2379:2379
-      - 2380:2380
-    command:
-      - --name=etcd0
-      - --data-dir=/var/lib/etcd
-      - --initial-advertise-peer-urls=http://etcd0:2380
-      - --listen-peer-urls=http://0.0.0.0:2380
-      - --listen-client-urls=http://0.0.0.0:2379
-      - --advertise-client-urls=http://etcd0:2379
-      - --heartbeat-interval=250
-      - --election-timeout=1250
-      - --initial-cluster=etcd0=http://etcd0:2380
-      - --initial-cluster-state=new
-      - *etcd_initial_cluster_token
-    volumes:
-      - /tmp/greptimedb-cluster-docker-compose/etcd0:/var/lib/etcd
-    healthcheck:
-      test: [ "CMD", "etcdctl", "--endpoints=http://etcd0:2379", "endpoint", "health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    networks:
-      - greptimedb
-
-  metasrv:
-    image: *greptimedb_image
-    container_name: metasrv
-    ports:
-      - 3002:3002
-    command:
-      - metasrv
-      - start
-      - --bind-addr=0.0.0.0:3002
-      - --server-addr=metasrv:3002
-      - --store-addrs=etcd0:2379
-    healthcheck:
-      test: [ "CMD", "curl", "-f", "http://metasrv:3002/health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    depends_on:
-      etcd0:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-  datanode0:
-    image: *greptimedb_image
-    container_name: datanode0
-    ports:
-      - 3001:3001
-      - 5000:5000
-    command:
-      - datanode
-      - start
-      - --node-id=0
-      - --rpc-addr=0.0.0.0:3001
-      - --rpc-hostname=datanode0:3001
-      - --metasrv-addrs=metasrv:3002
-      - --http-addr=0.0.0.0:5000
-    volumes:
-      - /tmp/greptimedb-cluster-docker-compose/datanode0:/tmp/greptimedb
-    healthcheck:
-      test: [ "CMD", "curl", "-f", "http://datanode0:5000/health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    depends_on:
-      metasrv:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-  frontend0:
-    image: *greptimedb_image
-    container_name: frontend0
-    ports:
-      - 4000:4000
-      - 4001:4001
-      - 4002:4002
-      - 4003:4003
-    command:
-      - frontend
-      - start
-      - --metasrv-addrs=metasrv:3002
-      - --http-addr=0.0.0.0:4000
-      - --rpc-addr=0.0.0.0:4001
-      - --mysql-addr=0.0.0.0:4002
-      - --postgres-addr=0.0.0.0:4003
-    healthcheck:
-      test: [ "CMD", "curl", "-f", "http://frontend0:4000/health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    depends_on:
-      datanode0:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-  flownode0:
-    image: *greptimedb_image
-    container_name: flownode0
-    ports:
-      - 4004:4004
-    command:
-      - flownode
-      - start
-      - --node-id=0
-      - --metasrv-addrs=metasrv:3002
-      - --rpc-addr=0.0.0.0:4004
-      - --rpc-hostname=flownode0:4004
-    depends_on:
-      frontend0:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-networks:
-  greptimedb:
-    name: greptimedb

docs/benchmarks/log/README.md

@@ -1,51 +0,0 @@
-# Log benchmark configuration
-This repo holds the configuration we used to benchmark GreptimeDB, Clickhouse and Elastic Search.
-
-Here are the versions of databases we used in the benchmark
-
-| name          | version    |
-| :------------ | :--------- |
-| GreptimeDB    | v0.9.2     |
-| Clickhouse    | 24.9.1.219 |
-| Elasticsearch | 8.15.0     |
-
-## Structured model vs Unstructured model
-We divide test into two parts, using structured model and unstructured model accordingly. You can also see the difference in create table clause.
-
-__Structured model__
-
-The log data is pre-processed into columns by vector. For example an insert request looks like following
-```SQL
-INSERT INTO test_table (bytes, http_version, ip, method, path, status, user, timestamp) VALUES ()
-```
-The goal is to test string/text support for each database. In real scenarios it means the datasource(or log data producers) have separate fields defined, or have already processed the raw input.
-
-__Unstructured model__
-
-The log data is inserted as a long string, and then we build fulltext index upon these strings. For example an insert request looks like following
-```SQL
-INSERT INTO test_table (message, timestamp) VALUES ()
-```
-The goal is to test fuzzy search performance for each database. In real scenarios it means the log is produced by some kind of middleware and inserted directly into the database.
-
-## Creating tables
-See [here](./create_table.sql) for GreptimeDB and Clickhouse's create table clause.
-The mapping of Elastic search is created automatically.
-
-## Vector Configuration
-We use vector to generate random log data and send inserts to databases.
-Please refer to [structured config](./structured_vector.toml) and [unstructured config](./unstructured_vector.toml) for detailed configuration.
-
-## SQLs and payloads
-Please refer to [SQL query](./query.sql) for GreptimeDB and Clickhouse, and [query payload](./query.md) for Elastic search.
-
-## Steps to reproduce
-0. Decide whether to run structured model test or unstructured mode test.
-1. Build vector binary(see vector's config file for specific branch) and databases binaries accordingly.
-2. Create table in GreptimeDB and Clickhouse in advance.
-3. Run vector to insert data.
-4. When data insertion is finished, run queries against each database. Note: you'll need to update timerange value after data insertion.
-
-## Addition
-- You can tune GreptimeDB's configuration to get better performance.
-- You can setup GreptimeDB to use S3 as storage, see [here](https://docs.greptime.com/user-guide/deployments/configuration#storage-options).

docs/benchmarks/log/create_table.sql

@@ -1,56 +0,0 @@
--- GreptimeDB create table clause
--- structured test, use vector to pre-process log data into fields
-CREATE TABLE IF NOT EXISTS `test_table` (
-    `bytes` Int64 NULL,
-    `http_version` STRING NULL,
-    `ip` STRING NULL,
-    `method` STRING NULL,
-    `path` STRING NULL,
-    `status` SMALLINT UNSIGNED NULL,
-    `user` STRING NULL,
-    `timestamp` TIMESTAMP(3) NOT NULL,
-    PRIMARY KEY (`user`, `path`, `status`),
-    TIME INDEX (`timestamp`)
-)
-ENGINE=mito
-WITH(
-    append_mode = 'true'
-);
-
--- unstructured test, build fulltext index on message column
-CREATE TABLE IF NOT EXISTS `test_table` (
-    `message` STRING NULL FULLTEXT WITH(analyzer = 'English', case_sensitive = 'false'),
-    `timestamp` TIMESTAMP(3) NOT NULL,
-    TIME INDEX (`timestamp`)
-)
-ENGINE=mito
-WITH(
-    append_mode = 'true'
-);
-
--- Clickhouse create table clause
--- structured test
-CREATE TABLE IF NOT EXISTS test_table
-(
-    bytes UInt64 NOT NULL,
-    http_version String NOT NULL,
-    ip String NOT NULL,
-    method String NOT NULL,
-    path String NOT NULL,
-    status UInt8 NOT NULL,
-    user String NOT NULL,
-    timestamp String NOT NULL,
-)
-ENGINE = MergeTree()
-ORDER BY (user, path, status);
-
--- unstructured test
-SET allow_experimental_full_text_index = true;
-CREATE TABLE IF NOT EXISTS test_table
-(
-    message String,
-    timestamp String,
-    INDEX inv_idx(message) TYPE full_text(0) GRANULARITY 1
-)
-ENGINE = MergeTree()
-ORDER BY tuple();

docs/benchmarks/log/query.md

@@ -1,199 +0,0 @@
-# Query URL and payload for Elastic Search
-## Count
-URL: `http://127.0.0.1:9200/_count`
-
-## Query by timerange
-URL: `http://127.0.0.1:9200/_search`
-
-You can use the following payload to get the full timerange first.
-```JSON
-{"size":0,"aggs":{"max_timestamp":{"max":{"field":"timestamp"}},"min_timestamp":{"min":{"field":"timestamp"}}}}
-```
-
-And then use this payload to query by timerange.
-```JSON
-{
-  "from": 0,
-  "size": 1000,
-  "query": {
-    "range": {
-      "timestamp": {
-        "gte": "2024-08-16T04:30:44.000Z",
-        "lte": "2024-08-16T04:51:52.000Z"
-      }
-    }
-  }
-}
-```
-
-## Query by condition
-URL: `http://127.0.0.1:9200/_search`
-### Structured payload
-```JSON
-{
-  "from": 0,
-  "size": 10000,
-  "query": {
-    "bool": {
-      "must": [
-        {
-          "term": {
-            "user.keyword": "CrucifiX"
-          }
-        },
-        {
-          "term": {
-            "method.keyword": "OPTION"
-          }
-        },
-        {
-          "term": {
-            "path.keyword": "/user/booperbot124"
-          }
-        },
-        {
-          "term": {
-            "http_version.keyword": "HTTP/1.1"
-          }
-        },
-        {
-          "term": {
-            "status": "401"
-          }
-        }
-      ]
-    }
-  }
-}
-```
-### Unstructured payload
-```JSON
-{
-  "from": 0,
-  "size": 10000,
-  "query": {
-    "bool": {
-      "must": [
-        {
-          "match_phrase": {
-            "message": "CrucifiX"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "OPTION"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "/user/booperbot124"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "HTTP/1.1"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "401"
-          }
-        }
-      ]
-    }
-  }
-}
-```
-
-## Query by condition and timerange
-URL: `http://127.0.0.1:9200/_search`
-### Structured payload
-```JSON
-{
-  "size": 10000,
-  "query": {
-    "bool": {
-      "must": [
-        {
-          "term": {
-            "user.keyword": "CrucifiX"
-          }
-        },
-        {
-          "term": {
-            "method.keyword": "OPTION"
-          }
-        },
-        {
-          "term": {
-            "path.keyword": "/user/booperbot124"
-          }
-        },
-        {
-          "term": {
-            "http_version.keyword": "HTTP/1.1"
-          }
-        },
-        {
-          "term": {
-            "status": "401"
-          }
-        },
-        {
-          "range": {
-            "timestamp": {
-              "gte": "2024-08-19T07:03:37.383Z",
-              "lte": "2024-08-19T07:24:58.883Z"
-            }
-          }
-        }
-      ]
-    }
-  }
-}
-```
-### Unstructured payload
-```JSON
-{
-  "size": 10000,
-  "query": {
-    "bool": {
-      "must": [
-        {
-          "match_phrase": {
-            "message": "CrucifiX"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "OPTION"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "/user/booperbot124"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "HTTP/1.1"
-          }
-        },
-        {
-          "match_phrase": {
-            "message": "401"
-          }
-        },
-        {
-          "range": {
-            "timestamp": {
-              "gte": "2024-08-19T05:16:17.099Z",
-              "lte": "2024-08-19T05:46:02.722Z"
-            }
-          }
-        }
-      ]
-    }
-  }
-}
-```

docs/benchmarks/log/query.sql

@@ -1,50 +0,0 @@
--- Structured query for GreptimeDB and Clickhouse
-
--- query count
-select count(*) from test_table;
-
--- query by timerange. Note: place the timestamp range in the where clause
--- GreptimeDB
--- you can use `select max(timestamp)::bigint from test_table;` and `select min(timestamp)::bigint from test_table;`
--- to get the full timestamp range
-select * from test_table where timestamp between 1723710843619 and 1723711367588;
--- Clickhouse
--- you can use `select max(timestamp) from test_table;` and `select min(timestamp) from test_table;`
--- to get the full timestamp range
-select * from test_table where timestamp between '2024-08-16T03:58:46Z' and '2024-08-16T04:03:50Z';
-
--- query by condition
-SELECT * FROM test_table WHERE user = 'CrucifiX' and method = 'OPTION' and path = '/user/booperbot124' and http_version = 'HTTP/1.1' and status = 401;
-
--- query by condition and timerange
--- GreptimeDB
-SELECT * FROM test_table WHERE user = "CrucifiX" and method = "OPTION" and path = "/user/booperbot124" and http_version = "HTTP/1.1" and status = 401 
-and timestamp between 1723774396760 and 1723774788760;
--- Clickhouse
-SELECT * FROM test_table WHERE user = 'CrucifiX' and method = 'OPTION' and path = '/user/booperbot124' and http_version = 'HTTP/1.1' and status = 401 
-and timestamp between '2024-08-16T03:58:46Z' and '2024-08-16T04:03:50Z';
-
--- Unstructured query for GreptimeDB and Clickhouse
-
-
--- query by condition
--- GreptimeDB
-SELECT * FROM test_table WHERE MATCHES(message, "+CrucifiX +OPTION +/user/booperbot124 +HTTP/1.1 +401");
--- Clickhouse
-SELECT * FROM test_table WHERE (message LIKE '%CrucifiX%') 
-AND (message LIKE '%OPTION%') 
-AND (message LIKE '%/user/booperbot124%') 
-AND (message LIKE '%HTTP/1.1%') 
-AND (message LIKE '%401%');
-
--- query by condition and timerange
--- GreptimeDB
-SELECT * FROM test_table WHERE MATCHES(message, "+CrucifiX +OPTION +/user/booperbot124 +HTTP/1.1 +401") 
-and timestamp between 1723710843619 and 1723711367588;
--- Clickhouse
-SELECT * FROM test_table WHERE (message LIKE '%CrucifiX%') 
-AND (message LIKE '%OPTION%') 
-AND (message LIKE '%/user/booperbot124%') 
-AND (message LIKE '%HTTP/1.1%') 
-AND (message LIKE '%401%') 
-AND timestamp between '2024-08-15T10:25:26.524000000Z' AND '2024-08-15T10:31:31.746000000Z';

docs/benchmarks/log/structured_vector.toml

@@ -1,57 +0,0 @@
-# Please note we use patched branch to build vector
-# https://github.com/shuiyisong/vector/tree/chore/greptime_log_ingester_logitem
-
-[sources.demo_logs]
-type = "demo_logs"
-format = "apache_common"
-# interval value = 1 / rps
-# say you want to insert at 20k/s, that is 1 / 20000 = 0.00005
-# set to 0 to run as fast as possible
-interval = 0
-# total rows to insert
-count = 100000000
-lines = [ "line1" ]
-
-[transforms.parse_logs]
-type = "remap"
-inputs = ["demo_logs"]
-source = '''
-. = parse_regex!(.message, r'^(?P<ip>\S+) - (?P<user>\S+) \[(?P<timestamp>[^\]]+)\] "(?P<method>\S+) (?P<path>\S+) (?P<http_version>\S+)" (?P<status>\d+) (?P<bytes>\d+)$')
-
-# Convert timestamp to a standard format
-.timestamp = parse_timestamp!(.timestamp, format: "%d/%b/%Y:%H:%M:%S %z")
-
-# Convert status and bytes to integers
-.status = to_int!(.status)
-.bytes = to_int!(.bytes)
-'''
-
-[sinks.sink_greptime_logs]
-type = "greptimedb_logs"
-# The table to insert into
-table = "test_table"
-pipeline_name = "demo_pipeline"
-compression = "none"
-inputs = [ "parse_logs" ]
-endpoint = "http://127.0.0.1:4000"
-# Batch size for each insertion
-batch.max_events = 4000
-
-[sinks.clickhouse]
-type = "clickhouse"
-inputs = [ "parse_logs" ]
-database = "default"
-endpoint = "http://127.0.0.1:8123"
-format = "json_each_row"
-# The table to insert into
-table = "test_table"
-
-[sinks.sink_elasticsearch]
-type = "elasticsearch"
-inputs = [ "parse_logs" ]
-api_version = "auto"
-compression = "none"
-doc_type = "_doc"
-endpoints = [ "http://127.0.0.1:9200" ]
-id_key = "id"
-mode = "bulk"

docs/benchmarks/log/unstructured_vector.toml

@@ -1,43 +0,0 @@
-# Please note we use patched branch to build vector
-# https://github.com/shuiyisong/vector/tree/chore/greptime_log_ingester_ft
-
-[sources.demo_logs]
-type = "demo_logs"
-format = "apache_common"
-# interval value = 1 / rps
-# say you want to insert at 20k/s, that is 1 / 20000 = 0.00005
-# set to 0 to run as fast as possible
-interval = 0
-# total rows to insert
-count = 100000000
-lines = [ "line1" ]
-
-[sinks.sink_greptime_logs]
-type = "greptimedb_logs"
-# The table to insert into
-table = "test_table"
-pipeline_name = "demo_pipeline"
-compression = "none"
-inputs = [ "demo_logs" ]
-endpoint = "http://127.0.0.1:4000"
-# Batch size for each insertion
-batch.max_events = 500
-
-[sinks.clickhouse]
-type = "clickhouse"
-inputs = [ "demo_logs" ]
-database = "default"
-endpoint = "http://127.0.0.1:8123"
-format = "json_each_row"
-# The table to insert into
-table = "test_table"
-
-[sinks.sink_elasticsearch]
-type = "elasticsearch"
-inputs = [ "demo_logs" ]
-api_version = "auto"
-compression = "none"
-doc_type = "_doc"
-endpoints = [ "http://127.0.0.1:9200" ]
-id_key = "id"
-mode = "bulk"

docs/benchmarks/tsbs/README.md

@@ -1,253 +0,0 @@
-# How to run TSBS Benchmark
-
-This document contains the steps to run TSBS Benchmark. Our results are listed in other files in the same directory.
-
-## Prerequires
-
-You need the following tools to run TSBS Benchmark:
-- Go
-- git
-- make
-- rust (optional, if you want to build the DB from source)
-
-## Build TSBS suite
-
-Clone our fork of TSBS:
-
-```shell
-git clone https://github.com/GreptimeTeam/tsbs.git
-```
-
-Then build it:
-
-```shell
-cd tsbs
-make
-```
-
-You can check the `bin/` directory for compiled binaries. We will only use some of them.
-
-```shell
-ls ./bin/
-```
-
-Binaries we will use later:
-- `tsbs_generate_data`
-- `tsbs_generate_queries`
-- `tsbs_load_greptime`
-- `tsbs_run_queries_influx`
-
-## Generate test data and queries
-
-The data is generated by `tsbs_generate_data`
-
-```shell
-mkdir bench-data
-./bin/tsbs_generate_data --use-case="cpu-only" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:00Z" \
-    --log-interval="10s" --format="influx" \
-    > ./bench-data/influx-data.lp
-```
-
-Here we generates 4000 time-series in 3 days with 10s interval. We'll use influx line protocol to write so the target format is `influx`.
-
-Queries are generated by `tsbs_generate_queries`. You can change the parameters but need to make sure it matches with `tsbs_generate_data`.
-
-```shell
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type cpu-max-all-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-cpu-max-all-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type cpu-max-all-8 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-cpu-max-all-8.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=50 \
-    --query-type double-groupby-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-double-groupby-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=50 \
-    --query-type double-groupby-5 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-double-groupby-5.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=50 \
-    --query-type double-groupby-all \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-double-groupby-all.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=50 \
-    --query-type groupby-orderby-limit \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-groupby-orderby-limit.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type high-cpu-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-high-cpu-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=50 \
-    --query-type high-cpu-all \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-high-cpu-all.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=10 \
-    --query-type lastpoint \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-lastpoint.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-1-1-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-1-1-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-1-1-12 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-1-1-12.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-1-8-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-1-8-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-5-1-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-5-1-1.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-5-1-12 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-5-1-12.dat
-./bin/tsbs_generate_queries \
-    --use-case="devops" --seed=123 --scale=4000 \
-    --timestamp-start="2023-06-11T00:00:00Z" \
-    --timestamp-end="2023-06-14T00:00:01Z" \
-    --queries=100 \
-    --query-type single-groupby-5-8-1 \
-    --format="greptime" \
-    > ./bench-data/greptime-queries-single-groupby-5-8-1.dat
-```
-
-## Start GreptimeDB
-
-Reference to our [document](https://docs.greptime.com/getting-started/installation/overview) for how to install and start a GreptimeDB. Or you can also check this [document](https://docs.greptime.com/contributor-guide/getting-started#compile-and-run) for how to build a GreptimeDB from source.
-
-## Write Data
-
-After the DB is started, we can use `tsbs_load_greptime` to test the write performance.
-
-```shell
-./bin/tsbs_load_greptime \
-    --urls=http://localhost:4000 \
-    --file=./bench-data/influx-data.lp \
-    --batch-size=3000 \
-    --gzip=false \
-    --workers=6
-```
-
-Parameters here are only provided as an example. You can choose whatever you like or adjust them to match your target scenario.
-
-Notice that if you want to rerun `tsbs_load_greptime`, please destroy and restart the DB and clear its previous data first. Existing duplicated data will impact the write and query performance.
-
-## Query Data
-
-After the data is imported, you can then run queries. The following script runs all queries. You can also choose a subset of queries to run.
-
-```shell
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-cpu-max-all-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-cpu-max-all-8.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-double-groupby-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-double-groupby-5.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-double-groupby-all.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-groupby-orderby-limit.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-high-cpu-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-high-cpu-all.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-lastpoint.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-1-1-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-1-1-12.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-1-8-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-5-1-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-5-1-12.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-./bin/tsbs_run_queries_influx --file=./bench-data/greptime-queries-single-groupby-5-8-1.dat \
-    --db-name=benchmark \
-    --urls="http://localhost:4000"
-```
-
-Rerun queries need not to re-import data. Just execute the corresponding command again is fine.