Revert "build(deps): upgrade opendal to 0.46 (#4037)"

This reverts commit f9db5ff0d6.

.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

.env.example

@@ -18,7 +18,6 @@ GT_AZBLOB_ENDPOINT=AZBLOB endpoint
 GT_GCS_BUCKET = GCS bucket 
 GT_GCS_SCOPE  = GCS scope
 GT_GCS_CREDENTIAL_PATH = GCS credential path 
-GT_GCS_CREDENTIAL = GCS credential
 GT_GCS_ENDPOINT = GCS end point
 # Settings for kafka wal test
 GT_KAFKA_ENDPOINTS = localhost:9092
@@ -29,8 +28,3 @@ 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/actions/build-dev-builder-images/action.yml

@@ -50,7 +50,7 @@ runs:
           BUILDX_MULTI_PLATFORM_BUILD=all \
           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
@@ -61,7 +61,7 @@ runs:
           BUILDX_MULTI_PLATFORM_BUILD=amd64 \
           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=${{ inputs.base-image }} \
+          BASE_IMAGE=${{ inputs.base-image }}
-          IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-          IMAGE_REGISTRY=${{ inputs.image-registry }}
 
     - 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 \
+        cd ${{ inputs.working-dir }} && make strip-android-bin
-          IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-          IMAGE_REGISTRY=${{ inputs.image-registry }}
 
     - name: Upload android artifacts
       uses: ./.github/actions/upload-artifacts

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

@@ -17,12 +17,6 @@ inputs:
     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
   working-dir:
     description: Working directory to build the artifacts
     required: false
@@ -36,9 +30,7 @@ runs:
       # NOTE: If the BUILD_JOBS > 4, it's always OOM in EC2 instance.
       run: |
         cd ${{ inputs.working-dir }} && \
-        make run-it-in-container BUILD_JOBS=4 \
+        make run-it-in-container BUILD_JOBS=4
-        IMAGE_NAMESPACE=${{ inputs.image-namespace }} \
-        IMAGE_REGISTRY=${{ inputs.image-registry }}
 
     - name: Upload sqlness logs
       if: ${{ failure() && inputs.disable-run-tests == 'false' }} # Only upload logs when the integration tests failed.
@@ -57,8 +49,6 @@ runs:
         artifacts-dir: greptime-linux-${{ 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
@@ -88,8 +76,6 @@ 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
@@ -100,5 +86,3 @@ runs:
         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' }}
@@ -55,16 +59,9 @@ 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
 
@@ -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
@@ -58,14 +62,13 @@ runs:
       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
       with:
         name: sqlness-logs
-        path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
+        path: /tmp/greptime-*.log
         retention-days: 3
 
     - name: Build greptime binary

.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-etcd-cluster/action.yml

@@ -2,7 +2,7 @@ name: Setup Etcd cluster
 description: Deploy Etcd cluster on Kubernetes
 inputs:
   etcd-replicas:
-    default: 1
+    default: 3
     description: "Etcd replicas"
   namespace:
     default: "etcd-cluster"
@@ -18,8 +18,6 @@ runs:
         --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 \

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

@@ -22,21 +22,13 @@ inputs:
   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: |
+    run: |
       helm repo add greptime https://greptimeteam.github.io/helm-charts/ 
       helm repo update
       helm upgrade \
@@ -52,7 +44,6 @@ runs:
       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=${{ inputs.image-tag }} \
@@ -66,7 +57,6 @@ runs:
         greptime/greptimedb-cluster \
         --create-namespace \
         -n my-greptimedb \
-        --values ./.github/actions/setup-greptimedb-cluster/${{ inputs.values-filename }} \
         --wait \
         --wait-for-jobs
   - name: Wait for GreptimeDB

.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

@@ -1,24 +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 listeners.controller.protocol=PLAINTEXT \
-        --set listeners.client.protocol=PLAINTEXT \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

.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/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/workflows/apidoc.yml

@@ -12,6 +12,9 @@ on:
 
 name: Build API docs
 
+env:
+  RUST_TOOLCHAIN: nightly-2024-04-20
+
 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

.github/workflows/dev-build.yml

@@ -177,8 +177,6 @@ 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 +206,6 @@ 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

.github/workflows/develop.yml

@@ -29,6 +29,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
+env:
+  RUST_TOOLCHAIN: nightly-2024-04-20
+
 jobs:
   check-typos-and-docs:
     name: Check typos and docs
@@ -61,7 +64,9 @@ 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 }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
@@ -77,7 +82,9 @@ 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:
@@ -100,7 +107,9 @@ 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 }}
       - uses: Swatinem/rust-cache@v2
         with:
           # Shares across multiple jobs
@@ -130,29 +139,17 @@ jobs:
     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
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
@@ -163,16 +160,14 @@ jobs:
         run: |
           sudo apt-get install -y libfuzzer-14-dev
           rustup install nightly
-          cargo +nightly install cargo-fuzz cargo-gc-bin
+          cargo +nightly install cargo-fuzz
       - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
           name: bins
           path: .
       - name: Unzip binaries
-        run: |
+        run: tar -xvf ./bins.tar.gz
-          tar -xvf ./bins.tar.gz
-          rm ./bins.tar.gz
       - name: Run GreptimeDB
         run: |
           ./bins/greptime standalone start&
@@ -187,30 +182,19 @@ jobs:
 
   unstable-fuzztest:
     name: Unstable Fuzz Test
-    needs: build-greptime-ci
+    needs: build
     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
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
@@ -220,22 +204,27 @@ jobs:
         shell: bash
         run: |
           sudo apt update && sudo apt install -y libfuzzer-14-dev
-          cargo install cargo-fuzz cargo-gc-bin
+          cargo install cargo-fuzz
-      - name: Download pre-built binariy
+      - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
-          name: bin
+          name: bins
           path: .
-      - name: Unzip bianry
+      - name: Unzip binaries
+        run: tar -xvf ./bins.tar.gz
+      - name: Build Fuzz Test
+        shell: bash
         run: |
-          tar -xvf ./bin.tar.gz
+          cd tests-fuzz &
-          rm ./bin.tar.gz
+          cargo install cargo-gc-bin &
+          cargo gc &
+          cd ..
       - 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_BINARY_PATH: ./bins/greptime
           GT_FUZZ_INSTANCE_ROOT_DIR: /tmp/unstable-greptime/
         with:
           target: ${{ matrix.target }}
@@ -261,7 +250,9 @@ 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 }}
       - uses: Swatinem/rust-cache@v2
         with:
           # Shares across multiple jobs
@@ -269,17 +260,10 @@ jobs:
       - name: Install cargo-gc-bin
         shell: bash
         run: cargo install cargo-gc-bin
-      - name: Check aws-lc-sys will not build
-        shell: bash
-        run: |
-             if cargo tree -i aws-lc-sys -e features | grep -q aws-lc-sys; then
-               echo "Found aws-lc-sys, which has compilation problems on older gcc versions. Please replace it with ring until its building experience improves."
-               exit 1
-             fi
       - name: Build greptime bianry
         shell: bash
         # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc --profile ci -- --bin greptime
+        run: cargo build --bin greptime --profile ci
       - name: Pack greptime binary
         shell: bash
         run: |
@@ -294,49 +278,25 @@ jobs:
           version: current
 
   distributed-fuzztest: 
-    name: Fuzz Test (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
+    name: Fuzz Test (Distributed, Disk)
     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
-      - name: Setup Postgres cluser
-        uses: ./.github/actions/setup-postgres-cluster
       # Prepares for fuzz tests
       - 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:
@@ -347,7 +307,7 @@ jobs:
         run: |
           sudo apt-get install -y libfuzzer-14-dev
           rustup install nightly
-          cargo +nightly install cargo-fuzz cargo-gc-bin
+          cargo +nightly install cargo-fuzz
       # Downloads ci image
       - name: Download pre-built binariy
         uses: actions/download-artifact@v4
@@ -355,9 +315,7 @@ jobs:
           name: bin
           path: .
       - name: Unzip binary
-        run: |
+        run: tar -xvf ./bin.tar.gz
-          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
@@ -367,22 +325,6 @@ jobs:
             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
@@ -391,7 +333,6 @@ jobs:
         uses: ./.github/actions/setup-greptimedb-cluster
         with:
           image-registry: localhost:5001
-          values-filename: ${{ matrix.mode.values }}
       - name: Port forward (mysql)
         run: |
           kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
@@ -417,191 +358,21 @@ jobs:
         if: failure()
         uses: actions/upload-artifact@v4
         with:
-          name: fuzz-tests-kind-logs-${{ matrix.mode.name }}-${{ matrix.target }}
+          name: fuzz-tests-kind-logs-${{ 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
-      - name: Setup Postgres cluser
-        uses: ./.github/actions/setup-postgres-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:
@@ -610,12 +381,42 @@ jobs:
       - name: Unzip binaries
         run: tar -xvf ./bins.tar.gz
       - name: Run sqlness
-        run: RUST_BACKTRACE=1 ./bins/sqlness-runner ${{ matrix.mode.opts }} -c ./tests/cases --bins-dir ./bins --preserve-state
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -c ./tests/cases --bins-dir ./bins --preserve-state
       - name: Upload sqlness logs
-        if: failure()
+        if: always()
         uses: actions/upload-artifact@v4
         with:
-          name: sqlness-logs-${{ matrix.mode.name }}
+          name: sqlness-logs
+          path: /tmp/sqlness*
+          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 --preserve-state
+      - name: Upload sqlness logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: sqlness-logs-with-kafka-wal
           path: /tmp/sqlness*
           retention-days: 3
 
@@ -628,16 +429,17 @@ 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:
           # Shares across multiple jobs
           shared-key: "check-rust-fmt"
-      - name: Check format
+      - name: Run cargo fmt
-        run: make fmt-check
+        run: cargo fmt --all -- --check
 
   clippy:
     name: Clippy
@@ -648,8 +450,9 @@ 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 }}
           components: clippy
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
@@ -673,8 +476,9 @@ 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
@@ -694,19 +498,13 @@ 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:
@@ -717,15 +515,8 @@ jobs:
           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_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

.github/workflows/docs.yml

@@ -67,13 +67,19 @@ jobs:
       - run: 'echo "No action required"'
 
   sqlness:
-    name: Sqlness Test (${{ matrix.mode.name }})
+    name: Sqlness Test
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-20.04 ]
+    steps:
+      - run: 'echo "No action required"'
+
+  sqlness-kafka-wal:
+    name: Sqlness Test with Kafka Wal
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ ubuntu-20.04 ]
-        mode:
-          - name: "Basic"
-          - name: "Remote WAL"
     steps:
       - run: 'echo "No action required"'

.github/workflows/nightly-build.yml

@@ -154,8 +154,6 @@ 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 +173,6 @@ 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
@@ -203,7 +199,7 @@ jobs:
           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
@@ -244,7 +240,7 @@ 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

.github/workflows/nightly-ci.yml

@@ -9,6 +9,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
+env:
+  RUST_TOOLCHAIN: nightly-2024-04-20
+
 permissions:
   issues: write
 
@@ -30,13 +33,6 @@ jobs:
           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
@@ -49,19 +45,19 @@ 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 }}
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Run sqlness
-        run: make sqlness-test
+        run: cargo sqlness
-        env:
-          SQLNESS_OPTS: "--preserve-state"
       - name: Upload sqlness logs
-        if: failure()
+        if: always()
         uses: actions/upload-artifact@v4
         with:
           name: sqlness-logs
-          path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
+          path: /tmp/greptime-*.log
           retention-days: 3
 
   test-on-windows:
@@ -80,8 +76,9 @@ jobs:
         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
@@ -92,7 +89,7 @@ jobs:
         with:
           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:
@@ -112,7 +109,11 @@ jobs:
 
   check-status:
     name: Check status
-    needs: [sqlness-test, sqlness-windows, test-on-windows]
+    needs: [
+      sqlness-test,
+      sqlness-windows,
+      test-on-windows,
+    ]
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     runs-on: ubuntu-20.04
     outputs:
@@ -126,7 +127,9 @@ jobs:
   notification:
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
-    needs: [check-status]
+    needs: [
+      check-status
+    ]
     runs-on: ubuntu-20.04
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}

.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:-$HOME/.docker}:/root/.docker:ro" \
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }} \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            quay.io/skopeo/stable:latest \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }}
-            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 }}
 
       - 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:-$HOME/.docker}:/root/.docker:ro" \
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }} \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            quay.io/skopeo/stable:latest \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }}
-            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 }}
 
       - 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:-$HOME/.docker}:/root/.docker:ro" \
+          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }} \
-            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            quay.io/skopeo/stable:latest \
+            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }}
-            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 }}

.github/workflows/release.yml

@@ -33,7 +33,6 @@ on:
         description: The runner uses to build linux-arm64 artifacts
         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-2024-04-20
   CARGO_PROFILE: nightly
 
   # Controls whether to run tests, include unit-test, integration-test and sqlness.
@@ -91,7 +91,7 @@ env:
   # The scheduled version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD', like v0.2.0-nigthly-20230313;
   NIGHTLY_RELEASE_PREFIX: nightly
   # Note: The NEXT_RELEASE_VERSION should be modified manually by every formal release.
-  NEXT_RELEASE_VERSION: v0.10.0
+  NEXT_RELEASE_VERSION: v0.9.0
 
 # Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
 permissions:
@@ -123,11 +123,6 @@ 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 +183,6 @@ 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 +202,6 @@ 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
@@ -249,11 +240,11 @@ 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: ${{ env.DISABLE_RUN_TESTS }}
-          disable-run-tests: true
           artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
 
       - name: Set build macos result
@@ -292,6 +283,7 @@ 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 }}

.pre-commit-config.yaml

@@ -16,7 +16,6 @@ repos:
     hooks:
     -    id: fmt
     -    id: clippy
-         args: ["--workspace", "--all-targets", "--all-features", "--", "-D", "warnings"]
+         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

@@ -1,43 +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)
-
-## 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)
-* [tisonkun](https://github.com/tisonkun)
-* [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)

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.
+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.
-
-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.
 
 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
 
@@ -55,7 +51,7 @@ GreptimeDB uses the [Apache 2.0 license](https://github.com/GreptimeTeam/greptim
 - To ensure that community is free and confident in its ability to use your contributions, please sign the Contributor License Agreement (CLA) which will be incorporated in the pull request process.
 - Make sure all files have proper license header (running `docker run --rm -v $(pwd):/github/workspace ghcr.io/korandoru/hawkeye-native:v3 format` from the project root).
 - Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/) 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 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

@@ -1,5 +1,6 @@
 [workspace]
 members = [
+    "benchmarks",
     "src/api",
     "src/auth",
     "src/catalog",
@@ -20,7 +21,6 @@ members = [
     "src/common/mem-prof",
     "src/common/meta",
     "src/common/plugins",
-    "src/common/pprof",
     "src/common/procedure",
     "src/common/procedure-test",
     "src/common/query",
@@ -46,7 +46,6 @@ members = [
     "src/object-store",
     "src/operator",
     "src/partition",
-    "src/pipeline",
     "src/plugins",
     "src/promql",
     "src/puffin",
@@ -65,7 +64,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.9.5"
+version = "0.8.1"
 edition = "2021"
 license = "Apache-2.0"
 
@@ -78,7 +77,6 @@ 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
@@ -91,7 +89,7 @@ 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-ipc = { version = "51.0.0", default-features = false, features = ["lz4"] }
 arrow-schema = { version = "51.0", features = ["serde"] }
 async-stream = "0.3"
 async-trait = "0.1"
@@ -100,34 +98,34 @@ 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 = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-functions = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-physical-plan = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
-datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
 derive_builder = "0.12"
 dotenv = "0.15"
-etcd-client = { version = "0.13" }
+# TODO(LFC): Wait for https://github.com/etcdv3/etcd-client/pull/76
+etcd-client = { git = "https://github.com/MichaelScofield/etcd-client.git", rev = "4c371e9b3ea8e0a8ee2f9cbd7ded26e54a45df3b" }
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "255f87a3318ace3f88a67f76995a0e14910983f4" }
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "ae26136accd82fbdf8be540cd502f2e94951077e" }
 humantime = "2.1"
 humantime-serde = "1.1"
 itertools = "0.10"
-jsonb = { git = "https://github.com/databendlabs/jsonb.git", rev = "46ad50fc71cf75afbf98eec455f7892a6387c1fc", 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 = "80b72716dcde47ec4161478416a5c6c21343364d" }
 mockall = "0.11.4"
 moka = "0.12"
 notify = "6.1"
@@ -137,59 +135,44 @@ opentelemetry-proto = { version = "0.5", 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"] }
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-promql-parser = { version = "0.4.3", features = ["ser"] }
+promql-parser = { version = "0.4" }
 prost = "0.12"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
-ratelimit = "0.9"
 regex = "1.8"
 regex-automata = { version = "0.4" }
-reqwest = { version = "0.12", default-features = false, features = [
+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 = [
+rskafka = "0.5"
-    "transport-tls",
-] }
-rstest = "0.21"
-rstest_reuse = "0.7"
 rust_decimal = "1.33"
-rustc-hash = "2.0"
 schemars = "0.8"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = { version = "1.0", features = ["float_roundtrip"] }
 serde_with = "3"
-shadow-rs = "0.35"
-similar-asserts = "1.6.0"
 smallvec = { version = "1", features = ["serde"] }
 snafu = "0.8"
 sysinfo = "0.30"
 # on branch v0.44.x
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "54a267ac89c09b11c0c88934690530807185d3e7", features = [
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "e4e496b8d62416ad50ce70a1b460c7313610cf5d", features = [
     "visitor",
 ] }
 strum = { version = "0.25", features = ["derive"] }
 tempfile = "3"
-tokio = { version = "1.40", features = ["full"] }
+tokio = { version = "1.36", features = ["full"] }
-tokio-postgres = "0.7"
 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 = { version = "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"
 
@@ -199,7 +182,7 @@ auth = { path = "src/auth" }
 cache = { path = "src/cache" }
 catalog = { path = "src/catalog" }
 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" }
@@ -215,7 +198,6 @@ common-macro = { path = "src/common/macro" }
 common-mem-prof = { path = "src/common/mem-prof" }
 common-meta = { path = "src/common/meta" }
 common-plugins = { path = "src/common/plugins" }
-common-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" }
@@ -230,7 +212,7 @@ 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" }
@@ -240,7 +222,6 @@ 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" }
@@ -253,37 +234,25 @@ 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" }
-
 [workspace.dependencies.meter-macros]
 git = "https://github.com/GreptimeTeam/greptime-meter.git"
-rev = "a10facb353b41460eeb98578868ebf19c2084fac"
+rev = "80b72716dcde47ec4161478416a5c6c21343364d"
 
 [profile.release]
 debug = 1
 
 [profile.nightly]
 inherits = "release"
-strip = "debuginfo"
+strip = true
 lto = "thin"
 debug = false
 incremental = false
 
 [profile.ci]
 inherits = "dev"
+debug = false
 strip = true
 
 [profile.dev.package.sqlness-runner]
 debug = false
 strip = true
-
-[profile.dev.package.tests-fuzz]
-debug = false
-strip = true

Makefile

@@ -8,7 +8,6 @@ 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 +15,6 @@ 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
@@ -78,7 +76,7 @@ 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 +90,7 @@ 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 +104,8 @@ 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} \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:latest \
-	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip --strip-debug /greptimedb/target/aarch64-linux-android/release/greptime'
+	bash -c '$${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 +144,7 @@ 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 +161,7 @@ nextest: ## Install nextest tools.
 
 .PHONY: sqlness-test
 sqlness-test: ## Run sqlness test.
-	cargo sqlness ${SQLNESS_OPTS}
+	cargo sqlness
-
-# 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
 
 .PHONY: check
 check: ## Cargo check all the targets.
@@ -191,7 +178,6 @@ fix-clippy: ## Fix clippy violations.
 .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.
@@ -205,23 +191,15 @@ 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 \
+    toml2docs/toml2docs:v0.1.1 \
     -p '##' \
     -t ./config-docs-template.md \
     -o ./config.md

README.md

@@ -6,12 +6,12 @@
   </picture>
 </p>
 
-<h2 align="center">Unified Time Series Database for Metrics, Logs, and Events</h2>
+<h1 align="center">Cloud-scale, Fast and Efficient Time Series Database</h1>
 
 <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://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>
@@ -50,23 +50,24 @@
 
 ## Introduction
 
-**GreptimeDB** is an open-source unified 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.
+**GreptimeDB** is an open-source time-series database focusing on efficiency, scalability, and analytical capabilities.
+Designed to work on infrastructure of the cloud era, GreptimeDB benefits users with its elasticity and commodity storage, offering a fast and cost-effective **alternative to InfluxDB** and a **long-term storage for Prometheus**.
 
 ## Why GreptimeDB
 
 Our core developers have been building time-series data platforms for years. Based on our best-practices, GreptimeDB is born to give you:
 
-* **Unified all kinds of time series**
+* **Easy horizontal scaling**
 
-  GreptimeDB treats all time series as contextual events with timestamp, and thus unifies the processing of metrics, logs, and events. It supports analyzing metrics, logs, and events with SQL and PromQL, and doing streaming with continuous aggregation.
+  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.
 
-* **Cloud-Edge collaboration**
+* **Analyzing time-series data**
 
-  GreptimeDB can be deployed on ARM architecture-compatible Android/Linux systems as well as cloud environments from various vendors. Both sides run the same software, providing identical APIs and control planes, so your application can run at the edge or on the cloud without modification, and data synchronization also becomes extremely easy and efficient.
+  Query your time-series data with SQL and PromQL. Use Python scripts to facilitate complex analytical tasks.
 
 * **Cloud-native distributed database**
 
-  By leveraging object storage (S3 and others), separating compute and storage, scaling stateless compute nodes arbitrarily, GreptimeDB implements seamless scalability. It also supports cross-cloud deployment with a built-in unified data access layer over different object storages.
+  Fully open-source distributed cluster architecture that harnesses the power of cloud-native elastic computing resources.
 
 * **Performance and Cost-effective**
 
@@ -74,7 +75,7 @@ Our core developers have been building time-series data platforms for years. Bas
 
 * **Compatible with InfluxDB, Prometheus and more protocols**
 
-  Widely adopted database protocols and APIs, including MySQL, PostgreSQL, and Prometheus Remote Storage, etc. [Read more](https://docs.greptime.com/user-guide/protocols/overview).
+  Widely adopted database protocols and APIs, including MySQL, PostgreSQL, and Prometheus Remote Storage, etc. [Read more](https://docs.greptime.com/user-guide/clients/overview).
 
 ## Try GreptimeDB
 
@@ -104,10 +105,10 @@ Read more about [Installation](https://docs.greptime.com/getting-started/install
 
 ## Getting Started
 
-* [Quickstart](https://docs.greptime.com/getting-started/quick-start)
+* [Quickstart](https://docs.greptime.com/getting-started/quick-start/overview)
-* [User Guide](https://docs.greptime.com/user-guide/overview)
+* [Write Data](https://docs.greptime.com/user-guide/clients/overview)
-* [Demos](https://github.com/GreptimeTeam/demo-scene)
+* [Query Data](https://docs.greptime.com/user-guide/query-data/overview)
-* [FAQ](https://docs.greptime.com/faq-and-others/faq)
+* [Operations](https://docs.greptime.com/user-guide/operations/overview)
 
 ## Build
 
@@ -150,10 +151,9 @@ Our official Grafana dashboard is available at [grafana](grafana/README.md) dire
 
 ## Project Status
 
-The current version has not yet reached the standards for General Availability.
+The current version has not yet reached General Availability version standards.
-According to our Greptime 2024 Roadmap, we aim to achieve a production-level version with the release of v1.0 by the end of 2024. [Join Us](https://github.com/GreptimeTeam/greptimedb/issues/3412)
+In line with our Greptime 2024 Roadmap, we plan to achieve a production-level
-
+version with the update to v1.0 in August. [[Join Force]](https://github.com/GreptimeTeam/greptimedb/issues/3412)
-We welcome you to test and use GreptimeDB. Some users have already adopted it in their production environments. If you're interested in trying it out, please use the latest stable release available.
 
 ## Community
 
@@ -172,13 +172,6 @@ In addition, you may:
 - Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
 - Follow us on [Twitter](https://twitter.com/greptime)
 
-## Commerial Support
-
-If you are running GreptimeDB OSS in your organization, we offer additional
-enterprise addons, installation service, training and consulting. [Contact
-us](https://greptime.com/contactus) and we will reach out to you with more
-detail of our commerial license.
-
 ## License
 
 GreptimeDB uses the [Apache License 2.0](https://apache.org/licenses/LICENSE-2.0.txt) to strike a balance between
@@ -190,8 +183,6 @@ Please refer to [contribution guidelines](CONTRIBUTING.md) and [internal concept
 
 ## 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 +1,38 @@
+[package]
+name = "benchmarks"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[lints]
+workspace = true
+
+[dependencies]
+api.workspace = true
+arrow.workspace = true
+chrono.workspace = true
+clap.workspace = true
+client = { workspace = true, features = ["testing"] }
+common-base.workspace = true
+common-telemetry.workspace = true
+common-wal.workspace = true
+dotenv.workspace = true
+futures.workspace = true
+futures-util.workspace = true
+humantime.workspace = true
+humantime-serde.workspace = true
+indicatif = "0.17.1"
+itertools.workspace = true
+lazy_static.workspace = true
+log-store.workspace = true
+mito2.workspace = true
+num_cpus.workspace = true
+parquet.workspace = true
+prometheus.workspace = true
+rand.workspace = true
+rskafka.workspace = true
+serde.workspace = true
+store-api.workspace = true
+tokio.workspace = true
+toml.workspace = true
+uuid.workspace = true

benchmarks/README.md

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

benchmarks/config/wal_bench.example.toml

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

benchmarks/src/bin/wal_bench.rs

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

benchmarks/src/lib.rs

@@ -12,6 +12,5 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-mod abort;
+pub mod metrics;
-mod finish;
+pub mod wal_bench;
-mod update;

benchmarks/src/metrics.rs

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

benchmarks/src/wal_bench.rs

@@ -0,0 +1,366 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::mem::size_of;
+use std::sync::atomic::{AtomicI64, AtomicU64, Ordering};
+use std::sync::{Arc, Mutex};
+use std::time::Duration;
+
+use api::v1::value::ValueData;
+use api::v1::{ColumnDataType, ColumnSchema, Mutation, OpType, Row, Rows, Value, WalEntry};
+use clap::{Parser, ValueEnum};
+use common_base::readable_size::ReadableSize;
+use common_wal::options::WalOptions;
+use futures::StreamExt;
+use mito2::wal::{Wal, WalWriter};
+use rand::distributions::{Alphanumeric, DistString, Uniform};
+use rand::rngs::SmallRng;
+use rand::{Rng, SeedableRng};
+use serde::{Deserialize, Serialize};
+use store_api::logstore::provider::Provider;
+use store_api::logstore::LogStore;
+use store_api::storage::RegionId;
+
+use crate::metrics;
+
+/// The wal provider.
+#[derive(Clone, ValueEnum, Default, Debug, PartialEq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum WalProvider {
+    #[default]
+    RaftEngine,
+    Kafka,
+}
+
+#[derive(Parser)]
+pub struct Args {
+    /// The provided configuration file.
+    /// The example configuration file can be found at `greptimedb/benchmarks/config/wal_bench.example.toml`.
+    #[clap(long, short = 'c')]
+    pub cfg_file: String,
+
+    /// The wal provider.
+    #[clap(long, value_enum, default_value_t = WalProvider::default())]
+    pub wal_provider: WalProvider,
+
+    /// The advertised addresses of the kafka brokers.
+    /// If there're multiple bootstrap brokers, their addresses should be separated by comma, for e.g. "localhost:9092,localhost:9093".
+    #[clap(long, short = 'b', default_value = "localhost:9092")]
+    pub bootstrap_brokers: String,
+
+    /// The number of workers each running in a dedicated thread.
+    #[clap(long, default_value_t = num_cpus::get() as u32)]
+    pub num_workers: u32,
+
+    /// The number of kafka topics to be created.
+    #[clap(long, default_value_t = 32)]
+    pub num_topics: u32,
+
+    /// The number of regions.
+    #[clap(long, default_value_t = 1000)]
+    pub num_regions: u32,
+
+    /// The number of times each region is scraped.
+    #[clap(long, default_value_t = 1000)]
+    pub num_scrapes: u32,
+
+    /// The number of rows in each wal entry.
+    /// Each time a region is scraped, a wal entry containing will be produced.
+    #[clap(long, default_value_t = 5)]
+    pub num_rows: u32,
+
+    /// The column types of the schema for each region.
+    /// Currently, three column types are supported:
+    /// - i = ColumnDataType::Int64
+    /// - f = ColumnDataType::Float64
+    /// - s = ColumnDataType::String  
+    /// For e.g., "ifs" will be parsed as three columns: i64, f64, and string.
+    ///
+    /// Additionally, a "x" sign can be provided to repeat the column types for a given number of times.
+    /// For e.g., "iix2" will be parsed as 4 columns: i64, i64, i64, and i64.
+    /// This feature is useful if you want to specify many columns.
+    #[clap(long, default_value = "ifs")]
+    pub col_types: String,
+
+    /// The maximum size of a batch of kafka records.
+    /// The default value is 1mb.
+    #[clap(long, default_value = "512KB")]
+    pub max_batch_size: ReadableSize,
+
+    /// The minimum latency the kafka client issues a batch of kafka records.
+    /// However, a batch of kafka records would be immediately issued if a record cannot be fit into the batch.
+    #[clap(long, default_value = "1ms")]
+    pub linger: String,
+
+    /// The initial backoff delay of the kafka consumer.
+    #[clap(long, default_value = "10ms")]
+    pub backoff_init: String,
+
+    /// The maximum backoff delay of the kafka consumer.
+    #[clap(long, default_value = "1s")]
+    pub backoff_max: String,
+
+    /// The exponential backoff rate of the kafka consumer. The next back off = base * the current backoff.
+    #[clap(long, default_value_t = 2)]
+    pub backoff_base: u32,
+
+    /// The deadline of backoff. The backoff ends if the total backoff delay reaches the deadline.
+    #[clap(long, default_value = "3s")]
+    pub backoff_deadline: String,
+
+    /// The client-side compression algorithm for kafka records.
+    #[clap(long, default_value = "zstd")]
+    pub compression: String,
+
+    /// The seed of random number generators.
+    #[clap(long, default_value_t = 42)]
+    pub rng_seed: u64,
+
+    /// Skips the read phase, aka. region replay, if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_read: bool,
+
+    /// Skips the write phase if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_write: bool,
+
+    /// Randomly generates topic names if set to true.
+    /// Useful when you want to run the benchmarker without worrying about the topics created before.
+    #[clap(long, default_value_t = false)]
+    pub random_topics: bool,
+
+    /// Logs out the gathered prometheus metrics when the benchmarker ends.
+    #[clap(long, default_value_t = false)]
+    pub report_metrics: bool,
+}
+
+/// Benchmarker config.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Config {
+    pub wal_provider: WalProvider,
+    pub bootstrap_brokers: Vec<String>,
+    pub num_workers: u32,
+    pub num_topics: u32,
+    pub num_regions: u32,
+    pub num_scrapes: u32,
+    pub num_rows: u32,
+    pub col_types: String,
+    pub max_batch_size: ReadableSize,
+    #[serde(with = "humantime_serde")]
+    pub linger: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_init: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_max: Duration,
+    pub backoff_base: u32,
+    #[serde(with = "humantime_serde")]
+    pub backoff_deadline: Duration,
+    pub compression: String,
+    pub rng_seed: u64,
+    pub skip_read: bool,
+    pub skip_write: bool,
+    pub random_topics: bool,
+    pub report_metrics: bool,
+}
+
+impl From<Args> for Config {
+    fn from(args: Args) -> Self {
+        let cfg = Self {
+            wal_provider: args.wal_provider,
+            bootstrap_brokers: args
+                .bootstrap_brokers
+                .split(',')
+                .map(ToString::to_string)
+                .collect::<Vec<_>>(),
+            num_workers: args.num_workers.min(num_cpus::get() as u32),
+            num_topics: args.num_topics,
+            num_regions: args.num_regions,
+            num_scrapes: args.num_scrapes,
+            num_rows: args.num_rows,
+            col_types: args.col_types,
+            max_batch_size: args.max_batch_size,
+            linger: humantime::parse_duration(&args.linger).unwrap(),
+            backoff_init: humantime::parse_duration(&args.backoff_init).unwrap(),
+            backoff_max: humantime::parse_duration(&args.backoff_max).unwrap(),
+            backoff_base: args.backoff_base,
+            backoff_deadline: humantime::parse_duration(&args.backoff_deadline).unwrap(),
+            compression: args.compression,
+            rng_seed: args.rng_seed,
+            skip_read: args.skip_read,
+            skip_write: args.skip_write,
+            random_topics: args.random_topics,
+            report_metrics: args.report_metrics,
+        };
+
+        cfg
+    }
+}
+
+/// The region used for wal benchmarker.
+pub struct Region {
+    id: RegionId,
+    schema: Vec<ColumnSchema>,
+    provider: Provider,
+    next_sequence: AtomicU64,
+    next_entry_id: AtomicU64,
+    next_timestamp: AtomicI64,
+    rng: Mutex<Option<SmallRng>>,
+    num_rows: u32,
+}
+
+impl Region {
+    /// Creates a new region.
+    pub fn new(
+        id: RegionId,
+        schema: Vec<ColumnSchema>,
+        wal_options: WalOptions,
+        num_rows: u32,
+        rng_seed: u64,
+    ) -> Self {
+        let provider = match wal_options {
+            WalOptions::RaftEngine => Provider::raft_engine_provider(id.as_u64()),
+            WalOptions::Kafka(opts) => Provider::kafka_provider(opts.topic),
+        };
+        Self {
+            id,
+            schema,
+            provider,
+            next_sequence: AtomicU64::new(1),
+            next_entry_id: AtomicU64::new(1),
+            next_timestamp: AtomicI64::new(1655276557000),
+            rng: Mutex::new(Some(SmallRng::seed_from_u64(rng_seed))),
+            num_rows,
+        }
+    }
+
+    /// Scrapes the region and adds the generated entry to wal.
+    pub fn add_wal_entry<S: LogStore>(&self, wal_writer: &mut WalWriter<S>) {
+        let mutation = Mutation {
+            op_type: OpType::Put as i32,
+            sequence: self
+                .next_sequence
+                .fetch_add(self.num_rows as u64, Ordering::Relaxed),
+            rows: Some(self.build_rows()),
+        };
+        let entry = WalEntry {
+            mutations: vec![mutation],
+        };
+        metrics::METRIC_WAL_WRITE_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+
+        wal_writer
+            .add_entry(
+                self.id,
+                self.next_entry_id.fetch_add(1, Ordering::Relaxed),
+                &entry,
+                &self.provider,
+            )
+            .unwrap();
+    }
+
+    /// Replays the region.
+    pub async fn replay<S: LogStore>(&self, wal: &Arc<Wal<S>>) {
+        let mut wal_stream = wal.scan(self.id, 0, &self.provider).unwrap();
+        while let Some(res) = wal_stream.next().await {
+            let (_, entry) = res.unwrap();
+            metrics::METRIC_WAL_READ_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+        }
+    }
+
+    /// Computes the estimated size in bytes of the entry.
+    pub fn entry_estimated_size(entry: &WalEntry) -> usize {
+        let wrapper_size = size_of::<WalEntry>()
+            + entry.mutations.capacity() * size_of::<Mutation>()
+            + size_of::<Rows>();
+
+        let rows = entry.mutations[0].rows.as_ref().unwrap();
+
+        let schema_size = rows.schema.capacity() * size_of::<ColumnSchema>()
+            + rows
+                .schema
+                .iter()
+                .map(|s| s.column_name.capacity())
+                .sum::<usize>();
+        let values_size = (rows.rows.capacity() * size_of::<Row>())
+            + rows
+                .rows
+                .iter()
+                .map(|r| r.values.capacity() * size_of::<Value>())
+                .sum::<usize>();
+
+        wrapper_size + schema_size + values_size
+    }
+
+    fn build_rows(&self) -> Rows {
+        let cols = self
+            .schema
+            .iter()
+            .map(|col_schema| {
+                let col_data_type = ColumnDataType::try_from(col_schema.datatype).unwrap();
+                self.build_col(&col_data_type, self.num_rows)
+            })
+            .collect::<Vec<_>>();
+
+        let rows = (0..self.num_rows)
+            .map(|i| {
+                let values = cols.iter().map(|col| col[i as usize].clone()).collect();
+                Row { values }
+            })
+            .collect();
+
+        Rows {
+            schema: self.schema.clone(),
+            rows,
+        }
+    }
+
+    fn build_col(&self, col_data_type: &ColumnDataType, num_rows: u32) -> Vec<Value> {
+        let mut rng_guard = self.rng.lock().unwrap();
+        let rng = rng_guard.as_mut().unwrap();
+        match col_data_type {
+            ColumnDataType::TimestampMillisecond => (0..num_rows)
+                .map(|_| {
+                    let ts = self.next_timestamp.fetch_add(1000, Ordering::Relaxed);
+                    Value {
+                        value_data: Some(ValueData::TimestampMillisecondValue(ts)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Int64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0, 10_000));
+                    Value {
+                        value_data: Some(ValueData::I64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Float64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0.0, 5000.0));
+                    Value {
+                        value_data: Some(ValueData::F64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::String => (0..num_rows)
+                .map(|_| {
+                    let v = Alphanumeric.sample_string(rng, 10);
+                    Value {
+                        value_data: Some(ValueData::StringValue(v)),
+                    }
+                })
+                .collect(),
+            _ => unreachable!(),
+        }
+    }
+}

config/config-docs-template.md

@@ -1,12 +1,10 @@
 # Configurations
 
-- [Configurations](#configurations)
+- [Standalone Mode](#standalone-mode)
-  - [Standalone Mode](#standalone-mode)
+- [Distributed Mode](#distributed-mode)
-  - [Distributed Mode](#distributed-mode)
     - [Frontend](#frontend)
     - [Metasrv](#metasrv)
     - [Datanode](#datanode)
-    - [Flownode](#flownode)
 
 ## Standalone Mode
 
@@ -25,7 +23,3 @@
 ### Datanode
 
 {{ toml2docs "./datanode.example.toml" }}
-
-### Flownode
-
-{{ toml2docs "./flownode.example.toml"}}

config/config.md

@@ -1,12 +1,10 @@
 # Configurations
 
-- [Configurations](#configurations)
+- [Standalone Mode](#standalone-mode)
-  - [Standalone Mode](#standalone-mode)
+- [Distributed Mode](#distributed-mode)
-  - [Distributed Mode](#distributed-mode)
     - [Frontend](#frontend)
     - [Metasrv](#metasrv)
     - [Datanode](#datanode)
-    - [Flownode](#flownode)
 
 ## Standalone Mode
 
@@ -14,24 +12,18 @@
 | --- | -----| ------- | ----------- |
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
 | `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
-| `default_timezone` | String | Unset | The default timezone of the server. |
+| `default_timezone` | String | `None` | 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. |
-| `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.timeout` | String | `30s` | HTTP request 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. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
 | `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
 | `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.cert_path` | String | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | Unset | Private key file path. |
+| `grpc.tls.key_path` | String | `None` | 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. |
@@ -39,8 +31,8 @@
 | `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.cert_path` | String | `None` | Certificate file path. |
-| `mysql.tls.key_path` | String | Unset | Private key file path. |
+| `mysql.tls.key_path` | String | `None` | Private key file path. |
 | `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `postgres` | -- | -- | PostgresSQL server options. |
 | `postgres.enable` | Bool | `true` | Whether to enable |
@@ -48,8 +40,8 @@
 | `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.cert_path` | String | `None` | Certificate file path. |
-| `postgres.tls.key_path` | String | Unset | Private key file path. |
+| `postgres.tls.key_path` | String | `None` | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
 | `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
@@ -60,7 +52,7 @@
 | `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.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
@@ -69,21 +61,14 @@
 | `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.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.num_topics` | Integer | `64` | Number of topics.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.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. |
@@ -93,22 +78,21 @@
 | `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 | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
+| `storage.cache_path` | String | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
-| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. |
+| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
-| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | 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.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
-| `storage.access_key_id` | String | 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.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
-| `storage.secret_access_key` | String | 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.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
-| `storage.access_key_secret` | String | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.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 | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `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 | `None` | The region 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`**. |
 | `[[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. |
@@ -116,71 +100,50 @@
 | `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_jobs` | Integer | `4` | Max number of running background jobs |
-| `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_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
-| `region_engine.mito.global_write_buffer_reject_size` | String | 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.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
-| `region_engine.mito.sst_meta_cache_size` | String | 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.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
-| `region_engine.mito.vector_cache_size` | String | 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.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.page_cache_size` | String | 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.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.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. |
 | `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/write_cache`. |
 | `region_engine.mito.experimental_write_cache_size` | String | `512MB` | Capacity for write cache. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | Unset | TTL for write cache. |
+| `region_engine.mito.experimental_write_cache_ttl` | String | `1h` | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
 | `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
 | `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
 | `region_engine.mito.allow_stale_entries` | Bool | `false` | Whether to allow stale WAL entries read during replay. |
-| `region_engine.mito.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_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `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.mem_threshold_on_create` | String | `64M` | Memory threshold for performing an external sort during index creation.<br/>Setting to empty will disable external sorting, forcing all sorting operations to happen in memory. |
-| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | Deprecated, use `region_engine.mito.index.aux_path` instead. |
+| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`). |
-| `region_engine.mito.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.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.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
 | `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `None` | 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` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | Unset | -- |
+| `export_metrics.self_import.db` | String | `None` | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
 ## Distributed Mode
@@ -189,25 +152,22 @@
 
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
-| `default_timezone` | String | Unset | The default timezone of the server. |
+| `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
-| `runtime` | -- | -- | The runtime options. |
+| `default_timezone` | String | `None` | The default timezone of the server. |
-| `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.timeout` | String | `30s` | HTTP request 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. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
-| `grpc.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.cert_path` | String | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | Unset | Private key file path. |
+| `grpc.tls.key_path` | String | `None` | 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. |
@@ -215,8 +175,8 @@
 | `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.cert_path` | String | `None` | Certificate file path. |
-| `mysql.tls.key_path` | String | Unset | Private key file path. |
+| `mysql.tls.key_path` | String | `None` | Private key file path. |
 | `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `postgres` | -- | -- | PostgresSQL server options. |
 | `postgres.enable` | Bool | `true` | Whether to enable |
@@ -224,8 +184,8 @@
 | `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.cert_path` | String | `None` | Certificate file path. |
-| `postgres.tls.key_path` | String | Unset | Private key file path. |
+| `postgres.tls.key_path` | String | `None` | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
 | `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
@@ -249,29 +209,23 @@
 | `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.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
 | `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `None` | 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` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | Unset | -- |
+| `export_metrics.self_import.db` | String | `None` | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
 ### Metasrv
@@ -281,37 +235,31 @@
 | `data_home` | String | `/tmp/metasrv/` | The working home directory. |
 | `bind_addr` | String | `127.0.0.1:3002` | The bind address of metasrv. |
 | `server_addr` | String | `127.0.0.1:3002` | The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost. |
-| `store_addr` | String | `127.0.0.1:2379` | Store server address default to etcd store. |
+| `store_addr` | String | `127.0.0.1:2379` | Etcd server address. |
-| `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". |
+| `selector` | String | `lease_based` | Datanode selector type.<br/>- `lease_based` (default value).<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
 | `use_memory_store` | Bool | `false` | Store data in memory. |
 | `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. |
 | `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
-| `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). |
-| `backend` | String | `EtcdStore` | The datastore for meta 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. |
 | `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.threshold` | Float | `8.0` | -- |
-| `failure_detector.min_std_deviation` | String | `100ms` | The minimum standard deviation of the heartbeat intervals, used to calculate acceptable variations. |
+| `failure_detector.min_std_deviation` | String | `100ms` | -- |
-| `failure_detector.acceptable_heartbeat_pause` | String | `10000ms` | The acceptable pause duration between heartbeats, used to determine if a heartbeat interval is acceptable. |
+| `failure_detector.acceptable_heartbeat_pause` | String | `3000ms` | -- |
-| `failure_detector.first_heartbeat_estimate` | String | `1000ms` | The initial estimate of the heartbeat interval used by the failure detector. |
+| `failure_detector.first_heartbeat_estimate` | String | `1000ms` | -- |
 | `datanode` | -- | -- | Datanode options. |
 | `datanode.client` | -- | -- | Datanode client options. |
-| `datanode.client.timeout` | String | `10s` | Operation timeout. |
+| `datanode.client.timeout` | String | `10s` | -- |
-| `datanode.client.connect_timeout` | String | `10s` | Connect server timeout. |
+| `datanode.client.connect_timeout` | String | `10s` | -- |
-| `datanode.client.tcp_nodelay` | Bool | `true` | `TCP_NODELAY` option for accepted connections. |
+| `datanode.client.tcp_nodelay` | Bool | `true` | -- |
 | `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 to be created upon start. |
-| `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.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`. |
 | `wal.replication_factor` | Integer | `1` | Expected number of replicas of each partition. |
 | `wal.create_topic_timeout` | String | `30s` | Above which a topic creation operation will be cancelled. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff for kafka clients. |
@@ -319,29 +267,23 @@
 | `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.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
 | `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `None` | 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` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | Unset | -- |
+| `export_metrics.self_import.db` | String | `None` | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
+| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
 ### Datanode
@@ -349,35 +291,15 @@
 | 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. |
+| `node_id` | Integer | `None` | The datanode identifier and should be unique in the cluster. |
 | `require_lease_before_startup` | Bool | `false` | Start services after regions have obtained leases.<br/>It will block the datanode start if it can't receive leases in the heartbeat from metasrv. |
 | `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
+| `rpc_addr` | String | `127.0.0.1:3001` | The gRPC address of the datanode. |
+| `rpc_hostname` | String | `None` | The hostname of the datanode. |
+| `rpc_runtime_size` | Integer | `8` | The number of gRPC server worker threads. |
+| `rpc_max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
+| `rpc_max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
 | `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
-| `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. |
-| `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. |
@@ -393,7 +315,7 @@
 | `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.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
@@ -402,36 +324,32 @@
 | `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.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_base` | Integer | `2` | The exponential backoff rate, i.e. next backoff = base * current backoff.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_deadline` | String | `5mins` | The deadline of retries.<br/>**It's only used when the provider is `kafka`**. |
-| `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 | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
+| `storage.cache_path` | String | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
-| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. |
+| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
-| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | 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.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
-| `storage.access_key_id` | String | 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.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
-| `storage.secret_access_key` | String | 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.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
-| `storage.access_key_secret` | String | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.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 | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `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 | `None` | The region 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`**. |
 | `[[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. |
@@ -439,109 +357,47 @@
 | `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_jobs` | Integer | `4` | Max number of running background jobs |
-| `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_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
-| `region_engine.mito.global_write_buffer_reject_size` | String | 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.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
-| `region_engine.mito.sst_meta_cache_size` | String | 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.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
-| `region_engine.mito.vector_cache_size` | String | 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.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.page_cache_size` | String | 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.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.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. |
 | `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/write_cache`. |
 | `region_engine.mito.experimental_write_cache_size` | String | `512MB` | Capacity for write cache. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | Unset | TTL for write cache. |
+| `region_engine.mito.experimental_write_cache_ttl` | String | `1h` | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
 | `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
 | `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
 | `region_engine.mito.allow_stale_entries` | Bool | `false` | Whether to allow stale WAL entries read during replay. |
-| `region_engine.mito.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_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically<br/>- `disable`: never |
-| `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `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.mem_threshold_on_create` | String | `64M` | Memory threshold for performing an external sort during index creation.<br/>Setting to empty will disable external sorting, forcing all sorting operations to happen in memory. |
-| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | Deprecated, use `region_engine.mito.index.aux_path` instead. |
+| `region_engine.mito.inverted_index.intermediate_path` | String | `""` | File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`). |
-| `region_engine.mito.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.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | Unset | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
 | `logging.enable_otlp_tracing` | Bool | `false` | Enable OTLP tracing. |
-| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `None` | 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` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | Unset | -- |
+| `export_metrics.self_import.db` | String | `None` | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
+| `tracing.tokio_console_addr` | String | `None` | 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

@@ -2,7 +2,7 @@
 mode = "standalone"
 
 ## The datanode identifier and should be unique in the cluster.
-## @toml2docs:none-default
+## +toml2docs:none-default
 node_id = 42
 
 ## Start services after regions have obtained leases.
@@ -13,84 +13,24 @@ require_lease_before_startup = false
 ## By default, it provides services after all regions have been initialized.
 init_regions_in_background = false
 
-## Enable telemetry to collect anonymous usage data.
+## The gRPC address of the datanode.
-enable_telemetry = true
-
-## 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.
+## The hostname of the datanode.
-## @toml2docs:none-default
+## +toml2docs:none-default
 rpc_hostname = "127.0.0.1"
 
-## Deprecated, use `grpc.runtime_size` instead.
+## The number of gRPC server worker threads.
-## @toml2docs:none-default
 rpc_runtime_size = 8
 
-## Deprecated, use `grpc.rpc_max_recv_message_size` instead.
+## The maximum receive message size for gRPC server.
-## @toml2docs:none-default
 rpc_max_recv_message_size = "512MB"
 
-## Deprecated, use `grpc.rpc_max_send_message_size` instead.
+## The maximum send message size for gRPC server.
-## @toml2docs:none-default
 rpc_max_send_message_size = "512MB"
 
-
+## Enable telemetry to collect anonymous usage data.
-## The HTTP server options.
+enable_telemetry = true
-[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]
@@ -138,7 +78,7 @@ provider = "raft_engine"
 
 ## The directory to store the WAL files.
 ## **It's only used when the provider is `raft_engine`**.
-## @toml2docs:none-default
+## +toml2docs:none-default
 dir = "/tmp/greptimedb/wal"
 
 ## The size of the WAL segment file.
@@ -173,9 +113,6 @@ prefill_log_files = false
 ## **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"]
@@ -183,7 +120,11 @@ 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"
+max_batch_size = "1MB"
+
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
 
 ## The consumer wait timeout.
 ## **It's only used when the provider is `kafka`**.
@@ -205,43 +146,6 @@ backoff_base = 2
 ## **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"
@@ -278,7 +182,6 @@ overwrite_entry_start_id = false
 # root = "data"
 # scope = "test"
 # credential_path = "123456"
-# credential = "base64-credential"
 # endpoint = "https://storage.googleapis.com"
 
 ## The data storage options.
@@ -296,104 +199,85 @@ type = "File"
 
 ## Cache configuration for object storage such as 'S3' etc.
 ## The local file cache directory.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cache_path = "/path/local_cache"
 
 ## The local file cache capacity in bytes.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cache_capacity = "256MB"
 
 ## The S3 bucket name.
 ## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
-## @toml2docs:none-default
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +toml2docs:none-default
 region = "us-west-2"
 
 # 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"
 
 ## The region engine options. You can configure multiple region engines.
 [[region_engine]]
@@ -402,7 +286,7 @@ region = "us-west-2"
 [region_engine.mito]
 
 ## Number of region workers.
-#+ num_workers = 8
+num_workers = 8
 
 ## Request channel size of each worker.
 worker_channel_size = 128
@@ -416,48 +300,29 @@ manifest_checkpoint_distance = 10
 ## 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).
+## Max number of running background jobs
-## @toml2docs:none-default="Auto"
+max_background_jobs = 4
-#+ 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.
 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 = "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"
-#+ 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"
-#+ 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"
-#+ 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"
+page_cache_size = "512MB"
-#+ selector_result_cache_size = "512MB"
 
 ## Whether to enable the experimental write cache.
 enable_experimental_write_cache = false
@@ -469,8 +334,7 @@ experimental_write_cache_path = ""
 experimental_write_cache_size = "512MB"
 
 ## TTL for write cache.
-## @toml2docs:none-default
+experimental_write_cache_ttl = "1h"
-experimental_write_cache_ttl = "8h"
 
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
@@ -487,76 +351,31 @@ parallel_scan_channel_size = 32
 ## 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)
+## - `auto`: automatically
 ## - `disable`: never
 create_on_flush = "auto"
 
 ## Whether to create the index on compaction.
-## - `auto`: automatically (default)
+## - `auto`: automatically
 ## - `disable`: never
 create_on_compaction = "auto"
 
 ## Whether to apply the index on query
-## - `auto`: automatically (default)
+## - `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)
+## Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
-## - `unlimited`: no memory limit
+mem_threshold_on_create = "64M"
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
 
-## Deprecated, use `region_engine.mito.index.aux_path` instead.
+## File system path to store intermediate files for external sorting (default `{data_home}/index_intermediate`).
 intermediate_path = ""
 
-## 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
@@ -575,53 +394,31 @@ data_freeze_threshold = 32768
 ## 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.
+## The directory to store the log files.
 dir = "/tmp/greptimedb/logs"
 
 ## The log level. Can be `info`/`debug`/`warn`/`error`.
-## @toml2docs:none-default
+## +toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-otlp_endpoint = "http://localhost:4317"
+## +toml2docs:none-default
+otlp_endpoint = ""
 
 ## 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]
@@ -633,20 +430,19 @@ enable = false
 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
+## +toml2docs:none-default
-db = "greptime_metrics"
+db = "information_schema"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-#+ [tracing]
+[tracing]
 ## The tokio console address.
-## @toml2docs:none-default
+## +toml2docs:none-default
-#+ tokio_console_addr = "127.0.0.1"
+tokio_console_addr = "127.0.0.1"

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

@@ -1,13 +1,9 @@
-## The default timezone of the server.
+## The running mode of the datanode. It can be `standalone` or `distributed`.
-## @toml2docs:none-default
+mode = "standalone"
-default_timezone = "UTC"
 
-## The runtime options.
+## The default timezone of the server.
-#+ [runtime]
+## +toml2docs:none-default
-## The number of threads to execute the runtime for global read operations.
+default_timezone = "UTC"
-#+ global_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-#+ compact_rt_size = 4
 
 ## The heartbeat options.
 [heartbeat]
@@ -21,20 +17,16 @@ retry_interval = "3s"
 [http]
 ## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
+## HTTP request timeout.
 timeout = "30s"
 ## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
+## Support 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 = "127.0.0.1:4001"
-## 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
 
@@ -44,11 +36,11 @@ runtime_size = 8
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload.
@@ -76,11 +68,11 @@ runtime_size = 2
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload
@@ -101,11 +93,11 @@ runtime_size = 2
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload
@@ -166,47 +158,29 @@ 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.
+## The directory to store the log files.
 dir = "/tmp/greptimedb/logs"
 
 ## The log level. Can be `info`/`debug`/`warn`/`error`.
-## @toml2docs:none-default
+## +toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-otlp_endpoint = "http://localhost:4317"
+## +toml2docs:none-default
+otlp_endpoint = ""
 
 ## 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]
@@ -218,20 +192,19 @@ enable = false
 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
+## +toml2docs:none-default
-db = "greptime_metrics"
+db = "information_schema"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-#+ [tracing]
+[tracing]
 ## The tokio console address.
-## @toml2docs:none-default
+## +toml2docs:none-default
-#+ tokio_console_addr = "127.0.0.1"
+tokio_console_addr = "127.0.0.1"

config/metasrv.example.toml

@@ -7,15 +7,14 @@ 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.
 server_addr = "127.0.0.1:3002"
 
-## Store server address default to etcd store.
+## Etcd server address.
 store_addr = "127.0.0.1:2379"
 
 ## Datanode selector type.
-## - `round_robin` (default value)
+## - `lease_based` (default value).
-## - `lease_based`
 ## - `load_based`
 ## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
-selector = "round_robin"
+selector = "lease_based"
 
 ## Store data in memory.
 use_memory_store = false
@@ -26,22 +25,6 @@ enable_telemetry = true
 ## If it's not empty, the metasrv will store all data with this key prefix.
 store_key_prefix = ""
 
-## 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
-
-## The datastore for meta server.
-backend = "EtcdStore"
-
-## 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]
 
@@ -60,32 +43,17 @@ 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"
-
+acceptable_heartbeat_pause = "3000ms"
-## 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.
 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
 
 [wal]
@@ -99,12 +67,7 @@ provider = "raft_engine"
 ## The broker endpoints of the Kafka cluster.
 broker_endpoints = ["127.0.0.1:9092"]
 
-## Automatically create topics for WAL.
+## Number of topics to be created upon start.
-## 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.
@@ -113,7 +76,6 @@ num_topics = 64
 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.
@@ -133,67 +95,31 @@ 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.
+## The directory to store the log files.
 dir = "/tmp/greptimedb/logs"
 
 ## The log level. Can be `info`/`debug`/`warn`/`error`.
-## @toml2docs:none-default
+## +toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-otlp_endpoint = "http://localhost:4317"
+## +toml2docs:none-default
+otlp_endpoint = ""
 
 ## 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]
@@ -205,20 +131,19 @@ enable = false
 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
+## +toml2docs:none-default
-db = "greptime_metrics"
+db = "information_schema"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-#+ [tracing]
+[tracing]
 ## The tokio console address.
-## @toml2docs:none-default
+## +toml2docs:none-default
-#+ tokio_console_addr = "127.0.0.1"
+tokio_console_addr = "127.0.0.1"

config/standalone.example.toml

@@ -5,35 +5,17 @@ mode = "standalone"
 enable_telemetry = true
 
 ## The default timezone of the server.
-## @toml2docs:none-default
+## +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
-
-## 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]
 ## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
+## HTTP request timeout.
 timeout = "30s"
 ## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
+## Support 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.
@@ -49,11 +31,11 @@ runtime_size = 8
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload.
@@ -81,11 +63,11 @@ runtime_size = 2
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload
@@ -106,11 +88,11 @@ runtime_size = 2
 mode = "disable"
 
 ## Certificate file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cert_path = ""
 
 ## Private key file path.
-## @toml2docs:none-default
+## +toml2docs:none-default
 key_path = ""
 
 ## Watch for Certificate and key file change and auto reload
@@ -142,7 +124,7 @@ provider = "raft_engine"
 
 ## The directory to store the WAL files.
 ## **It's only used when the provider is `raft_engine`**.
-## @toml2docs:none-default
+## +toml2docs:none-default
 dir = "/tmp/greptimedb/wal"
 
 ## The size of the WAL segment file.
@@ -177,45 +159,18 @@ prefill_log_files = false
 ## **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"
+max_batch_size = "1MB"
+
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
 
 ## The consumer wait timeout.
 ## **It's only used when the provider is `kafka`**.
@@ -237,35 +192,6 @@ backoff_base = 2
 ## **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.
@@ -316,7 +242,6 @@ retry_delay = "500ms"
 # root = "data"
 # scope = "test"
 # credential_path = "123456"
-# credential = "base64-credential"
 # endpoint = "https://storage.googleapis.com"
 
 ## The data storage options.
@@ -334,104 +259,85 @@ type = "File"
 
 ## Cache configuration for object storage such as 'S3' etc.
 ## The local file cache directory.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cache_path = "/path/local_cache"
 
 ## The local file cache capacity in bytes.
-## @toml2docs:none-default
+## +toml2docs:none-default
 cache_capacity = "256MB"
 
 ## The S3 bucket name.
 ## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
-## @toml2docs:none-default
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +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
+## +toml2docs:none-default
 region = "us-west-2"
 
 # 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"
 
 ## The region engine options. You can configure multiple region engines.
 [[region_engine]]
@@ -440,7 +346,7 @@ region = "us-west-2"
 [region_engine.mito]
 
 ## Number of region workers.
-#+ num_workers = 8
+num_workers = 8
 
 ## Request channel size of each worker.
 worker_channel_size = 128
@@ -454,48 +360,29 @@ manifest_checkpoint_distance = 10
 ## 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).
+## Max number of running background jobs
-## @toml2docs:none-default="Auto"
+max_background_jobs = 4
-#+ 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.
 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 = "1GB"
 
-## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`.
+## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
-## @toml2docs:none-default="Auto"
+global_write_buffer_reject_size = "2GB"
-#+ 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"
-#+ 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"
-#+ 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"
+page_cache_size = "512MB"
-#+ selector_result_cache_size = "512MB"
 
 ## Whether to enable the experimental write cache.
 enable_experimental_write_cache = false
@@ -507,8 +394,7 @@ experimental_write_cache_path = ""
 experimental_write_cache_size = "512MB"
 
 ## TTL for write cache.
-## @toml2docs:none-default
+experimental_write_cache_ttl = "1h"
-experimental_write_cache_ttl = "8h"
 
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
@@ -525,82 +411,31 @@ parallel_scan_channel_size = 32
 ## 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)
+## - `auto`: automatically
 ## - `disable`: never
 create_on_flush = "auto"
 
 ## Whether to create the index on compaction.
-## - `auto`: automatically (default)
+## - `auto`: automatically
 ## - `disable`: never
 create_on_compaction = "auto"
 
 ## Whether to apply the index on query
-## - `auto`: automatically (default)
+## - `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)
+## Setting to empty will disable external sorting, forcing all sorting operations to happen in memory.
-## - `unlimited`: no memory limit
+mem_threshold_on_create = "64M"
-## - `[size]` e.g. `64MB`: fixed memory threshold
-mem_threshold_on_create = "auto"
 
-## Deprecated, use `region_engine.mito.index.aux_path` instead.
+## 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"
-
-## Cache size for inverted index content.
-content_cache_size = "128MiB"
-
-## 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
@@ -619,53 +454,31 @@ data_freeze_threshold = 32768
 ## 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.
+## The directory to store the log files.
 dir = "/tmp/greptimedb/logs"
 
 ## The log level. Can be `info`/`debug`/`warn`/`error`.
-## @toml2docs:none-default
+## +toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-otlp_endpoint = "http://localhost:4317"
+## +toml2docs:none-default
+otlp_endpoint = ""
 
 ## 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]
@@ -676,21 +489,20 @@ enable = false
 ## The interval of export metrics.
 write_interval = "30s"
 
-## For `standalone` mode, `self_import` is recommended to collect metrics generated by itself
+## 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
+## +toml2docs:none-default
-db = "greptime_metrics"
+db = "information_schema"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-#+ [tracing]
+[tracing]
 ## The tokio console address.
-## @toml2docs:none-default
+## +toml2docs:none-default
-#+ tokio_console_addr = "127.0.0.1"
+tokio_console_addr = "127.0.0.1"

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/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

@@ -24,15 +24,6 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     python3.10 \
     python3.10-dev
 
-# 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 && \
@@ -64,11 +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.

docs/benchmarks/tsbs/v0.9.1.md

@@ -1,58 +0,0 @@
-# TSBS benchmark - v0.9.1
-
-## Environment
-
-### Local
-
-|        |                                    |
-| ------ | ---------------------------------- |
-| CPU    | AMD Ryzen 7 7735HS (8 core 3.2GHz) |
-| Memory | 32GB                               |
-| Disk   | SOLIDIGM SSDPFKNU010TZ             |
-| OS     | Ubuntu 22.04.2 LTS                 |
-
-### Amazon EC2
-
-|         |                         |
-| ------- | ----------------------- |
-| Machine | c5d.2xlarge             |
-| CPU     | 8 core                  |
-| Memory  | 16GB                    |
-| Disk    | 100GB (GP3)             |
-| OS      | Ubuntu Server 24.04 LTS |
-
-## Write performance
-
-| Environment     | Ingest rate (rows/s) |
-| --------------- | -------------------- |
-| Local           | 387697.68            |
-| EC2 c5d.2xlarge | 234620.19            |
-
-## Query performance
-
-| Query type            | Local (ms) | EC2 c5d.2xlarge (ms) |
-| --------------------- | ---------- | -------------------- |
-| cpu-max-all-1         | 21.14      | 14.75                |
-| cpu-max-all-8         | 36.79      | 30.69                |
-| double-groupby-1      | 529.02     | 987.85               |
-| double-groupby-5      | 1064.53    | 1455.95              |
-| double-groupby-all    | 1625.33    | 2143.96              |
-| groupby-orderby-limit | 529.19     | 1353.49              |
-| high-cpu-1            | 12.09      | 8.24                 |
-| high-cpu-all          | 3619.47    | 5312.82              |
-| lastpoint             | 224.91     | 576.06               |
-| single-groupby-1-1-1  | 10.82      | 6.01                 |
-| single-groupby-1-1-12 | 11.16      | 7.42                 |
-| single-groupby-1-8-1  | 13.50      | 10.20                |
-| single-groupby-5-1-1  | 11.99      | 6.70                 |
-| single-groupby-5-1-12 | 13.17      | 8.72                 |
-| single-groupby-5-8-1  | 16.01      | 12.07                |
-
-`single-groupby-1-1-1` query throughput
-
-| Environment     | Client concurrency | mean time (ms) | qps (queries/sec) |
-| --------------- | ------------------ | -------------- | ----------------- |
-| Local           | 50                 | 33.04          | 1511.74           |
-| Local           | 100                | 67.70          | 1476.14           |
-| EC2 c5d.2xlarge | 50                 | 61.93          | 806.97            |
-| EC2 c5d.2xlarge | 100                | 126.31         | 791.40            |

docs/how-to/how-to-change-log-level-on-the-fly.md

@@ -1,16 +0,0 @@
-# Change Log Level on the Fly
-
-## HTTP API
-
-example:
-```bash
-curl --data "trace;flow=debug" 127.0.0.1:4000/debug/log_level
-```
-And database will reply with something like:
-```bash
-Log Level changed from Some("info") to "trace;flow=debug"%
-```
-
-The data is a string in the format of `global_level;module1=level1;module2=level2;...` that follow the same rule of `RUST_LOG`. 
-
-The module is the module name of the log, and the level is the log level. The log level can be one of the following: `trace`, `debug`, `info`, `warn`, `error`, `off`(case insensitive).

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

@@ -105,7 +105,7 @@ use tests_fuzz::utils::{init_greptime_connections, Connections};
 
 fuzz_target!(|input: FuzzInput| {
     common_telemetry::init_default_ut_logging();
-    common_runtime::block_on_global(async {
+    common_runtime::block_on_write(async {
         let Connections { mysql } = init_greptime_connections().await;
             let mut rng = ChaChaRng::seed_from_u64(input.seed);
             let columns = rng.gen_range(2..30);

docs/rfcs/2024-08-06-json-datatype.md

@@ -1,197 +0,0 @@
----
-Feature Name: Json Datatype
-Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/4230
-Date: 2024-8-6
-Author: "Yuhan Wang <profsyb@gmail.com>"
----
-
-# Summary
-This RFC proposes a method for storing and querying JSON data in the database.
-
-# Motivation
-JSON is widely used across various scenarios. Direct support for writing and querying JSON can significantly enhance the database's flexibility.
-
-# Details
-
-## Storage and Query
-
-GreptimeDB's type system is built on Arrow/DataFusion, where each data type in GreptimeDB corresponds to a data type in Arrow/DataFusion. The proposed JSON type will be implemented on top of the existing `Binary` type, leveraging the current `datatype::value::Value` and `datatype::vectors::BinaryVector` implementations, utilizing the JSONB format as the encoding of JSON data. JSON data is stored and processed similarly to binary data within the storage layer and query engine.
-
-This approach brings problems when dealing with insertions and queries of JSON columns.
-
-## Insertion
-
-Users commonly write JSON data as strings. Thus we need to make conversions between string and JSONB. There are 2 ways to do this:
-
-1. MySQL and PostgreSQL servers provide auto-conversions between strings and JSONB. When a string is inserted into a JSON column, the server will try to parse the string as JSON and convert it to JSONB. The non-JSON strings will be rejected.
-
-2. A function `parse_json` is provided to convert string to JSONB. If the string is not a valid JSON string, the function will return an error.
-
-For example, in MySQL client:
-```SQL
-CREATE TABLE IF NOT EXISTS test (
-    ts TIMESTAMP TIME INDEX,
-    a INT,
-    b JSON
-);
-
-INSERT INTO test VALUES(
-    0,
-    0,
-    '{
-        "name": "jHl2oDDnPc1i2OzlP5Y",
-        "timestamp": "2024-07-25T04:33:11.369386Z",
-        "attributes": { "event_attributes": 48.28667 }
-    }'
-);
-
-INSERT INTO test VALUES(
-    0,
-    0,
-    parse_json('{
-        "name": "jHl2oDDnPc1i2OzlP5Y",
-        "timestamp": "2024-07-25T04:33:11.369386Z",
-        "attributes": { "event_attributes": 48.28667 }
-    }')
-);
-```
-Are both valid.
-
-The dataflow of the insertion process is as follows:
-```
-Insert JSON strings directly through client:
-                                   Parse                       Insert
-        String(Serialized JSON)┌──────────┐Arrow Binary(JSONB)┌──────┐Arrow Binary(JSONB)
- Client ---------------------->│  Server  │------------------>│ Mito │------------------> Storage
-                               └──────────┘                   └──────┘
-        (Server identifies JSON type and performs auto-conversion)
-
-Insert JSON strings through parse_json function:
-                                                                   Parse                     Insert
-        String(Serialized JSON)┌──────────┐String(Serialized JSON)┌─────┐Arrow Binary(JSONB)┌──────┐Arrow Binary(JSONB)
- Client ---------------------->│  Server  │---------------------->│ UDF │------------------>│ Mito │------------------> Storage
-                               └──────────┘                       └─────┘                   └──────┘
-                                            (Conversion is performed by UDF inside Query Engine)
-```
-
-Servers identify JSON column through column schema and perform auto-conversions. But when using prepared statements and binding parameters, the corresponding cached plans in datafusion generated by prepared statements cannot identify JSON columns. Under this circumstance, the servers identify JSON columns through the given parameters and perform auto-conversions.
-
-The following is an example of inserting JSON data through prepared statements:
-```Rust
-sqlx::query(
-    "create table test(ts timestamp time index, j json)",
-)
-.execute(&pool)
-.await
-.unwrap();
-
-let json = serde_json::json!({
-    "code": 200,
-    "success": true,
-    "payload": {
-        "features": [
-            "serde",
-            "json"
-        ],
-        "homepage": null
-    }
-});
-
-// Valid, can identify serde_json::Value as JSON type
-sqlx::query("insert into test values($1, $2)")
-    .bind(i)
-    .bind(json)
-    .execute(&pool)
-    .await
-    .unwrap();
-
-// Invalid, cannot identify String as JSON type
-sqlx::query("insert into test values($1, $2)")
-    .bind(i)
-    .bind(json.to_string())
-    .execute(&pool)
-    .await
-    .unwrap();
-```
-
-## Query
-
-Correspondingly, users prefer to display JSON data as strings. Thus we need to make conversions between JSON data and strings before presenting JSON data. There are also 2 ways to do this: auto-conversions on MySQL and PostgreSQL servers, and function `json_to_string`.
-
-For example, in MySQL client:
-```SQL
-SELECT b FROM test;
-
-SELECT json_to_string(b) FROM test;
-```
-Will both return the JSON as human-readable strings.
-
-Specifically, to perform auto-conversions, we attach a message to JSON data in the `metadata` of `Field` in Arrow/Datafusion schema when scanning a JSON column. Frontend servers could identify JSON data and convert it to strings.
-
-The dataflow of the query process is as follows:
-```
-Query directly through client:
-                                  Decode                            Scan
-        String(Serialized JSON)┌──────────┐Arrow Binary(JSONB)┌──────────────┐Arrow Binary(JSONB)
- Client <----------------------│  Server  │<------------------│ Query Engine │<----------------- Storage
-                               └──────────┘                   └──────────────┘
-(Server identifies JSON type and performs auto-conversion based on column metadata)
-
-Query through json_to_string function:
-                                                                   Scan & Decode
-        String(Serialized JSON)┌──────────┐String(Serialized JSON)┌──────────────┐Arrow Binary(JSONB)
- Client <----------------------│  Server  │<----------------------│ Query Engine │<----------------- Storage
-                               └──────────┘                       └──────────────┘
-                                                 (Conversion is performed by UDF inside Query Engine)
-
-```
-
-However, if a function uses JSON type as its return type, the metadata method mentioned above is not applicable. Thus the functions of JSON type should specify the return type explicitly instead of returning a JSON type, such as `json_get_int` and `json_get_float` which return corresponding data of `INT` and `FLOAT` type respectively.
-
-## Functions
-Similar to the common JSON type, JSON data can be queried with functions.
-
-For example:
-```SQL
-CREATE TABLE IF NOT EXISTS test (
-    ts TIMESTAMP TIME INDEX,
-    a INT,
-    b JSON
-);
-
-INSERT INTO test VALUES(
-    0,
-    0,
-    '{
-        "name": "jHl2oDDnPc1i2OzlP5Y",
-        "timestamp": "2024-07-25T04:33:11.369386Z",
-        "attributes": { "event_attributes": 48.28667 }
-    }'
-);
-
-SELECT json_get_string(b, 'name') FROM test;
-+---------------------+
-| b.name              |
-+---------------------+
-| jHl2oDDnPc1i2OzlP5Y |
-+---------------------+
-
-SELECT json_get_float(b, 'attributes.event_attributes') FROM test;
-+--------------------------------+
-| b.attributes.event_attributes  |
-+--------------------------------+
-| 48.28667                       |
-+--------------------------------+
-
-```
-And more functions can be added in the future.
-
-# Drawbacks
-
-As a general purpose JSON data type, JSONB may not be as efficient as specialized data types for specific scenarios.
-
-The auto-conversion mechanism is not supported in all scenarios. We need to find workarounds for these scenarios.
-
-# Alternatives
-
-Extract and flatten JSON schema to store in a structured format through pipeline. For nested data, we can provide nested types like `STRUCT` or `ARRAY`.

docs/schema-structs.md

@@ -0,0 +1,527 @@
+# Schema Structs
+
+# Common Schemas
+The `datatypes` crate defines the elementary schema struct to describe the metadata.
+
+## ColumnSchema
+[ColumnSchema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/datatypes/src/schema/column_schema.rs#L36) represents the metadata of a column. It is equivalent to arrow's [Field](https://docs.rs/arrow/latest/arrow/datatypes/struct.Field.html) with additional metadata such as default constraint and whether the column is a time index. The time index is the column with a `TIME INDEX` constraint of a table. We can convert the `ColumnSchema` into an arrow `Field` and convert the `Field` back to the `ColumnSchema` without losing metadata.
+
+```rust
+pub struct ColumnSchema {
+    pub name: String,
+    pub data_type: ConcreteDataType,
+    is_nullable: bool,
+    is_time_index: bool,
+    default_constraint: Option<ColumnDefaultConstraint>,
+    metadata: Metadata,
+}
+```
+
+## Schema
+[Schema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/datatypes/src/schema.rs#L38) is an ordered sequence of `ColumnSchema`. It is equivalent to arrow's [Schema](https://docs.rs/arrow/latest/arrow/datatypes/struct.Schema.html) with additional metadata including the index of the time index column and the version of this schema. Same as `ColumnSchema`, we can convert our `Schema` from/to arrow's `Schema`.
+
+```rust
+use arrow::datatypes::Schema as ArrowSchema;
+
+pub struct Schema {
+    column_schemas: Vec<ColumnSchema>,
+    name_to_index: HashMap<String, usize>,
+    arrow_schema: Arc<ArrowSchema>,
+    timestamp_index: Option<usize>,
+    version: u32,
+}
+
+pub type SchemaRef = Arc<Schema>;
+```
+
+We alias `Arc<Schema>` as `SchemaRef` since it is used frequently. Mostly, we use our `ColumnSchema` and `Schema` structs instead of Arrow's `Field` and `Schema` unless we need to invoke third-party libraries (like DataFusion or ArrowFlight) that rely on Arrow.
+
+## RawSchema
+`Schema` contains fields like a map from column names to their indices in the `ColumnSchema` sequences and a cached arrow `Schema`. We can construct these fields from the `ColumnSchema` sequences thus we don't want to serialize them. This is why we don't derive `Serialize` and `Deserialize` for `Schema`. We introduce a new struct [RawSchema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/datatypes/src/schema/raw.rs#L24) which keeps all required fields of a `Schema` and derives the serialization traits. To serialize a `Schema`, we need to convert it into a `RawSchema` first and serialize the `RawSchema`.
+
+```rust
+pub struct RawSchema {
+    pub column_schemas: Vec<ColumnSchema>,
+    pub timestamp_index: Option<usize>,
+    pub version: u32,
+}
+```
+
+We want to keep the `Schema` simple and avoid putting too much business-related metadata in it as many different structs or traits rely on it.
+
+# Schema of the Table
+A table maintains its schema in [TableMeta](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/table/src/metadata.rs#L97).
+```rust
+pub struct TableMeta {
+    pub schema: SchemaRef,
+    pub primary_key_indices: Vec<usize>,
+    pub value_indices: Vec<usize>,
+    // ...
+}
+```
+
+The order of columns in `TableMeta::schema` is the same as the order specified in the `CREATE TABLE` statement which users use to create this table.
+
+The field `primary_key_indices` stores indices of primary key columns. The field `value_indices` records the indices of value columns (non-primary key and time index, we sometimes call them field columns).
+
+Suppose we create a table with the following SQL
+```sql
+CREATE TABLE cpu (
+    ts TIMESTAMP,
+    host STRING,
+    usage_user DOUBLE,
+    usage_system DOUBLE,
+    datacenter STRING,
+    TIME INDEX (ts),
+    PRIMARY KEY(datacenter, host)) ENGINE=mito;
+```
+
+Then the table's `TableMeta` may look like this:
+```json
+{
+    "schema":{
+        "column_schemas":[
+            "ts",
+            "host",
+            "usage_user",
+            "usage_system",
+            "datacenter"
+        ],
+        "time_index":0,
+        "version":0
+    },
+    "primary_key_indices":[
+        4,
+        1
+    ],
+    "value_indices":[
+        2,
+        3
+    ]
+}
+```
+
+
+# Schemas of the storage engine
+We split a table into one or more units with the same schema and then store these units in the storage engine. Each unit is a region in the storage engine.
+
+The storage engine maintains schemas of regions in more complicated ways because it
+- adds internal columns that are invisible to users to store additional metadata for each row
+- provides a data model similar to the key-value model so it organizes columns in a different order
+- maintains additional metadata like column id or column family
+
+So the storage engine defines several schema structs:
+- RegionSchema
+- StoreSchema
+- ProjectedSchema
+
+## RegionSchema
+A [RegionSchema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/storage/src/schema/region.rs#L37) describes the schema of a region.
+
+```rust
+pub struct RegionSchema {
+    user_schema: SchemaRef,
+    store_schema: StoreSchemaRef,
+    columns: ColumnsMetadataRef,
+}
+```
+
+Each region reserves some columns called `internal columns` for internal usage:
+- `__sequence`, sequence number of a row
+- `__op_type`, operation type of a row, such as `PUT` or `DELETE`
+- `__version`, user-specified version of a row, reserved but not used. We might remove this in the future
+
+The table engine can't see the `__sequence` and `__op_type` columns, so the `RegionSchema` itself maintains two internal schemas:
+- User schema, a `Schema` struct that doesn't have internal columns
+- Store schema, a `StoreSchema` struct that has internal columns
+
+The `ColumnsMetadata` struct keeps metadata about all columns but most time we only need to use metadata in user schema and store schema, so we just ignore it. We may remove this struct in the future.
+
+`RegionSchema` organizes columns in the following order:
+```
+key columns, timestamp, [__version,] value columns, __sequence, __op_type
+```
+
+We can ignore the `__version` column because it is disabled now:
+
+```
+key columns, timestamp, value columns, __sequence, __op_type
+```
+
+Key columns are columns of a table's primary key. Timestamp is the time index column. A region sorts all rows by key columns, timestamp, sequence, and op type.
+
+So the `RegionSchema` of our `cpu` table above looks like this:
+```json
+{
+    "user_schema":[
+        "datacenter",
+        "host",
+        "ts",
+        "usage_user",
+        "usage_system"
+    ],
+    "store_schema":[
+        "datacenter",
+        "host",
+        "ts",
+        "usage_user",
+        "usage_system",
+        "__sequence",
+        "__op_type"
+    ]
+}
+```
+
+## StoreSchema
+As described above, a [StoreSchema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/storage/src/schema/store.rs#L36) is a schema that knows all internal columns.
+```rust
+struct StoreSchema {
+    columns: Vec<ColumnMetadata>,
+    schema: SchemaRef,
+    row_key_end: usize,
+    user_column_end: usize,
+}
+```
+
+The columns in the `columns` and `schema` fields have the same order. The `ColumnMetadata` has metadata like column id, column family id, and comment. The `StoreSchema` also stores this metadata in `StoreSchema::schema`, so we can convert the `StoreSchema` between arrow's `Schema`. We use this feature to persist the `StoreSchema` in the SST since our SST format is `Parquet`, which can take arrow's `Schema` as its schema.
+
+The `StoreSchema` of the region above is similar to this:
+```json
+{
+    "schema":{
+        "column_schemas":[
+            "datacenter",
+            "host",
+            "ts",
+            "usage_user",
+            "usage_system",
+            "__sequence",
+            "__op_type"
+        ],
+        "time_index":2,
+        "version":0
+    },
+    "row_key_end":3,
+    "user_column_end":5
+}
+```
+
+The key and timestamp columns form row keys of rows. We put them together so we can use `row_key_end` to get indices of all row key columns. Similarly, we can use the `user_column_end` to get indices of all user columns (non-internal columns).
+```rust
+impl StoreSchema {
+    #[inline]
+    pub(crate) fn row_key_indices(&self) -> impl Iterator<Item = usize> {
+        0..self.row_key_end
+    }
+
+    #[inline]
+    pub(crate) fn value_indices(&self) -> impl Iterator<Item = usize> {
+        self.row_key_end..self.user_column_end
+    }
+}
+```
+
+Another useful feature of `StoreSchema` is that we ensure it always contains key columns, a timestamp column, and internal columns because we need them to perform merge, deduplication, and delete. Projection on `StoreSchema` only projects value columns.
+
+## ProjectedSchema
+To support arbitrary projection, we introduce the [ProjectedSchema](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/storage/src/schema/projected.rs#L106).
+```rust
+pub struct ProjectedSchema {
+    projection: Option<Projection>,
+    schema_to_read: StoreSchemaRef,
+    projected_user_schema: SchemaRef,
+}
+```
+
+We need to handle many cases while doing projection:
+- The columns' order of table and region is different
+- The projection can be in arbitrary order, e.g. `select usage_user, host from cpu` and `select host, usage_user from cpu` have different projection order
+- We support `ALTER TABLE` so data files may have different schemas.
+
+### Projection
+Let's take an example to see how projection works. Suppose we want to select `ts`, `usage_system` from the `cpu` table.
+
+```sql
+CREATE TABLE cpu (
+    ts TIMESTAMP,
+    host STRING,
+    usage_user DOUBLE,
+    usage_system DOUBLE,
+    datacenter STRING,
+    TIME INDEX (ts),
+    PRIMARY KEY(datacenter, host)) ENGINE=mito;
+
+select ts, usage_system from cpu;
+```
+
+The query engine uses the projection `[0, 3]` to scan the table. However, columns in the region have a different order, so the table engine adjusts the projection to `2, 4`.
+```json
+{
+    "user_schema":[
+        "datacenter",
+        "host",
+        "ts",
+        "usage_user",
+        "usage_system"
+    ],
+}
+```
+
+As you can see, the output order is still `[ts, usage_system]`. This is the schema users can see after projection so we call it `projected user schema`.
+
+But the storage engine also needs to read key columns, a timestamp column, and internal columns. So we maintain a `StoreSchema` after projection in the `ProjectedSchema`.
+
+The `Projection` struct is a helper struct to help compute the projected user schema and store schema.
+
+So we can construct the following `ProjectedSchema`:
+```json
+{
+    "schema_to_read":{
+        "schema":{
+            "column_schemas":[
+                "datacenter",
+                "host",
+                "ts",
+                "usage_system",
+                "__sequence",
+                "__op_type"
+            ],
+            "time_index":2,
+            "version":0
+        },
+        "row_key_end":3,
+        "user_column_end":4
+    },
+    "projected_user_schema":{
+        "column_schemas":[
+            "ts",
+            "usage_system"
+        ],
+        "time_index":0
+    }
+}
+```
+
+As you can see, `schema_to_read` doesn't contain the column `usage_user` that is not intended to be read (not in projection).
+
+### ReadAdapter
+As mentioned above, we can alter a table so the underlying files (SSTs) and memtables in the storage engine may have different schemas.
+
+To simplify the logic of `ProjectedSchema`, we handle the difference between schemas before projection (constructing the `ProjectedSchema`). We introduce [ReadAdapter](https://github.com/GreptimeTeam/greptimedb/blob/9fa871a3fad07f583dc1863a509414da393747f8/src/storage/src/schema/compat.rs#L90) that adapts rows with different source schemas to the same expected schema.
+
+So we can always use the current `RegionSchema` of the region to construct the `ProjectedSchema`, and then create a `ReadAdapter` for each memtable or SST.
+```rust
+#[derive(Debug)]
+pub struct ReadAdapter {
+    source_schema: StoreSchemaRef,
+    dest_schema: ProjectedSchemaRef,
+    indices_in_result: Vec<Option<usize>>,
+    is_source_needed: Vec<bool>,
+}
+```
+
+For each column required by `dest_schema`, `indices_in_result` stores the index of that column in the row read from the source memtable or SST. If the source row doesn't contain that column, the index is `None`.
+
+The field `is_source_needed` stores whether a column in the source memtable or SST is needed.
+
+Suppose we add a new column `usage_idle` to the table `cpu`.
+```sql
+ALTER TABLE cpu ADD COLUMN usage_idle DOUBLE;
+```
+
+The new `StoreSchema` becomes:
+```json
+{
+    "schema":{
+        "column_schemas":[
+            "datacenter",
+            "host",
+            "ts",
+            "usage_user",
+            "usage_system",
+            "usage_idle",
+            "__sequence",
+            "__op_type"
+        ],
+        "time_index":2,
+        "version":1
+    },
+    "row_key_end":3,
+    "user_column_end":6
+}
+```
+
+Note that we bump the version of the schema to 1.
+
+If we want to select `ts`, `usage_system`, and `usage_idle`. While reading from the old schema, the storage engine creates a `ReadAdapter` like this:
+```json
+{
+    "source_schema":{
+        "schema":{
+            "column_schemas":[
+                "datacenter",
+                "host",
+                "ts",
+                "usage_user",
+                "usage_system",
+                "__sequence",
+                "__op_type"
+            ],
+            "time_index":2,
+            "version":0
+        },
+        "row_key_end":3,
+        "user_column_end":5
+    },
+    "dest_schema":{
+        "schema_to_read":{
+            "schema":{
+                "column_schemas":[
+                    "datacenter",
+                    "host",
+                    "ts",
+                    "usage_system",
+                    "usage_idle",
+                    "__sequence",
+                    "__op_type"
+                ],
+                "time_index":2,
+                "version":1
+            },
+            "row_key_end":3,
+            "user_column_end":5
+        },
+        "projected_user_schema":{
+            "column_schemas":[
+                "ts",
+                "usage_system",
+                "usage_idle"
+            ],
+            "time_index":0
+        }
+    },
+    "indices_in_result":[
+        0,
+        1,
+        2,
+        3,
+        null,
+        4,
+        5
+    ],
+    "is_source_needed":[
+        true,
+        true,
+        true,
+        false,
+        true,
+        true,
+        true
+    ]
+}
+```
+
+We don't need to read `usage_user` so `is_source_needed[3]` is false. The old schema doesn't have column `usage_idle` so `indices_in_result[4]` is `null` and the `ReadAdapter` needs to insert a null column to the output row so the output schema still contains `usage_idle`.
+
+The figure below shows the relationship between `RegionSchema`, `StoreSchema`, `ProjectedSchema`, and `ReadAdapter`.
+
+```text
+                   ┌──────────────────────────────┐
+                   │                              │
+                   │    ┌────────────────────┐    │
+                   │    │    store_schema    │    │
+                   │    │                    │    │
+                   │    │     StoreSchema    │    │
+                   │    │      version 1     │    │
+                   │    └────────────────────┘    │
+                   │                              │
+                   │    ┌────────────────────┐    │
+                   │    │     user_schema    │    │
+                   │    └────────────────────┘    │
+                   │                              │
+                   │         RegionSchema         │
+                   │                              │
+                   └──────────────┬───────────────┘
+                                  │
+                                  │
+                                  │
+                   ┌──────────────▼───────────────┐
+                   │                              │
+                   │ ┌──────────────────────────┐ │
+                   │ │     schema_to_read       │ │
+                   │ │                          │ │
+                   │ │  StoreSchema (projected) │ │
+                   │ │       version 1          │ │
+                   │ └──────────────────────────┘ │
+               ┌───┤                              ├───┐
+               │   │ ┌──────────────────────────┐ │   │
+               │   │ │  projected_user_schema   │ │   │
+               │   │ └──────────────────────────┘ │   │
+               │   │                              │   │
+               │   │       ProjectedSchema        │   │
+  dest schema  │   └──────────────────────────────┘   │   dest schema
+               │                                      │
+               │                                      │
+        ┌──────▼───────┐                      ┌───────▼──────┐
+        │              │                      │              │
+        │  ReadAdapter │                      │  ReadAdapter │
+        │              │                      │              │
+        └──────▲───────┘                      └───────▲──────┘
+               │                                      │
+               │                                      │
+source schema  │                                      │  source schema
+               │                                      │
+       ┌───────┴─────────┐                   ┌────────┴────────┐
+       │                 │                   │                 │
+       │ ┌─────────────┐ │                   │ ┌─────────────┐ │
+       │ │             │ │                   │ │             │ │
+       │ │ StoreSchema │ │                   │ │ StoreSchema │ │
+       │ │             │ │                   │ │             │ │
+       │ │  version 0  │ │                   │ │  version 1  │ │
+       │ │             │ │                   │ │             │ │
+       │ └─────────────┘ │                   │ └─────────────┘ │
+       │                 │                   │                 │
+       │      SST 0      │                   │      SST 1      │
+       │                 │                   │                 │
+       └─────────────────┘                   └─────────────────┘
+```
+
+# Conversion
+This figure shows the conversion between schemas:
+```text
+              ┌─────────────┐     schema                      From             ┌─────────────┐
+              │             ├──────────────────┐  ┌────────────────────────────►             │
+              │  TableMeta  │                  │  │                            │  RawSchema  │
+              │             │                  │  │  ┌─────────────────────────┤             │
+              └─────────────┘                  │  │  │        TryFrom          └─────────────┘
+                                               │  │  │
+                                               │  │  │
+                                               │  │  │
+                                               │  │  │
+                                               │  │  │
+    ┌───────────────────┐                ┌─────▼──┴──▼──┐   arrow_schema()    ┌─────────────────┐
+    │                   │                │              ├─────────────────────►                 │
+    │  ColumnsMetadata  │          ┌─────►    Schema    │                     │   ArrowSchema   ├──┐
+    │                   │          │     │              ◄─────────────────────┤                 │  │
+    └────┬───────────▲──┘          │     └───▲───▲──────┘       TryFrom       └─────────────────┘  │
+         │           │             │         │   │                                                 │
+         │           │             │         │   └────────────────────────────────────────┐        │
+         │           │             │         │                                            │        │
+         │   columns │    user_schema()      │                                            │        │
+         │           │             │         │ projected_user_schema()                 schema()    │
+         │           │             │         │                                            │        │
+         │       ┌───┴─────────────┴─┐       │                 ┌────────────────────┐     │        │
+columns  │       │                   │       └─────────────────┤                    │     │        │  TryFrom
+         │       │    RegionSchema   │                         │   ProjectedSchema  │     │        │
+         │       │                   ├─────────────────────────►                    │     │        │
+         │       └─────────────────┬─┘  ProjectedSchema::new() └──────────────────┬─┘     │        │
+         │                         │                                              │       │        │
+         │                         │                                              │       │        │
+         │                         │                                              │       │        │
+         │                         │                                              │       │        │
+    ┌────▼────────────────────┐    │               store_schema()            ┌────▼───────┴──┐     │
+    │                         │    └─────────────────────────────────────────►               │     │
+    │   Vec<ColumnMetadata>   │                                              │  StoreSchema  ◄─────┘
+    │                         ◄──────────────────────────────────────────────┤               │
+    └─────────────────────────┘                     columns                  └───────────────┘
+```

grafana/README.md

@@ -25,7 +25,7 @@ Please ensure the following configuration before importing the dashboard into Gr
 
 __1. Prometheus scrape config__
 
-Configure Prometheus to scrape the cluster.
+Assign `greptime_pod` label to each host target. We use this label to identify each node instance.
 
 ```yml
 # example config
@@ -34,15 +34,27 @@ Configure Prometheus to scrape the cluster.
 scrape_configs:
   - job_name: metasrv
     static_configs:
-    - targets: ['<metasrv-ip>:<port>']
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: metasrv
 
   - job_name: datanode
     static_configs:
-    - targets: ['<datanode0-ip>:<port>', '<datanode1-ip>:<port>', '<datanode2-ip>:<port>']
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode1
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode2
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: datanode3
 
   - job_name: frontend
     static_configs:
-    - targets: ['<frontend-ip>:<port>']
+    - targets: ['<ip>:<port>']
+      labels:
+        greptime_pod: frontend
 ```
 
 __2. Grafana config__
@@ -51,4 +63,4 @@ Create a Prometheus data source in Grafana before using this dashboard. We use `
 
 ### Usage
 
-Use `datasource` or `instance` on the upper-left corner to filter data from certain node.
+Use `datasource` or `greptime_pod` on the upper-left corner to filter data from certain node.

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "nightly-2024-10-19"
+channel = "nightly-2024-04-20"

scripts/check-builder-rust-version.sh

@@ -1,42 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-RUST_TOOLCHAIN_VERSION_FILE="rust-toolchain.toml"
-DEV_BUILDER_UBUNTU_REGISTRY="docker.io"
-DEV_BUILDER_UBUNTU_NAMESPACE="greptime"
-DEV_BUILDER_UBUNTU_NAME="dev-builder-ubuntu"
-
-function check_rust_toolchain_version() {
-  DEV_BUILDER_IMAGE_TAG=$(grep "DEV_BUILDER_IMAGE_TAG ?= " Makefile | cut -d= -f2 | sed 's/^[ \t]*//')
-  if [ -z "$DEV_BUILDER_IMAGE_TAG" ]; then
-    echo "Error: No DEV_BUILDER_IMAGE_TAG found in Makefile"
-    exit 1
-  fi
-
-  DEV_BUILDER_UBUNTU_IMAGE="$DEV_BUILDER_UBUNTU_REGISTRY/$DEV_BUILDER_UBUNTU_NAMESPACE/$DEV_BUILDER_UBUNTU_NAME:$DEV_BUILDER_IMAGE_TAG"
-
-  CURRENT_VERSION=$(grep -Eo '[0-9]{4}-[0-9]{2}-[0-9]{2}' "$RUST_TOOLCHAIN_VERSION_FILE")
-  if [ -z "$CURRENT_VERSION" ]; then
-    echo "Error: No rust toolchain version found in $RUST_TOOLCHAIN_VERSION_FILE"
-    exit 1
-  fi
-
-  RUST_TOOLCHAIN_VERSION_IN_BUILDER=$(docker run "$DEV_BUILDER_UBUNTU_IMAGE" rustc --version | grep  -Eo '[0-9]{4}-[0-9]{2}-[0-9]{2}')
-  if [ -z "$RUST_TOOLCHAIN_VERSION_IN_BUILDER" ]; then
-    echo "Error: No rustc version found in $DEV_BUILDER_UBUNTU_IMAGE"
-    exit 1
-  fi
-
-  # Compare the version and the difference should be less than 1 day.
-  current_rust_toolchain_seconds=$(date -d "$CURRENT_VERSION" +%s)
-  rust_toolchain_in_dev_builder_ubuntu_seconds=$(date -d "$RUST_TOOLCHAIN_VERSION_IN_BUILDER" +%s)
-  date_diff=$(( (current_rust_toolchain_seconds - rust_toolchain_in_dev_builder_ubuntu_seconds) / 86400 ))
-
-  if [ $date_diff -gt 1 ]; then
-    echo "Error: The rust toolchain '$RUST_TOOLCHAIN_VERSION_IN_BUILDER' in builder '$DEV_BUILDER_UBUNTU_IMAGE' maybe outdated, please update it to '$CURRENT_VERSION'"
-    exit 1
-  fi
-}
-
-check_rust_toolchain_version

scripts/check-snafu.py

@@ -1,69 +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 os
-import re
-
-
-def find_rust_files(directory):
-    error_files = []
-    other_rust_files = []
-    for root, _, files in os.walk(directory):
-        for file in files:
-            if file == "error.rs":
-                error_files.append(os.path.join(root, file))
-            elif file.endswith(".rs"):
-                other_rust_files.append(os.path.join(root, file))
-    return error_files, other_rust_files
-
-
-def extract_branch_names(file_content):
-    pattern = re.compile(r"#\[snafu\(display\([^\)]*\)\)\]\s*(\w+)\s*\{")
-    return pattern.findall(file_content)
-
-
-def check_snafu_in_files(branch_name, rust_files):
-    branch_name_snafu = f"{branch_name}Snafu"
-    for rust_file in rust_files:
-        with open(rust_file, "r") as file:
-            content = file.read()
-            if branch_name_snafu in content:
-                return True
-    return False
-
-
-def main():
-    error_files, other_rust_files = find_rust_files(".")
-    branch_names = []
-
-    for error_file in error_files:
-        with open(error_file, "r") as file:
-            content = file.read()
-            branch_names.extend(extract_branch_names(content))
-
-    unused_snafu = [
-        branch_name
-        for branch_name in branch_names
-        if not check_snafu_in_files(branch_name, other_rust_files)
-    ]
-
-    for name in unused_snafu:
-        print(name)
-
-    if unused_snafu:
-        raise SystemExit(1)
-
-
-if __name__ == "__main__":
-    main()

scripts/install.sh

@@ -1,21 +1,15 @@
-#!/usr/bin/env bash
+#!/bin/sh
 
 set -ue
 
 OS_TYPE=
 ARCH_TYPE=
-
-# Set the GitHub token to avoid GitHub API rate limit.
-# You can run with `GITHUB_TOKEN`:
-#  GITHUB_TOKEN=<your_token> ./scripts/install.sh
-GITHUB_TOKEN=${GITHUB_TOKEN:-}
-
 VERSION=${1:-latest}
 GITHUB_ORG=GreptimeTeam
 GITHUB_REPO=greptimedb
 BIN=greptime
 
-function get_os_type() {
+get_os_type() {
     os_type="$(uname -s)"
 
     case "$os_type" in
@@ -31,7 +25,7 @@ function get_os_type() {
     esac
 }
 
-function get_arch_type() {
+get_arch_type() {
     arch_type="$(uname -m)"
 
     case "$arch_type" in
@@ -53,19 +47,15 @@ function get_arch_type() {
     esac
 }
 
-function download_artifact() {
+get_os_type
-  if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
+get_arch_type
-    # Use the latest stable released version.
+
-    # GitHub API reference: https://docs.github.com/en/rest/releases/releases?apiVersion=2022-11-28#get-the-latest-release.
+if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
+    # Use the latest nightly version.
     if [ "${VERSION}" = "latest" ]; then
-      # To avoid other tools dependency, we choose to use `curl` to get the version metadata and parsed by `sed`.
+        VERSION=$(curl -s -XGET "https://api.github.com/repos/${GITHUB_ORG}/${GITHUB_REPO}/releases" | grep tag_name | grep nightly | cut -d: -f 2 | sed 's/.*"\(.*\)".*/\1/' | uniq | sort -r | head -n 1)
-      VERSION=$(curl -sL \
-        -H "Accept: application/vnd.github+json" \
-        -H "X-GitHub-Api-Version: 2022-11-28" \
-        ${GITHUB_TOKEN:+-H "Authorization: Bearer $GITHUB_TOKEN"} \
-        "https://api.github.com/repos/${GITHUB_ORG}/${GITHUB_REPO}/releases/latest" | sed -n 's/.*"tag_name": "\([^"]*\)".*/\1/p')
         if [ -z "${VERSION}" ]; then
-        echo "Failed to get the latest stable released version."
+            echo "Failed to get the latest version."
             exit 1
         fi
     fi
@@ -83,9 +73,4 @@ function download_artifact() {
       rm -r "${PACKAGE_NAME%.tar.gz}" && \
       echo "Run './${BIN} --help' to get started"
     fi
-  fi
+fi
-}
-
-get_os_type
-get_arch_type
-download_artifact

src/api/Cargo.toml

@@ -17,11 +17,10 @@ datatypes.workspace = true
 greptime-proto.workspace = true
 paste = "1.0"
 prost.workspace = true
-serde_json.workspace = true
 snafu.workspace = true
 
 [build-dependencies]
-tonic-build = "0.11"
+tonic-build = "0.9"
 
 [dev-dependencies]
 paste = "1.0"

src/api/src/error.rs

@@ -58,23 +58,13 @@ pub enum Error {
         location: Location,
         source: datatypes::error::Error,
     },
-
-    #[snafu(display("Failed to serialize JSON"))]
-    SerializeJson {
-        #[snafu(source)]
-        error: serde_json::Error,
-        #[snafu(implicit)]
-        location: Location,
-    },
 }
 
 impl ErrorExt for Error {
     fn status_code(&self) -> StatusCode {
         match self {
             Error::UnknownColumnDataType { .. } => StatusCode::InvalidArguments,
-            Error::IntoColumnDataType { .. } | Error::SerializeJson { .. } => {
+            Error::IntoColumnDataType { .. } => StatusCode::Unexpected,
-                StatusCode::Unexpected
-            }
             Error::ConvertColumnDefaultConstraint { source, .. }
             | Error::InvalidColumnDefaultConstraint { source, .. } => source.status_code(),
         }

src/api/src/helper.rs

@@ -17,11 +17,10 @@ use std::sync::Arc;
 use common_base::BitVec;
 use common_decimal::decimal128::{DECIMAL128_DEFAULT_SCALE, DECIMAL128_MAX_PRECISION};
 use common_decimal::Decimal128;
+use common_time::interval::IntervalUnit;
 use common_time::time::Time;
 use common_time::timestamp::TimeUnit;
-use common_time::{
+use common_time::{Date, DateTime, Interval, Timestamp};
-    Date, DateTime, IntervalDayTime, IntervalMonthDayNano, IntervalYearMonth, Timestamp,
-};
 use datatypes::prelude::{ConcreteDataType, ValueRef};
 use datatypes::scalars::ScalarVector;
 use datatypes::types::{
@@ -43,8 +42,7 @@ use greptime_proto::v1::greptime_request::Request;
 use greptime_proto::v1::query_request::Query;
 use greptime_proto::v1::value::ValueData;
 use greptime_proto::v1::{
-    ColumnDataTypeExtension, DdlRequest, DecimalTypeExtension, JsonTypeExtension, QueryRequest,
+    ColumnDataTypeExtension, DdlRequest, DecimalTypeExtension, QueryRequest, Row, SemanticType,
-    Row, SemanticType,
 };
 use paste::paste;
 use snafu::prelude::*;
@@ -105,18 +103,7 @@ impl From<ColumnDataTypeWrapper> for ConcreteDataType {
             ColumnDataType::Uint64 => ConcreteDataType::uint64_datatype(),
             ColumnDataType::Float32 => ConcreteDataType::float32_datatype(),
             ColumnDataType::Float64 => ConcreteDataType::float64_datatype(),
-            ColumnDataType::Binary => {
+            ColumnDataType::Binary => ConcreteDataType::binary_datatype(),
-                if let Some(TypeExt::JsonType(_)) = datatype_wrapper
-                    .datatype_ext
-                    .as_ref()
-                    .and_then(|datatype_ext| datatype_ext.type_ext.as_ref())
-                {
-                    ConcreteDataType::json_datatype()
-                } else {
-                    ConcreteDataType::binary_datatype()
-                }
-            }
-            ColumnDataType::Json => ConcreteDataType::json_datatype(),
             ColumnDataType::String => ConcreteDataType::string_datatype(),
             ColumnDataType::Date => ConcreteDataType::date_datatype(),
             ColumnDataType::Datetime => ConcreteDataType::datetime_datatype(),
@@ -249,7 +236,7 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
             ConcreteDataType::UInt64(_) => ColumnDataType::Uint64,
             ConcreteDataType::Float32(_) => ColumnDataType::Float32,
             ConcreteDataType::Float64(_) => ColumnDataType::Float64,
-            ConcreteDataType::Binary(_) | ConcreteDataType::Json(_) => ColumnDataType::Binary,
+            ConcreteDataType::Binary(_) => ColumnDataType::Binary,
             ConcreteDataType::String(_) => ColumnDataType::String,
             ConcreteDataType::Date(_) => ColumnDataType::Date,
             ConcreteDataType::DateTime(_) => ColumnDataType::Datetime,
@@ -289,16 +276,6 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
                         })),
                     })
             }
-            ColumnDataType::Binary => {
-                if datatype == ConcreteDataType::json_datatype() {
-                    // Json is the same as  binary in proto. The extension marks the binary in proto is actually a json.
-                    Some(ColumnDataTypeExtension {
-                        type_ext: Some(TypeExt::JsonType(JsonTypeExtension::JsonBinary.into())),
-                    })
-                } else {
-                    None
-                }
-            }
             _ => None,
         };
         Ok(Self {
@@ -418,10 +395,6 @@ pub fn values_with_capacity(datatype: ColumnDataType, capacity: usize) -> Values
             decimal128_values: Vec::with_capacity(capacity),
             ..Default::default()
         },
-        ColumnDataType::Json => Values {
-            string_values: Vec::with_capacity(capacity),
-            ..Default::default()
-        },
     }
 }
 
@@ -462,11 +435,13 @@ pub fn push_vals(column: &mut Column, origin_count: usize, vector: VectorRef) {
             TimeUnit::Microsecond => values.time_microsecond_values.push(val.value()),
             TimeUnit::Nanosecond => values.time_nanosecond_values.push(val.value()),
         },
-        Value::IntervalYearMonth(val) => values.interval_year_month_values.push(val.to_i32()),
+        Value::Interval(val) => match val.unit() {
-        Value::IntervalDayTime(val) => values.interval_day_time_values.push(val.to_i64()),
+            IntervalUnit::YearMonth => values.interval_year_month_values.push(val.to_i32()),
-        Value::IntervalMonthDayNano(val) => values
+            IntervalUnit::DayTime => values.interval_day_time_values.push(val.to_i64()),
+            IntervalUnit::MonthDayNano => values
                 .interval_month_day_nano_values
-            .push(convert_month_day_nano_to_pb(val)),
+                .push(convert_i128_to_interval(val.to_i128())),
+        },
         Value::Decimal128(val) => values.decimal128_values.push(convert_to_pb_decimal128(val)),
         Value::List(_) | Value::Duration(_) => unreachable!(),
     });
@@ -511,12 +486,14 @@ fn ddl_request_type(request: &DdlRequest) -> &'static str {
     }
 }
 
-/// Converts an interval to google protobuf type [IntervalMonthDayNano].
+/// Converts an i128 value to google protobuf type [IntervalMonthDayNano].
-pub fn convert_month_day_nano_to_pb(v: IntervalMonthDayNano) -> v1::IntervalMonthDayNano {
+pub fn convert_i128_to_interval(v: i128) -> v1::IntervalMonthDayNano {
+    let interval = Interval::from_i128(v);
+    let (months, days, nanoseconds) = interval.to_month_day_nano();
     v1::IntervalMonthDayNano {
-        months: v.months,
+        months,
-        days: v.days,
+        days,
-        nanoseconds: v.nanoseconds,
+        nanoseconds,
     }
 }
 
@@ -564,15 +541,11 @@ pub fn pb_value_to_value_ref<'a>(
         ValueData::TimeMillisecondValue(t) => ValueRef::Time(Time::new_millisecond(*t)),
         ValueData::TimeMicrosecondValue(t) => ValueRef::Time(Time::new_microsecond(*t)),
         ValueData::TimeNanosecondValue(t) => ValueRef::Time(Time::new_nanosecond(*t)),
-        ValueData::IntervalYearMonthValue(v) => {
+        ValueData::IntervalYearMonthValue(v) => ValueRef::Interval(Interval::from_i32(*v)),
-            ValueRef::IntervalYearMonth(IntervalYearMonth::from_i32(*v))
+        ValueData::IntervalDayTimeValue(v) => ValueRef::Interval(Interval::from_i64(*v)),
-        }
-        ValueData::IntervalDayTimeValue(v) => {
-            ValueRef::IntervalDayTime(IntervalDayTime::from_i64(*v))
-        }
         ValueData::IntervalMonthDayNanoValue(v) => {
-            let interval = IntervalMonthDayNano::new(v.months, v.days, v.nanoseconds);
+            let interval = Interval::from_month_day_nano(v.months, v.days, v.nanoseconds);
-            ValueRef::IntervalMonthDayNano(interval)
+            ValueRef::Interval(interval)
         }
         ValueData::Decimal128Value(v) => {
             // get precision and scale from datatype_extension
@@ -663,7 +636,7 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
             IntervalType::MonthDayNano(_) => {
                 Arc::new(IntervalMonthDayNanoVector::from_iter_values(
                     values.interval_month_day_nano_values.iter().map(|x| {
-                        IntervalMonthDayNano::new(x.months, x.days, x.nanoseconds).to_i128()
+                        Interval::from_month_day_nano(x.months, x.days, x.nanoseconds).to_i128()
                     }),
                 ))
             }
@@ -676,8 +649,7 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
         ConcreteDataType::Null(_)
         | ConcreteDataType::List(_)
         | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_)
+        | ConcreteDataType::Duration(_) => {
-        | ConcreteDataType::Json(_) => {
             unreachable!()
         }
     }
@@ -808,18 +780,18 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
         ConcreteDataType::Interval(IntervalType::YearMonth(_)) => values
             .interval_year_month_values
             .into_iter()
-            .map(|v| Value::IntervalYearMonth(IntervalYearMonth::from_i32(v)))
+            .map(|v| Value::Interval(Interval::from_i32(v)))
             .collect(),
         ConcreteDataType::Interval(IntervalType::DayTime(_)) => values
             .interval_day_time_values
             .into_iter()
-            .map(|v| Value::IntervalDayTime(IntervalDayTime::from_i64(v)))
+            .map(|v| Value::Interval(Interval::from_i64(v)))
             .collect(),
         ConcreteDataType::Interval(IntervalType::MonthDayNano(_)) => values
             .interval_month_day_nano_values
             .into_iter()
             .map(|v| {
-                Value::IntervalMonthDayNano(IntervalMonthDayNano::new(
+                Value::Interval(Interval::from_month_day_nano(
                     v.months,
                     v.days,
                     v.nanoseconds,
@@ -841,8 +813,7 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
         ConcreteDataType::Null(_)
         | ConcreteDataType::List(_)
         | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_)
+        | ConcreteDataType::Duration(_) => {
-        | ConcreteDataType::Json(_) => {
             unreachable!()
         }
     }
@@ -860,13 +831,7 @@ pub fn is_column_type_value_eq(
     expect_type: &ConcreteDataType,
 ) -> bool {
     ColumnDataTypeWrapper::try_new(type_value, type_extension)
-        .map(|wrapper| {
+        .map(|wrapper| ConcreteDataType::from(wrapper) == *expect_type)
-            let datatype = ConcreteDataType::from(wrapper);
-            (datatype == *expect_type)
-            // Json type leverage binary type in pb, so this is valid.
-                || (datatype == ConcreteDataType::binary_datatype()
-                    && *expect_type == ConcreteDataType::json_datatype())
-        })
         .unwrap_or(false)
 }
 
@@ -947,17 +912,19 @@ pub fn to_proto_value(value: Value) -> Option<v1::Value> {
                 value_data: Some(ValueData::TimeNanosecondValue(v.value())),
             },
         },
-        Value::IntervalYearMonth(v) => v1::Value {
+        Value::Interval(v) => match v.unit() {
+            IntervalUnit::YearMonth => v1::Value {
                 value_data: Some(ValueData::IntervalYearMonthValue(v.to_i32())),
             },
-        Value::IntervalDayTime(v) => v1::Value {
+            IntervalUnit::DayTime => v1::Value {
                 value_data: Some(ValueData::IntervalDayTimeValue(v.to_i64())),
             },
-        Value::IntervalMonthDayNano(v) => v1::Value {
+            IntervalUnit::MonthDayNano => v1::Value {
                 value_data: Some(ValueData::IntervalMonthDayNanoValue(
-                convert_month_day_nano_to_pb(v),
+                    convert_i128_to_interval(v.to_i128()),
                 )),
             },
+        },
         Value::Decimal128(v) => v1::Value {
             value_data: Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
         },
@@ -1048,11 +1015,13 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
                 TimeUnit::Microsecond => ValueData::TimeMicrosecondValue(v.value()),
                 TimeUnit::Nanosecond => ValueData::TimeNanosecondValue(v.value()),
             }),
-            Value::IntervalYearMonth(v) => Some(ValueData::IntervalYearMonthValue(v.to_i32())),
+            Value::Interval(v) => Some(match v.unit() {
-            Value::IntervalDayTime(v) => Some(ValueData::IntervalDayTimeValue(v.to_i64())),
+                IntervalUnit::YearMonth => ValueData::IntervalYearMonthValue(v.to_i32()),
-            Value::IntervalMonthDayNano(v) => Some(ValueData::IntervalMonthDayNanoValue(
+                IntervalUnit::DayTime => ValueData::IntervalDayTimeValue(v.to_i64()),
-                convert_month_day_nano_to_pb(v),
+                IntervalUnit::MonthDayNano => {
-            )),
+                    ValueData::IntervalMonthDayNanoValue(convert_i128_to_interval(v.to_i128()))
+                }
+            }),
             Value::Decimal128(v) => Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
             Value::List(_) | Value::Duration(_) => unreachable!(),
         },
@@ -1063,7 +1032,6 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
 mod tests {
     use std::sync::Arc;
 
-    use common_time::interval::IntervalUnit;
     use datatypes::types::{
         Int32Type, IntervalDayTimeType, IntervalMonthDayNanoType, IntervalYearMonthType,
         TimeMillisecondType, TimeSecondType, TimestampMillisecondType, TimestampSecondType,
@@ -1509,11 +1477,11 @@ mod tests {
 
     #[test]
     fn test_convert_i128_to_interval() {
-        let i128_val = 3;
+        let i128_val = 3000;
-        let interval = convert_month_day_nano_to_pb(IntervalMonthDayNano::from_i128(i128_val));
+        let interval = convert_i128_to_interval(i128_val);
         assert_eq!(interval.months, 0);
         assert_eq!(interval.days, 0);
-        assert_eq!(interval.nanoseconds, 3);
+        assert_eq!(interval.nanoseconds, 3000);
     }
 
     #[test]
@@ -1593,9 +1561,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::IntervalYearMonth(IntervalYearMonth::new(1_i32)),
+            Value::Interval(Interval::from_year_month(1_i32)),
-            Value::IntervalYearMonth(IntervalYearMonth::new(2_i32)),
+            Value::Interval(Interval::from_year_month(2_i32)),
-            Value::IntervalYearMonth(IntervalYearMonth::new(3_i32)),
+            Value::Interval(Interval::from_year_month(3_i32)),
         ];
         assert_eq!(expect, actual);
 
@@ -1608,9 +1576,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::IntervalDayTime(IntervalDayTime::from_i64(1_i64)),
+            Value::Interval(Interval::from_i64(1_i64)),
-            Value::IntervalDayTime(IntervalDayTime::from_i64(2_i64)),
+            Value::Interval(Interval::from_i64(2_i64)),
-            Value::IntervalDayTime(IntervalDayTime::from_i64(3_i64)),
+            Value::Interval(Interval::from_i64(3_i64)),
         ];
         assert_eq!(expect, actual);
 
@@ -1639,9 +1607,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(1, 2, 3)),
+            Value::Interval(Interval::from_month_day_nano(1, 2, 3)),
-            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(5, 6, 7)),
+            Value::Interval(Interval::from_month_day_nano(5, 6, 7)),
-            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(9, 10, 11)),
+            Value::Interval(Interval::from_month_day_nano(9, 10, 11)),
         ];
         assert_eq!(expect, actual);
     }
@@ -1875,7 +1843,6 @@ mod tests {
             null_mask: vec![2],
             datatype: ColumnDataType::Boolean as i32,
             datatype_extension: None,
-            options: None,
         };
         assert!(is_column_type_value_eq(
             column1.datatype,

src/api/src/lib.rs

@@ -12,8 +12,6 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-#![feature(let_chains)]
-
 pub mod error;
 pub mod helper;
 

src/api/src/region.rs

@@ -21,14 +21,14 @@ use greptime_proto::v1::region::RegionResponse as RegionResponseV1;
 #[derive(Debug)]
 pub struct RegionResponse {
     pub affected_rows: AffectedRows,
-    pub extensions: HashMap<String, Vec<u8>>,
+    pub extension: HashMap<String, Vec<u8>>,
 }
 
 impl RegionResponse {
     pub fn from_region_response(region_response: RegionResponseV1) -> Self {
         Self {
             affected_rows: region_response.affected_rows as _,
-            extensions: region_response.extensions,
+            extension: region_response.extension,
         }
     }
 
@@ -36,7 +36,7 @@ impl RegionResponse {
     pub fn new(affected_rows: AffectedRows) -> Self {
         Self {
             affected_rows,
-            extensions: Default::default(),
+            extension: Default::default(),
         }
     }
 }

src/api/src/v1/column_def.rs

@@ -14,19 +14,13 @@
 
 use std::collections::HashMap;
 
-use datatypes::schema::{
+use datatypes::schema::{ColumnDefaultConstraint, ColumnSchema, COMMENT_KEY};
-    ColumnDefaultConstraint, ColumnSchema, FulltextOptions, COMMENT_KEY, FULLTEXT_KEY,
-};
 use snafu::ResultExt;
 
 use crate::error::{self, Result};
 use crate::helper::ColumnDataTypeWrapper;
-use crate::v1::{ColumnDef, ColumnOptions, SemanticType};
+use crate::v1::ColumnDef;
 
-/// Key used to store fulltext options in gRPC column options.
-const FULLTEXT_GRPC_KEY: &str = "fulltext";
-
-/// Tries to construct a `ColumnSchema` from the given  `ColumnDef`.
 pub fn try_as_column_schema(column_def: &ColumnDef) -> Result<ColumnSchema> {
     let data_type = ColumnDataTypeWrapper::try_new(
         column_def.data_type,
@@ -49,147 +43,13 @@ pub fn try_as_column_schema(column_def: &ColumnDef) -> Result<ColumnSchema> {
     if !column_def.comment.is_empty() {
         metadata.insert(COMMENT_KEY.to_string(), column_def.comment.clone());
     }
-    if let Some(options) = column_def.options.as_ref()
-        && let Some(fulltext) = options.options.get(FULLTEXT_GRPC_KEY)
-    {
-        metadata.insert(FULLTEXT_KEY.to_string(), fulltext.to_string());
-    }
 
+    Ok(
         ColumnSchema::new(&column_def.name, data_type.into(), column_def.is_nullable)
-        .with_metadata(metadata)
-        .with_time_index(column_def.semantic_type() == SemanticType::Timestamp)
             .with_default_constraint(constraint)
             .context(error::InvalidColumnDefaultConstraintSnafu {
                 column: &column_def.name,
-        })
+            })?
-}
+            .with_metadata(metadata),
-
+    )
-/// Constructs a `ColumnOptions` from the given `ColumnSchema`.
-pub fn options_from_column_schema(column_schema: &ColumnSchema) -> Option<ColumnOptions> {
-    let mut options = ColumnOptions::default();
-    if let Some(fulltext) = column_schema.metadata().get(FULLTEXT_KEY) {
-        options
-            .options
-            .insert(FULLTEXT_GRPC_KEY.to_string(), fulltext.to_string());
-    }
-
-    (!options.options.is_empty()).then_some(options)
-}
-
-/// Checks if the `ColumnOptions` contains fulltext options.
-pub fn contains_fulltext(options: &Option<ColumnOptions>) -> bool {
-    options
-        .as_ref()
-        .map_or(false, |o| o.options.contains_key(FULLTEXT_GRPC_KEY))
-}
-
-/// Tries to construct a `ColumnOptions` from the given `FulltextOptions`.
-pub fn options_from_fulltext(fulltext: &FulltextOptions) -> Result<Option<ColumnOptions>> {
-    let mut options = ColumnOptions::default();
-
-    let v = serde_json::to_string(fulltext).context(error::SerializeJsonSnafu)?;
-    options.options.insert(FULLTEXT_GRPC_KEY.to_string(), v);
-
-    Ok((!options.options.is_empty()).then_some(options))
-}
-
-#[cfg(test)]
-mod tests {
-
-    use datatypes::data_type::ConcreteDataType;
-    use datatypes::schema::FulltextAnalyzer;
-
-    use super::*;
-    use crate::v1::ColumnDataType;
-
-    #[test]
-    fn test_try_as_column_schema() {
-        let column_def = ColumnDef {
-            name: "test".to_string(),
-            data_type: ColumnDataType::String as i32,
-            is_nullable: true,
-            default_constraint: ColumnDefaultConstraint::Value("test_default".into())
-                .try_into()
-                .unwrap(),
-            semantic_type: SemanticType::Field as i32,
-            comment: "test_comment".to_string(),
-            datatype_extension: None,
-            options: Some(ColumnOptions {
-                options: HashMap::from([(
-                    FULLTEXT_GRPC_KEY.to_string(),
-                    "{\"enable\":true}".to_string(),
-                )]),
-            }),
-        };
-
-        let schema = try_as_column_schema(&column_def).unwrap();
-        assert_eq!(schema.name, "test");
-        assert_eq!(schema.data_type, ConcreteDataType::string_datatype());
-        assert!(!schema.is_time_index());
-        assert!(schema.is_nullable());
-        assert_eq!(
-            schema.default_constraint().unwrap(),
-            &ColumnDefaultConstraint::Value("test_default".into())
-        );
-        assert_eq!(schema.metadata().get(COMMENT_KEY).unwrap(), "test_comment");
-        assert_eq!(
-            schema.fulltext_options().unwrap().unwrap(),
-            FulltextOptions {
-                enable: true,
-                ..Default::default()
-            }
-        );
-    }
-
-    #[test]
-    fn test_options_from_column_schema() {
-        let schema = ColumnSchema::new("test", ConcreteDataType::string_datatype(), true);
-        let options = options_from_column_schema(&schema);
-        assert!(options.is_none());
-
-        let schema = ColumnSchema::new("test", ConcreteDataType::string_datatype(), true)
-            .with_fulltext_options(FulltextOptions {
-                enable: true,
-                analyzer: FulltextAnalyzer::English,
-                case_sensitive: false,
-            })
-            .unwrap();
-        let options = options_from_column_schema(&schema).unwrap();
-        assert_eq!(
-            options.options.get(FULLTEXT_GRPC_KEY).unwrap(),
-            "{\"enable\":true,\"analyzer\":\"English\",\"case-sensitive\":false}"
-        );
-    }
-
-    #[test]
-    fn test_options_with_fulltext() {
-        let fulltext = FulltextOptions {
-            enable: true,
-            analyzer: FulltextAnalyzer::English,
-            case_sensitive: false,
-        };
-        let options = options_from_fulltext(&fulltext).unwrap().unwrap();
-        assert_eq!(
-            options.options.get(FULLTEXT_GRPC_KEY).unwrap(),
-            "{\"enable\":true,\"analyzer\":\"English\",\"case-sensitive\":false}"
-        );
-    }
-
-    #[test]
-    fn test_contains_fulltext() {
-        let options = ColumnOptions {
-            options: HashMap::from([(
-                FULLTEXT_GRPC_KEY.to_string(),
-                "{\"enable\":true}".to_string(),
-            )]),
-        };
-        assert!(contains_fulltext(&Some(options)));
-
-        let options = ColumnOptions {
-            options: HashMap::new(),
-        };
-        assert!(!contains_fulltext(&Some(options)));
-
-        assert!(!contains_fulltext(&None));
-    }
 }

src/auth/src/common.rs

@@ -75,16 +75,6 @@ pub enum Password<'a> {
     PgMD5(HashedPassword<'a>, Salt<'a>),
 }
 
-impl Password<'_> {
-    pub fn r#type(&self) -> &str {
-        match self {
-            Password::PlainText(_) => "plain_text",
-            Password::MysqlNativePassword(_, _) => "mysql_native_password",
-            Password::PgMD5(_, _) => "pg_md5",
-        }
-    }
-}
-
 pub fn auth_mysql(
     auth_data: HashedPassword,
     salt: Salt,

src/auth/src/error.rs

@@ -38,11 +38,10 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display("Authentication source failure"))]
+    #[snafu(display("Auth failed"))]
     AuthBackend {
         #[snafu(implicit)]
         location: Location,
-        #[snafu(source)]
         source: BoxedError,
     },
 
@@ -88,8 +87,8 @@ impl ErrorExt for Error {
             Error::IllegalParam { .. } => StatusCode::InvalidArguments,
             Error::FileWatch { .. } => StatusCode::InvalidArguments,
             Error::InternalState { .. } => StatusCode::Unexpected,
-            Error::Io { .. } => StatusCode::StorageUnavailable,
+            Error::Io { .. } => StatusCode::Internal,
-            Error::AuthBackend { source, .. } => source.status_code(),
+            Error::AuthBackend { .. } => StatusCode::Internal,
 
             Error::UserNotFound { .. } => StatusCode::UserNotFound,
             Error::UnsupportedPasswordType { .. } => StatusCode::UnsupportedPasswordType,

src/auth/src/permission.rs

@@ -30,7 +30,6 @@ pub enum PermissionReq<'a> {
     PromStoreWrite,
     PromStoreRead,
     Otlp,
-    LogWrite,
 }
 
 #[derive(Debug)]
@@ -42,7 +41,7 @@ pub enum PermissionResp {
 pub trait PermissionChecker: Send + Sync {
     fn check_permission(
         &self,
-        user_info: UserInfoRef,
+        user_info: Option<UserInfoRef>,
         req: PermissionReq,
     ) -> Result<PermissionResp>;
 }
@@ -50,7 +49,7 @@ pub trait PermissionChecker: Send + Sync {
 impl PermissionChecker for Option<&PermissionCheckerRef> {
     fn check_permission(
         &self,
-        user_info: UserInfoRef,
+        user_info: Option<UserInfoRef>,
         req: PermissionReq,
     ) -> Result<PermissionResp> {
         match self {

src/auth/src/tests.rs

@@ -13,11 +13,9 @@
 // limitations under the License.
 
 use common_base::secrets::ExposeSecret;
-use common_error::ext::BoxedError;
-use snafu::{OptionExt, ResultExt};
 
 use crate::error::{
-    AccessDeniedSnafu, AuthBackendSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
+    AccessDeniedSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
     UserPasswordMismatchSnafu,
 };
 use crate::user_info::DefaultUserInfo;
@@ -51,19 +49,6 @@ impl MockUserProvider {
         info.schema.clone_into(&mut self.schema);
         info.username.clone_into(&mut self.username);
     }
-
-    // this is a deliberate function to ref AuthBackendSnafu
-    // so that it won't get deleted in the future
-    pub fn ref_auth_backend_snafu(&self) -> Result<()> {
-        let none_option = None;
-
-        none_option
-            .context(UserNotFoundSnafu {
-                username: "no_user".to_string(),
-            })
-            .map_err(BoxedError::new)
-            .context(AuthBackendSnafu)
-    }
 }
 
 #[async_trait::async_trait]

src/auth/src/user_provider.rs

@@ -57,11 +57,6 @@ pub trait UserProvider: Send + Sync {
         self.authorize(catalog, schema, &user_info).await?;
         Ok(user_info)
     }
-
-    /// Returns whether this user provider implementation is backed by an external system.
-    fn external(&self) -> bool {
-        false
-    }
 }
 
 fn load_credential_from_file(filepath: &str) -> Result<Option<HashMap<String, Vec<u8>>>> {

src/auth/src/user_provider/static_user_provider.rs

@@ -33,7 +33,7 @@ impl StaticUserProvider {
             value: value.to_string(),
             msg: "StaticUserProviderOption must be in format `<option>:<value>`",
         })?;
-        match mode {
+        return match mode {
             "file" => {
                 let users = load_credential_from_file(content)?
                     .context(InvalidConfigSnafu {
@@ -58,7 +58,7 @@ impl StaticUserProvider {
                 msg: "StaticUserProviderOption must be in format `file:<path>` or `cmd:<values>`",
             }
                 .fail(),
-        }
+        };
     }
 }
 

src/auth/tests/mod.rs

@@ -18,7 +18,6 @@ use std::sync::Arc;
 
 use api::v1::greptime_request::Request;
 use auth::error::Error::InternalState;
-use auth::error::InternalStateSnafu;
 use auth::{PermissionChecker, PermissionCheckerRef, PermissionReq, PermissionResp, UserInfoRef};
 use sql::statements::show::{ShowDatabases, ShowKind};
 use sql::statements::statement::Statement;
@@ -28,16 +27,15 @@ struct DummyPermissionChecker;
 impl PermissionChecker for DummyPermissionChecker {
     fn check_permission(
         &self,
-        _user_info: UserInfoRef,
+        _user_info: Option<UserInfoRef>,
         req: PermissionReq,
     ) -> auth::error::Result<PermissionResp> {
         match req {
             PermissionReq::GrpcRequest(_) => Ok(PermissionResp::Allow),
             PermissionReq::SqlStatement(_) => Ok(PermissionResp::Reject),
-            _ => InternalStateSnafu {
+            _ => Err(InternalState {
                 msg: "testing".to_string(),
-            }
+            }),
-            .fail(),
         }
     }
 }
@@ -47,21 +45,17 @@ fn test_permission_checker() {
     let checker: PermissionCheckerRef = Arc::new(DummyPermissionChecker);
 
     let grpc_result = checker.check_permission(
-        auth::userinfo_by_name(None),
+        None,
         PermissionReq::GrpcRequest(&Request::Query(Default::default())),
     );
     assert_matches!(grpc_result, Ok(PermissionResp::Allow));
 
     let sql_result = checker.check_permission(
-        auth::userinfo_by_name(None),
+        None,
-        PermissionReq::SqlStatement(&Statement::ShowDatabases(ShowDatabases::new(
+        PermissionReq::SqlStatement(&Statement::ShowDatabases(ShowDatabases::new(ShowKind::All))),
-            ShowKind::All,
-            false,
-        ))),
     );
     assert_matches!(sql_result, Ok(PermissionResp::Reject));
 
-    let err_result =
+    let err_result = checker.check_permission(None, PermissionReq::Opentsdb);
-        checker.check_permission(auth::userinfo_by_name(None), PermissionReq::Opentsdb);
     assert_matches!(err_result, Err(InternalState { msg }) if msg == "testing");
 }

src/cache/src/error.rs

@@ -34,7 +34,7 @@ pub type Result<T> = std::result::Result<T, Error>;
 impl ErrorExt for Error {
     fn status_code(&self) -> StatusCode {
         match self {
-            Error::CacheRequired { .. } => StatusCode::Unexpected,
+            Error::CacheRequired { .. } => StatusCode::Internal,
         }
     }
 

src/catalog/Cargo.toml

@@ -22,10 +22,8 @@ common-config.workspace = true
 common-error.workspace = true
 common-macro.workspace = true
 common-meta.workspace = true
-common-procedure.workspace = true
 common-query.workspace = true
 common-recordbatch.workspace = true
-common-runtime.workspace = true
 common-telemetry.workspace = true
 common-time.workspace = true
 common-version.workspace = true
@@ -42,7 +40,6 @@ moka = { workspace = true, features = ["future", "sync"] }
 partition.workspace = true
 paste = "1.0"
 prometheus.workspace = true
-rustc-hash.workspace = true
 serde_json.workspace = true
 session.workspace = true
 snafu.workspace = true
@@ -50,7 +47,6 @@ sql.workspace = true
 store-api.workspace = true
 table.workspace = true
 tokio.workspace = true
-tokio-stream = "0.1"
 
 [dev-dependencies]
 cache.workspace = true

src/catalog/src/error.rs

@@ -18,7 +18,6 @@ use std::fmt::Debug;
 use common_error::ext::{BoxedError, ErrorExt};
 use common_error::status_code::StatusCode;
 use common_macro::stack_trace_debug;
-use common_query::error::datafusion_status_code;
 use datafusion::error::DataFusionError;
 use snafu::{Location, Snafu};
 
@@ -50,71 +49,13 @@ pub enum Error {
         source: BoxedError,
     },
 
-    #[snafu(display("Failed to list nodes in cluster"))]
+    #[snafu(display("Failed to list nodes in cluster: {source}"))]
     ListNodes {
         #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
 
-    #[snafu(display("Failed to region stats in cluster"))]
-    ListRegionStats {
-        #[snafu(implicit)]
-        location: Location,
-        source: BoxedError,
-    },
-
-    #[snafu(display("Failed to list flows in catalog {catalog}"))]
-    ListFlows {
-        #[snafu(implicit)]
-        location: Location,
-        catalog: String,
-        source: BoxedError,
-    },
-
-    #[snafu(display("Flow info not found: {flow_name} in catalog {catalog_name}"))]
-    FlowInfoNotFound {
-        flow_name: String,
-        catalog_name: String,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("Can't convert value to json, input={input}"))]
-    Json {
-        input: String,
-        #[snafu(source)]
-        error: serde_json::error::Error,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("Failed to get information extension client"))]
-    GetInformationExtension {
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("Failed to list procedures"))]
-    ListProcedures {
-        #[snafu(implicit)]
-        location: Location,
-        source: BoxedError,
-    },
-
-    #[snafu(display("Procedure id not found"))]
-    ProcedureIdNotFound {
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("convert proto data error"))]
-    ConvertProtoData {
-        #[snafu(implicit)]
-        location: Location,
-        source: BoxedError,
-    },
-
     #[snafu(display("Failed to re-compile script due to internal error"))]
     CompileScriptInternal {
         #[snafu(implicit)]
@@ -130,6 +71,13 @@ pub enum Error {
         source: table::error::Error,
     },
 
+    #[snafu(display("System catalog is not valid: {}", msg))]
+    SystemCatalog {
+        msg: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
+
     #[snafu(display("Cannot find catalog by name: {}", catalog_name))]
     CatalogNotFound {
         catalog_name: String,
@@ -166,18 +114,6 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display(
-        "View plan columns changed from: {} to: {}",
-        origin_names,
-        actual_names
-    ))]
-    ViewPlanColumnsChanged {
-        origin_names: String,
-        actual_names: String,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
     #[snafu(display("Failed to find table partitions"))]
     FindPartitions { source: partition::error::Error },
 
@@ -212,6 +148,13 @@ pub enum Error {
         source: common_query::error::Error,
     },
 
+    #[snafu(display("Failed to perform metasrv operation"))]
+    Metasrv {
+        #[snafu(implicit)]
+        location: Location,
+        source: meta_client::error::Error,
+    },
+
     #[snafu(display("Invalid table info in catalog"))]
     InvalidTableInfoInCatalog {
         #[snafu(implicit)]
@@ -230,14 +173,6 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display("Failed to project view columns"))]
-    ProjectViewColumns {
-        #[snafu(source)]
-        error: DataFusionError,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
     #[snafu(display("Table metadata manager error"))]
     TableMetadataManager {
         source: common_meta::error::Error,
@@ -273,21 +208,6 @@ pub enum Error {
     },
 }
 
-impl Error {
-    pub fn should_fail(&self) -> bool {
-        use Error::*;
-
-        matches!(
-            self,
-            GetViewCache { .. }
-                | ViewInfoNotFound { .. }
-                | DecodePlan { .. }
-                | ViewPlanColumnsChanged { .. }
-                | ProjectViewColumns { .. }
-        )
-    }
-}
-
 pub type Result<T> = std::result::Result<T, Error>;
 
 impl ErrorExt for Error {
@@ -298,16 +218,11 @@ impl ErrorExt for Error {
             | Error::FindPartitions { .. }
             | Error::FindRegionRoutes { .. }
             | Error::CacheNotFound { .. }
-            | Error::CastManager { .. }
+            | Error::CastManager { .. } => StatusCode::Unexpected,
-            | Error::Json { .. }
-            | Error::GetInformationExtension { .. }
-            | Error::ProcedureIdNotFound { .. } => StatusCode::Unexpected,
-
-            Error::ViewPlanColumnsChanged { .. } => StatusCode::InvalidArguments,
 
             Error::ViewInfoNotFound { .. } => StatusCode::TableNotFound,
 
-            Error::FlowInfoNotFound { .. } => StatusCode::FlowNotFound,
+            Error::SystemCatalog { .. } => StatusCode::StorageUnavailable,
 
             Error::UpgradeWeakCatalogManagerRef { .. } => StatusCode::Internal,
 
@@ -317,14 +232,11 @@ impl ErrorExt for Error {
             Error::ListCatalogs { source, .. }
             | Error::ListNodes { source, .. }
             | Error::ListSchemas { source, .. }
-            | Error::ListTables { source, .. }
+            | Error::ListTables { source, .. } => source.status_code(),
-            | Error::ListFlows { source, .. }
-            | Error::ListProcedures { source, .. }
-            | Error::ListRegionStats { source, .. }
-            | Error::ConvertProtoData { source, .. } => source.status_code(),
 
             Error::CreateTable { source, .. } => source.status_code(),
 
+            Error::Metasrv { source, .. } => source.status_code(),
             Error::DecodePlan { source, .. } => source.status_code(),
             Error::InvalidTableInfoInCatalog { source, .. } => source.status_code(),
 
@@ -333,8 +245,7 @@ impl ErrorExt for Error {
             }
 
             Error::QueryAccessDenied { .. } => StatusCode::AccessDenied,
-            Error::Datafusion { error, .. } => datafusion_status_code::<Self>(error, None),
+            Error::Datafusion { .. } => StatusCode::EngineExecuteQuery,
-            Error::ProjectViewColumns { .. } => StatusCode::EngineExecuteQuery,
             Error::TableMetadataManager { source, .. } => source.status_code(),
             Error::GetViewCache { source, .. } | Error::GetTableCache { source, .. } => {
                 source.status_code()
@@ -349,7 +260,7 @@ impl ErrorExt for Error {
 
 impl From<Error> for DataFusionError {
     fn from(e: Error) -> Self {
-        DataFusionError::External(Box::new(e))
+        DataFusionError::Internal(e.to_string())
     }
 }
 
@@ -359,6 +270,27 @@ mod tests {
 
     use super::*;
 
+    #[test]
+    pub fn test_error_status_code() {
+        assert_eq!(
+            StatusCode::TableAlreadyExists,
+            Error::TableExists {
+                table: "some_table".to_string(),
+                location: Location::generate(),
+            }
+            .status_code()
+        );
+
+        assert_eq!(
+            StatusCode::StorageUnavailable,
+            Error::SystemCatalog {
+                msg: String::default(),
+                location: Location::generate(),
+            }
+            .status_code()
+        );
+    }
+
     #[test]
     pub fn test_errors_to_datafusion_error() {
         let e: DataFusionError = Error::TableExists {
@@ -367,7 +299,7 @@ mod tests {
         }
         .into();
         match e {
-            DataFusionError::External(_) => {}
+            DataFusionError::Internal(_) => {}
             _ => {
                 panic!("catalog error should be converted to DataFusionError::Internal")
             }

src/catalog/src/information_schema.rs

@@ -14,55 +14,50 @@
 
 mod cluster_info;
 pub mod columns;
-pub mod flows;
-mod information_memory_table;
 pub mod key_column_usage;
+mod memory_table;
 mod partitions;
-mod procedure_info;
+mod predicate;
 mod region_peers;
-mod region_statistics;
 mod runtime_metrics;
 pub mod schemata;
 mod table_constraints;
 mod table_names;
 pub mod tables;
-mod views;
+pub(crate) mod utils;
 
 use std::collections::HashMap;
 use std::sync::{Arc, Weak};
 
 use common_catalog::consts::{self, DEFAULT_CATALOG_NAME, INFORMATION_SCHEMA_NAME};
-use common_error::ext::ErrorExt;
+use common_error::ext::BoxedError;
-use common_meta::cluster::NodeInfo;
+use common_recordbatch::{RecordBatchStreamWrapper, SendableRecordBatchStream};
-use common_meta::datanode::RegionStat;
-use common_meta::key::flow::FlowMetadataManager;
-use common_procedure::ProcedureInfo;
-use common_recordbatch::SendableRecordBatchStream;
 use datatypes::schema::SchemaRef;
+use futures_util::StreamExt;
 use lazy_static::lazy_static;
 use paste::paste;
+pub(crate) use predicate::Predicates;
+use snafu::ResultExt;
+use store_api::data_source::DataSource;
 use store_api::storage::{ScanRequest, TableId};
-use table::metadata::TableType;
+use table::error::{SchemaConversionSnafu, TablesRecordBatchSnafu};
-use table::TableRef;
+use table::metadata::{
+    FilterPushDownType, TableInfoBuilder, TableInfoRef, TableMetaBuilder, TableType,
+};
+use table::{Table, TableRef};
 pub use table_names::*;
-use views::InformationSchemaViews;
 
 use self::columns::InformationSchemaColumns;
-use super::{SystemSchemaProviderInner, SystemTable, SystemTableRef};
+use crate::error::Result;
-use crate::error::{Error, Result};
+use crate::information_schema::cluster_info::InformationSchemaClusterInfo;
-use crate::system_schema::information_schema::cluster_info::InformationSchemaClusterInfo;
+use crate::information_schema::key_column_usage::InformationSchemaKeyColumnUsage;
-use crate::system_schema::information_schema::flows::InformationSchemaFlows;
+use crate::information_schema::memory_table::{get_schema_columns, MemoryTable};
-use crate::system_schema::information_schema::information_memory_table::get_schema_columns;
+use crate::information_schema::partitions::InformationSchemaPartitions;
-use crate::system_schema::information_schema::key_column_usage::InformationSchemaKeyColumnUsage;
+use crate::information_schema::region_peers::InformationSchemaRegionPeers;
-use crate::system_schema::information_schema::partitions::InformationSchemaPartitions;
+use crate::information_schema::runtime_metrics::InformationSchemaMetrics;
-use crate::system_schema::information_schema::region_peers::InformationSchemaRegionPeers;
+use crate::information_schema::schemata::InformationSchemaSchemata;
-use crate::system_schema::information_schema::runtime_metrics::InformationSchemaMetrics;
+use crate::information_schema::table_constraints::InformationSchemaTableConstraints;
-use crate::system_schema::information_schema::schemata::InformationSchemaSchemata;
+use crate::information_schema::tables::InformationSchemaTables;
-use crate::system_schema::information_schema::table_constraints::InformationSchemaTableConstraints;
-use crate::system_schema::information_schema::tables::InformationSchemaTables;
-use crate::system_schema::memory_table::MemoryTable;
-pub(crate) use crate::system_schema::predicate::Predicates;
-use crate::system_schema::SystemSchemaProvider;
 use crate::CatalogManager;
 
 lazy_static! {
@@ -111,26 +106,107 @@ macro_rules! setup_memory_table {
 pub struct InformationSchemaProvider {
     catalog_name: String,
     catalog_manager: Weak<dyn CatalogManager>,
-    flow_metadata_manager: Arc<FlowMetadataManager>,
     tables: HashMap<String, TableRef>,
 }
 
-impl SystemSchemaProvider for InformationSchemaProvider {
+impl InformationSchemaProvider {
-    fn tables(&self) -> &HashMap<String, TableRef> {
+    pub fn new(catalog_name: String, catalog_manager: Weak<dyn CatalogManager>) -> Self {
+        let mut provider = Self {
+            catalog_name,
+            catalog_manager,
+            tables: HashMap::new(),
+        };
+
+        provider.build_tables();
+
+        provider
+    }
+
+    /// Returns table names in the order of table id.
+    pub fn table_names(&self) -> Vec<String> {
+        let mut tables = self.tables.values().clone().collect::<Vec<_>>();
+
+        tables.sort_by(|t1, t2| {
+            t1.table_info()
+                .table_id()
+                .partial_cmp(&t2.table_info().table_id())
+                .unwrap()
+        });
+        tables
+            .into_iter()
+            .map(|t| t.table_info().name.clone())
+            .collect()
+    }
+
+    /// Returns a map of [TableRef] in information schema.
+    pub fn tables(&self) -> &HashMap<String, TableRef> {
         assert!(!self.tables.is_empty());
 
         &self.tables
     }
-}
+
-impl SystemSchemaProviderInner for InformationSchemaProvider {
+    /// Returns the [TableRef] by table name.
-    fn catalog_name(&self) -> &str {
+    pub fn table(&self, name: &str) -> Option<TableRef> {
-        &self.catalog_name
+        self.tables.get(name).cloned()
-    }
-    fn schema_name() -> &'static str {
-        INFORMATION_SCHEMA_NAME
     }
 
-    fn system_table(&self, name: &str) -> Option<SystemTableRef> {
+    fn build_tables(&mut self) {
+        let mut tables = HashMap::new();
+
+        // SECURITY NOTE:
+        // Carefully consider the tables that may expose sensitive cluster configurations,
+        // authentication details, and other critical information.
+        // Only put these tables under `greptime` catalog to prevent info leak.
+        if self.catalog_name == DEFAULT_CATALOG_NAME {
+            tables.insert(
+                RUNTIME_METRICS.to_string(),
+                self.build_table(RUNTIME_METRICS).unwrap(),
+            );
+            tables.insert(
+                BUILD_INFO.to_string(),
+                self.build_table(BUILD_INFO).unwrap(),
+            );
+            tables.insert(
+                REGION_PEERS.to_string(),
+                self.build_table(REGION_PEERS).unwrap(),
+            );
+            tables.insert(
+                CLUSTER_INFO.to_string(),
+                self.build_table(CLUSTER_INFO).unwrap(),
+            );
+        }
+
+        tables.insert(TABLES.to_string(), self.build_table(TABLES).unwrap());
+        tables.insert(SCHEMATA.to_string(), self.build_table(SCHEMATA).unwrap());
+        tables.insert(COLUMNS.to_string(), self.build_table(COLUMNS).unwrap());
+        tables.insert(
+            KEY_COLUMN_USAGE.to_string(),
+            self.build_table(KEY_COLUMN_USAGE).unwrap(),
+        );
+        tables.insert(
+            TABLE_CONSTRAINTS.to_string(),
+            self.build_table(TABLE_CONSTRAINTS).unwrap(),
+        );
+
+        // Add memory tables
+        for name in MEMORY_TABLES.iter() {
+            tables.insert((*name).to_string(), self.build_table(name).expect(name));
+        }
+
+        self.tables = tables;
+    }
+
+    fn build_table(&self, name: &str) -> Option<TableRef> {
+        self.information_table(name).map(|table| {
+            let table_info = Self::table_info(self.catalog_name.clone(), &table);
+            let filter_pushdown = FilterPushDownType::Inexact;
+            let data_source = Arc::new(InformationTableDataSource::new(table));
+            let table = Table::new(table_info, filter_pushdown, data_source);
+            Arc::new(table)
+        })
+    }
+
+    fn information_table(&self, name: &str) -> Option<InformationTableRef> {
         match name.to_ascii_lowercase().as_str() {
             TABLES => Some(Arc::new(InformationSchemaTables::new(
                 self.catalog_name.clone(),
@@ -186,100 +262,27 @@ impl SystemSchemaProviderInner for InformationSchemaProvider {
             CLUSTER_INFO => Some(Arc::new(InformationSchemaClusterInfo::new(
                 self.catalog_manager.clone(),
             )) as _),
-            VIEWS => Some(Arc::new(InformationSchemaViews::new(
-                self.catalog_name.clone(),
-                self.catalog_manager.clone(),
-            )) as _),
-            FLOWS => Some(Arc::new(InformationSchemaFlows::new(
-                self.catalog_name.clone(),
-                self.flow_metadata_manager.clone(),
-            )) as _),
-            PROCEDURE_INFO => Some(
-                Arc::new(procedure_info::InformationSchemaProcedureInfo::new(
-                    self.catalog_manager.clone(),
-                )) as _,
-            ),
-            REGION_STATISTICS => Some(Arc::new(
-                region_statistics::InformationSchemaRegionStatistics::new(
-                    self.catalog_manager.clone(),
-                ),
-            ) as _),
             _ => None,
         }
     }
-}
 
-impl InformationSchemaProvider {
+    fn table_info(catalog_name: String, table: &InformationTableRef) -> TableInfoRef {
-    pub fn new(
+        let table_meta = TableMetaBuilder::default()
-        catalog_name: String,
+            .schema(table.schema())
-        catalog_manager: Weak<dyn CatalogManager>,
+            .primary_key_indices(vec![])
-        flow_metadata_manager: Arc<FlowMetadataManager>,
+            .next_column_id(0)
-    ) -> Self {
+            .build()
-        let mut provider = Self {
+            .unwrap();
-            catalog_name,
+        let table_info = TableInfoBuilder::default()
-            catalog_manager,
+            .table_id(table.table_id())
-            flow_metadata_manager,
+            .name(table.table_name().to_string())
-            tables: HashMap::new(),
+            .catalog_name(catalog_name)
-        };
+            .schema_name(INFORMATION_SCHEMA_NAME.to_string())
-
+            .meta(table_meta)
-        provider.build_tables();
+            .table_type(table.table_type())
-
+            .build()
-        provider
+            .unwrap();
-    }
+        Arc::new(table_info)
-
-    fn build_tables(&mut self) {
-        let mut tables = HashMap::new();
-
-        // SECURITY NOTE:
-        // Carefully consider the tables that may expose sensitive cluster configurations,
-        // authentication details, and other critical information.
-        // Only put these tables under `greptime` catalog to prevent info leak.
-        if self.catalog_name == DEFAULT_CATALOG_NAME {
-            tables.insert(
-                RUNTIME_METRICS.to_string(),
-                self.build_table(RUNTIME_METRICS).unwrap(),
-            );
-            tables.insert(
-                BUILD_INFO.to_string(),
-                self.build_table(BUILD_INFO).unwrap(),
-            );
-            tables.insert(
-                REGION_PEERS.to_string(),
-                self.build_table(REGION_PEERS).unwrap(),
-            );
-            tables.insert(
-                CLUSTER_INFO.to_string(),
-                self.build_table(CLUSTER_INFO).unwrap(),
-            );
-            tables.insert(
-                PROCEDURE_INFO.to_string(),
-                self.build_table(PROCEDURE_INFO).unwrap(),
-            );
-            tables.insert(
-                REGION_STATISTICS.to_string(),
-                self.build_table(REGION_STATISTICS).unwrap(),
-            );
-        }
-
-        tables.insert(TABLES.to_string(), self.build_table(TABLES).unwrap());
-        tables.insert(VIEWS.to_string(), self.build_table(VIEWS).unwrap());
-        tables.insert(SCHEMATA.to_string(), self.build_table(SCHEMATA).unwrap());
-        tables.insert(COLUMNS.to_string(), self.build_table(COLUMNS).unwrap());
-        tables.insert(
-            KEY_COLUMN_USAGE.to_string(),
-            self.build_table(KEY_COLUMN_USAGE).unwrap(),
-        );
-        tables.insert(
-            TABLE_CONSTRAINTS.to_string(),
-            self.build_table(TABLE_CONSTRAINTS).unwrap(),
-        );
-        tables.insert(FLOWS.to_string(), self.build_table(FLOWS).unwrap());
-        // Add memory tables
-        for name in MEMORY_TABLES.iter() {
-            tables.insert((*name).to_string(), self.build_table(name).expect(name));
-        }
-
-        self.tables = tables;
     }
 }
 
@@ -297,64 +300,57 @@ trait InformationTable {
     }
 }
 
-// Provide compatibility for legacy `information_schema` code.
+type InformationTableRef = Arc<dyn InformationTable + Send + Sync>;
-impl<T> SystemTable for T
+
-where
+struct InformationTableDataSource {
-    T: InformationTable,
+    table: InformationTableRef,
-{
+}
-    fn table_id(&self) -> TableId {
+
-        InformationTable::table_id(self)
+impl InformationTableDataSource {
+    fn new(table: InformationTableRef) -> Self {
+        Self { table }
     }
 
-    fn table_name(&self) -> &'static str {
+    fn try_project(&self, projection: &[usize]) -> std::result::Result<SchemaRef, BoxedError> {
-        InformationTable::table_name(self)
+        let schema = self
-    }
+            .table
-
+            .schema()
-    fn schema(&self) -> SchemaRef {
+            .try_project(projection)
-        InformationTable::schema(self)
+            .context(SchemaConversionSnafu)
-    }
+            .map_err(BoxedError::new)?;
-
+        Ok(Arc::new(schema))
-    fn table_type(&self) -> TableType {
-        InformationTable::table_type(self)
-    }
-
-    fn to_stream(&self, request: ScanRequest) -> Result<SendableRecordBatchStream> {
-        InformationTable::to_stream(self, request)
     }
 }
 
-pub type InformationExtensionRef = Arc<dyn InformationExtension<Error = Error> + Send + Sync>;
+impl DataSource for InformationTableDataSource {
+    fn get_stream(
+        &self,
+        request: ScanRequest,
+    ) -> std::result::Result<SendableRecordBatchStream, BoxedError> {
+        let projection = request.projection.clone();
+        let projected_schema = match &projection {
+            Some(projection) => self.try_project(projection)?,
+            None => self.table.schema(),
+        };
 
-/// The `InformationExtension` trait provides the extension methods for the `information_schema` tables.
+        let stream = self
-#[async_trait::async_trait]
+            .table
-pub trait InformationExtension {
+            .to_stream(request)
-    type Error: ErrorExt;
+            .map_err(BoxedError::new)
+            .context(TablesRecordBatchSnafu)
+            .map_err(BoxedError::new)?
+            .map(move |batch| match &projection {
+                Some(p) => batch.and_then(|b| b.try_project(p)),
+                None => batch,
+            });
 
-    /// Gets the nodes information.
+        let stream = RecordBatchStreamWrapper {
-    async fn nodes(&self) -> std::result::Result<Vec<NodeInfo>, Self::Error>;
+            schema: projected_schema,
+            stream: Box::pin(stream),
+            output_ordering: None,
+            metrics: Default::default(),
+        };
 
-    /// Gets the procedures information.
+        Ok(Box::pin(stream))
-    async fn procedures(&self) -> std::result::Result<Vec<(String, ProcedureInfo)>, Self::Error>;
-
-    /// Gets the region statistics.
-    async fn region_stats(&self) -> std::result::Result<Vec<RegionStat>, Self::Error>;
-}
-
-pub struct NoopInformationExtension;
-
-#[async_trait::async_trait]
-impl InformationExtension for NoopInformationExtension {
-    type Error = Error;
-
-    async fn nodes(&self) -> std::result::Result<Vec<NodeInfo>, Self::Error> {
-        Ok(vec![])
-    }
-
-    async fn procedures(&self) -> std::result::Result<Vec<(String, ProcedureInfo)>, Self::Error> {
-        Ok(vec![])
-    }
-
-    async fn region_stats(&self) -> std::result::Result<Vec<RegionStat>, Self::Error> {
-        Ok(vec![])
     }
 }

src/catalog/src/information_schema/cluster_info.rs

@@ -17,10 +17,13 @@ use std::time::Duration;
 
 use arrow_schema::SchemaRef as ArrowSchemaRef;
 use common_catalog::consts::INFORMATION_SCHEMA_CLUSTER_INFO_TABLE_ID;
+use common_config::Mode;
 use common_error::ext::BoxedError;
-use common_meta::cluster::NodeInfo;
+use common_meta::cluster::{ClusterInfo, NodeInfo, NodeStatus};
+use common_meta::peer::Peer;
 use common_recordbatch::adapter::RecordBatchStreamAdapter;
 use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
+use common_telemetry::warn;
 use common_time::timestamp::Timestamp;
 use datafusion::execution::TaskContext;
 use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
@@ -37,9 +40,8 @@ use snafu::ResultExt;
 use store_api::storage::{ScanRequest, TableId};
 
 use super::CLUSTER_INFO;
-use crate::error::{CreateRecordBatchSnafu, InternalSnafu, Result};
+use crate::error::{CreateRecordBatchSnafu, InternalSnafu, ListNodesSnafu, Result};
-use crate::system_schema::information_schema::{InformationTable, Predicates};
+use crate::information_schema::{utils, InformationTable, Predicates};
-use crate::system_schema::utils;
 use crate::CatalogManager;
 
 const PEER_ID: &str = "peer_id";
@@ -67,6 +69,7 @@ const INIT_CAPACITY: usize = 42;
 pub(super) struct InformationSchemaClusterInfo {
     schema: SchemaRef,
     catalog_manager: Weak<dyn CatalogManager>,
+    start_time_ms: u64,
 }
 
 impl InformationSchemaClusterInfo {
@@ -74,6 +77,7 @@ impl InformationSchemaClusterInfo {
         Self {
             schema: Self::schema(),
             catalog_manager,
+            start_time_ms: common_time::util::current_time_millis() as u64,
         }
     }
 
@@ -95,7 +99,11 @@ impl InformationSchemaClusterInfo {
     }
 
     fn builder(&self) -> InformationSchemaClusterInfoBuilder {
-        InformationSchemaClusterInfoBuilder::new(self.schema.clone(), self.catalog_manager.clone())
+        InformationSchemaClusterInfoBuilder::new(
+            self.schema.clone(),
+            self.catalog_manager.clone(),
+            self.start_time_ms,
+        )
     }
 }
 
@@ -135,6 +143,7 @@ impl InformationTable for InformationSchemaClusterInfo {
 
 struct InformationSchemaClusterInfoBuilder {
     schema: SchemaRef,
+    start_time_ms: u64,
     catalog_manager: Weak<dyn CatalogManager>,
 
     peer_ids: Int64VectorBuilder,
@@ -148,7 +157,11 @@ struct InformationSchemaClusterInfoBuilder {
 }
 
 impl InformationSchemaClusterInfoBuilder {
-    fn new(schema: SchemaRef, catalog_manager: Weak<dyn CatalogManager>) -> Self {
+    fn new(
+        schema: SchemaRef,
+        catalog_manager: Weak<dyn CatalogManager>,
+        start_time_ms: u64,
+    ) -> Self {
         Self {
             schema,
             catalog_manager,
@@ -160,17 +173,56 @@ impl InformationSchemaClusterInfoBuilder {
             start_times: TimestampMillisecondVectorBuilder::with_capacity(INIT_CAPACITY),
             uptimes: StringVectorBuilder::with_capacity(INIT_CAPACITY),
             active_times: StringVectorBuilder::with_capacity(INIT_CAPACITY),
+            start_time_ms,
         }
     }
 
     /// Construct the `information_schema.cluster_info` virtual table
     async fn make_cluster_info(&mut self, request: Option<ScanRequest>) -> Result<RecordBatch> {
         let predicates = Predicates::from_scan_request(&request);
-        let information_extension = utils::information_extension(&self.catalog_manager)?;
+        let mode = utils::running_mode(&self.catalog_manager)?.unwrap_or(Mode::Standalone);
-        let node_infos = information_extension.nodes().await?;
+
+        match mode {
+            Mode::Standalone => {
+                let build_info = common_version::build_info();
+
+                self.add_node_info(
+                    &predicates,
+                    NodeInfo {
+                        // For the standalone:
+                        // - id always 0
+                        // - empty string for peer_addr
+                        peer: Peer {
+                            id: 0,
+                            addr: "".to_string(),
+                        },
+                        last_activity_ts: -1,
+                        status: NodeStatus::Standalone,
+                        version: build_info.version.to_string(),
+                        git_commit: build_info.commit_short.to_string(),
+                        // Use `self.start_time_ms` instead.
+                        // It's not precise but enough.
+                        start_time_ms: self.start_time_ms,
+                    },
+                );
+            }
+            Mode::Distributed => {
+                if let Some(meta_client) = utils::meta_client(&self.catalog_manager)? {
+                    let node_infos = meta_client
+                        .list_nodes(None)
+                        .await
+                        .map_err(BoxedError::new)
+                        .context(ListNodesSnafu)?;
+
                     for node_info in node_infos {
                         self.add_node_info(&predicates, node_info);
                     }
+                } else {
+                    warn!("Could not find meta client in distributed mode.");
+                }
+            }
+        }
+
         self.finish()
     }
 

src/catalog/src/information_schema/columns.rs

@@ -257,8 +257,8 @@ impl InformationSchemaColumnsBuilder {
             .context(UpgradeWeakCatalogManagerRefSnafu)?;
         let predicates = Predicates::from_scan_request(&request);
 
-        for schema_name in catalog_manager.schema_names(&catalog_name, None).await? {
+        for schema_name in catalog_manager.schema_names(&catalog_name).await? {
-            let mut stream = catalog_manager.tables(&catalog_name, &schema_name, None);
+            let mut stream = catalog_manager.tables(&catalog_name, &schema_name);
 
             while let Some(table) = stream.try_next().await? {
                 let keys = &table.table_info().meta.primary_key_indices;

src/catalog/src/information_schema/key_column_usage.rs

@@ -27,7 +27,6 @@ use datatypes::prelude::{ConcreteDataType, MutableVector, ScalarVectorBuilder, V
 use datatypes::schema::{ColumnSchema, Schema, SchemaRef};
 use datatypes::value::Value;
 use datatypes::vectors::{ConstantVector, StringVector, StringVectorBuilder, UInt32VectorBuilder};
-use futures_util::TryStreamExt;
 use snafu::{OptionExt, ResultExt};
 use store_api::storage::{ScanRequest, TableId};
 
@@ -35,7 +34,7 @@ use super::KEY_COLUMN_USAGE;
 use crate::error::{
     CreateRecordBatchSnafu, InternalSnafu, Result, UpgradeWeakCatalogManagerRefSnafu,
 };
-use crate::system_schema::information_schema::{InformationTable, Predicates};
+use crate::information_schema::{InformationTable, Predicates};
 use crate::CatalogManager;
 
 pub const CONSTRAINT_SCHEMA: &str = "constraint_schema";
@@ -212,15 +211,25 @@ impl InformationSchemaKeyColumnUsageBuilder {
             .context(UpgradeWeakCatalogManagerRefSnafu)?;
         let predicates = Predicates::from_scan_request(&request);
 
-        for schema_name in catalog_manager.schema_names(&catalog_name, None).await? {
-            let mut stream = catalog_manager.tables(&catalog_name, &schema_name, None);
-
-            while let Some(table) = stream.try_next().await? {
         let mut primary_constraints = vec![];
 
-                let table_info = table.table_info();
+        for schema_name in catalog_manager.schema_names(&catalog_name).await? {
-                let table_name = &table_info.name;
+            if !catalog_manager
-                let keys = &table_info.meta.primary_key_indices;
+                .schema_exists(&catalog_name, &schema_name)
+                .await?
+            {
+                continue;
+            }
+
+            for table_name in catalog_manager
+                .table_names(&catalog_name, &schema_name)
+                .await?
+            {
+                if let Some(table) = catalog_manager
+                    .table(&catalog_name, &schema_name, &table_name)
+                    .await?
+                {
+                    let keys = &table.table_info().meta.primary_key_indices;
                     let schema = table.schema();
 
                     for (idx, column) in schema.column_schemas().iter().enumerate() {
@@ -231,7 +240,7 @@ impl InformationSchemaKeyColumnUsageBuilder {
                                 TIME_INDEX_CONSTRAINT_NAME,
                                 &catalog_name,
                                 &schema_name,
-                            table_name,
+                                &table_name,
                                 &column.name,
                                 1, //always 1 for time index
                             );
@@ -240,12 +249,17 @@ impl InformationSchemaKeyColumnUsageBuilder {
                             primary_constraints.push((
                                 catalog_name.clone(),
                                 schema_name.clone(),
-                            table_name.to_string(),
+                                table_name.clone(),
                                 column.name.clone(),
                             ));
                         }
                         // TODO(dimbtp): foreign key constraint not supported yet
                     }
+                } else {
+                    unreachable!();
+                }
+            }
+        }
 
         for (i, (catalog_name, schema_name, table_name, column_name)) in
             primary_constraints.into_iter().enumerate()
@@ -261,8 +275,6 @@ impl InformationSchemaKeyColumnUsageBuilder {
                 i as u32 + 1,
             );
         }
-            }
-        }
 
         self.finish()
     }

src/catalog/src/information_schema/memory_table.rs

@@ -12,8 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-mod table_columns;
+mod tables;
-
 use std::sync::Arc;
 
 use arrow_schema::SchemaRef as ArrowSchemaRef;
@@ -28,21 +27,22 @@ use datatypes::schema::SchemaRef;
 use datatypes::vectors::VectorRef;
 use snafu::ResultExt;
 use store_api::storage::{ScanRequest, TableId};
+pub use tables::get_schema_columns;
 
-use super::SystemTable;
 use crate::error::{CreateRecordBatchSnafu, InternalSnafu, Result};
+use crate::information_schema::InformationTable;
 
 /// A memory table with specified schema and columns.
-pub(crate) struct MemoryTable {
+pub(super) struct MemoryTable {
-    pub(crate) table_id: TableId,
+    table_id: TableId,
-    pub(crate) table_name: &'static str,
+    table_name: &'static str,
-    pub(crate) schema: SchemaRef,
+    schema: SchemaRef,
-    pub(crate) columns: Vec<VectorRef>,
+    columns: Vec<VectorRef>,
 }
 
 impl MemoryTable {
     /// Creates a memory table with table id, name, schema and columns.
-    pub fn new(
+    pub(super) fn new(
         table_id: TableId,
         table_name: &'static str,
         schema: SchemaRef,
@@ -56,54 +56,12 @@ impl MemoryTable {
         }
     }
 
-    pub fn builder(&self) -> MemoryTableBuilder {
+    fn builder(&self) -> MemoryTableBuilder {
         MemoryTableBuilder::new(self.schema.clone(), self.columns.clone())
     }
 }
 
-pub(crate) struct MemoryTableBuilder {
+impl InformationTable for MemoryTable {
-    schema: SchemaRef,
-    columns: Vec<VectorRef>,
-}
-
-impl MemoryTableBuilder {
-    fn new(schema: SchemaRef, columns: Vec<VectorRef>) -> Self {
-        Self { schema, columns }
-    }
-
-    /// Construct the `information_schema.{table_name}` virtual table
-    pub async fn memory_records(&mut self) -> Result<RecordBatch> {
-        if self.columns.is_empty() {
-            Ok(RecordBatch::new_empty(self.schema.clone()))
-        } else {
-            RecordBatch::new(self.schema.clone(), std::mem::take(&mut self.columns))
-                .context(CreateRecordBatchSnafu)
-        }
-    }
-}
-
-impl DfPartitionStream for MemoryTable {
-    fn schema(&self) -> &ArrowSchemaRef {
-        self.schema.arrow_schema()
-    }
-
-    fn execute(&self, _: Arc<TaskContext>) -> DfSendableRecordBatchStream {
-        let schema = self.schema.arrow_schema().clone();
-        let mut builder = self.builder();
-        Box::pin(DfRecordBatchStreamAdapter::new(
-            schema,
-            futures::stream::once(async move {
-                builder
-                    .memory_records()
-                    .await
-                    .map(|x| x.into_df_record_batch())
-                    .map_err(Into::into)
-            }),
-        ))
-    }
-}
-
-impl SystemTable for MemoryTable {
     fn table_id(&self) -> TableId {
         self.table_id
     }
@@ -137,6 +95,48 @@ impl SystemTable for MemoryTable {
     }
 }
 
+struct MemoryTableBuilder {
+    schema: SchemaRef,
+    columns: Vec<VectorRef>,
+}
+
+impl MemoryTableBuilder {
+    fn new(schema: SchemaRef, columns: Vec<VectorRef>) -> Self {
+        Self { schema, columns }
+    }
+
+    /// Construct the `information_schema.{table_name}` virtual table
+    async fn memory_records(&mut self) -> Result<RecordBatch> {
+        if self.columns.is_empty() {
+            RecordBatch::new_empty(self.schema.clone()).context(CreateRecordBatchSnafu)
+        } else {
+            RecordBatch::new(self.schema.clone(), std::mem::take(&mut self.columns))
+                .context(CreateRecordBatchSnafu)
+        }
+    }
+}
+
+impl DfPartitionStream for MemoryTable {
+    fn schema(&self) -> &ArrowSchemaRef {
+        self.schema.arrow_schema()
+    }
+
+    fn execute(&self, _: Arc<TaskContext>) -> DfSendableRecordBatchStream {
+        let schema = self.schema.arrow_schema().clone();
+        let mut builder = self.builder();
+        Box::pin(DfRecordBatchStreamAdapter::new(
+            schema,
+            futures::stream::once(async move {
+                builder
+                    .memory_records()
+                    .await
+                    .map(|x| x.into_df_record_batch())
+                    .map_err(Into::into)
+            }),
+        ))
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use std::sync::Arc;
@@ -147,7 +147,6 @@ mod tests {
     use datatypes::vectors::StringVector;
 
     use super::*;
-    use crate::system_schema::SystemTable;
 
     #[tokio::test]
     async fn test_memory_table() {
@@ -167,8 +166,8 @@ mod tests {
         );
 
         assert_eq!(42, table.table_id());
-        assert_eq!("test", table.table_name);
+        assert_eq!("test", table.table_name());
-        assert_eq!(schema, SystemTable::schema(&table));
+        assert_eq!(schema, InformationTable::schema(&table));
 
         let stream = table.to_stream(ScanRequest::default()).unwrap();
 
@@ -197,7 +196,7 @@ mod tests {
 
         assert_eq!(42, table.table_id());
         assert_eq!("test", table.table_name());
-        assert_eq!(schema, SystemTable::schema(&table));
+        assert_eq!(schema, InformationTable::schema(&table));
 
         let stream = table.to_stream(ScanRequest::default()).unwrap();
 

src/catalog/src/information_schema/memory_table/tables.rs

@@ -15,19 +15,17 @@
 use std::sync::Arc;
 
 use common_catalog::consts::{METRIC_ENGINE, MITO_ENGINE};
-use datatypes::schema::{Schema, SchemaRef};
+use datatypes::prelude::{ConcreteDataType, VectorRef};
-use datatypes::vectors::{Int64Vector, StringVector, VectorRef};
+use datatypes::schema::{ColumnSchema, Schema, SchemaRef};
+use datatypes::vectors::{Int64Vector, StringVector};
 
-use super::table_names::*;
+use crate::information_schema::table_names::*;
-use crate::system_schema::utils::tables::{
-    bigint_column, datetime_column, string_column, string_columns,
-};
 
 const NO_VALUE: &str = "NO";
 
 /// Find the schema and columns by the table_name, only valid for memory tables.
 /// Safety: the user MUST ensure the table schema exists, panic otherwise.
-pub(super) fn get_schema_columns(table_name: &str) -> (SchemaRef, Vec<VectorRef>) {
+pub fn get_schema_columns(table_name: &str) -> (SchemaRef, Vec<VectorRef>) {
     let (column_schemas, columns): (_, Vec<VectorRef>) = match table_name {
         COLUMN_PRIVILEGES => (
             string_columns(&[
@@ -82,7 +80,7 @@ pub(super) fn get_schema_columns(table_name: &str) -> (SchemaRef, Vec<VectorRef>
                     "GIT_BRANCH",
                     "GIT_COMMIT",
                     "GIT_COMMIT_SHORT",
-                    "GIT_CLEAN",
+                    "GIT_DIRTY",
                     "PKG_VERSION",
                 ]),
                 vec![
@@ -91,7 +89,7 @@ pub(super) fn get_schema_columns(table_name: &str) -> (SchemaRef, Vec<VectorRef>
                     Arc::new(StringVector::from(vec![build_info
                         .commit_short
                         .to_string()])),
-                    Arc::new(StringVector::from(vec![build_info.clean.to_string()])),
+                    Arc::new(StringVector::from(vec![build_info.dirty.to_string()])),
                     Arc::new(StringVector::from(vec![build_info.version.to_string()])),
                 ],
             )
@@ -416,3 +414,50 @@ pub(super) fn get_schema_columns(table_name: &str) -> (SchemaRef, Vec<VectorRef>
 
     (Arc::new(Schema::new(column_schemas)), columns)
 }
+
+fn string_columns(names: &[&'static str]) -> Vec<ColumnSchema> {
+    names.iter().map(|name| string_column(name)).collect()
+}
+
+fn string_column(name: &str) -> ColumnSchema {
+    ColumnSchema::new(
+        str::to_lowercase(name),
+        ConcreteDataType::string_datatype(),
+        false,
+    )
+}
+
+fn bigint_column(name: &str) -> ColumnSchema {
+    ColumnSchema::new(
+        str::to_lowercase(name),
+        ConcreteDataType::int64_datatype(),
+        false,
+    )
+}
+
+fn datetime_column(name: &str) -> ColumnSchema {
+    ColumnSchema::new(
+        str::to_lowercase(name),
+        ConcreteDataType::datetime_datatype(),
+        false,
+    )
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_string_columns() {
+        let columns = ["a", "b", "c"];
+        let column_schemas = string_columns(&columns);
+
+        assert_eq!(3, column_schemas.len());
+        for (i, name) in columns.iter().enumerate() {
+            let cs = column_schemas.get(i).unwrap();
+
+            assert_eq!(*name, cs.name);
+            assert_eq!(ConcreteDataType::string_datatype(), cs.data_type);
+        }
+    }
+}

src/catalog/src/information_schema/partitions.rs

@@ -44,8 +44,8 @@ use crate::error::{
     CreateRecordBatchSnafu, FindPartitionsSnafu, InternalSnafu, Result,
     UpgradeWeakCatalogManagerRefSnafu,
 };
+use crate::information_schema::{InformationTable, Predicates};
 use crate::kvbackend::KvBackendCatalogManager;
-use crate::system_schema::information_schema::{InformationTable, Predicates};
 use crate::CatalogManager;
 
 const TABLE_CATALOG: &str = "table_catalog";
@@ -240,9 +240,9 @@ impl InformationSchemaPartitionsBuilder {
 
         let predicates = Predicates::from_scan_request(&request);
 
-        for schema_name in catalog_manager.schema_names(&catalog_name, None).await? {
+        for schema_name in catalog_manager.schema_names(&catalog_name).await? {
             let table_info_stream = catalog_manager
-                .tables(&catalog_name, &schema_name, None)
+                .tables(&catalog_name, &schema_name)
                 .try_filter_map(|t| async move {
                     let table_info = t.table_info();
                     if table_info.table_type == TableType::Temporary {

src/catalog/src/information_schema/predicate.rs

@@ -25,7 +25,7 @@ type ColumnName = String;
 /// we only support these simple predicates currently.
 /// TODO(dennis): supports more predicate types.
 #[derive(Clone, PartialEq, Eq, Debug)]
-pub(crate) enum Predicate {
+enum Predicate {
     Eq(ColumnName, Value),
     Like(ColumnName, String, bool),
     NotEq(ColumnName, Value),