feat(promql-planner): introduce vector matching binary operation (#5578)

* feat(promql-planner): support vector matching for binary operation

* test: add sqlness tests

.env.example

@@ -14,10 +14,11 @@ GT_AZBLOB_CONTAINER=AZBLOB container
 GT_AZBLOB_ACCOUNT_NAME=AZBLOB account name
 GT_AZBLOB_ACCOUNT_KEY=AZBLOB account key
 GT_AZBLOB_ENDPOINT=AZBLOB endpoint
-# Settings for gcs test 
-GT_GCS_BUCKET = GCS bucket 
+# Settings for gcs test
+GT_GCS_BUCKET = GCS bucket
 GT_GCS_SCOPE  = GCS scope
-GT_GCS_CREDENTIAL_PATH = GCS credential path 
+GT_GCS_CREDENTIAL_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

.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 }} \
-          IMAGE_TAG=${{ inputs.version }}
+          DEV_BUILDER_IMAGE_TAG=${{ 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 }} \
-          IMAGE_TAG=${{ inputs.version }}
+          DEV_BUILDER_IMAGE_TAG=${{ 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 }} \
-          IMAGE_TAG=${{ inputs.version }} && \
+          DEV_BUILDER_IMAGE_TAG=${{ inputs.version }} && \
 
         docker push ${{ inputs.dockerhub-image-registry }}/${{ inputs.dockerhub-image-namespace }}/dev-builder-android:${{ inputs.version }}

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

@@ -54,7 +54,7 @@ runs:
         PROFILE_TARGET: ${{ inputs.cargo-profile == 'dev' && 'debug' || inputs.cargo-profile }}
       with:
         artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: ./target/$PROFILE_TARGET/greptime
+        target-files: ./target/$PROFILE_TARGET/greptime
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
 
@@ -72,6 +72,6 @@ runs:
       if: ${{ inputs.build-android-artifacts == 'true' }}
       with:
         artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: ./target/aarch64-linux-android/release/greptime
+        target-files: ./target/aarch64-linux-android/release/greptime
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}

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

@@ -34,8 +34,8 @@ inputs:
     required: true
   push-latest-tag:
     description: Whether to push the latest tag
-    required: false
-    default: 'true'
+    required: true
+    default: 'false'
 runs:
   using: composite
   steps:
@@ -47,7 +47,11 @@ runs:
         password: ${{ inputs.image-registry-password }}
 
     - name: Set up qemu for multi-platform builds
-      uses: docker/setup-qemu-action@v2
+      uses: docker/setup-qemu-action@v3
+      with:
+        platforms: linux/amd64,linux/arm64
+        # The latest version will lead to segmentation fault.
+        image: tonistiigi/binfmt:qemu-v7.0.0-28
 
     - name: Set up buildx
       uses: docker/setup-buildx-action@v2

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

@@ -22,8 +22,8 @@ inputs:
     required: true
   push-latest-tag:
     description: Whether to push the latest tag
-    required: false
-    default: 'true'
+    required: true
+    default: 'false'
   dev-mode:
     description: Enable dev mode, only build standard greptime
     required: false
@@ -41,8 +41,8 @@ runs:
         image-name: ${{ inputs.image-name }}
         image-tag: ${{ inputs.version }}
         docker-file: docker/ci/ubuntu/Dockerfile
-        amd64-artifact-name: greptime-linux-amd64-pyo3-${{ inputs.version }}
-        arm64-artifact-name: greptime-linux-arm64-pyo3-${{ inputs.version }}
+        amd64-artifact-name: greptime-linux-amd64-${{ inputs.version }}
+        arm64-artifact-name: greptime-linux-arm64-${{ inputs.version }}
         platforms: linux/amd64,linux/arm64
         push-latest-tag: ${{ inputs.push-latest-tag }}
 

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

@@ -17,6 +17,12 @@ 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
@@ -31,8 +37,8 @@ runs:
       run: |
         cd ${{ inputs.working-dir }} && \
         make run-it-in-container BUILD_JOBS=4 \
-        IMAGE_NAMESPACE=i8k6a5e1/greptime \
-        IMAGE_REGISTRY=public.ecr.aws
+        IMAGE_NAMESPACE=${{ 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.
@@ -42,30 +48,17 @@ runs:
         path: /tmp/greptime-*.log
         retention-days: 3
 
-    - name: Build standard greptime
+    - name: Build greptime # Builds standard greptime binary
       uses: ./.github/actions/build-greptime-binary
       with:
         base-image: ubuntu
-        features: pyo3_backend,servers/dashboard
-        cargo-profile: ${{ inputs.cargo-profile }}
-        artifacts-dir: greptime-linux-${{ inputs.arch }}-pyo3-${{ inputs.version }}
-        version: ${{ inputs.version }}
-        working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime        
-
-    - name: Build greptime without pyo3
-      if: ${{ inputs.dev-mode == 'false' }}
-      uses: ./.github/actions/build-greptime-binary
-      with:
-        base-image: ubuntu
-        features: servers/dashboard
+        features: servers/dashboard,pg_kvbackend
         cargo-profile: ${{ inputs.cargo-profile }}
         artifacts-dir: greptime-linux-${{ inputs.arch }}-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime
+        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
@@ -77,13 +70,13 @@ runs:
       if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds greptime for centos if the host machine is amd64.
       with:
         base-image: centos
-        features: servers/dashboard
+        features: servers/dashboard,pg_kvbackend
         cargo-profile: ${{ inputs.cargo-profile }}
         artifacts-dir: greptime-linux-${{ inputs.arch }}-centos-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime
+        image-registry: ${{ inputs.image-registry }}
+        image-namespace: ${{ inputs.image-namespace }}
 
     - name: Build greptime on android base image
       uses: ./.github/actions/build-greptime-binary
@@ -94,5 +87,5 @@ runs:
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
         build-android-artifacts: true
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime
+        image-registry: ${{ inputs.image-registry }}
+        image-namespace: ${{ inputs.image-namespace }}

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

@@ -4,9 +4,6 @@ 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
@@ -43,10 +40,9 @@ runs:
         brew install protobuf
 
     - name: Install rust toolchain
-      uses: dtolnay/rust-toolchain@master
+      uses: actions-rust-lang/setup-rust-toolchain@v1
       with:
-        toolchain: ${{ inputs.rust-toolchain }}
-        targets: ${{ inputs.arch }}
+        target: ${{ inputs.arch }}
 
     - name: Start etcd # For integration tests.
       if: ${{ inputs.disable-run-tests == 'false' }}
@@ -94,5 +90,5 @@ runs:
       uses: ./.github/actions/upload-artifacts
       with:
         artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime
+        target-files: target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime
         version: ${{ inputs.version }}

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

@@ -4,9 +4,6 @@ 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
@@ -28,24 +25,14 @@ runs:
     - uses: arduino/setup-protoc@v3
 
     - name: Install rust toolchain
-      uses: dtolnay/rust-toolchain@master
+      uses: actions-rust-lang/setup-rust-toolchain@v1
       with:
-        toolchain: ${{ inputs.rust-toolchain }}
-        targets: ${{ inputs.arch }}
+        target: ${{ inputs.arch }}
         components: llvm-tools-preview
 
     - name: Rust Cache
       uses: Swatinem/rust-cache@v2
 
-    - name: Install Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: "3.10"
-
-    - name: Install PyArrow Package
-      shell: pwsh
-      run: pip install pyarrow
-
     - name: Install WSL distribution
       uses: Vampire/setup-wsl@v2
       with:
@@ -69,7 +56,7 @@ runs:
       uses: actions/upload-artifact@v4
       with:
         name: sqlness-logs
-        path: C:\tmp\greptime-*.log
+        path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
         retention-days: 3
 
     - name: Build greptime binary
@@ -80,5 +67,5 @@ runs:
       uses: ./.github/actions/upload-artifacts
       with:
         artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime
+        target-files: target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime,target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime.pdb
         version: ${{ inputs.version }}

.github/actions/publish-github-release/action.yml

@@ -9,8 +9,8 @@ runs:
   steps:
     # Download artifacts from previous jobs, the artifacts will be downloaded to:
     # ${WORKING_DIR}
-    #   |- greptime-darwin-amd64-pyo3-v0.5.0/greptime-darwin-amd64-pyo3-v0.5.0.tar.gz
-    #   |- greptime-darwin-amd64-pyo3-v0.5.0.sha256sum/greptime-darwin-amd64-pyo3-v0.5.0.sha256sum
+    #   |- greptime-darwin-amd64-v0.5.0/greptime-darwin-amd64-v0.5.0.tar.gz
+    #   |- greptime-darwin-amd64-v0.5.0.sha256sum/greptime-darwin-amd64-v0.5.0.sha256sum
     #   |- greptime-darwin-amd64-v0.5.0/greptime-darwin-amd64-v0.5.0.tar.gz
     #   |- greptime-darwin-amd64-v0.5.0.sha256sum/greptime-darwin-amd64-v0.5.0.sha256sum
     #   ...

.github/actions/release-cn-artifacts/action.yaml

@@ -51,8 +51,8 @@ inputs:
     required: true
   upload-to-s3:
     description: Upload to S3
-    required: false
-    default: 'true'
+    required: true
+    default: 'false'
   artifacts-dir:
     description: Directory to store artifacts
     required: false
@@ -77,13 +77,21 @@ runs:
       with:
         path: ${{ inputs.artifacts-dir }}
 
+    - name: Install s5cmd
+      shell: bash
+      run: |
+        wget https://github.com/peak/s5cmd/releases/download/v2.3.0/s5cmd_2.3.0_Linux-64bit.tar.gz
+        tar -xzf s5cmd_2.3.0_Linux-64bit.tar.gz
+        sudo mv s5cmd /usr/local/bin/
+        sudo chmod +x /usr/local/bin/s5cmd
+
     - name: Release artifacts to cn region
       uses: nick-invision/retry@v2
       if: ${{ inputs.upload-to-s3 == 'true' }}
       env:
         AWS_ACCESS_KEY_ID: ${{ inputs.aws-cn-access-key-id }}
         AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-cn-secret-access-key }}
-        AWS_DEFAULT_REGION: ${{ inputs.aws-cn-region }}
+        AWS_REGION: ${{ inputs.aws-cn-region }}
         UPDATE_VERSION_INFO: ${{ inputs.update-version-info }}
       with:
         max_attempts: ${{ inputs.upload-max-retry-times }}

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

@@ -18,6 +18,8 @@ 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

@@ -8,7 +8,7 @@ inputs:
     default: 2
     description: "Number of Datanode replicas"
   meta-replicas:
-    default: 3
+    default: 1
     description: "Number of Metasrv replicas"
   image-registry: 
     default: "docker.io"
@@ -58,7 +58,7 @@ runs:
         --set image.tag=${{ inputs.image-tag }} \
         --set base.podTemplate.main.resources.requests.cpu=50m \
         --set base.podTemplate.main.resources.requests.memory=256Mi \
-        --set base.podTemplate.main.resources.limits.cpu=1000m \
+        --set base.podTemplate.main.resources.limits.cpu=2000m \
         --set base.podTemplate.main.resources.limits.memory=2Gi \
         --set frontend.replicas=${{ inputs.frontend-replicas }} \
         --set datanode.replicas=${{ inputs.datanode-replicas }} \

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

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

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

@@ -1,13 +1,13 @@
 meta:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
 
     [datanode]
     [datanode.client]
-    timeout = "60s"
+    timeout = "120s"
 datanode:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
     compact_rt_size = 2
@@ -16,12 +16,12 @@ datanode:
     cache_path = "/data/greptimedb/s3cache"
     cache_capacity = "256MB"
 frontend:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
 
     [meta_client]
-    ddl_timeout = "60s"
+    ddl_timeout = "120s"
 objectStorage:
   s3:
     bucket: default

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

@@ -1,23 +1,23 @@
 meta:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
     
     [datanode]
     [datanode.client]
-    timeout = "60s"
+    timeout = "120s"
 datanode:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
     compact_rt_size = 2
 frontend:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
 
     [meta_client]
-    ddl_timeout = "60s"
+    ddl_timeout = "120s"
 objectStorage:
   s3:
     bucket: default

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

@@ -1,5 +1,5 @@
 meta:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
     
@@ -11,9 +11,9 @@ meta:
         
     [datanode]
     [datanode.client]
-    timeout = "60s"
+    timeout = "120s"
 datanode:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
     compact_rt_size = 2
@@ -23,12 +23,12 @@ datanode:
     broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
     linger = "2ms"
 frontend:
-  config: |-
+  configData: |-
     [runtime]
     global_rt_size = 4
 
     [meta_client]
-    ddl_timeout = "60s"
+    ddl_timeout = "120s"
 objectStorage:
   s3:
     bucket: default

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

@@ -18,6 +18,8 @@ runs:
         --set controller.replicaCount=${{ inputs.controller-replicas }} \
         --set controller.resources.requests.cpu=50m \
         --set controller.resources.requests.memory=128Mi \
+        --set controller.resources.limits.cpu=2000m \
+        --set controller.resources.limits.memory=2Gi \
         --set listeners.controller.protocol=PLAINTEXT \
         --set listeners.client.protocol=PLAINTEXT \
         --create-namespace \

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

@@ -0,0 +1,30 @@
+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@v2
+      uses: aws-actions/configure-aws-credentials@v4
       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@v2
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-access-key-id: ${{ inputs.aws-access-key-id }}
         aws-secret-access-key: ${{ inputs.aws-secret-access-key }}

.github/actions/upload-artifacts/action.yml

@@ -4,8 +4,8 @@ inputs:
   artifacts-dir:
     description: Directory to store artifacts
     required: true
-  target-file:
-    description: The path of the target artifact
+  target-files:
+    description: The multiple target files to upload, separated by comma
     required: false
   version:
     description: Version of the artifact
@@ -18,17 +18,21 @@ runs:
   using: composite
   steps:
     - name: Create artifacts directory
-      if: ${{ inputs.target-file != '' }}
+      if: ${{ inputs.target-files != '' }}
       working-directory: ${{ inputs.working-dir }}
       shell: bash
       run: |
-        mkdir -p ${{ inputs.artifacts-dir }} && \
-        cp ${{ inputs.target-file }} ${{ inputs.artifacts-dir }}
+        set -e
+        mkdir -p ${{ inputs.artifacts-dir }}
+        IFS=',' read -ra FILES <<< "${{ inputs.target-files }}"
+        for file in "${FILES[@]}"; do
+          cp "$file" ${{ inputs.artifacts-dir }}/
+        done
 
     # The compressed artifacts will use the following layout:
-    # greptime-linux-amd64-pyo3-v0.3.0sha256sum
-    # greptime-linux-amd64-pyo3-v0.3.0.tar.gz
-    #   greptime-linux-amd64-pyo3-v0.3.0
+    # greptime-linux-amd64-v0.3.0sha256sum
+    # greptime-linux-amd64-v0.3.0.tar.gz
+    #   greptime-linux-amd64-v0.3.0
     #   └── greptime
     - name: Compress artifacts and calculate checksum
       working-directory: ${{ inputs.working-dir }}

.github/cargo-blacklist.txt

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

.github/pull_request_template.md

@@ -4,7 +4,8 @@ I hereby agree to the terms of the [GreptimeDB CLA](https://github.com/GreptimeT
 
 ## What's changed and what's your intention?
 
-__!!! DO NOT LEAVE THIS BLOCK EMPTY !!!__
+<!--    
+ __!!! DO NOT LEAVE THIS BLOCK EMPTY !!!__
 
 Please explain IN DETAIL what the changes are in this PR and why they are needed:
 
@@ -12,9 +13,14 @@ Please explain IN DETAIL what the changes are in this PR and why they are needed
 - How does this PR work? Need a brief introduction for the changed logic (optional)
 - Describe clearly one logical change and avoid lazy messages (optional)
 - Describe any limitations of the current code (optional)
+- Describe if this PR will break **API or data compatibility**  (optional)
+-->
 
-## Checklist
+## PR Checklist
+Please convert it to a draft if some of the following conditions are not met.
 
 - [ ] I have written the necessary rustdoc comments.
 - [ ] I have added the necessary unit tests and integration tests.
 - [ ] This PR requires documentation updates.
+- [ ] API changes are backward compatible.
+- [ ] Schema or data changes are backward compatible.

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

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

.github/scripts/upload-artifacts-to-s3.sh

@@ -27,13 +27,13 @@ function upload_artifacts() {
   # ├── latest-version.txt
   # ├── latest-nightly-version.txt
   # ├── v0.1.0
-  # │   ├── greptime-darwin-amd64-pyo3-v0.1.0.sha256sum
-  # │   └── greptime-darwin-amd64-pyo3-v0.1.0.tar.gz
+  # │   ├── greptime-darwin-amd64-v0.1.0.sha256sum
+  # │   └── greptime-darwin-amd64-v0.1.0.tar.gz
   # └── v0.2.0
-  #    ├── greptime-darwin-amd64-pyo3-v0.2.0.sha256sum
-  #    └── greptime-darwin-amd64-pyo3-v0.2.0.tar.gz
+  #    ├── greptime-darwin-amd64-v0.2.0.sha256sum
+  #    └── greptime-darwin-amd64-v0.2.0.tar.gz
   find "$ARTIFACTS_DIR" -type f \( -name "*.tar.gz" -o -name "*.sha256sum" \) | while IFS= read -r file; do
-    aws s3 cp \
+    s5cmd cp \
       "$file" "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/$VERSION/$(basename "$file")"
   done
 }
@@ -45,7 +45,7 @@ function update_version_info() {
     if [[ "$VERSION" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
       echo "Updating latest-version.txt"
       echo "$VERSION" > latest-version.txt
-      aws s3 cp \
+      s5cmd cp \
         latest-version.txt "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/latest-version.txt"
     fi
 
@@ -53,7 +53,7 @@ function update_version_info() {
     if [[ "$VERSION" == *"nightly"* ]]; then
       echo "Updating latest-nightly-version.txt"
       echo "$VERSION" > latest-nightly-version.txt
-      aws s3 cp \
+      s5cmd cp \
         latest-nightly-version.txt "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/latest-nightly-version.txt"
     fi
   fi

.github/workflows/apidoc.yml

@@ -12,20 +12,17 @@ on:
 
 name: Build API docs
 
-env:
-  RUST_TOOLCHAIN: nightly-2024-04-20
-
 jobs:
   apidoc:
     runs-on: ubuntu-20.04
     steps:
     - uses: actions/checkout@v4
+      with:
+        persist-credentials: false
     - uses: arduino/setup-protoc@v3
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
-    - uses: dtolnay/rust-toolchain@master
-      with:
-        toolchain: ${{ env.RUST_TOOLCHAIN }}
+    - uses: actions-rust-lang/setup-rust-toolchain@v1
     - run: cargo doc --workspace --no-deps --document-private-items
     - run: |
         cat <<EOF > target/doc/index.html

.github/workflows/dependency-check.yml

@@ -0,0 +1,35 @@
+name: Check Dependencies
+
+on:
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  check-dependencies:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        persist-credentials: false
+
+    - name: Set up Rust
+      uses: actions-rust-lang/setup-rust-toolchain@v1
+
+    - name: Run cargo tree
+      run: cargo tree --prefix none > dependencies.txt
+
+    - name: Extract dependency names
+      run: awk '{print $1}' dependencies.txt > dependency_names.txt
+
+    - name: Check for blacklisted crates
+      run: |
+        while read -r dep; do
+          if grep -qFx "$dep" dependency_names.txt; then
+            echo "Blacklisted crate '$dep' found in dependencies."
+            exit 1
+          fi
+        done < .github/cargo-blacklist.txt
+        echo "No blacklisted crates found."

.github/workflows/dev-build.yml

@@ -76,15 +76,9 @@ env:
 
   NIGHTLY_RELEASE_PREFIX: nightly
 
-  # Use the different image name to avoid conflict with the release images.
-  IMAGE_NAME: greptimedb-dev
-
   # The source code will check out in the following path: '${WORKING_DIR}/dev/greptime'.
   CHECKOUT_GREPTIMEDB_PATH: dev/greptimedb
 
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -107,6 +101,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Create version
         id: create-version
@@ -161,6 +156,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Checkout greptimedb
         uses: actions/checkout@v4
@@ -168,6 +164,7 @@ jobs:
           repository: ${{ inputs.repository }}
           ref: ${{ inputs.commit }}
           path: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+          persist-credentials: true
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -177,6 +174,8 @@ 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
@@ -190,6 +189,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Checkout greptimedb
         uses: actions/checkout@v4
@@ -197,6 +197,7 @@ jobs:
           repository: ${{ inputs.repository }}
           ref: ${{ inputs.commit }}
           path: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+          persist-credentials: true
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -206,6 +207,8 @@ 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
@@ -222,13 +225,14 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Build and push images to dockerhub
         uses: ./.github/actions/build-images
         with:
           image-registry: docker.io
           image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          image-name: ${{ env.IMAGE_NAME }}
+          image-name: ${{ vars.DEV_BUILD_IMAGE_NAME }}
           image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
           version: ${{ needs.allocate-runners.outputs.version }}
@@ -253,13 +257,14 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Release artifacts to CN region
         uses: ./.github/actions/release-cn-artifacts
         with:
           src-image-registry: docker.io
           src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: ${{ env.IMAGE_NAME }}
+          src-image-name: ${{ vars.DEV_BUILD_IMAGE_NAME }}
           dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
           dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
           dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
@@ -269,6 +274,7 @@ jobs:
           aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
           aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
           aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          upload-to-s3: false
           dev-mode: true                     # Only build the standard images(exclude centos images).
           push-latest-tag: false             # Don't push the latest tag to registry.
           update-version-info: false         # Don't update the version info in S3.
@@ -287,6 +293,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -312,6 +319,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -330,10 +338,16 @@ jobs:
       release-images-to-dockerhub
     ]
     runs-on: ubuntu-20.04
+    permissions:
+      issues: write
+
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Report CI status
         id: report-ci-status

.github/workflows/develop.yml

@@ -1,4 +1,6 @@
 on:
+  schedule:
+    - cron: "0 15 * * 1-5"
   merge_group:
   pull_request:
     types: [ opened, synchronize, reopened, ready_for_review ]
@@ -10,17 +12,6 @@ on:
       - 'docker/**'
       - '.gitignore'
       - 'grafana/**'
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-      - 'grafana/**'
   workflow_dispatch:
 
 name: CI
@@ -29,15 +20,14 @@ 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
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: crate-ci/typos@master
       - name: Check the config docs
         run: |
@@ -50,6 +40,8 @@ jobs:
     name: Check License Header
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: korandoru/hawkeye@v5
 
   check:
@@ -57,22 +49,24 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ windows-2022, ubuntu-20.04 ]
+        os: [ ubuntu-20.04 ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
           # Shares across multiple jobs
           # Shares with `Clippy` job
           shared-key: "check-lint"
+          cache-all-crates: "true"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Run cargo check
         run: cargo check --locked --workspace --all-targets
 
@@ -82,16 +76,11 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@master
         with:
-          toolchain: stable
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "check-toml"
+          persist-credentials: false
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - name: Install taplo
-        run: cargo +stable install taplo-cli --version ^0.9 --locked
+        run: cargo +stable install taplo-cli --version ^0.9 --locked --force
       - name: Run taplo
         run: taplo format --check
 
@@ -104,23 +93,25 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - uses: Swatinem/rust-cache@v2
         with:
           # Shares across multiple jobs
           shared-key: "build-binaries"
+          cache-all-crates: "true"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install cargo-gc-bin
         shell: bash
-        run: cargo install cargo-gc-bin
+        run: cargo install cargo-gc-bin --force
       - name: Build greptime binaries
         shell: bash
         # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc -- --bin greptime --bin sqlness-runner
+        run: cargo gc -- --bin greptime --bin sqlness-runner --features pg_kvbackend
       - name: Pack greptime binaries
         shell: bash
         run: |
@@ -145,31 +136,38 @@ jobs:
       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
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - 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
+          cargo +nightly install cargo-fuzz cargo-gc-bin --force
       - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
           name: bins
           path: .
       - name: Unzip binaries
-        run: | 
+        run: |
           tar -xvf ./bins.tar.gz
           rm ./bins.tar.gz
       - name: Run GreptimeDB
@@ -193,23 +191,30 @@ jobs:
       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
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - name: Set Rust Fuzz
         shell: bash
         run: |
           sudo apt update && sudo apt install -y libfuzzer-14-dev
-          cargo install cargo-fuzz cargo-gc-bin
+          cargo install cargo-fuzz cargo-gc-bin --force
       - name: Download pre-built binariy
         uses: actions/download-artifact@v4
         with:
@@ -247,23 +252,25 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - uses: Swatinem/rust-cache@v2
         with:
           # Shares across multiple jobs
           shared-key: "build-greptime-ci"
+          cache-all-crates: "true"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install cargo-gc-bin
         shell: bash
-        run: cargo install cargo-gc-bin
+        run: cargo install cargo-gc-bin --force
       - name: Build greptime bianry
         shell: bash
         # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc --profile ci -- --bin greptime 
+        run: cargo gc --profile ci -- --bin greptime --features pg_kvbackend
       - name: Pack greptime binary
         shell: bash
         run: |
@@ -277,7 +284,7 @@ jobs:
           artifacts-dir: bin
           version: current
 
-  distributed-fuzztest: 
+  distributed-fuzztest:
     name: Fuzz Test (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
     runs-on: ubuntu-latest
     needs:  build-greptime-ci
@@ -285,25 +292,27 @@ jobs:
     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: "Disk"
-            minio: false
-            kafka: false
-            values: "with-disk.yaml"
-          - name: "Minio"
-            minio: true
-            kafka: false
-            values: "with-minio.yaml"
-          - name: "Minio with Cache"
-            minio: true
-            kafka: false
-            values: "with-minio-and-cache.yaml"
+        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
+        with:
+          persist-credentials: false
       - name: Setup Kind
         uses: ./.github/actions/setup-kind
       - if: matrix.mode.minio
@@ -318,20 +327,13 @@ jobs:
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - 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
+          cargo +nightly install cargo-fuzz cargo-gc-bin --force
       # Downloads ci image
       - name: Download pre-built binariy
         uses: actions/download-artifact@v4
@@ -390,12 +392,12 @@ jobs:
       - name: Describe Nodes
         if: failure()
         shell: bash
-        run: | 
-          kubectl describe nodes      
+        run: |
+          kubectl describe nodes
       - name: Export kind logs
         if: failure()
         shell: bash
-        run: | 
+        run: |
           kind export logs /tmp/kind
       - name: Upload logs
         if: failure()
@@ -407,27 +409,54 @@ jobs:
       - name: Delete cluster
         if: success()
         shell: bash
-        run: | 
+        run: |
           kind delete cluster
           docker stop $(docker ps -a -q)
           docker rm $(docker ps -a -q)
           docker system prune -f
 
-  distributed-fuzztest-with-chaos: 
+  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_failover_mito_regions", "fuzz_failover_metric_regions"]
-        mode: 
+        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
+        with:
+          persist-credentials: false
       - name: Setup Kind
         uses: ./.github/actions/setup-kind
       - name: Setup Chaos Mesh
@@ -444,20 +473,13 @@ jobs:
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - 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
+          cargo +nightly install cargo-fuzz cargo-gc-bin --force
       # Downloads ci image
       - name: Download pre-built binariy
         uses: actions/download-artifact@v4
@@ -502,7 +524,7 @@ jobs:
         with:
           image-registry: localhost:5001
           values-filename: ${{ matrix.mode.values }}
-          enable-region-failover: true
+          enable-region-failover: ${{ matrix.mode.kafka }}
       - name: Port forward (mysql)
         run: |
           kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
@@ -517,12 +539,12 @@ jobs:
       - name: Describe Nodes
         if: failure()
         shell: bash
-        run: | 
-          kubectl describe nodes      
+        run: |
+          kubectl describe nodes
       - name: Export kind logs
         if: failure()
         shell: bash
-        run: | 
+        run: |
           kind export logs /tmp/kind
       - name: Upload logs
         if: failure()
@@ -534,7 +556,7 @@ jobs:
       - name: Delete cluster
         if: success()
         shell: bash
-        run: | 
+        run: |
           kind delete cluster
           docker stop $(docker ps -a -q)
           docker rm $(docker ps -a -q)
@@ -554,9 +576,18 @@ jobs:
           - name: "Remote WAL"
             opts: "-w kafka -k 127.0.0.1:9092"
             kafka: true
+          - name: "Pg Kvbackend"
+            opts: "--setup-pg"
+            kafka: false
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - if: matrix.mode.kafka
+        name: Setup kafka server
+        working-directory: tests-integration/fixtures
+        run: docker compose up -d --wait kafka
       - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
@@ -564,10 +595,6 @@ jobs:
           path: .
       - name: Unzip binaries
         run: tar -xvf ./bins.tar.gz
-      - 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: Run sqlness
         run: RUST_BACKTRACE=1 ./bins/sqlness-runner ${{ matrix.mode.opts }} -c ./tests/cases --bins-dir ./bins --preserve-state
       - name: Upload sqlness logs
@@ -584,20 +611,16 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
         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: Run cargo fmt
-        run: cargo fmt --all -- --check
+      - name: Check format
+        run: make fmt-check
 
   clippy:
     name: Clippy
@@ -605,12 +628,13 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
           components: clippy
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
@@ -618,58 +642,106 @@ jobs:
           # Shares across multiple jobs
           # Shares with `Check` job
           shared-key: "check-lint"
+          cache-all-crates: "true"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Run cargo clippy
         run: make clippy
 
-  coverage:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04-8-cores
-    timeout-minutes: 60
+  conflict-check:
+    name: Check for conflict
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - name: Merge Conflict Finder
+        uses: olivernybroe/action-conflict-finder@v4.0
+
+  test:
+    if: github.event_name != 'merge_group'
+    runs-on: ubuntu-22.04-arm
+    timeout-minutes: 60
+    needs:  [conflict-check, clippy, fmt]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: KyleMayes/install-llvm-action@v1
-        with:
-          version: "14.0"
+      - uses: rui314/setup-mold@v1
       - name: Install toolchain
-        uses: dtolnay/rust-toolchain@master
+        uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-          components: llvm-tools-preview
+            cache: false
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
         with:
           # Shares cross multiple jobs
           shared-key: "coverage-test"
-      - name: Docker Cache
-        uses: ScribeMD/docker-cache@0.3.7
+          cache-all-crates: "true"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
+      - name: Install latest nextest release
+        uses: taiki-e/install-action@nextest
+      - name: Setup external services
+        working-directory: tests-integration/fixtures
+        run: docker compose up -d --wait
+      - name: Run nextest cases
+        run: cargo nextest run --workspace -F dashboard -F pg_kvbackend
+        env:
+          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=mold"
+          RUST_BACKTRACE: 1
+          RUST_MIN_STACK: 8388608 # 8MB
+          CARGO_INCREMENTAL: 0
+          GT_S3_BUCKET: ${{ vars.AWS_CI_TEST_BUCKET }}
+          GT_S3_ACCESS_KEY_ID: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
+          GT_S3_ACCESS_KEY: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
+          GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
+          GT_MINIO_BUCKET: greptime
+          GT_MINIO_ACCESS_KEY_ID: superpower_ci_user
+          GT_MINIO_ACCESS_KEY: superpower_password
+          GT_MINIO_REGION: us-west-2
+          GT_MINIO_ENDPOINT_URL: http://127.0.0.1:9000
+          GT_ETCD_ENDPOINTS: http://127.0.0.1:2379
+          GT_POSTGRES_ENDPOINTS: postgres://greptimedb:admin@127.0.0.1:5432/postgres
+          GT_KAFKA_ENDPOINTS: 127.0.0.1:9092
+          GT_KAFKA_SASL_ENDPOINTS: 127.0.0.1:9093
+          UNITTEST_LOG_DIR: "__unittest_logs"
+
+  coverage:
+    if: github.event_name == 'merge_group'
+    runs-on: ubuntu-20.04-8-cores
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v4
         with:
-          key: docker-${{ runner.os }}-coverage
+          persist-credentials: false
+      - uses: arduino/setup-protoc@v3
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: rui314/setup-mold@v1
+      - name: Install toolchain
+        uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          components: llvm-tools
+          cache: false
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2
+        with:
+          # Shares cross multiple jobs
+          shared-key: "coverage-test"
+          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install latest nextest release
         uses: taiki-e/install-action@nextest
       - name: Install cargo-llvm-cov
         uses: taiki-e/install-action@cargo-llvm-cov
-      - name: Install Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-      - name: Install PyArrow Package
-        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 external services
+        working-directory: tests-integration/fixtures
+        run: docker compose up -d --wait
       - name: Run nextest cases
-        run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F pyo3_backend -F dashboard
+        run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F dashboard -F pg_kvbackend
         env:
-          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
+          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=mold"
           RUST_BACKTRACE: 1
           CARGO_INCREMENTAL: 0
           GT_S3_BUCKET: ${{ vars.AWS_CI_TEST_BUCKET }}
@@ -682,7 +754,9 @@ jobs:
           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/docbot.yml

@@ -3,16 +3,21 @@ on:
   pull_request_target:
     types: [opened, edited]
 
-permissions:
-  pull-requests: write
-  contents: read
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
 
 jobs:
   docbot:
     runs-on: ubuntu-20.04
+    permissions:
+      pull-requests: write
+      contents: read
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Maybe Follow Up Docs Issue
         working-directory: cyborg

.github/workflows/docs.yml

@@ -34,6 +34,8 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: crate-ci/typos@master
 
   license-header-check:
@@ -41,6 +43,8 @@ jobs:
     name: Check License Header
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: korandoru/hawkeye@v5
 
   check:
@@ -66,6 +70,11 @@ jobs:
     steps:
       - run: 'echo "No action required"'
 
+  test:
+    runs-on: ubuntu-20.04
+    steps:
+      - run: 'echo "No action required"'
+
   sqlness:
     name: Sqlness Test (${{ matrix.mode.name }})
     runs-on: ${{ matrix.os }}

.github/workflows/nightly-build.yml

@@ -12,7 +12,7 @@ on:
       linux_amd64_runner:
         type: choice
         description: The runner uses to build linux-amd64 artifacts
-        default: ec2-c6i.2xlarge-amd64
+        default: ec2-c6i.4xlarge-amd64
         options:
           - ubuntu-20.04
           - ubuntu-20.04-8-cores
@@ -27,7 +27,7 @@ on:
       linux_arm64_runner:
         type: choice
         description: The runner uses to build linux-arm64 artifacts
-        default: ec2-c6g.2xlarge-arm64
+        default: ec2-c6g.4xlarge-arm64
         options:
           - ec2-c6g.xlarge-arm64 # 4C8G
           - ec2-c6g.2xlarge-arm64 # 8C16G
@@ -66,13 +66,6 @@ env:
 
   NIGHTLY_RELEASE_PREFIX: nightly
 
-  # Use the different image name to avoid conflict with the release images.
-  # The DockerHub image will be greptime/greptimedb-nightly.
-  IMAGE_NAME: greptimedb-nightly
-
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -95,6 +88,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Create version
         id: create-version
@@ -147,6 +141,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -154,6 +149,8 @@ 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
@@ -166,6 +163,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -173,6 +171,8 @@ 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
@@ -189,17 +189,18 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Build and push images to dockerhub
         uses: ./.github/actions/build-images
         with:
           image-registry: docker.io
           image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          image-name: ${{ env.IMAGE_NAME }}
+          image-name: ${{ vars.NIGHTLY_BUILD_IMAGE_NAME }}
           image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
           version: ${{ needs.allocate-runners.outputs.version }}
-          push-latest-tag: true
+          push-latest-tag: false
 
       - name: Set nightly build result
         id: set-nightly-build-result
@@ -222,13 +223,14 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Release artifacts to CN region
         uses: ./.github/actions/release-cn-artifacts
         with:
           src-image-registry: docker.io
           src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: ${{ env.IMAGE_NAME }}
+          src-image-name: ${{ vars.NIGHTLY_BUILD_IMAGE_NAME }}
           dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
           dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
           dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
@@ -238,9 +240,10 @@ jobs:
           aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
           aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
           aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          upload-to-s3: false
           dev-mode: false
           update-version-info: false  # Don't update version info in S3.
-          push-latest-tag: true
+          push-latest-tag: false
 
   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
@@ -256,6 +259,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -281,6 +285,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -299,10 +304,14 @@ jobs:
       release-images-to-dockerhub
     ]
     runs-on: ubuntu-20.04
+    permissions:
+      issues: write
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Report CI status
         id: report-ci-status

.github/workflows/nightly-ci.yml

@@ -1,6 +1,6 @@
 on:
   schedule:
-    - cron: "0 23 * * 1-5"
+    - cron: "0 23 * * 1-4"
   workflow_dispatch:
 
 name: Nightly CI
@@ -9,12 +9,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
-env:
-  RUST_TOOLCHAIN: nightly-2024-04-20
-
-permissions:
-  issues: write
-
 jobs:
   sqlness-test:
     name: Run sqlness test
@@ -25,6 +19,11 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
+
+      - name: Check install.sh
+        run: ./.github/scripts/check-install-script.sh
+
       - name: Run sqlness test
         uses: ./.github/actions/sqlness-test
         with:
@@ -33,21 +32,31 @@ 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
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     runs-on: windows-2022-8-cores
+    permissions:
+      issues: write
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Run sqlness
@@ -55,11 +64,11 @@ jobs:
         env:
           SQLNESS_OPTS: "--preserve-state"
       - name: Upload sqlness logs
-        if: always()
+        if: failure()
         uses: actions/upload-artifact@v4
         with:
           name: sqlness-logs
-          path: C:\tmp\greptime-*.log
+          path: C:\Users\RUNNER~1\AppData\Local\Temp\sqlness*
           retention-days: 3
 
   test-on-windows:
@@ -70,6 +79,9 @@ jobs:
     steps:
       - run: git config --global core.autocrlf false
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - uses: arduino/setup-protoc@v3
         with:
@@ -78,26 +90,19 @@ jobs:
         with:
           version: "14.0"
       - name: Install Rust toolchain
-        uses: dtolnay/rust-toolchain@master
+        uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
           components: llvm-tools-preview
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Install Cargo Nextest
         uses: taiki-e/install-action@nextest
-      - name: Install Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-      - name: Install PyArrow Package
-        run: pip install pyarrow
       - name: Install WSL distribution
         uses: Vampire/setup-wsl@v2
         with:
           distribution: Ubuntu-22.04
       - name: Running tests
-        run: cargo nextest run -F pyo3_backend,dashboard
+        run: cargo nextest run -F dashboard
         env:
           CARGO_BUILD_RUSTFLAGS: "-C linker=lld-link"
           RUST_BACKTRACE: 1
@@ -109,6 +114,21 @@ jobs:
           GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
           UNITTEST_LOG_DIR: "__unittest_logs"
 
+  cleanbuild-linux-nix:
+    name: Run clean build on Linux
+    runs-on: ubuntu-latest
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: cachix/install-nix-action@v27
+        with:
+          nix_path: nixpkgs=channel:nixos-24.11
+      - run: nix develop --command cargo build
+
   check-status:
     name: Check status
     needs: [sqlness-test, sqlness-windows, test-on-windows]
@@ -131,6 +151,9 @@ jobs:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Report CI status
         id: report-ci-status

.github/workflows/release-dev-builder-images.yaml

@@ -1,12 +1,14 @@
 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
@@ -28,22 +30,122 @@ 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
+          persist-credentials: false
+
+      - 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: ${{ inputs.version }}
+          version: ${{ env.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 }}
+        env:
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ECR_IMAGE_REGISTRY: ${{ vars.ECR_IMAGE_REGISTRY }}
+          ECR_IMAGE_NAMESPACE: ${{ vars.ECR_IMAGE_NAMESPACE }}
+        run: |
+          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
+            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            quay.io/skopeo/stable:latest \
+            copy -a docker://docker.io/$IMAGE_NAMESPACE/dev-builder-ubuntu:$IMAGE_VERSION \
+            docker://$ECR_IMAGE_REGISTRY/$ECR_IMAGE_NAMESPACE/dev-builder-ubuntu:$IMAGE_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/$IMAGE_NAMESPACE/dev-builder-ubuntu:latest \
+            docker://$ECR_IMAGE_REGISTRY/$ECR_IMAGE_NAMESPACE/dev-builder-ubuntu:latest
+
+      - name: Push dev-builder-centos image
+        shell: bash
+        if: ${{ inputs.release_dev_builder_centos_image }}
+        env:
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ECR_IMAGE_REGISTRY: ${{ vars.ECR_IMAGE_REGISTRY }}
+          ECR_IMAGE_NAMESPACE: ${{ vars.ECR_IMAGE_NAMESPACE }}
+        run: |
+          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
+            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            quay.io/skopeo/stable:latest \
+            copy -a docker://docker.io/$IMAGE_NAMESPACE/dev-builder-centos:$IMAGE_VERSION \
+            docker://$ECR_IMAGE_REGISTRY/$ECR_IMAGE_NAMESPACE/dev-builder-centos:$IMAGE_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/$IMAGE_NAMESPACE/dev-builder-centos:latest \
+            docker://$ECR_IMAGE_REGISTRY/$ECR_IMAGE_NAMESPACE/dev-builder-centos:latest
+
+      - name: Push dev-builder-android image
+        shell: bash
+        if: ${{ inputs.release_dev_builder_android_image }}
+        env:
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ECR_IMAGE_REGISTRY: ${{ vars.ECR_IMAGE_REGISTRY }}
+          ECR_IMAGE_NAMESPACE: ${{ vars.ECR_IMAGE_NAMESPACE }}
+        run: |
+          docker run -v "${DOCKER_CONFIG:-$HOME/.docker}:/root/.docker:ro" \
+            -e "REGISTRY_AUTH_FILE=/root/.docker/config.json" \
+            quay.io/skopeo/stable:latest \
+            copy -a docker://docker.io/$IMAGE_NAMESPACE/dev-builder-android:$IMAGE_VERSION \
+            docker://$ECR_IMAGE_REGISTRY/$ECR_IMAGE_NAMESPACE/dev-builder-android:$IMAGE_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/$IMAGE_NAMESPACE/dev-builder-android:latest \
+            docker://$ECR_IMAGE_REGISTRY/$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
@@ -51,35 +153,51 @@ 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 }}
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ACR_IMAGE_REGISTRY: ${{ vars.ACR_IMAGE_REGISTRY }}
         run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }}
+          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/$IMAGE_NAMESPACE/dev-builder-ubuntu:$IMAGE_VERSION \
+            docker://$ACR_IMAGE_REGISTRY/$IMAGE_NAMESPACE/dev-builder-ubuntu:$IMAGE_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 }}
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ACR_IMAGE_REGISTRY: ${{ vars.ACR_IMAGE_REGISTRY }}
         run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }}
+          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/$IMAGE_NAMESPACE/dev-builder-centos:$IMAGE_VERSION \
+            docker://$ACR_IMAGE_REGISTRY/$IMAGE_NAMESPACE/dev-builder-centos:$IMAGE_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 }}
+          IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
+          IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
+          ACR_IMAGE_REGISTRY: ${{ vars.ACR_IMAGE_REGISTRY }}
         run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }}
+          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/$IMAGE_NAMESPACE/dev-builder-android:$IMAGE_VERSION \
+            docker://$ACR_IMAGE_REGISTRY/$IMAGE_NAMESPACE/dev-builder-android:$IMAGE_VERSION

.github/workflows/release.yml

@@ -31,8 +31,9 @@ on:
       linux_arm64_runner:
         type: choice
         description: The runner uses to build linux-arm64 artifacts
-        default: ec2-c6g.4xlarge-arm64
+        default: ec2-c6g.8xlarge-arm64
         options:
+          - ubuntu-2204-32-cores-arm
           - ec2-c6g.xlarge-arm64 # 4C8G
           - ec2-c6g.2xlarge-arm64 # 8C16G
           - ec2-c6g.4xlarge-arm64 # 16C32G
@@ -82,7 +83,6 @@ 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.
@@ -91,12 +91,7 @@ env:
   # The scheduled version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD', like v0.2.0-nigthly-20230313;
   NIGHTLY_RELEASE_PREFIX: nightly
   # Note: The NEXT_RELEASE_VERSION should be modified manually by every formal release.
-  NEXT_RELEASE_VERSION: v0.10.0
-
-# Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
-permissions:
-  issues: write # Allows the action to create issues for cyborg.
-  contents: write # Allows the action to create a release.
+  NEXT_RELEASE_VERSION: v0.12.0
 
 jobs:
   allocate-runners:
@@ -122,6 +117,12 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
+
+      - 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 }});
@@ -176,6 +177,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -183,6 +185,8 @@ 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
@@ -195,6 +199,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - uses: ./.github/actions/build-linux-artifacts
         with:
@@ -202,6 +207,8 @@ 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
@@ -213,18 +220,10 @@ jobs:
             arch: aarch64-apple-darwin
             features: servers/dashboard
             artifacts-dir-prefix: greptime-darwin-arm64
-          - os: ${{ needs.allocate-runners.outputs.macos-runner }}
-            arch: aarch64-apple-darwin
-            features: pyo3_backend,servers/dashboard
-            artifacts-dir-prefix: greptime-darwin-arm64-pyo3
           - os: ${{ needs.allocate-runners.outputs.macos-runner }}
             features: servers/dashboard
             arch: x86_64-apple-darwin
             artifacts-dir-prefix: greptime-darwin-amd64
-          - os: ${{ needs.allocate-runners.outputs.macos-runner }}
-            features: pyo3_backend,servers/dashboard
-            arch: x86_64-apple-darwin
-            artifacts-dir-prefix: greptime-darwin-amd64-pyo3
     runs-on: ${{ matrix.os }}
     outputs:
       build-macos-result: ${{ steps.set-build-macos-result.outputs.build-macos-result }}
@@ -236,15 +235,16 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - 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 }}
-          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          # We decide to disable the integration tests on macOS because it's unnecessary and time-consuming.
+          disable-run-tests: true
           artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
 
       - name: Set build macos result
@@ -262,10 +262,6 @@ jobs:
             arch: x86_64-pc-windows-msvc
             features: servers/dashboard
             artifacts-dir-prefix: greptime-windows-amd64
-          - os: ${{ needs.allocate-runners.outputs.windows-runner }}
-            arch: x86_64-pc-windows-msvc
-            features: pyo3_backend,servers/dashboard
-            artifacts-dir-prefix: greptime-windows-amd64-pyo3
     runs-on: ${{ matrix.os }}
     outputs:
       build-windows-result: ${{ steps.set-build-windows-result.outputs.build-windows-result }}
@@ -279,11 +275,11 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - 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 }}
@@ -310,15 +306,18 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Build and push images to dockerhub
         uses: ./.github/actions/build-images
         with:
           image-registry: docker.io
           image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-name: ${{ vars.GREPTIMEDB_IMAGE_NAME }}
           image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
           version: ${{ needs.allocate-runners.outputs.version }}
+          push-latest-tag: true
 
       - name: Set build image result
         id: set-build-image-result
@@ -345,13 +344,14 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Release artifacts to CN region
         uses: ./.github/actions/release-cn-artifacts
         with:
           src-image-registry: docker.io
           src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: greptimedb
+          src-image-name: ${{ vars.GREPTIMEDB_IMAGE_NAME }}
           dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
           dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
           dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
@@ -362,6 +362,7 @@ jobs:
           aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
           aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
           dev-mode: false
+          upload-to-s3: true
           update-version-info: true
           push-latest-tag: true
 
@@ -381,6 +382,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Publish GitHub release
         uses: ./.github/actions/publish-github-release
@@ -404,6 +406,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -429,6 +432,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Stop EC2 runner
         uses: ./.github/actions/stop-runner
@@ -440,6 +444,29 @@ jobs:
           aws-region: ${{ vars.EC2_RUNNER_REGION }}
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
+  bump-doc-version:
+    name: Bump doc version
+    if: ${{ github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [allocate-runners]
+    runs-on: ubuntu-20.04
+    # Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
+    permissions:
+      issues: write # Allows the action to create issues for cyborg.
+      contents: write # Allows the action to create a release.
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: ./.github/actions/setup-cyborg
+      - name: Bump doc version
+        working-directory: cyborg
+        run: pnpm tsx bin/bump-doc-version.ts
+        env:
+          VERSION: ${{ needs.allocate-runners.outputs.version }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          DOCS_REPO_TOKEN: ${{ secrets.DOCS_REPO_TOKEN }}
+
   notification:
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' && (github.event_name == 'push' || github.event_name == 'schedule') && always() }}
     name: Send notification to Greptime team
@@ -449,10 +476,17 @@ jobs:
       build-windows-artifacts,
     ]
     runs-on: ubuntu-20.04
+    # Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
+    permissions:
+      issues: write # Allows the action to create issues for cyborg.
+      contents: write # Allows the action to create a release.
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Report CI status
         id: report-ci-status

.github/workflows/schedule.yml

@@ -4,18 +4,20 @@ on:
     - cron: '4 2 * * *'
   workflow_dispatch:
 
-permissions:
-  contents: read
-  issues: write
-  pull-requests: write
 
 jobs:
   maintenance:
     name: Periodic Maintenance
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: write
+      pull-requests: write
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Do Maintenance
         working-directory: cyborg

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

@@ -1,18 +1,24 @@
 name: "Semantic Pull Request"
 
 on:
-  pull_request_target:
+  pull_request:
     types:
       - opened
       - reopened
       - edited
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   check:
     runs-on: ubuntu-20.04
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: ./.github/actions/setup-cyborg
       - name: Check Pull Request
         working-directory: cyborg

.gitignore

@@ -47,6 +47,10 @@ benchmarks/data
 
 venv/
 
-# Fuzz tests 
+# Fuzz tests
 tests-fuzz/artifacts/
 tests-fuzz/corpus/
+
+# Nix
+.direnv
+.envrc

.pre-commit-config.yaml

@@ -17,6 +17,6 @@ repos:
     -    id: fmt
     -    id: clippy
          args: ["--workspace", "--all-targets", "--all-features", "--", "-D", "warnings"]
-         stages: [push]
+         stages: [pre-push]
     -    id: cargo-check
          args: ["--workspace", "--all-targets", "--all-features"]

AUTHOR.md

@@ -3,41 +3,43 @@
 ## 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)
+* [KKould](https://github.com/KKould)
+* [Lanqing Yang](https://github.com/lyang24)
+* [NiwakaDev](https://github.com/NiwakaDev)
+* [tisonkun](https://github.com/tisonkun)
+
 
 ## 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)
+* [Breeze-P](https://github.com/Breeze-P)
 * [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)
+* [GrepTime](https://github.com/GrepTime)
 * [holalengyu](https://github.com/holalengyu)
 * [killme2008](https://github.com/killme2008)
+* [MichaelScofield](https://github.com/MichaelScofield)
 * [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)
+* [Wenjie0329](https://github.com/Wenjie0329)
+* [WenyXu](https://github.com/WenyXu)
 * [xtang](https://github.com/xtang)
 * [zhaoyingnan01](https://github.com/zhaoyingnan01)
 * [zhongzc](https://github.com/zhongzc)
+* [ZonaHex](https://github.com/ZonaHex)
 * [zyy17](https://github.com/zyy17)
 
 ## All Contributors
 
-[![All Contributors](https://contrib.rocks/image?repo=GreptimeTeam/greptimedb)](https://github.com/GreptimeTeam/greptimedb/graphs/contributors)
+To see the full list of contributors, please visit our [Contributors page](https://github.com/GreptimeTeam/greptimedb/graphs/contributors)

Cargo.toml

@@ -2,24 +2,28 @@
 members = [
     "src/api",
     "src/auth",
-    "src/catalog",
     "src/cache",
+    "src/catalog",
+    "src/cli",
     "src/client",
     "src/cmd",
     "src/common/base",
     "src/common/catalog",
     "src/common/config",
     "src/common/datasource",
+    "src/common/decimal",
     "src/common/error",
     "src/common/frontend",
     "src/common/function",
-    "src/common/macro",
     "src/common/greptimedb-telemetry",
     "src/common/grpc",
     "src/common/grpc-expr",
+    "src/common/macro",
     "src/common/mem-prof",
     "src/common/meta",
+    "src/common/options",
     "src/common/plugins",
+    "src/common/pprof",
     "src/common/procedure",
     "src/common/procedure-test",
     "src/common/query",
@@ -29,7 +33,6 @@ members = [
     "src/common/telemetry",
     "src/common/test-util",
     "src/common/time",
-    "src/common/decimal",
     "src/common/version",
     "src/common/wal",
     "src/datanode",
@@ -37,6 +40,8 @@ members = [
     "src/file-engine",
     "src/flow",
     "src/frontend",
+    "src/index",
+    "src/log-query",
     "src/log-store",
     "src/meta-client",
     "src/meta-srv",
@@ -50,13 +55,11 @@ members = [
     "src/promql",
     "src/puffin",
     "src/query",
-    "src/script",
     "src/servers",
     "src/session",
     "src/sql",
     "src/store-api",
     "src/table",
-    "src/index",
     "tests-fuzz",
     "tests-integration",
     "tests/runner",
@@ -64,7 +67,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.9.0"
+version = "0.12.0"
 edition = "2021"
 license = "Apache-2.0"
 
@@ -75,10 +78,10 @@ clippy.dbg_macro = "warn"
 clippy.implicit_clone = "warn"
 clippy.readonly_write_lock = "allow"
 rust.unknown_lints = "deny"
-# Remove this after https://github.com/PyO3/pyo3/issues/4094
-rust.non_local_definitions = "allow"
+rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
 
 [workspace.dependencies]
+# DO_NOT_REMOVE_THIS: BEGIN_OF_EXTERNAL_DEPENDENCIES
 # We turn off default-features for some dependencies here so the workspaces which inherit them can
 # selectively turn them on if needed, since we can override default-features = true (from false)
 # for the inherited dependency but cannot do the reverse (override from true to false).
@@ -86,102 +89,136 @@ rust.non_local_definitions = "allow"
 # See for more detaiils: https://github.com/rust-lang/cargo/issues/11329
 ahash = { version = "0.8", features = ["compile-time-rng"] }
 aquamarine = "0.3"
-arrow = { version = "51.0.0", features = ["prettyprint"] }
-arrow-array = { version = "51.0.0", default-features = false, features = ["chrono-tz"] }
-arrow-flight = "51.0"
-arrow-ipc = { version = "51.0.0", default-features = false, features = ["lz4"] }
-arrow-schema = { version = "51.0", features = ["serde"] }
+arrow = { version = "53.0.0", features = ["prettyprint"] }
+arrow-array = { version = "53.0.0", default-features = false, features = ["chrono-tz"] }
+arrow-flight = "53.0"
+arrow-ipc = { version = "53.0.0", default-features = false, features = ["lz4", "zstd"] }
+arrow-schema = { version = "53.0", features = ["serde"] }
 async-stream = "0.3"
 async-trait = "0.1"
-axum = { version = "0.6", features = ["headers"] }
+# Remember to update axum-extra, axum-macros when updating axum
+axum = "0.8"
+axum-extra = "0.10"
+axum-macros = "0.4"
+backon = "1"
 base64 = "0.21"
 bigdecimal = "0.4.2"
 bitflags = "2.4.1"
 bytemuck = "1.12"
-bytes = { version = "1.5", features = ["serde"] }
+bytes = { version = "1.7", features = ["serde"] }
 chrono = { version = "0.4", features = ["serde"] }
+chrono-tz = "0.10.1"
 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 = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
-datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "d7bda5c9b762426e81f144296deadc87e5f4a0b8" }
+datafusion = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-common = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-expr = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-functions = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-optimizer = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-physical-expr = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-physical-plan = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-sql = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-substrait = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+deadpool = "0.10"
+deadpool-postgres = "0.12"
 derive_builder = "0.12"
 dotenv = "0.15"
-etcd-client = { version = "0.13" }
+etcd-client = "0.14"
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "c437b55725b7f5224fe9d46db21072b4a682ee4b" }
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "072ce580502e015df1a6b03a185b60309a7c2a7a" }
+hex = "0.4"
+http = "1"
 humantime = "2.1"
 humantime-serde = "1.1"
+hyper = "1.1"
+hyper-util = "0.1"
 itertools = "0.10"
+jsonb = { git = "https://github.com/databendlabs/jsonb.git", rev = "8c8d2fc294a39f3ff08909d60f718639cfba3875", default-features = false }
 lazy_static = "1.4"
-meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "049171eb16cb4249d8099751a0c46750d1fe88e7" }
+local-ip-address = "0.6"
+loki-proto = { git = "https://github.com/GreptimeTeam/loki-proto.git", rev = "1434ecf23a2654025d86188fb5205e7a74b225d3" }
+meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "5618e779cf2bb4755b499c630fba4c35e91898cb" }
 mockall = "0.11.4"
 moka = "0.12"
+nalgebra = "0.33"
 notify = "6.1"
 num_cpus = "1.16"
 once_cell = "1.18"
-opentelemetry-proto = { version = "0.5", features = [
+opentelemetry-proto = { version = "0.27", features = [
     "gen-tonic",
     "metrics",
     "trace",
+    "with-serde",
+    "logs",
 ] }
-parquet = { version = "51.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
+parking_lot = "0.12"
+parquet = { version = "53.0.0", 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" }
-prost = "0.12"
+promql-parser = { git = "https://github.com/GreptimeTeam/promql-parser.git", features = [
+    "ser",
+], rev = "27abb8e16003a50c720f00d6c85f41f5fa2a2a8e" }
+prost = "0.13"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
+ratelimit = "0.9"
 regex = "1.8"
-regex-automata = { version = "0.4" }
+regex-automata = "0.4"
 reqwest = { version = "0.12", default-features = false, features = [
     "json",
     "rustls-tls-native-roots",
     "stream",
     "multipart",
 ] }
-rskafka = "0.5"
+rskafka = { git = "https://github.com/influxdata/rskafka.git", rev = "75535b5ad9bae4a5dbb582c82e44dfd81ec10105", features = [
+    "transport-tls",
+] }
 rstest = "0.21"
 rstest_reuse = "0.7"
 rust_decimal = "1.33"
-schemars = "0.8"
+rustc-hash = "2.0"
+rustls = { version = "0.23.20", default-features = false } # override by patch, see [patch.crates-io]
 serde = { version = "1.0", features = ["derive"] }
 serde_json = { version = "1.0", features = ["float_roundtrip"] }
 serde_with = "3"
+shadow-rs = "0.38"
+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 = [
+# on branch v0.52.x
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "71dd86058d2af97b9925093d40c4e03360403170", features = [
     "visitor",
-] }
+    "serde",
+] } # on branch v0.44.x
 strum = { version = "0.25", features = ["derive"] }
 tempfile = "3"
-tokio = { version = "1.36", features = ["full"] }
-tokio-stream = { version = "0.1" }
+tokio = { version = "1.40", features = ["full"] }
+tokio-postgres = "0.7"
+tokio-rustls = { version = "0.26.0", default-features = false } # override by patch, see [patch.crates-io]
+tokio-stream = "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" }
+tonic = { version = "0.12", features = ["tls", "gzip", "zstd"] }
+tower = "0.5"
+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"
+# DO_NOT_REMOVE_THIS: END_OF_EXTERNAL_DEPENDENCIES
 
 ## workspaces members
 api = { path = "src/api" }
 auth = { path = "src/auth" }
 cache = { path = "src/cache" }
 catalog = { path = "src/catalog" }
+cli = { path = "src/cli" }
 client = { path = "src/client" }
 cmd = { path = "src/cmd", default-features = false }
 common-base = { path = "src/common/base" }
@@ -198,7 +235,9 @@ common-grpc-expr = { path = "src/common/grpc-expr" }
 common-macro = { path = "src/common/macro" }
 common-mem-prof = { path = "src/common/mem-prof" }
 common-meta = { path = "src/common/meta" }
+common-options = { path = "src/common/options" }
 common-plugins = { path = "src/common/plugins" }
+common-pprof = { path = "src/common/pprof" }
 common-procedure = { path = "src/common/procedure" }
 common-procedure-test = { path = "src/common/procedure-test" }
 common-query = { path = "src/common/query" }
@@ -215,6 +254,7 @@ file-engine = { path = "src/file-engine" }
 flow = { path = "src/flow" }
 frontend = { path = "src/frontend", default-features = false }
 index = { path = "src/index" }
+log-query = { path = "src/log-query" }
 log-store = { path = "src/log-store" }
 meta-client = { path = "src/meta-client" }
 meta-srv = { path = "src/meta-srv" }
@@ -228,7 +268,6 @@ plugins = { path = "src/plugins" }
 promql = { path = "src/promql" }
 puffin = { path = "src/puffin" }
 query = { path = "src/query" }
-script = { path = "src/script" }
 servers = { path = "src/servers" }
 session = { path = "src/session" }
 sql = { path = "src/sql" }
@@ -236,16 +275,25 @@ 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", rev = "a951e03" } # version = "0.27.5" with ring patch
+rustls = { git = "https://github.com/GreptimeTeam/rustls", rev = "34fd0c6" }             # version = "0.23.20" with ring patch
+tokio-rustls = { git = "https://github.com/GreptimeTeam/tokio-rustls", rev = "4604ca6" } # version = "0.26.0" with ring patch
+# 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 = "049171eb16cb4249d8099751a0c46750d1fe88e7"
+rev = "5618e779cf2bb4755b499c630fba4c35e91898cb"
 
 [profile.release]
 debug = 1
 
 [profile.nightly]
 inherits = "release"
-strip = true
+strip = "debuginfo"
 lto = "thin"
 debug = false
 incremental = false

Cross.toml

@@ -1,3 +1,6 @@
+[target.aarch64-unknown-linux-gnu]
+image = "ghcr.io/cross-rs/aarch64-unknown-linux-gnu:0.2.5"
+
 [build]
 pre-build = [
     "dpkg --add-architecture $CROSS_DEB_ARCH",
@@ -5,3 +8,8 @@ pre-build = [
     "curl -LO https://github.com/protocolbuffers/protobuf/releases/download/v3.15.8/protoc-3.15.8-linux-x86_64.zip && unzip protoc-3.15.8-linux-x86_64.zip -d /usr/",
     "chmod a+x /usr/bin/protoc && chmod -R a+rx /usr/include/google",
 ]
+
+[build.env]
+passthrough = [
+    "JEMALLOC_SYS_WITH_LG_PAGE",
+]

Makefile

@@ -8,6 +8,7 @@ CARGO_BUILD_OPTS := --locked
 IMAGE_REGISTRY ?= docker.io
 IMAGE_NAMESPACE ?= greptime
 IMAGE_TAG ?= latest
+DEV_BUILDER_IMAGE_TAG ?= 2024-12-25-9d0fa5d5-20250124085746
 BUILDX_MULTI_PLATFORM_BUILD ?= false
 BUILDX_BUILDER_NAME ?= gtbuilder
 BASE_IMAGE ?= ubuntu
@@ -77,7 +78,7 @@ 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}:latest \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} \
 	make build \
 	CARGO_EXTENSION="${CARGO_EXTENSION}" \
 	CARGO_PROFILE=${CARGO_PROFILE} \
@@ -91,7 +92,7 @@ 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:latest \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:${DEV_BUILDER_IMAGE_TAG} \
 	make build \
 	CARGO_EXTENSION="ndk --platform 23 -t aarch64-linux-android" \
 	CARGO_PROFILE=release \
@@ -105,8 +106,8 @@ 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:latest \
-	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip /greptimedb/target/aarch64-linux-android/release/greptime'
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:${DEV_BUILDER_IMAGE_TAG} \
+	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip --strip-debug /greptimedb/target/aarch64-linux-android/release/greptime'
 
 .PHONY: clean
 clean: ## Clean the project.
@@ -145,7 +146,7 @@ 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-${BASE_IMAGE}:${IMAGE_TAG} ${BUILDX_MULTI_PLATFORM_BUILD_OPTS} .
+	-t ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} ${BUILDX_MULTI_PLATFORM_BUILD_OPTS} .
 
 .PHONY: multi-platform-buildx
 multi-platform-buildx: ## Create buildx multi-platform builder.
@@ -164,15 +165,14 @@ nextest: ## Install nextest tools.
 sqlness-test: ## Run sqlness test.
 	cargo sqlness ${SQLNESS_OPTS}
 
-# Run fuzz test ${FUZZ_TARGET}.
 RUNS ?= 1
 FUZZ_TARGET ?= fuzz_alter_table
 .PHONY: fuzz
-fuzz:
+fuzz: ## Run fuzz test ${FUZZ_TARGET}.
 	cargo fuzz run ${FUZZ_TARGET} --fuzz-dir tests-fuzz -D -s none -- -runs=${RUNS}
 
 .PHONY: fuzz-ls
-fuzz-ls:
+fuzz-ls: ## List all fuzz targets.
 	cargo fuzz list --fuzz-dir tests-fuzz
 
 .PHONY: check
@@ -190,6 +190,7 @@ 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.
@@ -203,7 +204,7 @@ 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}:latest \
+	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:${DEV_BUILDER_IMAGE_TAG} \
 	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
 
 .PHONY: start-cluster
@@ -219,7 +220,7 @@ config-docs: ## Generate configuration documentation from toml files.
 	docker run --rm \
     -v ${PWD}:/greptimedb \
     -w /greptimedb/config \
-    toml2docs/toml2docs:v0.1.1 \
+    toml2docs/toml2docs:v0.1.3 \
     -p '##' \
     -t ./config-docs-template.md \
     -o ./config.md

README.md

@@ -6,14 +6,14 @@
   </picture>
 </p>
 
-<h2 align="center">Unified Time Series Database for Metrics, Logs, and Events</h2>
+<h2 align="center">Unified & Cost-Effective Time Series Database for Metrics, Logs, and Events</h2>
 
 <div align="center">
 <h3 align="center">
   <a href="https://greptime.com/product/cloud">GreptimeCloud</a> |
   <a href="https://docs.greptime.com/">User Guide</a> |
   <a href="https://greptimedb.rs/">API Docs</a> |
-  <a href="https://github.com/GreptimeTeam/greptimedb/issues/3412">Roadmap 2024</a>
+  <a href="https://github.com/GreptimeTeam/greptimedb/issues/5446">Roadmap 2025</a>
 </h4>
 
 <a href="https://github.com/GreptimeTeam/greptimedb/releases/latest">
@@ -48,37 +48,51 @@
 </a>
 </div>
 
+- [Introduction](#introduction)
+- [**Features: Why GreptimeDB**](#why-greptimedb)
+- [Architecture](https://docs.greptime.com/contributor-guide/overview/#architecture)
+- [Try it for free](#try-greptimedb)
+- [Getting Started](#getting-started)
+- [Project Status](#project-status)
+- [Join the community](#community)
+  - [Contributing](#contributing)
+- [Tools & Extensions](#tools--extensions)
+- [License](#license)
+- [Acknowledgement](#acknowledgement)
+
 ## 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 unified & cost-effective time-series database for **Metrics**, **Logs**, and **Events** (also **Traces** in plan). You can gain real-time insights from Edge to Cloud at Any Scale.
 
 ## 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:
+Our core developers have been building time-series data platforms for years. Based on our best practices, GreptimeDB was born to give you:
 
-* **Unified all kinds of time series**
+* **Unified Processing of Metrics, Logs, and Events**
 
-  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.
+  GreptimeDB unifies time series data processing by treating all data - whether metrics, logs, or events - as timestamped events with context. Users can analyze this data using either [SQL](https://docs.greptime.com/user-guide/query-data/sql) or [PromQL](https://docs.greptime.com/user-guide/query-data/promql) and leverage stream processing ([Flow](https://docs.greptime.com/user-guide/flow-computation/overview)) to enable continuous aggregation. [Read more](https://docs.greptime.com/user-guide/concepts/data-model).
 
-* **Cloud-Edge collaboration**
+* **Cloud-native Distributed Database**
 
-  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.
-
-* **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.
+  Built for [Kubernetes](https://docs.greptime.com/user-guide/deployments/deploy-on-kubernetes/greptimedb-operator-management). GreptimeDB achieves seamless scalability with its [cloud-native architecture](https://docs.greptime.com/user-guide/concepts/architecture) of separated compute and storage, built on object storage (AWS S3, Azure Blob Storage, etc.) while enabling cross-cloud deployment through a unified data access layer.
 
 * **Performance and Cost-effective**
 
-  Flexible indexing capabilities and distributed, parallel-processing query engine, tackling high cardinality issues down. Optimized columnar layout for handling time-series data; compacted, compressed, and stored on various storage backends, particularly cloud object storage with 50x cost efficiency.
+  Written in pure Rust for superior performance and reliability. GreptimeDB features a distributed query engine with intelligent indexing to handle high cardinality data efficiently. Its optimized columnar storage achieves 50x cost efficiency on cloud object storage through advanced compression. [Benchmark reports](https://www.greptime.com/blogs/2024-09-09-report-summary).
 
-* **Compatible with InfluxDB, Prometheus and more protocols**
+* **Cloud-Edge Collaboration**
 
-  Widely adopted database protocols and APIs, including MySQL, PostgreSQL, and Prometheus Remote Storage, etc. [Read more](https://docs.greptime.com/user-guide/clients/overview).
+  GreptimeDB seamlessly operates across cloud and edge (ARM/Android/Linux), providing consistent APIs and control plane for unified data management and efficient synchronization. [Learn how to run on Android](https://docs.greptime.com/user-guide/deployments/run-on-android/).
+
+* **Multi-protocol Ingestion, SQL & PromQL Ready**
+
+  Widely adopted database protocols and APIs, including MySQL, PostgreSQL, InfluxDB, OpenTelemetry, Loki and Prometheus, etc.  Effortless Adoption & Seamless Migration. [Supported Protocols Overview](https://docs.greptime.com/user-guide/protocols/overview).
+
+For more detailed info please read  [Why GreptimeDB](https://docs.greptime.com/user-guide/concepts/why-greptimedb).
 
 ## Try GreptimeDB
 
-### 1. [GreptimePlay](https://greptime.com/playground)
+### 1. [Live Demo](https://greptime.com/playground)
 
 Try out the features of GreptimeDB right from your browser.
 
@@ -97,9 +111,18 @@ docker pull greptime/greptimedb
 Start a GreptimeDB container with:
 
 ```shell
-docker run --rm --name greptime --net=host greptime/greptimedb standalone start
+docker run -p 127.0.0.1:4000-4003:4000-4003 \
+  -v "$(pwd)/greptimedb:/tmp/greptimedb" \
+  --name greptime --rm \
+  greptime/greptimedb:latest standalone start \
+  --http-addr 0.0.0.0:4000 \
+  --rpc-bind-addr 0.0.0.0:4001 \
+  --mysql-addr 0.0.0.0:4002 \
+  --postgres-addr 0.0.0.0:4003
 ```
 
+Access the dashboard via `http://localhost:4000/dashboard`.
+
 Read more about [Installation](https://docs.greptime.com/getting-started/installation/overview) on docs.
 
 ## Getting Started
@@ -115,7 +138,8 @@ Check the prerequisite:
 
 * [Rust toolchain](https://www.rust-lang.org/tools/install) (nightly)
 * [Protobuf compiler](https://grpc.io/docs/protoc-installation/) (>= 3.15)
-* Python toolchain (optional): Required only if built with PyO3 backend. More detail for compiling with PyO3 can be found in its [documentation](https://pyo3.rs/v0.18.1/building_and_distribution#configuring-the-python-version).
+* C/C++ building essentials, including `gcc`/`g++`/`autoconf` and glibc library (eg. `libc6-dev` on Ubuntu and `glibc-devel` on Fedora)
+* Python toolchain (optional): Required only if using some test scripts.
 
 Build GreptimeDB binary:
 
@@ -129,7 +153,11 @@ Run a standalone server:
 cargo run -- standalone start
 ```
 
-## Extension
+## Tools & Extensions
+
+### Kubernetes
+
+- [GreptimeDB Operator](https://github.com/GrepTimeTeam/greptimedb-operator)
 
 ### Dashboard
 
@@ -146,14 +174,19 @@ cargo run -- standalone start
 
 ### Grafana Dashboard
 
-Our official Grafana dashboard is available at [grafana](grafana/README.md) directory.
+Our official Grafana dashboard for monitoring GreptimeDB is available at [grafana](grafana/README.md) directory.
 
 ## Project Status
 
-The current version has not yet reached the standards for General Availability. 
-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)
+GreptimeDB is currently in Beta. We are targeting GA (General Availability) with v1.0 release by Early 2025.
 
-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.
+While in Beta, GreptimeDB is already:
+
+* Being used in production by early adopters
+* Actively maintained with regular releases, [about version number](https://docs.greptime.com/nightly/reference/about-greptimedb-version)
+* Suitable for testing and evaluation
+
+For production use, we recommend using the latest stable release.
 
 ## Community
 
@@ -172,6 +205,13 @@ In addition, you may:
 - Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
 - Follow us on [Twitter](https://twitter.com/greptime)
 
+## Commercial Support
+
+If you are running GreptimeDB OSS in your organization, we offer additional
+enterprise add-ons, installation services, training, and consulting. [Contact
+us](https://greptime.com/contactus) and we will reach out to you with more
+detail of our commercial license.
+
 ## License
 
 GreptimeDB uses the [Apache License 2.0](https://apache.org/licenses/LICENSE-2.0.txt) to strike a balance between
@@ -189,4 +229,3 @@ Special thanks to all the contributors who have propelled GreptimeDB forward. Fo
 - 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.
 - GreptimeDB's meta service is based on [etcd](https://etcd.io/).
-- GreptimeDB uses [RustPython](https://github.com/RustPython/RustPython) for experimental embedded python scripting.

config/config.md

@@ -13,8 +13,12 @@
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
-| `default_timezone` | String | `None` | The default timezone of the server. |
+| `default_timezone` | String | Unset | The default timezone of the server. |
+| `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
+| `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
+| `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
+| `max_in_flight_write_bytes` | String | Unset | The maximum in-flight write bytes. |
 | `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. |
@@ -22,81 +26,104 @@
 | `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. |
+| `http.enable_cors` | Bool | `true` | HTTP CORS support, it's turned on by default<br/>This allows browser to access http APIs without CORS restrictions |
+| `http.cors_allowed_origins` | Array | Unset | Customize allowed origins for HTTP CORS. |
 | `grpc` | -- | -- | The gRPC server options. |
-| `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
+| `grpc.bind_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 | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
+| `grpc.tls.cert_path` | String | Unset | Certificate file path. |
+| `grpc.tls.key_path` | String | Unset | Private key file path. |
 | `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
 | `mysql` | -- | -- | MySQL server options. |
 | `mysql.enable` | Bool | `true` | Whether to enable. |
 | `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
 | `mysql.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `mysql.keep_alive` | String | `0s` | Server-side keep-alive time.<br/>Set to 0 (default) to disable. |
 | `mysql.tls` | -- | -- | -- |
 | `mysql.tls.mode` | String | `disable` | TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html<br/>- `disable` (default value)<br/>- `prefer`<br/>- `require`<br/>- `verify-ca`<br/>- `verify-full` |
-| `mysql.tls.cert_path` | String | `None` | Certificate file path. |
-| `mysql.tls.key_path` | String | `None` | Private key file path. |
+| `mysql.tls.cert_path` | String | Unset | Certificate file path. |
+| `mysql.tls.key_path` | String | Unset | Private key file path. |
 | `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `postgres` | -- | -- | PostgresSQL server options. |
 | `postgres.enable` | Bool | `true` | Whether to enable |
 | `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
 | `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `postgres.keep_alive` | String | `0s` | Server-side keep-alive time.<br/>Set to 0 (default) to disable. |
 | `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql.tls` section. |
 | `postgres.tls.mode` | String | `disable` | TLS mode. |
-| `postgres.tls.cert_path` | String | `None` | Certificate file path. |
-| `postgres.tls.key_path` | String | `None` | Private key file path. |
+| `postgres.tls.cert_path` | String | Unset | Certificate file path. |
+| `postgres.tls.key_path` | String | Unset | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
 | `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
 | `influxdb` | -- | -- | InfluxDB protocol options. |
 | `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
+| `jaeger` | -- | -- | Jaeger protocol options. |
+| `jaeger.enable` | Bool | `true` | Whether to enable Jaeger protocol in HTTP API. |
 | `prom_store` | -- | -- | Prometheus remote storage options |
 | `prom_store.enable` | Bool | `true` | Whether to enable Prometheus remote write and read in HTTP API. |
 | `prom_store.with_metric_engine` | Bool | `true` | Whether to store the data from Prometheus remote write in metric engine. |
 | `wal` | -- | -- | The WAL options. |
 | `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
-| `wal.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.dir` | String | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `1GB` | The threshold of the WAL size to trigger a purge.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `1m` | The interval to trigger a purge.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.recovery_parallelism` | Integer | `2` | Parallelism during WAL recovery. |
 | `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.auto_create_topics` | Bool | `true` | Automatically create topics for WAL.<br/>Set to `true` to automatically create topics for WAL.<br/>Otherwise, use topics named `topic_name_prefix_[0..num_topics)` |
+| `wal.num_topics` | Integer | `64` | Number of topics.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.selector_type` | String | `round_robin` | Topic selector type.<br/>Available selector types:<br/>- `round_robin` (default)<br/>**It's only used when the provider is `kafka`**. |
+| `wal.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.<br/>i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.replication_factor` | Integer | `1` | Expected number of replicas of each partition.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.create_topic_timeout` | String | `30s` | Above which a topic creation operation will be cancelled.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.max_batch_bytes` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_base` | Integer | `2` | The exponential backoff rate, i.e. next backoff = base * current backoff.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_deadline` | String | `5mins` | The deadline of retries.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.overwrite_entry_start_id` | Bool | `false` | Ignore missing entries during read WAL.<br/>**It's only used when the provider is `kafka`**.<br/><br/>This option ensures that when Kafka messages are deleted, the system<br/>can still successfully replay memtable data without throwing an<br/>out-of-range error.<br/>However, enabling this option might lead to unexpected data loss,<br/>as the system will skip over missing entries instead of treating<br/>them as critical errors. |
 | `metadata_store` | -- | -- | Metadata storage options. |
-| `metadata_store.file_size` | String | `256MB` | Kv file size in bytes. |
-| `metadata_store.purge_threshold` | String | `4GB` | Kv purge threshold. |
+| `metadata_store.file_size` | String | `64MB` | The size of the metadata store log file. |
+| `metadata_store.purge_threshold` | String | `256MB` | The threshold of the metadata store size to trigger a purge. |
+| `metadata_store.purge_interval` | String | `1m` | The interval of the metadata store to trigger a purge. |
 | `procedure` | -- | -- | Procedure storage options. |
 | `procedure.max_retry_times` | Integer | `3` | Procedure max retry time. |
 | `procedure.retry_delay` | String | `500ms` | Initial retry delay of procedures, increases exponentially |
+| `flow` | -- | -- | flow engine options. |
+| `flow.num_workers` | Integer | `0` | The number of flow worker in flownode.<br/>Not setting(or set to 0) this value will use the number of CPU cores divided by 2. |
 | `storage` | -- | -- | The data storage options. |
 | `storage.data_home` | String | `/tmp/greptimedb/` | The working home directory. |
 | `storage.type` | String | `File` | The storage type used to store the data.<br/>- `File`: the data is stored in the local file system.<br/>- `S3`: the data is stored in the S3 object storage.<br/>- `Gcs`: the data is stored in the Google Cloud Storage.<br/>- `Azblob`: the data is stored in the Azure Blob Storage.<br/>- `Oss`: the data is stored in the Aliyun OSS. |
-| `storage.cache_path` | String | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
-| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
-| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
-| `storage.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
-| `storage.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
-| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.endpoint` | String | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.region` | String | `None` | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.cache_path` | String | Unset | Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.<br/>A local file directory, defaults to `{data_home}`. An empty string means disabling. |
+| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger. |
+| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.root` | String | Unset | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
+| `storage.access_key_id` | String | Unset | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
+| `storage.secret_access_key` | String | Unset | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
+| `storage.access_key_secret` | String | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | Unset | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.endpoint` | String | Unset | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.region` | String | Unset | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.http_client` | -- | -- | The http client options to the storage.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.http_client.pool_max_idle_per_host` | Integer | `1024` | The maximum idle connection per host allowed in the pool. |
+| `storage.http_client.connect_timeout` | String | `30s` | The timeout for only the connect phase of a http client. |
+| `storage.http_client.timeout` | String | `30s` | The total request timeout, applied from when the request starts connecting until the response body has finished.<br/>Also considered a total deadline. |
+| `storage.http_client.pool_idle_timeout` | String | `90s` | The timeout for idle sockets being kept-alive. |
 | `[[region_engine]]` | -- | -- | The region engine options. You can configure multiple region engines. |
 | `region_engine.mito` | -- | -- | The Mito engine options. |
 | `region_engine.mito.num_workers` | Integer | `8` | Number of region workers. |
@@ -104,61 +131,79 @@
 | `region_engine.mito.worker_request_batch_size` | Integer | `64` | Max batch size for a worker to handle requests. |
 | `region_engine.mito.manifest_checkpoint_distance` | Integer | `10` | Number of meta action updated to trigger a new checkpoint for the manifest. |
 | `region_engine.mito.compress_manifest` | Bool | `false` | Whether to compress manifest and checkpoint file by gzip (default false). |
-| `region_engine.mito.max_background_jobs` | Integer | `4` | Max number of running background jobs |
+| `region_engine.mito.max_background_flushes` | Integer | Auto | Max number of running background flush jobs (default: 1/2 of cpu cores). |
+| `region_engine.mito.max_background_compactions` | Integer | Auto | Max number of running background compaction jobs (default: 1/4 of cpu cores). |
+| `region_engine.mito.max_background_purges` | Integer | Auto | Max number of running background purge jobs (default: number of cpu cores). |
 | `region_engine.mito.auto_flush_interval` | String | `1h` | Interval to auto flush a region if it has not flushed yet. |
-| `region_engine.mito.global_write_buffer_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
-| `region_engine.mito.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
-| `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
-| `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.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 | `1h` | TTL for write cache. |
+| `region_engine.mito.global_write_buffer_size` | String | Auto | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
+| `region_engine.mito.global_write_buffer_reject_size` | String | Auto | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`. |
+| `region_engine.mito.sst_meta_cache_size` | String | Auto | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
+| `region_engine.mito.vector_cache_size` | String | Auto | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.page_cache_size` | String | Auto | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/8 of OS memory. |
+| `region_engine.mito.selector_result_cache_size` | String | Auto | Cache size for time series selector (e.g. `last_value()`). Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.enable_write_cache` | Bool | `false` | Whether to enable the write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance. |
+| `region_engine.mito.write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}`. |
+| `region_engine.mito.write_cache_size` | String | `5GiB` | Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger. |
+| `region_engine.mito.write_cache_ttl` | String | Unset | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
-| `region_engine.mito.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.index.staging_ttl` | String | `7d` | The TTL of the staging directory.<br/>Defaults to 7 days.<br/>Setting it to "0s" to disable TTL. |
+| `region_engine.mito.index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
+| `region_engine.mito.index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
+| `region_engine.mito.index.content_cache_page_size` | String | `64KiB` | Page size for inverted index content cache. |
 | `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
 | `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.mem_threshold_on_create` | String | `auto` | Memory threshold for performing an external sort during index creation.<br/>- `auto`: automatically determine the threshold based on the system memory size (default)<br/>- `unlimited`: no memory limit<br/>- `[size]` e.g. `64MB`: fixed memory threshold |
 | `region_engine.mito.inverted_index.intermediate_path` | String | `""` | Deprecated, use `region_engine.mito.index.aux_path` instead. |
-| `region_engine.mito.inverted_index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
-| `region_engine.mito.inverted_index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
 | `region_engine.mito.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.bloom_filter_index` | -- | -- | The options for bloom filter in Mito engine. |
+| `region_engine.mito.bloom_filter_index.create_on_flush` | String | `auto` | Whether to create the bloom filter on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.create_on_compaction` | String | `auto` | Whether to create the bloom filter on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.apply_on_query` | String | `auto` | Whether to apply the bloom filter on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.mem_threshold_on_create` | String | `auto` | Memory threshold for bloom filter 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. |
+| `region_engine.metric` | -- | -- | Metric engine options. |
+| `region_engine.metric.experimental_sparse_primary_key_encoding` | Bool | `false` | Whether to enable the experimental sparse primary key encoding. |
 | `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.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 | `None` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
 | `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
+| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
-| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommended to collect metrics generated by itself<br/>You must create the database before enabling it. |
+| `export_metrics.self_import.db` | String | Unset | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
 
 
 ## Distributed Mode
@@ -167,7 +212,8 @@
 
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
-| `default_timezone` | String | `None` | The default timezone of the server. |
+| `default_timezone` | String | Unset | The default timezone of the server. |
+| `max_in_flight_write_bytes` | String | Unset | The maximum in-flight write bytes. |
 | `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. |
@@ -178,37 +224,43 @@
 | `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. |
+| `http.enable_cors` | Bool | `true` | HTTP CORS support, it's turned on by default<br/>This allows browser to access http APIs without CORS restrictions |
+| `http.cors_allowed_origins` | Array | Unset | Customize allowed origins for HTTP CORS. |
 | `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.bind_addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
+| `grpc.server_addr` | String | `127.0.0.1:4001` | The address advertised to the metasrv, and used for connections from outside the host.<br/>If left empty or unset, the server will automatically use the IP address of the first network interface<br/>on the host, with the same port number as the one specified in `grpc.bind_addr`. |
 | `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 | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
+| `grpc.tls.cert_path` | String | Unset | Certificate file path. |
+| `grpc.tls.key_path` | String | Unset | Private key file path. |
 | `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
 | `mysql` | -- | -- | MySQL server options. |
 | `mysql.enable` | Bool | `true` | Whether to enable. |
 | `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
 | `mysql.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `mysql.keep_alive` | String | `0s` | Server-side keep-alive time.<br/>Set to 0 (default) to disable. |
 | `mysql.tls` | -- | -- | -- |
 | `mysql.tls.mode` | String | `disable` | TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html<br/>- `disable` (default value)<br/>- `prefer`<br/>- `require`<br/>- `verify-ca`<br/>- `verify-full` |
-| `mysql.tls.cert_path` | String | `None` | Certificate file path. |
-| `mysql.tls.key_path` | String | `None` | Private key file path. |
+| `mysql.tls.cert_path` | String | Unset | Certificate file path. |
+| `mysql.tls.key_path` | String | Unset | Private key file path. |
 | `mysql.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `postgres` | -- | -- | PostgresSQL server options. |
 | `postgres.enable` | Bool | `true` | Whether to enable |
 | `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
 | `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
+| `postgres.keep_alive` | String | `0s` | Server-side keep-alive time.<br/>Set to 0 (default) to disable. |
 | `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql.tls` section. |
 | `postgres.tls.mode` | String | `disable` | TLS mode. |
-| `postgres.tls.cert_path` | String | `None` | Certificate file path. |
-| `postgres.tls.key_path` | String | `None` | Private key file path. |
+| `postgres.tls.cert_path` | String | Unset | Certificate file path. |
+| `postgres.tls.key_path` | String | Unset | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
 | `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
 | `influxdb` | -- | -- | InfluxDB protocol options. |
 | `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
+| `jaeger` | -- | -- | Jaeger protocol options. |
+| `jaeger.enable` | Bool | `true` | Whether to enable Jaeger protocol in HTTP API. |
 | `prom_store` | -- | -- | Prometheus remote storage options |
 | `prom_store.enable` | Bool | `true` | Whether to enable Prometheus remote write and read in HTTP API. |
 | `prom_store.with_metric_engine` | Bool | `true` | Whether to store the data from Prometheus remote write in metric engine. |
@@ -227,23 +279,29 @@
 | `datanode.client.connect_timeout` | String | `10s` | -- |
 | `datanode.client.tcp_nodelay` | Bool | `true` | -- |
 | `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.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 | `None` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
 | `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
+| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
-| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself<br/>You must create the database before enabling it. |
+| `export_metrics.self_import.db` | String | Unset | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
 
 
 ### Metasrv
@@ -252,13 +310,17 @@
 | --- | -----| ------- | ----------- |
 | `data_home` | String | `/tmp/metasrv/` | The working home directory. |
 | `bind_addr` | String | `127.0.0.1:3002` | The bind address of metasrv. |
-| `server_addr` | String | `127.0.0.1:3002` | The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost. |
-| `store_addr` | String | `127.0.0.1:2379` | Etcd server address. |
-| `selector` | String | `lease_based` | Datanode selector type.<br/>- `lease_based` (default value).<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
-| `use_memory_store` | Bool | `false` | Store data in memory. |
-| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. |
+| `server_addr` | String | `127.0.0.1:3002` | The communication server address for the frontend and datanode to connect to metasrv.<br/>If left empty or unset, the server will automatically use the IP address of the first network interface<br/>on the host, with the same port number as the one specified in `bind_addr`. |
+| `store_addrs` | Array | -- | Store server address default to etcd store.<br/>For postgres store, the format is:<br/>"password=password dbname=postgres user=postgres host=localhost port=5432"<br/>For etcd store, the format is:<br/>"127.0.0.1:2379" |
 | `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
+| `backend` | String | `etcd_store` | The datastore for meta server.<br/>Available values:<br/>- `etcd_store` (default value)<br/>- `memory_store`<br/>- `postgres_store` |
+| `meta_table_name` | String | `greptime_metakv` | Table name in RDS to store metadata. Effect when using a RDS kvbackend.<br/>**Only used when backend is `postgres_store`.** |
+| `meta_election_lock_id` | Integer | `1` | Advisory lock id in PostgreSQL for election. Effect when using PostgreSQL as kvbackend<br/>Only used when backend is `postgres_store`. |
+| `selector` | String | `round_robin` | Datanode selector type.<br/>- `round_robin` (default value)<br/>- `lease_based`<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
+| `use_memory_store` | Bool | `false` | Store data in memory. |
 | `enable_region_failover` | Bool | `false` | Whether to enable region failover.<br/>This feature is only available on GreptimeDB running on cluster mode and<br/>- Using Remote WAL<br/>- Using shared storage (e.g., s3). |
+| `node_max_idle_time` | String | `24hours` | Max allowed idle time before removing node info from metasrv memory. |
+| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. Enabled by default. |
 | `runtime` | -- | -- | The runtime options. |
 | `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
 | `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
@@ -279,9 +341,10 @@
 | `wal` | -- | -- | -- |
 | `wal.provider` | String | `raft_engine` | -- |
 | `wal.broker_endpoints` | Array | -- | The broker endpoints of the Kafka cluster. |
-| `wal.num_topics` | Integer | `64` | Number of topics to be created upon start. |
+| `wal.auto_create_topics` | Bool | `true` | Automatically create topics for WAL.<br/>Set to `true` to automatically create topics for WAL.<br/>Otherwise, use topics named `topic_name_prefix_[0..num_topics)` |
+| `wal.num_topics` | Integer | `64` | Number of topics. |
 | `wal.selector_type` | String | `round_robin` | Topic selector type.<br/>Available selector types:<br/>- `round_robin` (default) |
-| `wal.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`. |
+| `wal.topic_name_prefix` | String | `greptimedb_wal_topic` | A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.<br/>Only accepts strings that match the following regular expression pattern:<br/>[a-zA-Z_:-][a-zA-Z0-9_:\-\.@#]*<br/>i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1. |
 | `wal.replication_factor` | Integer | `1` | Expected number of replicas of each partition. |
 | `wal.create_topic_timeout` | String | `30s` | Above which a topic creation operation will be cancelled. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff for kafka clients. |
@@ -289,23 +352,29 @@
 | `wal.backoff_base` | Integer | `2` | Exponential backoff rate, i.e. next backoff = base * current backoff. |
 | `wal.backoff_deadline` | String | `5mins` | Stop reconnecting if the total wait time reaches the deadline. If this config is missing, the reconnecting won't terminate. |
 | `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.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 | `None` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
 | `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
+| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
-| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself<br/>You must create the database before enabling it. |
+| `export_metrics.self_import.db` | String | Unset | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
 
 
 ### Datanode
@@ -313,26 +382,26 @@
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
-| `node_id` | Integer | `None` | The datanode identifier and should be unique in the cluster. |
+| `node_id` | Integer | Unset | The datanode identifier and should be unique in the cluster. |
 | `require_lease_before_startup` | Bool | `false` | Start services after regions have obtained leases.<br/>It will block the datanode start if it can't receive leases in the heartbeat from metasrv. |
 | `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
 | `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
-| `rpc_addr` | String | `None` | Deprecated, use `grpc.addr` instead. |
-| `rpc_hostname` | String | `None` | Deprecated, use `grpc.hostname` instead. |
-| `rpc_runtime_size` | Integer | `None` | Deprecated, use `grpc.runtime_size` instead. |
-| `rpc_max_recv_message_size` | String | `None` | Deprecated, use `grpc.rpc_max_recv_message_size` instead. |
-| `rpc_max_send_message_size` | String | `None` | Deprecated, use `grpc.rpc_max_send_message_size` instead. |
+| `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
+| `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.bind_addr` | String | `127.0.0.1:3001` | The address to bind the gRPC server. |
+| `grpc.server_addr` | String | `127.0.0.1:3001` | The address advertised to the metasrv, and used for connections from outside the host.<br/>If left empty or unset, the server will automatically use the IP address of the first network interface<br/>on the host, with the same port number as the one specified in `grpc.bind_addr`. |
 | `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 | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
+| `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. |
@@ -352,15 +421,16 @@
 | `meta_client.metadata_cache_tti` | String | `5m` | -- |
 | `wal` | -- | -- | The WAL options. |
 | `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
-| `wal.dir` | String | `None` | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.dir` | String | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `1GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `1m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.recovery_parallelism` | Integer | `2` | Parallelism during WAL recovery. |
 | `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.max_batch_bytes` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
@@ -368,24 +438,33 @@
 | `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 | `None` | Cache configuration for object storage such as 'S3' etc.<br/>The local file cache directory. |
-| `storage.cache_capacity` | String | `None` | The local file cache capacity in bytes. |
-| `storage.bucket` | String | `None` | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
-| `storage.root` | String | `None` | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
-| `storage.access_key_id` | String | `None` | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
-| `storage.secret_access_key` | String | `None` | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
-| `storage.access_key_secret` | String | `None` | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
-| `storage.account_name` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.account_key` | String | `None` | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.scope` | String | `None` | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.credential_path` | String | `None` | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
-| `storage.container` | String | `None` | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.sas_token` | String | `None` | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
-| `storage.endpoint` | String | `None` | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
-| `storage.region` | String | `None` | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.cache_path` | String | Unset | Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.<br/>A local file directory, defaults to `{data_home}`. An empty string means disabling. |
+| `storage.cache_capacity` | String | Unset | The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger. |
+| `storage.bucket` | String | Unset | The S3 bucket name.<br/>**It's only used when the storage type is `S3`, `Oss` and `Gcs`**. |
+| `storage.root` | String | Unset | The S3 data will be stored in the specified prefix, for example, `s3://${bucket}/${root}`.<br/>**It's only used when the storage type is `S3`, `Oss` and `Azblob`**. |
+| `storage.access_key_id` | String | Unset | The access key id of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3` and `Oss`**. |
+| `storage.secret_access_key` | String | Unset | The secret access key of the aws account.<br/>It's **highly recommended** to use AWS IAM roles instead of hardcoding the access key id and secret key.<br/>**It's only used when the storage type is `S3`**. |
+| `storage.access_key_secret` | String | Unset | The secret access key of the aliyun account.<br/>**It's only used when the storage type is `Oss`**. |
+| `storage.account_name` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.account_key` | String | Unset | The account key of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.scope` | String | Unset | The scope of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential_path` | String | Unset | The credential path of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.credential` | String | Unset | The credential of the google cloud storage.<br/>**It's only used when the storage type is `Gcs`**. |
+| `storage.container` | String | Unset | The container of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.sas_token` | String | Unset | The sas token of the azure account.<br/>**It's only used when the storage type is `Azblob`**. |
+| `storage.endpoint` | String | Unset | The endpoint of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.region` | String | Unset | The region of the S3 service.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.http_client` | -- | -- | The http client options to the storage.<br/>**It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**. |
+| `storage.http_client.pool_max_idle_per_host` | Integer | `1024` | The maximum idle connection per host allowed in the pool. |
+| `storage.http_client.connect_timeout` | String | `30s` | The timeout for only the connect phase of a http client. |
+| `storage.http_client.timeout` | String | `30s` | The total request timeout, applied from when the request starts connecting until the response body has finished.<br/>Also considered a total deadline. |
+| `storage.http_client.pool_idle_timeout` | String | `90s` | The timeout for idle sockets being kept-alive. |
 | `[[region_engine]]` | -- | -- | The region engine options. You can configure multiple region engines. |
 | `region_engine.mito` | -- | -- | The Mito engine options. |
 | `region_engine.mito.num_workers` | Integer | `8` | Number of region workers. |
@@ -393,24 +472,31 @@
 | `region_engine.mito.worker_request_batch_size` | Integer | `64` | Max batch size for a worker to handle requests. |
 | `region_engine.mito.manifest_checkpoint_distance` | Integer | `10` | Number of meta action updated to trigger a new checkpoint for the manifest. |
 | `region_engine.mito.compress_manifest` | Bool | `false` | Whether to compress manifest and checkpoint file by gzip (default false). |
-| `region_engine.mito.max_background_jobs` | Integer | `4` | Max number of running background jobs |
+| `region_engine.mito.max_background_flushes` | Integer | Auto | Max number of running background flush jobs (default: 1/2 of cpu cores). |
+| `region_engine.mito.max_background_compactions` | Integer | Auto | Max number of running background compaction jobs (default: 1/4 of cpu cores). |
+| `region_engine.mito.max_background_purges` | Integer | Auto | Max number of running background purge jobs (default: number of cpu cores). |
 | `region_engine.mito.auto_flush_interval` | String | `1h` | Interval to auto flush a region if it has not flushed yet. |
-| `region_engine.mito.global_write_buffer_size` | String | `1GB` | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
-| `region_engine.mito.global_write_buffer_reject_size` | String | `2GB` | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
-| `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
-| `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.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 | `1h` | TTL for write cache. |
+| `region_engine.mito.global_write_buffer_size` | String | Auto | Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB. |
+| `region_engine.mito.global_write_buffer_reject_size` | String | Auto | Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size` |
+| `region_engine.mito.sst_meta_cache_size` | String | Auto | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
+| `region_engine.mito.vector_cache_size` | String | Auto | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.page_cache_size` | String | Auto | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/8 of OS memory. |
+| `region_engine.mito.selector_result_cache_size` | String | Auto | Cache size for time series selector (e.g. `last_value()`). Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
+| `region_engine.mito.enable_write_cache` | Bool | `false` | Whether to enable the write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance. |
+| `region_engine.mito.write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}`. |
+| `region_engine.mito.write_cache_size` | String | `5GiB` | Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger. |
+| `region_engine.mito.write_cache_ttl` | String | Unset | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
-| `region_engine.mito.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.index.staging_ttl` | String | `7d` | The TTL of the staging directory.<br/>Defaults to 7 days.<br/>Setting it to "0s" to disable TTL. |
+| `region_engine.mito.index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
+| `region_engine.mito.index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
+| `region_engine.mito.index.content_cache_page_size` | String | `64KiB` | Page size for inverted index content cache. |
 | `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
 | `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
@@ -422,30 +508,43 @@
 | `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.bloom_filter_index` | -- | -- | The options for bloom filter index in Mito engine. |
+| `region_engine.mito.bloom_filter_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.apply_on_query` | String | `auto` | Whether to apply the index on query<br/>- `auto`: automatically (default)<br/>- `disable`: never |
+| `region_engine.mito.bloom_filter_index.mem_threshold_on_create` | String | `auto` | Memory threshold for the 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. |
+| `region_engine.metric` | -- | -- | Metric engine options. |
+| `region_engine.metric.experimental_sparse_primary_key_encoding` | Bool | `false` | Whether to enable the experimental sparse primary key encoding. |
 | `logging` | -- | -- | The logging options. |
-| `logging.dir` | String | `/tmp/greptimedb/logs` | The directory to store the log files. |
-| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `logging.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 | `None` | The OTLP tracing endpoint. |
+| `logging.otlp_endpoint` | String | `http://localhost:4317` | The OTLP tracing endpoint. |
 | `logging.append_stdout` | Bool | `true` | Whether to append logs to stdout. |
+| `logging.log_format` | String | `text` | The log format. Can be `text`/`json`. |
+| `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
-| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself |
-| `export_metrics.self_import.db` | String | `None` | -- |
+| `export_metrics.self_import` | -- | -- | For `standalone` mode, `self_import` is recommend to collect metrics generated by itself<br/>You must create the database before enabling it. |
+| `export_metrics.self_import.db` | String | Unset | -- |
 | `export_metrics.remote_write` | -- | -- | -- |
-| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
+| `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
+| `tracing.tokio_console_addr` | String | Unset | The tokio console address. |
 
 
 ### Flownode
@@ -453,13 +552,19 @@
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
 | `mode` | String | `distributed` | The running mode of the flownode. It can be `standalone` or `distributed`. |
-| `node_id` | Integer | `None` | The flownode identifier and should be unique in the cluster. |
+| `node_id` | Integer | Unset | The flownode identifier and should be unique in the cluster. |
+| `flow` | -- | -- | flow engine options. |
+| `flow.num_workers` | Integer | `0` | The number of flow worker in flownode.<br/>Not setting(or set to 0) this value will use the number of CPU cores divided by 2. |
 | `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.bind_addr` | String | `127.0.0.1:6800` | The address to bind the gRPC server. |
+| `grpc.server_addr` | String | `127.0.0.1:6800` | The address 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. |
+| `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. |
 | `meta_client` | -- | -- | The metasrv client options. |
 | `meta_client.metasrv_addrs` | Array | -- | The addresses of the metasrv. |
 | `meta_client.timeout` | String | `3s` | Operation timeout. |
@@ -474,12 +579,18 @@
 | `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. |
-| `logging.level` | String | `None` | The log level. Can be `info`/`debug`/`warn`/`error`. |
+| `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 | `None` | The OTLP tracing endpoint. |
+| `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 | `None` | The tokio console address. |
+| `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.
@@ -13,39 +13,34 @@ 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.
-enable_telemetry = true
-
 ## Parallelism of initializing regions.
 init_regions_parallelism = 16
 
-## Deprecated, use `grpc.addr` instead.
-## +toml2docs:none-default
-rpc_addr = "127.0.0.1:3001"
+## The maximum current queries allowed to be executed. Zero means unlimited.
+max_concurrent_queries = 0
 
-## Deprecated, use `grpc.hostname` instead.
-## +toml2docs:none-default
-rpc_hostname = "127.0.0.1"
+## Enable telemetry to collect anonymous usage data. Enabled by default.
+#+ enable_telemetry = true
 
-## Deprecated, use `grpc.runtime_size` instead.
-## +toml2docs:none-default
-rpc_runtime_size = 8
-
-## Deprecated, use `grpc.rpc_max_recv_message_size` instead.
-## +toml2docs:none-default
-rpc_max_recv_message_size = "512MB"
-
-## Deprecated, use `grpc.rpc_max_send_message_size` instead.
-## +toml2docs:none-default
-rpc_max_send_message_size = "512MB"
+## The HTTP server options.
+[http]
+## The address to bind the HTTP server.
+addr = "127.0.0.1:4000"
+## HTTP request timeout. Set to 0 to disable timeout.
+timeout = "30s"
+## HTTP request body limit.
+## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
+## Set to 0 to disable limit.
+body_limit = "64MB"
 
 ## The gRPC server options.
 [grpc]
 ## The address to bind the gRPC server.
-addr = "127.0.0.1:3001"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
+bind_addr = "127.0.0.1:3001"
+## The address advertised to the metasrv, and used for connections from outside the host.
+## If left empty or unset, the server will automatically use the IP address of the first network interface
+## on the host, with the same port number as the one specified in `grpc.bind_addr`.
+server_addr = "127.0.0.1:3001"
 ## The number of server worker threads.
 runtime_size = 8
 ## The maximum receive message size for gRPC server.
@@ -59,11 +54,11 @@ max_send_message_size = "512MB"
 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.
@@ -71,11 +66,11 @@ key_path = ""
 watch = false
 
 ## The runtime options.
-[runtime]
+#+ [runtime]
 ## The number of threads to execute the runtime for global read operations.
-global_rt_size = 8
+#+ global_rt_size = 8
 ## The number of threads to execute the runtime for global write operations.
-compact_rt_size = 4
+#+ compact_rt_size = 4
 
 ## The heartbeat options.
 [heartbeat]
@@ -123,20 +118,20 @@ 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.
 ## **It's only used when the provider is `raft_engine`**.
-file_size = "256MB"
+file_size = "128MB"
 
 ## The threshold of the WAL size to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "4GB"
+purge_threshold = "1GB"
 
 ## The interval to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_interval = "10m"
+purge_interval = "1m"
 
 ## The read batch size.
 ## **It's only used when the provider is `raft_engine`**.
@@ -158,6 +153,9 @@ 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"]
@@ -187,6 +185,43 @@ 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"
@@ -223,6 +258,7 @@ backoff_deadline = "5mins"
 # root = "data"
 # scope = "test"
 # credential_path = "123456"
+# credential = "base64-credential"
 # endpoint = "https://storage.googleapis.com"
 
 ## The data storage options.
@@ -238,87 +274,123 @@ data_home = "/tmp/greptimedb/"
 ## - `Oss`: the data is stored in the Aliyun OSS.
 type = "File"
 
-## Cache configuration for object storage such as 'S3' etc.
-## The local file cache directory.
-## +toml2docs:none-default
-cache_path = "/path/local_cache"
+## Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.
+## A local file directory, defaults to `{data_home}`. An empty string means disabling.
+## @toml2docs:none-default
+#+ cache_path = ""
 
-## The local file cache capacity in bytes.
-## +toml2docs:none-default
-cache_capacity = "256MB"
+## The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger.
+## @toml2docs:none-default
+cache_capacity = "5GiB"
 
 ## The S3 bucket name.
 ## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
-## +toml2docs:none-default
+## @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"
 
+## The http client options to the storage.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+[storage.http_client]
+
+## The maximum idle connection per host allowed in the pool.
+pool_max_idle_per_host = 1024
+
+## The timeout for only the connect phase of a http client.
+connect_timeout = "30s"
+
+## The total request timeout, applied from when the request starts connecting until the response body has finished.
+## Also considered a total deadline.
+timeout = "30s"
+
+## The timeout for idle sockets being kept-alive.
+pool_idle_timeout = "90s"
+
 # 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]]
@@ -327,7 +399,7 @@ 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
@@ -341,57 +413,75 @@ manifest_checkpoint_distance = 10
 ## Whether to compress manifest and checkpoint file by gzip (default false).
 compress_manifest = false
 
-## Max number of running background jobs
-max_background_jobs = 4
+## Max number of running background flush jobs (default: 1/2 of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_flushes = 4
+
+## Max number of running background compaction jobs (default: 1/4 of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_compactions = 2
+
+## Max number of running background purge jobs (default: number of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_purges = 8
 
 ## Interval to auto flush a region if it has not flushed yet.
 auto_flush_interval = "1h"
 
 ## Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
-global_write_buffer_size = "1GB"
+## @toml2docs:none-default="Auto"
+#+ global_write_buffer_size = "1GB"
 
 ## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
-global_write_buffer_reject_size = "2GB"
+## @toml2docs:none-default="Auto"
+#+ global_write_buffer_reject_size = "2GB"
 
 ## Cache size for SST metadata. Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
-sst_meta_cache_size = "128MB"
+## @toml2docs:none-default="Auto"
+#+ sst_meta_cache_size = "128MB"
 
 ## Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
-vector_cache_size = "512MB"
+## @toml2docs:none-default="Auto"
+#+ vector_cache_size = "512MB"
 
 ## Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/8 of OS memory.
+## @toml2docs:none-default="Auto"
+#+ page_cache_size = "512MB"
+
+## Cache size for time series selector (e.g. `last_value()`). Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
-page_cache_size = "512MB"
+## @toml2docs:none-default="Auto"
+#+ selector_result_cache_size = "512MB"
 
-## Whether to enable the experimental write cache.
-enable_experimental_write_cache = false
+## Whether to enable the write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance.
+enable_write_cache = false
 
-## File system path for write cache, defaults to `{data_home}/write_cache`.
-experimental_write_cache_path = ""
+## File system path for write cache, defaults to `{data_home}`.
+write_cache_path = ""
 
-## Capacity for write cache.
-experimental_write_cache_size = "512MB"
+## Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger.
+write_cache_size = "5GiB"
 
 ## TTL for write cache.
-experimental_write_cache_ttl = "1h"
+## @toml2docs:none-default
+write_cache_ttl = "8h"
 
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
 
-## Parallelism to scan a region (default: 1/4 of cpu cores).
-## - `0`: using the default value (1/4 of cpu cores).
-## - `1`: scan in current thread.
-## - `n`: scan in parallelism n.
-scan_parallelism = 0
-
 ## Capacity of the channel to send data from parallel scan tasks to the main task.
 parallel_scan_channel_size = 32
 
 ## Whether to allow stale WAL entries read during replay.
 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]
 
@@ -407,6 +497,20 @@ aux_path = ""
 ## The max capacity of the staging directory.
 staging_size = "2GB"
 
+## The TTL of the staging directory.
+## Defaults to 7 days.
+## Setting it to "0s" to disable TTL.
+staging_ttl = "7d"
+
+## Cache size for inverted index metadata.
+metadata_cache_size = "64MiB"
+
+## Cache size for inverted index content.
+content_cache_size = "128MiB"
+
+## Page size for inverted index content cache.
+content_cache_page_size = "64KiB"
+
 ## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
 
@@ -458,6 +562,30 @@ apply_on_query = "auto"
 ## - `[size]` e.g. `64MB`: fixed memory threshold
 mem_threshold_on_create = "auto"
 
+## The options for bloom filter index in Mito engine.
+[region_engine.mito.bloom_filter_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 the 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
@@ -480,31 +608,55 @@ fork_dictionary_bytes = "1GiB"
 ## Enable the file engine.
 [region_engine.file]
 
+[[region_engine]]
+## Metric engine options.
+[region_engine.metric]
+## Whether to enable the experimental sparse primary key encoding.
+experimental_sparse_primary_key_encoding = false
+
 ## The logging options.
 [logging]
-## The directory to store the log files.
+## 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
+## @toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-## +toml2docs:none-default
-otlp_endpoint = ""
+otlp_endpoint = "http://localhost:4317"
 
 ## Whether to append logs to stdout.
 append_stdout = true
 
+## The log format. Can be `text`/`json`.
+log_format = "text"
+
+## The maximum amount of log files.
+max_log_files = 720
+
 ## The percentage of tracing will be sampled and exported.
 ## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
 ## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]
@@ -516,19 +668,20 @@ 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
-db = "information_schema"
+## @toml2docs:none-default
+db = "greptime_metrics"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
+#+ [tracing]
 ## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"
+## @toml2docs:none-default
+#+ tokio_console_addr = "127.0.0.1"

config/flownode.example.toml

@@ -2,16 +2,22 @@
 mode = "distributed"
 
 ## The flownode identifier and should be unique in the cluster.
-## +toml2docs:none-default
+## @toml2docs:none-default
 node_id = 14
 
+## flow engine options.
+[flow]
+## The number of flow worker in flownode.
+## Not setting(or set to 0) this value will use the number of CPU cores divided by 2.
+#+num_workers=0
+
 ## The gRPC server options.
 [grpc]
 ## The address to bind the gRPC server.
-addr = "127.0.0.1:6800"
-## The hostname advertised to the metasrv,
+bind_addr = "127.0.0.1:6800"
+## The address advertised to the metasrv,
 ## and used for connections from outside the host
-hostname = "127.0.0.1"
+server_addr = "127.0.0.1:6800"
 ## The number of server worker threads.
 runtime_size = 2
 ## The maximum receive message size for gRPC server.
@@ -19,6 +25,16 @@ max_recv_message_size = "512MB"
 ## The maximum send message size for gRPC server.
 max_send_message_size = "512MB"
 
+## The HTTP server options.
+[http]
+## The address to bind the HTTP server.
+addr = "127.0.0.1:4000"
+## HTTP request timeout. Set to 0 to disable timeout.
+timeout = "30s"
+## HTTP request body limit.
+## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
+## Set to 0 to disable limit.
+body_limit = "64MB"
 
 ## The metasrv client options.
 [meta_client]
@@ -59,32 +75,50 @@ retry_interval = "3s"
 
 ## The logging options.
 [logging]
-## The directory to store the log files.
+## 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
+## @toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-## +toml2docs:none-default
-otlp_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 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"
+## 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 +1,17 @@
 ## The default timezone of the server.
-## +toml2docs:none-default
+## @toml2docs:none-default
 default_timezone = "UTC"
 
+## The maximum in-flight write bytes.
+## @toml2docs:none-default
+#+ max_in_flight_write_bytes = "500MB"
+
 ## The runtime options.
-[runtime]
+#+ [runtime]
 ## The number of threads to execute the runtime for global read operations.
-global_rt_size = 8
+#+ global_rt_size = 8
 ## The number of threads to execute the runtime for global write operations.
-compact_rt_size = 4
+#+ compact_rt_size = 4
 
 ## The heartbeat options.
 [heartbeat]
@@ -27,14 +31,21 @@ timeout = "30s"
 ## 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"
+## HTTP CORS support, it's turned on by default
+## This allows browser to access http APIs without CORS restrictions
+enable_cors = true
+## Customize allowed origins for HTTP CORS.
+## @toml2docs:none-default
+cors_allowed_origins = ["https://example.com"]
 
 ## 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"
+bind_addr = "127.0.0.1:4001"
+## The address advertised to the metasrv, and used for connections from outside the host.
+## If left empty or unset, the server will automatically use the IP address of the first network interface
+## on the host, with the same port number as the one specified in `grpc.bind_addr`.
+server_addr = "127.0.0.1:4001"
 ## The number of server worker threads.
 runtime_size = 8
 
@@ -44,11 +55,11 @@ 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.
@@ -63,6 +74,9 @@ enable = true
 addr = "127.0.0.1:4002"
 ## The number of server worker threads.
 runtime_size = 2
+## Server-side keep-alive time.
+## Set to 0 (default) to disable.
+keep_alive = "0s"
 
 # MySQL server TLS options.
 [mysql.tls]
@@ -76,11 +90,11 @@ 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
@@ -94,6 +108,9 @@ enable = true
 addr = "127.0.0.1:4003"
 ## The number of server worker threads.
 runtime_size = 2
+## Server-side keep-alive time.
+## Set to 0 (default) to disable.
+keep_alive = "0s"
 
 ## PostgresSQL server TLS options, see `mysql.tls` section.
 [postgres.tls]
@@ -101,11 +118,11 @@ 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
@@ -121,6 +138,11 @@ enable = true
 ## Whether to enable InfluxDB protocol in HTTP API.
 enable = true
 
+## Jaeger protocol options.
+[jaeger]
+## Whether to enable Jaeger protocol in HTTP API.
+enable = true
+
 ## Prometheus remote storage options
 [prom_store]
 ## Whether to enable Prometheus remote write and read in HTTP API.
@@ -166,29 +188,47 @@ tcp_nodelay = true
 
 ## The logging options.
 [logging]
-## The directory to store the log files.
+## 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
+## @toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-## +toml2docs:none-default
-otlp_endpoint = ""
+otlp_endpoint = "http://localhost:4317"
 
 ## Whether to append logs to stdout.
 append_stdout = true
 
+## The log format. Can be `text`/`json`.
+log_format = "text"
+
+## The maximum amount of log files.
+max_log_files = 720
+
 ## The percentage of tracing will be sampled and exported.
 ## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
 ## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]
@@ -200,19 +240,20 @@ 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
-db = "information_schema"
+## @toml2docs:none-default
+db = "greptime_metrics"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
+#+ [tracing]
 ## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"
+## @toml2docs:none-default
+#+ tokio_console_addr = "127.0.0.1"

config/metasrv.example.toml

@@ -4,39 +4,64 @@ data_home = "/tmp/metasrv/"
 ## The bind address of metasrv.
 bind_addr = "127.0.0.1:3002"
 
-## The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost.
+## The communication server address for the frontend and datanode to connect to metasrv.
+## If left empty or unset, the server will automatically use the IP address of the first network interface
+## on the host, with the same port number as the one specified in `bind_addr`.
 server_addr = "127.0.0.1:3002"
 
-## Etcd server address.
-store_addr = "127.0.0.1:2379"
-
-## Datanode selector type.
-## - `lease_based` (default value).
-## - `load_based`
-## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
-selector = "lease_based"
-
-## Store data in memory.
-use_memory_store = false
-
-## Whether to enable greptimedb telemetry.
-enable_telemetry = true
+## Store server address default to etcd store.
+## For postgres store, the format is:
+## "password=password dbname=postgres user=postgres host=localhost port=5432"
+## For etcd store, the format is:
+## "127.0.0.1:2379"
+store_addrs = ["127.0.0.1:2379"]
 
 ## If it's not empty, the metasrv will store all data with this key prefix.
 store_key_prefix = ""
 
+## The datastore for meta server.
+## Available values:
+## - `etcd_store` (default value)
+## - `memory_store`
+## - `postgres_store`
+backend = "etcd_store"
+
+## Table name in RDS to store metadata. Effect when using a RDS kvbackend.
+## **Only used when backend is `postgres_store`.**
+meta_table_name = "greptime_metakv"
+
+## Advisory lock id in PostgreSQL for election. Effect when using PostgreSQL as kvbackend
+## Only used when backend is `postgres_store`.
+meta_election_lock_id = 1
+
+## Datanode selector type.
+## - `round_robin` (default value)
+## - `lease_based`
+## - `load_based`
+## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
+selector = "round_robin"
+
+## Store data in memory.
+use_memory_store = false
+
 ## Whether to enable region failover.
 ## This feature is only available on GreptimeDB running on cluster mode and
 ## - Using Remote WAL
 ## - Using shared storage (e.g., s3).
 enable_region_failover = false
 
+## Max allowed idle time before removing node info from metasrv memory.
+node_max_idle_time = "24hours"
+
+## Whether to enable greptimedb telemetry. Enabled by default.
+#+ enable_telemetry = true
+
 ## The runtime options.
-[runtime]
+#+ [runtime]
 ## The number of threads to execute the runtime for global read operations.
-global_rt_size = 8
+#+ global_rt_size = 8
 ## The number of threads to execute the runtime for global write operations.
-compact_rt_size = 4
+#+ compact_rt_size = 4
 
 ## Procedure storage options.
 [procedure]
@@ -95,7 +120,12 @@ provider = "raft_engine"
 ## The broker endpoints of the Kafka cluster.
 broker_endpoints = ["127.0.0.1:9092"]
 
-## Number of topics to be created upon start.
+## Automatically create topics for WAL.
+## Set to `true` to automatically create topics for WAL.
+## Otherwise, use topics named `topic_name_prefix_[0..num_topics)`
+auto_create_topics = true
+
+## Number of topics.
 num_topics = 64
 
 ## Topic selector type.
@@ -104,6 +134,9 @@ num_topics = 64
 selector_type = "round_robin"
 
 ## A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.
+## Only accepts strings that match the following regular expression pattern:
+## [a-zA-Z_:-][a-zA-Z0-9_:\-\.@#]*
+## i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.
 topic_name_prefix = "greptimedb_wal_topic"
 
 ## Expected number of replicas of each partition.
@@ -123,31 +156,67 @@ 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.
+## 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
+## @toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-## +toml2docs:none-default
-otlp_endpoint = ""
+otlp_endpoint = "http://localhost:4317"
 
 ## Whether to append logs to stdout.
 append_stdout = true
 
+## The log format. Can be `text`/`json`.
+log_format = "text"
+
+## The maximum amount of log files.
+max_log_files = 720
+
 ## The percentage of tracing will be sampled and exported.
 ## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
 ## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]
@@ -159,19 +228,20 @@ 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
-db = "information_schema"
+## @toml2docs:none-default
+db = "greptime_metrics"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
+#+ [tracing]
 ## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"
+## @toml2docs:none-default
+#+ tokio_console_addr = "127.0.0.1"

config/standalone.example.toml

@@ -1,19 +1,33 @@
 ## The running mode of the datanode. It can be `standalone` or `distributed`.
 mode = "standalone"
 
-## Enable telemetry to collect anonymous usage data.
-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
+
+## Enable telemetry to collect anonymous usage data. Enabled by default.
+#+ enable_telemetry = true
+
+## The maximum in-flight write bytes.
+## @toml2docs:none-default
+#+ max_in_flight_write_bytes = "500MB"
+
 ## The runtime options.
-[runtime]
+#+ [runtime]
 ## The number of threads to execute the runtime for global read operations.
-global_rt_size = 8
+#+ global_rt_size = 8
 ## The number of threads to execute the runtime for global write operations.
-compact_rt_size = 4
+#+ compact_rt_size = 4
 
 ## The HTTP server options.
 [http]
@@ -25,11 +39,17 @@ timeout = "30s"
 ## 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"
+## HTTP CORS support, it's turned on by default
+## This allows browser to access http APIs without CORS restrictions
+enable_cors = true
+## Customize allowed origins for HTTP CORS.
+## @toml2docs:none-default
+cors_allowed_origins = ["https://example.com"]
 
 ## The gRPC server options.
 [grpc]
 ## The address to bind the gRPC server.
-addr = "127.0.0.1:4001"
+bind_addr = "127.0.0.1:4001"
 ## The number of server worker threads.
 runtime_size = 8
 
@@ -39,11 +59,11 @@ 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.
@@ -58,6 +78,9 @@ enable = true
 addr = "127.0.0.1:4002"
 ## The number of server worker threads.
 runtime_size = 2
+## Server-side keep-alive time.
+## Set to 0 (default) to disable.
+keep_alive = "0s"
 
 # MySQL server TLS options.
 [mysql.tls]
@@ -71,11 +94,11 @@ 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
@@ -89,6 +112,9 @@ enable = true
 addr = "127.0.0.1:4003"
 ## The number of server worker threads.
 runtime_size = 2
+## Server-side keep-alive time.
+## Set to 0 (default) to disable.
+keep_alive = "0s"
 
 ## PostgresSQL server TLS options, see `mysql.tls` section.
 [postgres.tls]
@@ -96,11 +122,11 @@ 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
@@ -116,6 +142,11 @@ enable = true
 ## Whether to enable InfluxDB protocol in HTTP API.
 enable = true
 
+## Jaeger protocol options.
+[jaeger]
+## Whether to enable Jaeger protocol in HTTP API.
+enable = true
+
 ## Prometheus remote storage options
 [prom_store]
 ## Whether to enable Prometheus remote write and read in HTTP API.
@@ -132,20 +163,20 @@ 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.
 ## **It's only used when the provider is `raft_engine`**.
-file_size = "256MB"
+file_size = "128MB"
 
-## The threshold of the WAL size to trigger a flush.
+## The threshold of the WAL size to trigger a purge.
 ## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "4GB"
+purge_threshold = "1GB"
 
-## The interval to trigger a flush.
+## The interval to trigger a purge.
 ## **It's only used when the provider is `raft_engine`**.
-purge_interval = "10m"
+purge_interval = "1m"
 
 ## The read batch size.
 ## **It's only used when the provider is `raft_engine`**.
@@ -167,10 +198,41 @@ 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`**.
@@ -196,12 +258,43 @@ 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.
-file_size = "256MB"
-## Kv purge threshold.
-purge_threshold = "4GB"
+## The size of the metadata store log file.
+file_size = "64MB"
+## The threshold of the metadata store size to trigger a purge.
+purge_threshold = "256MB"
+## The interval of the metadata store to trigger a purge.
+purge_interval = "1m"
 
 ## Procedure storage options.
 [procedure]
@@ -210,6 +303,12 @@ max_retry_times = 3
 ## Initial retry delay of procedures, increases exponentially
 retry_delay = "500ms"
 
+## flow engine options.
+[flow]
+## The number of flow worker in flownode.
+## Not setting(or set to 0) this value will use the number of CPU cores divided by 2.
+#+num_workers=0
+
 # Example of using S3 as the storage.
 # [storage]
 # type = "S3"
@@ -246,6 +345,7 @@ retry_delay = "500ms"
 # root = "data"
 # scope = "test"
 # credential_path = "123456"
+# credential = "base64-credential"
 # endpoint = "https://storage.googleapis.com"
 
 ## The data storage options.
@@ -261,87 +361,123 @@ data_home = "/tmp/greptimedb/"
 ## - `Oss`: the data is stored in the Aliyun OSS.
 type = "File"
 
-## Cache configuration for object storage such as 'S3' etc.
-## The local file cache directory.
-## +toml2docs:none-default
-cache_path = "/path/local_cache"
+## Read cache configuration for object storage such as 'S3' etc, it's configured by default when using object storage. It is recommended to configure it when using object storage for better performance.
+## A local file directory, defaults to `{data_home}`. An empty string means disabling.
+## @toml2docs:none-default
+#+ cache_path = ""
 
-## The local file cache capacity in bytes.
-## +toml2docs:none-default
-cache_capacity = "256MB"
+## The local file cache capacity in bytes. If your disk space is sufficient, it is recommended to set it larger.
+## @toml2docs:none-default
+cache_capacity = "5GiB"
 
 ## The S3 bucket name.
 ## **It's only used when the storage type is `S3`, `Oss` and `Gcs`**.
-## +toml2docs:none-default
+## @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"
 
+## The http client options to the storage.
+## **It's only used when the storage type is `S3`, `Oss`, `Gcs` and `Azblob`**.
+[storage.http_client]
+
+## The maximum idle connection per host allowed in the pool.
+pool_max_idle_per_host = 1024
+
+## The timeout for only the connect phase of a http client.
+connect_timeout = "30s"
+
+## The total request timeout, applied from when the request starts connecting until the response body has finished.
+## Also considered a total deadline.
+timeout = "30s"
+
+## The timeout for idle sockets being kept-alive.
+pool_idle_timeout = "90s"
+
 # 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]]
@@ -350,7 +486,7 @@ 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
@@ -364,57 +500,75 @@ manifest_checkpoint_distance = 10
 ## Whether to compress manifest and checkpoint file by gzip (default false).
 compress_manifest = false
 
-## Max number of running background jobs
-max_background_jobs = 4
+## Max number of running background flush jobs (default: 1/2 of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_flushes = 4
+
+## Max number of running background compaction jobs (default: 1/4 of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_compactions = 2
+
+## Max number of running background purge jobs (default: number of cpu cores).
+## @toml2docs:none-default="Auto"
+#+ max_background_purges = 8
 
 ## Interval to auto flush a region if it has not flushed yet.
 auto_flush_interval = "1h"
 
 ## Global write buffer size for all regions. If not set, it's default to 1/8 of OS memory with a max limitation of 1GB.
-global_write_buffer_size = "1GB"
+## @toml2docs:none-default="Auto"
+#+ global_write_buffer_size = "1GB"
 
-## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`
-global_write_buffer_reject_size = "2GB"
+## Global write buffer size threshold to reject write requests. If not set, it's default to 2 times of `global_write_buffer_size`.
+## @toml2docs:none-default="Auto"
+#+ global_write_buffer_reject_size = "2GB"
 
 ## Cache size for SST metadata. Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/32 of OS memory with a max limitation of 128MB.
-sst_meta_cache_size = "128MB"
+## @toml2docs:none-default="Auto"
+#+ sst_meta_cache_size = "128MB"
 
 ## Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
-vector_cache_size = "512MB"
+## @toml2docs:none-default="Auto"
+#+ vector_cache_size = "512MB"
 
 ## Cache size for pages of SST row groups. Setting it to 0 to disable the cache.
+## If not set, it's default to 1/8 of OS memory.
+## @toml2docs:none-default="Auto"
+#+ page_cache_size = "512MB"
+
+## Cache size for time series selector (e.g. `last_value()`). Setting it to 0 to disable the cache.
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
-page_cache_size = "512MB"
+## @toml2docs:none-default="Auto"
+#+ selector_result_cache_size = "512MB"
 
-## Whether to enable the experimental write cache.
-enable_experimental_write_cache = false
+## Whether to enable the write cache, it's enabled by default when using object storage. It is recommended to enable it when using object storage for better performance.
+enable_write_cache = false
 
-## File system path for write cache, defaults to `{data_home}/write_cache`.
-experimental_write_cache_path = ""
+## File system path for write cache, defaults to `{data_home}`.
+write_cache_path = ""
 
-## Capacity for write cache.
-experimental_write_cache_size = "512MB"
+## Capacity for write cache. If your disk space is sufficient, it is recommended to set it larger.
+write_cache_size = "5GiB"
 
 ## TTL for write cache.
-experimental_write_cache_ttl = "1h"
+## @toml2docs:none-default
+write_cache_ttl = "8h"
 
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
 
-## Parallelism to scan a region (default: 1/4 of cpu cores).
-## - `0`: using the default value (1/4 of cpu cores).
-## - `1`: scan in current thread.
-## - `n`: scan in parallelism n.
-scan_parallelism = 0
-
 ## Capacity of the channel to send data from parallel scan tasks to the main task.
 parallel_scan_channel_size = 32
 
 ## Whether to allow stale WAL entries read during replay.
 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]
 
@@ -430,6 +584,20 @@ aux_path = ""
 ## The max capacity of the staging directory.
 staging_size = "2GB"
 
+## The TTL of the staging directory.
+## Defaults to 7 days.
+## Setting it to "0s" to disable TTL.
+staging_ttl = "7d"
+
+## Cache size for inverted index metadata.
+metadata_cache_size = "64MiB"
+
+## Cache size for inverted index content.
+content_cache_size = "128MiB"
+
+## Page size for inverted index content cache.
+content_cache_page_size = "64KiB"
+
 ## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
 
@@ -457,12 +625,6 @@ mem_threshold_on_create = "auto"
 ## Deprecated, use `region_engine.mito.index.aux_path` instead.
 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]
 
@@ -487,6 +649,30 @@ apply_on_query = "auto"
 ## - `[size]` e.g. `64MB`: fixed memory threshold
 mem_threshold_on_create = "auto"
 
+## The options for bloom filter in Mito engine.
+[region_engine.mito.bloom_filter_index]
+
+## Whether to create the bloom filter on flush.
+## - `auto`: automatically (default)
+## - `disable`: never
+create_on_flush = "auto"
+
+## Whether to create the bloom filter on compaction.
+## - `auto`: automatically (default)
+## - `disable`: never
+create_on_compaction = "auto"
+
+## Whether to apply the bloom filter on query
+## - `auto`: automatically (default)
+## - `disable`: never
+apply_on_query = "auto"
+
+## Memory threshold for bloom filter 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
@@ -509,31 +695,55 @@ fork_dictionary_bytes = "1GiB"
 ## Enable the file engine.
 [region_engine.file]
 
+[[region_engine]]
+## Metric engine options.
+[region_engine.metric]
+## Whether to enable the experimental sparse primary key encoding.
+experimental_sparse_primary_key_encoding = false
+
 ## The logging options.
 [logging]
-## The directory to store the log files.
+## 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
+## @toml2docs:none-default
 level = "info"
 
 ## Enable OTLP tracing.
 enable_otlp_tracing = false
 
 ## The OTLP tracing endpoint.
-## +toml2docs:none-default
-otlp_endpoint = ""
+otlp_endpoint = "http://localhost:4317"
 
 ## Whether to append logs to stdout.
 append_stdout = true
 
+## The log format. Can be `text`/`json`.
+log_format = "text"
+
+## The maximum amount of log files.
+max_log_files = 720
+
 ## The percentage of tracing will be sampled and exported.
 ## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
 ## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]
@@ -544,20 +754,21 @@ enable = false
 ## The interval of export metrics.
 write_interval = "30s"
 
-## For `standalone` mode, `self_import` is recommend to collect metrics generated by itself
+## For `standalone` mode, `self_import` is recommended to collect metrics generated by itself
+## You must create the database before enabling it.
 [export_metrics.self_import]
-## +toml2docs:none-default
-db = "information_schema"
+## @toml2docs:none-default
+db = "greptime_metrics"
 
 [export_metrics.remote_write]
-## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`.
+## The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
 url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
 
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
+#+ [tracing]
 ## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"
+## @toml2docs:none-default
+#+ tokio_console_addr = "127.0.0.1"

cyborg/bin/bump-doc-version.ts

@@ -0,0 +1,75 @@
+/*
+ * Copyright 2023 Greptime Team
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import * as core from "@actions/core";
+import {obtainClient} from "@/common";
+
+async function triggerWorkflow(workflowId: string, version: string) {
+  const docsClient = obtainClient("DOCS_REPO_TOKEN")
+  try {
+    await docsClient.rest.actions.createWorkflowDispatch({
+      owner: "GreptimeTeam",
+      repo: "docs",
+      workflow_id: workflowId,
+      ref: "main",
+      inputs: {
+        version,
+      },
+    });
+    console.log(`Successfully triggered ${workflowId} workflow with version ${version}`);
+  } catch (error) {
+    core.setFailed(`Failed to trigger workflow: ${error.message}`);
+  }
+}
+
+function determineWorkflow(version: string): [string, string] {
+  // Check if it's a nightly version
+  if (version.includes('nightly')) {
+    return ['bump-nightly-version.yml', version];
+  }
+
+  const parts = version.split('.');
+
+  if (parts.length !== 3) {
+    throw new Error('Invalid version format');
+  }
+
+  // If patch version (last number) is 0, it's a major version
+  // Return only major.minor version
+  if (parts[2] === '0') {
+    return ['bump-version.yml', `${parts[0]}.${parts[1]}`];
+  }
+
+  // Otherwise it's a patch version, use full version
+  return ['bump-patch-version.yml', version];
+}
+
+const version = process.env.VERSION;
+if (!version) {
+  core.setFailed("VERSION environment variable is required");
+  process.exit(1);
+}
+
+// Remove 'v' prefix if exists
+const cleanVersion = version.startsWith('v') ? version.slice(1) : version;
+
+try {
+  const [workflowId, apiVersion] = determineWorkflow(cleanVersion);
+  triggerWorkflow(workflowId, apiVersion);
+} catch (error) {
+  core.setFailed(`Error processing version: ${error.message}`);
+  process.exit(1);
+}

docker/buildx/centos/Dockerfile

@@ -13,8 +13,6 @@ RUN yum install -y epel-release  \
     openssl \
     openssl-devel  \
     centos-release-scl  \
-    rh-python38  \
-    rh-python38-python-devel \
     which
 
 # Install protoc
@@ -24,7 +22,7 @@ RUN unzip protoc-3.15.8-linux-x86_64.zip -d /usr/local/
 # Install Rust
 SHELL ["/bin/bash", "-c"]
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --no-modify-path --default-toolchain none -y
-ENV PATH /opt/rh/rh-python38/root/usr/bin:/usr/local/bin:/root/.cargo/bin/:$PATH
+ENV PATH /usr/local/bin:/root/.cargo/bin/:$PATH
 
 # Build the project in release mode.
 RUN --mount=target=.,rw \
@@ -43,8 +41,6 @@ RUN yum install -y epel-release \
     openssl \
     openssl-devel  \
     centos-release-scl  \
-    rh-python38  \
-    rh-python38-python-devel \
     which
 
 WORKDIR /greptime

docker/buildx/ubuntu/Dockerfile

@@ -7,10 +7,8 @@ ARG OUTPUT_DIR
 ENV LANG en_US.utf8
 WORKDIR /greptimedb
 
-# Add PPA for Python 3.10.
 RUN apt-get update && \
-    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa -y
+    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common
 
 # Install dependencies.
 RUN --mount=type=cache,target=/var/cache/apt \
@@ -20,10 +18,7 @@ RUN --mount=type=cache,target=/var/cache/apt \
     curl \
     git \
     build-essential \
-    pkg-config \
-    python3.10 \
-    python3.10-dev \
-    python3-pip
+    pkg-config
 
 # Install Rust.
 SHELL ["/bin/bash", "-c"]
@@ -46,15 +41,8 @@ ARG OUTPUT_DIR
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get \
     -y install ca-certificates \
-    python3.10 \
-    python3.10-dev \
-    python3-pip \
     curl
 
-COPY ./docker/python/requirements.txt /etc/greptime/requirements.txt
-
-RUN python3 -m pip install -r /etc/greptime/requirements.txt
-
 WORKDIR /greptime
 COPY --from=builder /out/target/${OUTPUT_DIR}/greptime /greptime/bin/
 ENV PATH /greptime/bin/:$PATH

docker/ci/centos/Dockerfile

@@ -7,9 +7,7 @@ RUN sed -i s/^#.*baseurl=http/baseurl=http/g /etc/yum.repos.d/*.repo
 RUN yum install -y epel-release \
     openssl \
     openssl-devel  \
-    centos-release-scl  \
-    rh-python38  \
-    rh-python38-python-devel
+    centos-release-scl
 
 ARG TARGETARCH
 

docker/ci/ubuntu/Dockerfile

@@ -8,15 +8,8 @@ ARG TARGET_BIN=greptime
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     ca-certificates \
-    python3.10 \
-    python3.10-dev \
-    python3-pip \
     curl
 
-COPY $DOCKER_BUILD_ROOT/docker/python/requirements.txt /etc/greptime/requirements.txt
-
-RUN python3 -m pip install -r /etc/greptime/requirements.txt
-
 ARG TARGETARCH
 
 ADD $TARGETARCH/$TARGET_BIN /greptime/bin/

docker/dev-builder/android/Dockerfile

@@ -9,16 +9,20 @@ RUN cp ${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/lib64/clang/14.0.7/lib/
 # Install dependencies.
 RUN apt-get update && apt-get install -y \
     libssl-dev \
-    protobuf-compiler \
     curl \
     git \
+    unzip \
     build-essential \
-    pkg-config \
-    python3 \
-    python3-dev \
-    python3-pip \
-    && pip3 install --upgrade pip \
-    && pip3 install pyarrow
+    pkg-config
+
+# Install protoc
+ARG PROTOBUF_VERSION=29.3
+
+RUN curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_VERSION}/protoc-${PROTOBUF_VERSION}-linux-x86_64.zip && \
+    unzip protoc-${PROTOBUF_VERSION}-linux-x86_64.zip -d protoc3;
+    
+RUN mv protoc3/bin/* /usr/local/bin/
+RUN mv protoc3/include/* /usr/local/include/
 
 # Trust workdir
 RUN git config --global --add safe.directory /greptimedb

docker/dev-builder/binstall/pull_binstall.sh

@@ -0,0 +1,50 @@
+#!/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

@@ -12,18 +12,21 @@ RUN yum install -y epel-release  \
     openssl \
     openssl-devel  \
     centos-release-scl  \
-    rh-python38  \
-    rh-python38-python-devel \
     which
 
 # Install protoc
-RUN curl -LO https://github.com/protocolbuffers/protobuf/releases/download/v3.15.8/protoc-3.15.8-linux-x86_64.zip
-RUN unzip protoc-3.15.8-linux-x86_64.zip -d /usr/local/
+ARG PROTOBUF_VERSION=29.3
+
+RUN curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_VERSION}/protoc-${PROTOBUF_VERSION}-linux-x86_64.zip && \
+    unzip protoc-${PROTOBUF_VERSION}-linux-x86_64.zip -d protoc3;
+    
+RUN mv protoc3/bin/* /usr/local/bin/
+RUN mv protoc3/include/* /usr/local/include/
 
 # Install Rust
 SHELL ["/bin/bash", "-c"]
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --no-modify-path --default-toolchain none -y
-ENV PATH /opt/rh/rh-python38/root/usr/bin:/usr/local/bin:/root/.cargo/bin/:$PATH
+ENV PATH /usr/local/bin:/root/.cargo/bin/:$PATH
 
 # Install Rust toolchains.
 ARG RUST_TOOLCHAIN
@@ -32,7 +35,9 @@ 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
+# 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 binstall cargo-nextest --no-confirm

docker/dev-builder/ubuntu/Dockerfile

@@ -6,29 +6,34 @@ ARG DOCKER_BUILD_ROOT=.
 ENV LANG en_US.utf8
 WORKDIR /greptimedb
 
-# Add PPA for Python 3.10.
 RUN apt-get update && \
-    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa -y
-
+    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common
 # Install dependencies.
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     libssl-dev \
     tzdata \
-    protobuf-compiler \
     curl \
+    unzip \
     ca-certificates \
     git \
     build-essential \
-    pkg-config \
-    python3.10 \
-    python3.10-dev
+    pkg-config
 
-# Remove Python 3.8 and install pip.
-RUN apt-get -y purge python3.8 && \
-    apt-get -y autoremove && \
-    ln -s /usr/bin/python3.10 /usr/bin/python3 && \
-    curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
+ARG TARGETPLATFORM
+RUN echo "target platform: $TARGETPLATFORM"
+
+ARG PROTOBUF_VERSION=29.3
+
+# Install protobuf, because the one in the apt is too old (v3.12).
+RUN if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
+    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_VERSION}/protoc-${PROTOBUF_VERSION}-linux-aarch_64.zip && \
+    unzip protoc-${PROTOBUF_VERSION}-linux-aarch_64.zip -d protoc3; \
+elif [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
+    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOBUF_VERSION}/protoc-${PROTOBUF_VERSION}-linux-x86_64.zip && \
+    unzip protoc-${PROTOBUF_VERSION}-linux-x86_64.zip -d protoc3; \
+fi
+RUN mv protoc3/bin/* /usr/local/bin/
+RUN mv protoc3/include/* /usr/local/include/
 
 # Silence all `safe.directory` warnings, to avoid the "detect dubious repository" error when building with submodules.
 # Disabling the safe directory check here won't pose extra security issues, because in our usage for this dev build
@@ -40,11 +45,7 @@ RUN apt-get -y purge python3.8 && \
 # wildcard here. However, that requires the git's config files and the submodules all owned by the very same user.
 # It's troublesome to do this since the dev build runs in Docker, which is under user "root"; while outside the Docker,
 # it can be a different user that have prepared the submodules.
-RUN git config --global --add safe.directory *
-
-# Install Python dependencies.
-COPY $DOCKER_BUILD_ROOT/docker/python/requirements.txt /etc/greptime/requirements.txt
-RUN python3 -m pip install -r /etc/greptime/requirements.txt
+RUN git config --global --add safe.directory '*'
 
 # Install Rust.
 SHELL ["/bin/bash", "-c"]
@@ -57,7 +58,9 @@ 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
+# 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 binstall cargo-nextest --no-confirm

docker/dev-builder/ubuntu/Dockerfile-18.10

@@ -21,7 +21,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
     pkg-config
 
 # Install protoc.
-ENV PROTOC_VERSION=25.1
+ENV PROTOC_VERSION=29.3
 RUN if [ "$(uname -m)" = "x86_64" ]; then \
         PROTOC_ZIP=protoc-${PROTOC_VERSION}-linux-x86_64.zip; \
     elif [ "$(uname -m)" = "aarch64" ]; then \

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

@@ -1,9 +1,9 @@
 x-custom:
   etcd_initial_cluster_token: &etcd_initial_cluster_token "--initial-cluster-token=etcd-cluster"
   etcd_common_settings: &etcd_common_settings
-    image: quay.io/coreos/etcd:v3.5.10
+    image: "${ETCD_REGISTRY:-quay.io}/${ETCD_NAMESPACE:-coreos}/etcd:${ETCD_VERSION:-v3.5.10}"
     entrypoint: /usr/local/bin/etcd
-  greptimedb_image: &greptimedb_image docker.io/greptimedb/greptimedb:latest
+  greptimedb_image: &greptimedb_image "${GREPTIMEDB_REGISTRY:-docker.io}/${GREPTIMEDB_NAMESPACE:-greptime}/greptimedb:${GREPTIMEDB_VERSION:-latest}"
 
 services:
   etcd0:
@@ -39,14 +39,16 @@ services:
     container_name: metasrv
     ports:
       - 3002:3002
+      - 3000:3000
     command:
       - metasrv
       - start
-      - --bind-addr=0.0.0.0:3002
-      - --server-addr=metasrv:3002
+      - --rpc-bind-addr=0.0.0.0:3002
+      - --rpc-server-addr=metasrv:3002
       - --store-addrs=etcd0:2379
+      - --http-addr=0.0.0.0:3000
     healthcheck:
-      test: [ "CMD", "curl", "-f", "http://metasrv:3002/health" ]
+      test: [ "CMD", "curl", "-f", "http://metasrv:3000/health" ]
       interval: 5s
       timeout: 3s
       retries: 5
@@ -66,17 +68,17 @@ services:
       - datanode
       - start
       - --node-id=0
-      - --rpc-addr=0.0.0.0:3001
-      - --rpc-hostname=datanode0:3001
+      - --rpc-bind-addr=0.0.0.0:3001
+      - --rpc-server-addr=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" ]
+      test: [ "CMD", "curl", "-fv", "http://datanode0:5000/health" ]
       interval: 5s
       timeout: 3s
-      retries: 5
+      retries: 10
     depends_on:
       metasrv:
         condition: service_healthy
@@ -96,7 +98,7 @@ services:
       - start
       - --metasrv-addrs=metasrv:3002
       - --http-addr=0.0.0.0:4000
-      - --rpc-addr=0.0.0.0:4001
+      - --rpc-bind-addr=0.0.0.0:4001
       - --mysql-addr=0.0.0.0:4002
       - --postgres-addr=0.0.0.0:4003
     healthcheck:
@@ -115,16 +117,23 @@ services:
     container_name: flownode0
     ports:
       - 4004:4004
+      - 4005:4005
     command:
       - flownode
       - start
       - --node-id=0
       - --metasrv-addrs=metasrv:3002
-      - --rpc-addr=0.0.0.0:4004
-      - --rpc-hostname=flownode0:4004
+      - --rpc-bind-addr=0.0.0.0:4004
+      - --rpc-server-addr=flownode0:4004
+      - --http-addr=0.0.0.0:4005
     depends_on:
       frontend0:
         condition: service_healthy
+    healthcheck:
+      test: [ "CMD", "curl", "-f", "http://flownode0:4005/health" ]
+      interval: 5s
+      timeout: 3s
+      retries: 5
     networks:
       - greptimedb
 

docker/python/requirements.txt

@@ -1,5 +0,0 @@
-numpy>=1.24.2
-pandas>=1.5.3
-pyarrow>=11.0.0
-requests>=2.28.2
-scipy>=1.10.1

docs/benchmarks/log/README.md

@@ -0,0 +1,51 @@
+# 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

@@ -0,0 +1,56 @@
+-- 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

@@ -0,0 +1,199 @@
+# 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

@@ -0,0 +1,50 @@
+-- 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

@@ -0,0 +1,57 @@
+# 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

@@ -0,0 +1,43 @@
+# 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/v0.9.1.md

@@ -0,0 +1,58 @@
+# 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

@@ -0,0 +1,16 @@
+# 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-profile-cpu.md

@@ -1,15 +1,9 @@
 # Profiling CPU
 
-## Build GreptimeDB with `pprof` feature
-
-```bash
-cargo build --features=pprof
-```
-
 ## HTTP API
 Sample at 99 Hertz, for 5 seconds, output report in [protobuf format](https://github.com/google/pprof/blob/master/proto/profile.proto).
 ```bash
-curl -s '0:4000/v1/prof/cpu' > /tmp/pprof.out
+curl -X POST -s '0:4000/debug/prof/cpu' > /tmp/pprof.out
 ```
 
 Then you can use `pprof` command with the protobuf file.
@@ -19,10 +13,10 @@ go tool pprof -top /tmp/pprof.out
 
 Sample at 99 Hertz, for 60 seconds, output report in flamegraph format.
 ```bash
-curl -s '0:4000/v1/prof/cpu?seconds=60&output=flamegraph' > /tmp/pprof.svg
+curl -X POST -s '0:4000/debug/prof/cpu?seconds=60&output=flamegraph' > /tmp/pprof.svg
 ```
 
 Sample at 49 Hertz, for 10 seconds, output report in text format.
 ```bash
-curl -s '0:4000/v1/prof/cpu?seconds=10&frequency=49&output=text' > /tmp/pprof.txt
+curl -X POST -s '0:4000/debug/prof/cpu?seconds=10&frequency=49&output=text' > /tmp/pprof.txt
 ```

docs/how-to/how-to-profile-memory.md

@@ -0,0 +1,61 @@
+# Profile memory usage of GreptimeDB
+
+This crate provides an easy approach to dump memory profiling info.
+
+## Prerequisites
+### jemalloc
+jeprof is already compiled in the target directory of GreptimeDB. You can find the binary and use it.
+```
+# find jeprof binary
+find . -name 'jeprof'
+# add executable permission
+chmod +x <path_to_jeprof>
+```
+The path is usually under `./target/${PROFILE}/build/tikv-jemalloc-sys-${HASH}/out/build/bin/jeprof`.
+The default version of jemalloc installed from the package manager may not have the `--collapsed` option.
+You may need to check the whether the `jeprof` version is >= `5.3.0` if you want to install it from the package manager.
+```bash
+# for macOS
+brew install jemalloc
+
+# for Ubuntu
+sudo apt install libjemalloc-dev
+```
+
+### [flamegraph](https://github.com/brendangregg/FlameGraph)
+
+```bash
+curl https://raw.githubusercontent.com/brendangregg/FlameGraph/master/flamegraph.pl > ./flamegraph.pl
+```
+
+## Profiling
+
+Start GreptimeDB instance with environment variables:
+
+```bash
+# for Linux
+MALLOC_CONF=prof:true ./target/debug/greptime standalone start
+
+# for macOS
+_RJEM_MALLOC_CONF=prof:true ./target/debug/greptime standalone start
+```
+
+Dump memory profiling data through HTTP API:
+
+```bash
+curl -X POST localhost:4000/debug/prof/mem > greptime.hprof
+```
+
+You can periodically dump profiling data and compare them to find the delta memory usage.
+
+## Analyze profiling data with flamegraph
+
+To create flamegraph according to dumped profiling data:
+
+```bash
+sudo apt install -y libjemalloc-dev
+
+jeprof <path_to_greptime_binary> <profile_data> --collapse | ./flamegraph.pl > mem-prof.svg
+
+jeprof <path_to_greptime_binary> --base <baseline_prof> <profile_data> --collapse | ./flamegraph.pl > output.svg
+```

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

@@ -0,0 +1,197 @@
+---
+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`.

flake.lock

@@ -0,0 +1,100 @@
+{
+  "nodes": {
+    "fenix": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs"
+        ],
+        "rust-analyzer-src": "rust-analyzer-src"
+      },
+      "locked": {
+        "lastModified": 1737613896,
+        "narHash": "sha256-ldqXIglq74C7yKMFUzrS9xMT/EVs26vZpOD68Sh7OcU=",
+        "owner": "nix-community",
+        "repo": "fenix",
+        "rev": "303a062fdd8e89f233db05868468975d17855d80",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "fenix",
+        "type": "github"
+      }
+    },
+    "flake-utils": {
+      "inputs": {
+        "systems": "systems"
+      },
+      "locked": {
+        "lastModified": 1731533236,
+        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1737569578,
+        "narHash": "sha256-6qY0pk2QmUtBT9Mywdvif0i/CLVgpCjMUn6g9vB+f3M=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "47addd76727f42d351590c905d9d1905ca895b82",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-24.11",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "fenix": "fenix",
+        "flake-utils": "flake-utils",
+        "nixpkgs": "nixpkgs"
+      }
+    },
+    "rust-analyzer-src": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1737581772,
+        "narHash": "sha256-t1P2Pe3FAX9TlJsCZbmJ3wn+C4qr6aSMypAOu8WNsN0=",
+        "owner": "rust-lang",
+        "repo": "rust-analyzer",
+        "rev": "582af7ee9c8d84f5d534272fc7de9f292bd849be",
+        "type": "github"
+      },
+      "original": {
+        "owner": "rust-lang",
+        "ref": "nightly",
+        "repo": "rust-analyzer",
+        "type": "github"
+      }
+    },
+    "systems": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,56 @@
+{
+  description = "Development environment flake";
+
+  inputs = {
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
+    fenix = {
+      url = "github:nix-community/fenix";
+      inputs.nixpkgs.follows = "nixpkgs";
+    };
+    flake-utils.url = "github:numtide/flake-utils";
+  };
+
+  outputs = { self, nixpkgs, fenix, flake-utils }:
+    flake-utils.lib.eachDefaultSystem (system:
+      let
+        pkgs = nixpkgs.legacyPackages.${system};
+        buildInputs = with pkgs; [
+          libgit2
+          libz
+        ];
+        lib = nixpkgs.lib;
+        rustToolchain = fenix.packages.${system}.fromToolchainName {
+          name = (lib.importTOML ./rust-toolchain.toml).toolchain.channel;
+          sha256 = "sha256-f/CVA1EC61EWbh0SjaRNhLL0Ypx2ObupbzigZp8NmL4=";
+        };
+      in
+      {
+        devShells.default = pkgs.mkShell {
+          nativeBuildInputs = with pkgs; [
+            pkg-config
+            git
+            clang
+            gcc
+            protobuf
+            gnumake
+            mold
+            (rustToolchain.withComponents [
+              "cargo"
+              "clippy"
+              "rust-src"
+              "rustc"
+              "rustfmt"
+              "rust-analyzer"
+              "llvm-tools"
+            ])
+            cargo-nextest
+            cargo-llvm-cov
+            taplo
+            curl
+            gnuplot ## for cargo bench
+          ];
+
+          LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath buildInputs;
+        };
+      });
+}

grafana/README.md

@@ -5,6 +5,13 @@ GreptimeDB's official Grafana dashboard.
 
 Status notify: we are still working on this config. It's expected to change frequently in the recent days. Please feel free to submit your feedback and/or contribution to this dashboard 🤗
 
+If you use Helm [chart](https://github.com/GreptimeTeam/helm-charts) to deploy GreptimeDB cluster, you can enable self-monitoring by setting the following values in your Helm chart:
+
+- `monitoring.enabled=true`: Deploys a standalone GreptimeDB instance dedicated to monitoring the cluster;
+- `grafana.enabled=true`: Deploys Grafana and automatically imports the monitoring dashboard;
+
+The standalone GreptimeDB instance will collect metrics from your cluster and the dashboard will be available in the Grafana UI. For detailed deployment instructions, please refer to our [Kubernetes deployment guide](https://docs.greptime.com/nightly/user-guide/deployments/deploy-on-kubernetes/getting-started).
+
 # How to use
 
 ## `greptimedb.json`
@@ -25,7 +32,7 @@ Please ensure the following configuration before importing the dashboard into Gr
 
 __1. Prometheus scrape config__
 
-Assign `greptime_pod` label to each host target. We use this label to identify each node instance.
+Configure Prometheus to scrape the cluster.
 
 ```yml
 # example config
@@ -34,27 +41,15 @@ Assign `greptime_pod` label to each host target. We use this label to identify e
 scrape_configs:
   - job_name: metasrv
     static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: metasrv
+    - targets: ['<metasrv-ip>:<port>']
 
   - job_name: datanode
     static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode1
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode2
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode3
+    - targets: ['<datanode0-ip>:<port>', '<datanode1-ip>:<port>', '<datanode2-ip>:<port>']
 
   - job_name: frontend
     static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: frontend
+    - targets: ['<frontend-ip>:<port>']
 ```
 
 __2. Grafana config__
@@ -63,4 +58,4 @@ Create a Prometheus data source in Grafana before using this dashboard. We use `
 
 ### Usage
 
-Use `datasource` or `greptime_pod` on the upper-left corner to filter data from certain node.
+Use `datasource` or `instance` on the upper-left corner to filter data from certain node.

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "nightly-2024-04-20"
+channel = "nightly-2024-12-25"

scripts/check-builder-rust-version.sh

@@ -0,0 +1,42 @@
+#!/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

@@ -0,0 +1,73 @@
+# Copyright 2023 Greptime Team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+import re
+from multiprocessing import Pool
+
+
+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_content):
+    branch_name_snafu = f"{branch_name}Snafu"
+    for content in rust_files_content.values():
+        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:
+            branch_names.extend(extract_branch_names(file.read()))
+
+    # Read all rust files into memory once
+    rust_files_content = {}
+    for rust_file in other_rust_files:
+        with open(rust_file, "r") as file:
+            rust_files_content[rust_file] = file.read()
+
+    with Pool() as pool:
+        results = pool.starmap(
+            check_snafu_in_files, [(bn, rust_files_content) for bn in branch_names]
+        )
+    unused_snafu = [bn for bn, found in zip(branch_names, results) if not found]
+
+    if unused_snafu:
+        print("Unused error variants:")
+        for name in unused_snafu:
+            print(name)
+        raise SystemExit(1)
+
+
+if __name__ == "__main__":
+    main()

scripts/install.sh

@@ -4,59 +4,69 @@ 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
 
 get_os_type() {
-    os_type="$(uname -s)"
+  os_type="$(uname -s)"
 
-    case "$os_type" in
+  case "$os_type" in
     Darwin)
-        OS_TYPE=darwin
-        ;;
+      OS_TYPE=darwin
+      ;;
     Linux)
-        OS_TYPE=linux
-        ;;
+      OS_TYPE=linux
+      ;;
     *)
-        echo "Error: Unknown OS type: $os_type"
-        exit 1
-    esac
+      echo "Error: Unknown OS type: $os_type"
+      exit 1
+  esac
 }
 
 get_arch_type() {
-    arch_type="$(uname -m)"
+  arch_type="$(uname -m)"
 
-    case "$arch_type" in
+  case "$arch_type" in
     arm64)
-        ARCH_TYPE=arm64
-        ;;
+      ARCH_TYPE=arm64
+      ;;
     aarch64)
-        ARCH_TYPE=arm64
-        ;;
+      ARCH_TYPE=arm64
+      ;;
     x86_64)
-        ARCH_TYPE=amd64
-        ;;
+      ARCH_TYPE=amd64
+      ;;
     amd64)
-        ARCH_TYPE=amd64
-        ;;
+      ARCH_TYPE=amd64
+      ;;
     *)
-        echo "Error: Unknown CPU type: $arch_type"
-        exit 1
-    esac
+      echo "Error: Unknown CPU type: $arch_type"
+      exit 1
+  esac
 }
 
-get_os_type
-get_arch_type
-
-if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
-    # Use the latest nightly version.
+download_artifact() {
+  if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
+    # 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 [ "${VERSION}" = "latest" ]; then
-        VERSION=$(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)
-        if [ -z "${VERSION}" ]; then
-            echo "Failed to get the latest version."
-            exit 1
+      # To avoid other tools dependency, we choose to use `curl` to get the version metadata and parsed by `sed`.
+      VERSION=$(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."
+        exit 1
         fi
     fi
 
@@ -73,4 +83,9 @@ if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
       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

@@ -15,13 +15,10 @@ common-macro.workspace = true
 common-time.workspace = true
 datatypes.workspace = true
 greptime-proto.workspace = true
-paste = "1.0"
+paste.workspace = true
 prost.workspace = true
 serde_json.workspace = true
 snafu.workspace = true
 
 [build-dependencies]
 tonic-build = "0.11"
-
-[dev-dependencies]
-paste = "1.0"

src/api/src/error.rs

@@ -33,7 +33,7 @@ pub enum Error {
         #[snafu(implicit)]
         location: Location,
         #[snafu(source)]
-        error: prost::DecodeError,
+        error: prost::UnknownEnumValue,
     },
 
     #[snafu(display("Failed to create column datatype from {:?}", from))]

src/api/src/helper.rs

@@ -17,10 +17,11 @@ 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::{Date, DateTime, Interval, Timestamp};
+use common_time::{
+    Date, DateTime, IntervalDayTime, IntervalMonthDayNano, IntervalYearMonth, Timestamp,
+};
 use datatypes::prelude::{ConcreteDataType, ValueRef};
 use datatypes::scalars::ScalarVector;
 use datatypes::types::{
@@ -35,14 +36,14 @@ use datatypes::vectors::{
     TimestampMillisecondVector, TimestampNanosecondVector, TimestampSecondVector, UInt32Vector,
     UInt64Vector, VectorRef,
 };
-use greptime_proto::v1;
 use greptime_proto::v1::column_data_type_extension::TypeExt;
 use greptime_proto::v1::ddl_request::Expr;
 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, QueryRequest, Row, SemanticType,
+    self, ColumnDataTypeExtension, DdlRequest, DecimalTypeExtension, JsonTypeExtension,
+    QueryRequest, Row, SemanticType, VectorTypeExtension,
 };
 use paste::paste;
 use snafu::prelude::*;
@@ -85,7 +86,7 @@ impl ColumnDataTypeWrapper {
 
     /// Get a tuple of ColumnDataType and ColumnDataTypeExtension.
     pub fn to_parts(&self) -> (ColumnDataType, Option<ColumnDataTypeExtension>) {
-        (self.datatype, self.datatype_ext.clone())
+        (self.datatype, self.datatype_ext)
     }
 }
 
@@ -103,7 +104,18 @@ impl From<ColumnDataTypeWrapper> for ConcreteDataType {
             ColumnDataType::Uint64 => ConcreteDataType::uint64_datatype(),
             ColumnDataType::Float32 => ConcreteDataType::float32_datatype(),
             ColumnDataType::Float64 => ConcreteDataType::float64_datatype(),
-            ColumnDataType::Binary => ConcreteDataType::binary_datatype(),
+            ColumnDataType::Binary => {
+                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(),
@@ -137,6 +149,17 @@ impl From<ColumnDataTypeWrapper> for ConcreteDataType {
                     ConcreteDataType::decimal128_default_datatype()
                 }
             }
+            ColumnDataType::Vector => {
+                if let Some(TypeExt::VectorType(d)) = datatype_wrapper
+                    .datatype_ext
+                    .as_ref()
+                    .and_then(|datatype_ext| datatype_ext.type_ext.as_ref())
+                {
+                    ConcreteDataType::vector_datatype(d.dim)
+                } else {
+                    ConcreteDataType::vector_default_datatype()
+                }
+            }
         }
     }
 }
@@ -218,6 +241,15 @@ impl ColumnDataTypeWrapper {
             }),
         }
     }
+
+    pub fn vector_datatype(dim: u32) -> Self {
+        ColumnDataTypeWrapper {
+            datatype: ColumnDataType::Vector,
+            datatype_ext: Some(ColumnDataTypeExtension {
+                type_ext: Some(TypeExt::VectorType(VectorTypeExtension { dim })),
+            }),
+        }
+    }
 }
 
 impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
@@ -258,6 +290,8 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
                 IntervalType::MonthDayNano(_) => ColumnDataType::IntervalMonthDayNano,
             },
             ConcreteDataType::Decimal128(_) => ColumnDataType::Decimal128,
+            ConcreteDataType::Json(_) => ColumnDataType::Json,
+            ConcreteDataType::Vector(_) => ColumnDataType::Vector,
             ConcreteDataType::Null(_)
             | ConcreteDataType::List(_)
             | ConcreteDataType::Dictionary(_)
@@ -276,6 +310,18 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
                         })),
                     })
             }
+            ColumnDataType::Json => datatype.as_json().map(|_| ColumnDataTypeExtension {
+                type_ext: Some(TypeExt::JsonType(JsonTypeExtension::JsonBinary.into())),
+            }),
+            ColumnDataType::Vector => {
+                datatype
+                    .as_vector()
+                    .map(|vector_type| ColumnDataTypeExtension {
+                        type_ext: Some(TypeExt::VectorType(VectorTypeExtension {
+                            dim: vector_type.dim as _,
+                        })),
+                    })
+            }
             _ => None,
         };
         Ok(Self {
@@ -395,6 +441,14 @@ 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()
+        },
+        ColumnDataType::Vector => Values {
+            binary_values: Vec::with_capacity(capacity),
+            ..Default::default()
+        },
     }
 }
 
@@ -435,13 +489,11 @@ 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::Interval(val) => match val.unit() {
-            IntervalUnit::YearMonth => values.interval_year_month_values.push(val.to_i32()),
-            IntervalUnit::DayTime => values.interval_day_time_values.push(val.to_i64()),
-            IntervalUnit::MonthDayNano => values
-                .interval_month_day_nano_values
-                .push(convert_i128_to_interval(val.to_i128())),
-        },
+        Value::IntervalYearMonth(val) => values.interval_year_month_values.push(val.to_i32()),
+        Value::IntervalDayTime(val) => values.interval_day_time_values.push(val.to_i64()),
+        Value::IntervalMonthDayNano(val) => values
+            .interval_month_day_nano_values
+            .push(convert_month_day_nano_to_pb(val)),
         Value::Decimal128(val) => values.decimal128_values.push(convert_to_pb_decimal128(val)),
         Value::List(_) | Value::Duration(_) => unreachable!(),
     });
@@ -475,25 +527,24 @@ fn ddl_request_type(request: &DdlRequest) -> &'static str {
     match request.expr {
         Some(Expr::CreateDatabase(_)) => "ddl.create_database",
         Some(Expr::CreateTable(_)) => "ddl.create_table",
-        Some(Expr::Alter(_)) => "ddl.alter",
+        Some(Expr::AlterTable(_)) => "ddl.alter_table",
         Some(Expr::DropTable(_)) => "ddl.drop_table",
         Some(Expr::TruncateTable(_)) => "ddl.truncate_table",
         Some(Expr::CreateFlow(_)) => "ddl.create_flow",
         Some(Expr::DropFlow(_)) => "ddl.drop_flow",
         Some(Expr::CreateView(_)) => "ddl.create_view",
         Some(Expr::DropView(_)) => "ddl.drop_view",
+        Some(Expr::AlterDatabase(_)) => "ddl.alter_database",
         None => "ddl.empty",
     }
 }
 
-/// Converts an i128 value to google protobuf type [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();
+/// Converts an interval to google protobuf type [IntervalMonthDayNano].
+pub fn convert_month_day_nano_to_pb(v: IntervalMonthDayNano) -> v1::IntervalMonthDayNano {
     v1::IntervalMonthDayNano {
-        months,
-        days,
-        nanoseconds,
+        months: v.months,
+        days: v.days,
+        nanoseconds: v.nanoseconds,
     }
 }
 
@@ -541,11 +592,15 @@ 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) => ValueRef::Interval(Interval::from_i32(*v)),
-        ValueData::IntervalDayTimeValue(v) => ValueRef::Interval(Interval::from_i64(*v)),
+        ValueData::IntervalYearMonthValue(v) => {
+            ValueRef::IntervalYearMonth(IntervalYearMonth::from_i32(*v))
+        }
+        ValueData::IntervalDayTimeValue(v) => {
+            ValueRef::IntervalDayTime(IntervalDayTime::from_i64(*v))
+        }
         ValueData::IntervalMonthDayNanoValue(v) => {
-            let interval = Interval::from_month_day_nano(v.months, v.days, v.nanoseconds);
-            ValueRef::Interval(interval)
+            let interval = IntervalMonthDayNano::new(v.months, v.days, v.nanoseconds);
+            ValueRef::IntervalMonthDayNano(interval)
         }
         ValueData::Decimal128Value(v) => {
             // get precision and scale from datatype_extension
@@ -630,14 +685,18 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
             IntervalType::YearMonth(_) => Arc::new(IntervalYearMonthVector::from_vec(
                 values.interval_year_month_values,
             )),
-            IntervalType::DayTime(_) => Arc::new(IntervalDayTimeVector::from_vec(
-                values.interval_day_time_values,
+            IntervalType::DayTime(_) => Arc::new(IntervalDayTimeVector::from_iter_values(
+                values
+                    .interval_day_time_values
+                    .iter()
+                    .map(|x| IntervalDayTime::from_i64(*x).into()),
             )),
             IntervalType::MonthDayNano(_) => {
                 Arc::new(IntervalMonthDayNanoVector::from_iter_values(
-                    values.interval_month_day_nano_values.iter().map(|x| {
-                        Interval::from_month_day_nano(x.months, x.days, x.nanoseconds).to_i128()
-                    }),
+                    values
+                        .interval_month_day_nano_values
+                        .iter()
+                        .map(|x| IntervalMonthDayNano::new(x.months, x.days, x.nanoseconds).into()),
                 ))
             }
         },
@@ -646,10 +705,12 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
                 Decimal128::from_value_precision_scale(x.hi, x.lo, d.precision(), d.scale()).into()
             }),
         )),
+        ConcreteDataType::Vector(_) => Arc::new(BinaryVector::from_vec(values.binary_values)),
         ConcreteDataType::Null(_)
         | ConcreteDataType::List(_)
         | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_) => {
+        | ConcreteDataType::Duration(_)
+        | ConcreteDataType::Json(_) => {
             unreachable!()
         }
     }
@@ -780,18 +841,18 @@ 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::Interval(Interval::from_i32(v)))
+            .map(|v| Value::IntervalYearMonth(IntervalYearMonth::from_i32(v)))
             .collect(),
         ConcreteDataType::Interval(IntervalType::DayTime(_)) => values
             .interval_day_time_values
             .into_iter()
-            .map(|v| Value::Interval(Interval::from_i64(v)))
+            .map(|v| Value::IntervalDayTime(IntervalDayTime::from_i64(v)))
             .collect(),
         ConcreteDataType::Interval(IntervalType::MonthDayNano(_)) => values
             .interval_month_day_nano_values
             .into_iter()
             .map(|v| {
-                Value::Interval(Interval::from_month_day_nano(
+                Value::IntervalMonthDayNano(IntervalMonthDayNano::new(
                     v.months,
                     v.days,
                     v.nanoseconds,
@@ -810,10 +871,12 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
                 ))
             })
             .collect(),
+        ConcreteDataType::Vector(_) => values.binary_values.into_iter().map(|v| v.into()).collect(),
         ConcreteDataType::Null(_)
         | ConcreteDataType::List(_)
         | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_) => {
+        | ConcreteDataType::Duration(_)
+        | ConcreteDataType::Json(_) => {
             unreachable!()
         }
     }
@@ -831,7 +894,10 @@ pub fn is_column_type_value_eq(
     expect_type: &ConcreteDataType,
 ) -> bool {
     ColumnDataTypeWrapper::try_new(type_value, type_extension)
-        .map(|wrapper| ConcreteDataType::from(wrapper) == *expect_type)
+        .map(|wrapper| {
+            let datatype = ConcreteDataType::from(wrapper);
+            expect_type == &datatype
+        })
         .unwrap_or(false)
 }
 
@@ -912,18 +978,16 @@ pub fn to_proto_value(value: Value) -> Option<v1::Value> {
                 value_data: Some(ValueData::TimeNanosecondValue(v.value())),
             },
         },
-        Value::Interval(v) => match v.unit() {
-            IntervalUnit::YearMonth => v1::Value {
-                value_data: Some(ValueData::IntervalYearMonthValue(v.to_i32())),
-            },
-            IntervalUnit::DayTime => v1::Value {
-                value_data: Some(ValueData::IntervalDayTimeValue(v.to_i64())),
-            },
-            IntervalUnit::MonthDayNano => v1::Value {
-                value_data: Some(ValueData::IntervalMonthDayNanoValue(
-                    convert_i128_to_interval(v.to_i128()),
-                )),
-            },
+        Value::IntervalYearMonth(v) => v1::Value {
+            value_data: Some(ValueData::IntervalYearMonthValue(v.to_i32())),
+        },
+        Value::IntervalDayTime(v) => v1::Value {
+            value_data: Some(ValueData::IntervalDayTimeValue(v.to_i64())),
+        },
+        Value::IntervalMonthDayNano(v) => v1::Value {
+            value_data: Some(ValueData::IntervalMonthDayNanoValue(
+                convert_month_day_nano_to_pb(v),
+            )),
         },
         Value::Decimal128(v) => v1::Value {
             value_data: Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
@@ -1015,13 +1079,11 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
                 TimeUnit::Microsecond => ValueData::TimeMicrosecondValue(v.value()),
                 TimeUnit::Nanosecond => ValueData::TimeNanosecondValue(v.value()),
             }),
-            Value::Interval(v) => Some(match v.unit() {
-                IntervalUnit::YearMonth => ValueData::IntervalYearMonthValue(v.to_i32()),
-                IntervalUnit::DayTime => ValueData::IntervalDayTimeValue(v.to_i64()),
-                IntervalUnit::MonthDayNano => {
-                    ValueData::IntervalMonthDayNanoValue(convert_i128_to_interval(v.to_i128()))
-                }
-            }),
+            Value::IntervalYearMonth(v) => Some(ValueData::IntervalYearMonthValue(v.to_i32())),
+            Value::IntervalDayTime(v) => Some(ValueData::IntervalDayTimeValue(v.to_i64())),
+            Value::IntervalMonthDayNano(v) => Some(ValueData::IntervalMonthDayNanoValue(
+                convert_month_day_nano_to_pb(v),
+            )),
             Value::Decimal128(v) => Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
             Value::List(_) | Value::Duration(_) => unreachable!(),
         },
@@ -1032,6 +1094,7 @@ 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,
@@ -1120,6 +1183,10 @@ mod tests {
         let values = values_with_capacity(ColumnDataType::Decimal128, 2);
         let values = values.decimal128_values;
         assert_eq!(2, values.capacity());
+
+        let values = values_with_capacity(ColumnDataType::Vector, 2);
+        let values = values.binary_values;
+        assert_eq!(2, values.capacity());
     }
 
     #[test]
@@ -1207,7 +1274,11 @@ mod tests {
         assert_eq!(
             ConcreteDataType::decimal128_datatype(10, 2),
             ColumnDataTypeWrapper::decimal128_datatype(10, 2).into()
-        )
+        );
+        assert_eq!(
+            ConcreteDataType::vector_datatype(3),
+            ColumnDataTypeWrapper::vector_datatype(3).into()
+        );
     }
 
     #[test]
@@ -1303,6 +1374,10 @@ mod tests {
                 .try_into()
                 .unwrap()
         );
+        assert_eq!(
+            ColumnDataTypeWrapper::vector_datatype(3),
+            ConcreteDataType::vector_datatype(3).try_into().unwrap()
+        );
 
         let result: Result<ColumnDataTypeWrapper> = ConcreteDataType::null_datatype().try_into();
         assert!(result.is_err());
@@ -1424,14 +1499,22 @@ mod tests {
             column.values.as_ref().unwrap().interval_year_month_values
         );
 
-        let vector = Arc::new(IntervalDayTimeVector::from_vec(vec![4, 5, 6]));
+        let vector = Arc::new(IntervalDayTimeVector::from_vec(vec![
+            IntervalDayTime::new(0, 4).into(),
+            IntervalDayTime::new(0, 5).into(),
+            IntervalDayTime::new(0, 6).into(),
+        ]));
         push_vals(&mut column, 3, vector);
         assert_eq!(
             vec![4, 5, 6],
             column.values.as_ref().unwrap().interval_day_time_values
         );
 
-        let vector = Arc::new(IntervalMonthDayNanoVector::from_vec(vec![7, 8, 9]));
+        let vector = Arc::new(IntervalMonthDayNanoVector::from_vec(vec![
+            IntervalMonthDayNano::new(0, 0, 7).into(),
+            IntervalMonthDayNano::new(0, 0, 8).into(),
+            IntervalMonthDayNano::new(0, 0, 9).into(),
+        ]));
         let len = vector.len();
         push_vals(&mut column, 3, vector);
         (0..len).for_each(|i| {
@@ -1477,11 +1560,11 @@ mod tests {
 
     #[test]
     fn test_convert_i128_to_interval() {
-        let i128_val = 3000;
-        let interval = convert_i128_to_interval(i128_val);
+        let i128_val = 3;
+        let interval = convert_month_day_nano_to_pb(IntervalMonthDayNano::from_i128(i128_val));
         assert_eq!(interval.months, 0);
         assert_eq!(interval.days, 0);
-        assert_eq!(interval.nanoseconds, 3000);
+        assert_eq!(interval.nanoseconds, 3);
     }
 
     #[test]
@@ -1561,9 +1644,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::Interval(Interval::from_year_month(1_i32)),
-            Value::Interval(Interval::from_year_month(2_i32)),
-            Value::Interval(Interval::from_year_month(3_i32)),
+            Value::IntervalYearMonth(IntervalYearMonth::new(1_i32)),
+            Value::IntervalYearMonth(IntervalYearMonth::new(2_i32)),
+            Value::IntervalYearMonth(IntervalYearMonth::new(3_i32)),
         ];
         assert_eq!(expect, actual);
 
@@ -1576,9 +1659,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::Interval(Interval::from_i64(1_i64)),
-            Value::Interval(Interval::from_i64(2_i64)),
-            Value::Interval(Interval::from_i64(3_i64)),
+            Value::IntervalDayTime(IntervalDayTime::from_i64(1_i64)),
+            Value::IntervalDayTime(IntervalDayTime::from_i64(2_i64)),
+            Value::IntervalDayTime(IntervalDayTime::from_i64(3_i64)),
         ];
         assert_eq!(expect, actual);
 
@@ -1607,9 +1690,9 @@ mod tests {
             },
         );
         let expect = vec![
-            Value::Interval(Interval::from_month_day_nano(1, 2, 3)),
-            Value::Interval(Interval::from_month_day_nano(5, 6, 7)),
-            Value::Interval(Interval::from_month_day_nano(9, 10, 11)),
+            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(1, 2, 3)),
+            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(5, 6, 7)),
+            Value::IntervalMonthDayNano(IntervalMonthDayNano::new(9, 10, 11)),
         ];
         assert_eq!(expect, actual);
     }

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 extension: HashMap<String, Vec<u8>>,
+    pub extensions: HashMap<String, Vec<u8>>,
 }
 
 impl RegionResponse {
     pub fn from_region_response(region_response: RegionResponseV1) -> Self {
         Self {
             affected_rows: region_response.affected_rows as _,
-            extension: region_response.extension,
+            extensions: region_response.extensions,
         }
     }
 
@@ -36,7 +36,7 @@ impl RegionResponse {
     pub fn new(affected_rows: AffectedRows) -> Self {
         Self {
             affected_rows,
-            extension: Default::default(),
+            extensions: Default::default(),
         }
     }
 }

src/api/src/v1/column_def.rs

@@ -15,8 +15,10 @@
 use std::collections::HashMap;
 
 use datatypes::schema::{
-    ColumnDefaultConstraint, ColumnSchema, FulltextOptions, COMMENT_KEY, FULLTEXT_KEY,
+    ColumnDefaultConstraint, ColumnSchema, FulltextAnalyzer, FulltextOptions, SkippingIndexType,
+    COMMENT_KEY, FULLTEXT_KEY, INVERTED_INDEX_KEY, SKIPPING_INDEX_KEY,
 };
+use greptime_proto::v1::{Analyzer, SkippingIndexType as PbSkippingIndexType};
 use snafu::ResultExt;
 
 use crate::error::{self, Result};
@@ -25,13 +27,15 @@ use crate::v1::{ColumnDef, ColumnOptions, SemanticType};
 
 /// Key used to store fulltext options in gRPC column options.
 const FULLTEXT_GRPC_KEY: &str = "fulltext";
+/// Key used to store inverted index options in gRPC column options.
+const INVERTED_INDEX_GRPC_KEY: &str = "inverted_index";
+/// Key used to store skip index options in gRPC column options.
+const SKIPPING_INDEX_GRPC_KEY: &str = "skipping_index";
 
 /// 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,
-        column_def.datatype_extension.clone(),
-    )?;
+    let data_type =
+        ColumnDataTypeWrapper::try_new(column_def.data_type, column_def.datatype_extension)?;
 
     let constraint = if column_def.default_constraint.is_empty() {
         None
@@ -49,10 +53,16 @@ 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());
+    if let Some(options) = column_def.options.as_ref() {
+        if let Some(fulltext) = options.options.get(FULLTEXT_GRPC_KEY) {
+            metadata.insert(FULLTEXT_KEY.to_string(), fulltext.to_owned());
+        }
+        if let Some(inverted_index) = options.options.get(INVERTED_INDEX_GRPC_KEY) {
+            metadata.insert(INVERTED_INDEX_KEY.to_string(), inverted_index.to_owned());
+        }
+        if let Some(skipping_index) = options.options.get(SKIPPING_INDEX_GRPC_KEY) {
+            metadata.insert(SKIPPING_INDEX_KEY.to_string(), skipping_index.to_owned());
+        }
     }
 
     ColumnSchema::new(&column_def.name, data_type.into(), column_def.is_nullable)
@@ -70,7 +80,17 @@ pub fn options_from_column_schema(column_schema: &ColumnSchema) -> Option<Column
     if let Some(fulltext) = column_schema.metadata().get(FULLTEXT_KEY) {
         options
             .options
-            .insert(FULLTEXT_GRPC_KEY.to_string(), fulltext.to_string());
+            .insert(FULLTEXT_GRPC_KEY.to_string(), fulltext.to_owned());
+    }
+    if let Some(inverted_index) = column_schema.metadata().get(INVERTED_INDEX_KEY) {
+        options
+            .options
+            .insert(INVERTED_INDEX_GRPC_KEY.to_string(), inverted_index.clone());
+    }
+    if let Some(skipping_index) = column_schema.metadata().get(SKIPPING_INDEX_KEY) {
+        options
+            .options
+            .insert(SKIPPING_INDEX_GRPC_KEY.to_string(), skipping_index.clone());
     }
 
     (!options.options.is_empty()).then_some(options)
@@ -80,7 +100,7 @@ pub fn options_from_column_schema(column_schema: &ColumnSchema) -> Option<Column
 pub fn contains_fulltext(options: &Option<ColumnOptions>) -> bool {
     options
         .as_ref()
-        .map_or(false, |o| o.options.contains_key(FULLTEXT_GRPC_KEY))
+        .is_some_and(|o| o.options.contains_key(FULLTEXT_GRPC_KEY))
 }
 
 /// Tries to construct a `ColumnOptions` from the given `FulltextOptions`.
@@ -93,6 +113,21 @@ pub fn options_from_fulltext(fulltext: &FulltextOptions) -> Result<Option<Column
     Ok((!options.options.is_empty()).then_some(options))
 }
 
+/// Tries to construct a `FulltextAnalyzer` from the given analyzer.
+pub fn as_fulltext_option(analyzer: Analyzer) -> FulltextAnalyzer {
+    match analyzer {
+        Analyzer::English => FulltextAnalyzer::English,
+        Analyzer::Chinese => FulltextAnalyzer::Chinese,
+    }
+}
+
+/// Tries to construct a `SkippingIndexType` from the given skipping index type.
+pub fn as_skipping_index_type(skipping_index_type: PbSkippingIndexType) -> SkippingIndexType {
+    match skipping_index_type {
+        PbSkippingIndexType::BloomFilter => SkippingIndexType::BloomFilter,
+    }
+}
+
 #[cfg(test)]
 mod tests {
 
@@ -115,10 +150,13 @@ mod tests {
             comment: "test_comment".to_string(),
             datatype_extension: None,
             options: Some(ColumnOptions {
-                options: HashMap::from([(
-                    FULLTEXT_GRPC_KEY.to_string(),
-                    "{\"enable\":true}".to_string(),
-                )]),
+                options: HashMap::from([
+                    (
+                        FULLTEXT_GRPC_KEY.to_string(),
+                        "{\"enable\":true}".to_string(),
+                    ),
+                    (INVERTED_INDEX_GRPC_KEY.to_string(), "true".to_string()),
+                ]),
             }),
         };
 
@@ -139,6 +177,7 @@ mod tests {
                 ..Default::default()
             }
         );
+        assert!(schema.is_inverted_indexed());
     }
 
     #[test]
@@ -147,18 +186,23 @@ mod tests {
         let options = options_from_column_schema(&schema);
         assert!(options.is_none());
 
-        let schema = ColumnSchema::new("test", ConcreteDataType::string_datatype(), true)
+        let mut schema = ColumnSchema::new("test", ConcreteDataType::string_datatype(), true)
             .with_fulltext_options(FulltextOptions {
                 enable: true,
                 analyzer: FulltextAnalyzer::English,
                 case_sensitive: false,
             })
             .unwrap();
+        schema.set_inverted_index(true);
         let options = options_from_column_schema(&schema).unwrap();
         assert_eq!(
             options.options.get(FULLTEXT_GRPC_KEY).unwrap(),
             "{\"enable\":true,\"analyzer\":\"English\",\"case-sensitive\":false}"
         );
+        assert_eq!(
+            options.options.get(INVERTED_INDEX_GRPC_KEY).unwrap(),
+            "true"
+        );
     }
 
     #[test]

src/auth/src/common.rs

@@ -75,6 +75,16 @@ 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

@@ -89,7 +89,7 @@ impl ErrorExt for Error {
             Error::FileWatch { .. } => StatusCode::InvalidArguments,
             Error::InternalState { .. } => StatusCode::Unexpected,
             Error::Io { .. } => StatusCode::StorageUnavailable,
-            Error::AuthBackend { .. } => StatusCode::Internal,
+            Error::AuthBackend { source, .. } => source.status_code(),
 
             Error::UserNotFound { .. } => StatusCode::UserNotFound,
             Error::UnsupportedPasswordType { .. } => StatusCode::UnsupportedPasswordType,

src/auth/src/permission.rs

@@ -25,6 +25,7 @@ pub enum PermissionReq<'a> {
     GrpcRequest(&'a Request),
     SqlStatement(&'a Statement),
     PromQuery,
+    LogQuery,
     Opentsdb,
     LineProtocol,
     PromStoreWrite,

src/auth/src/tests.rs

@@ -13,9 +13,11 @@
 // limitations under the License.
 
 use common_base::secrets::ExposeSecret;
+use common_error::ext::BoxedError;
+use snafu::{OptionExt, ResultExt};
 
 use crate::error::{
-    AccessDeniedSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
+    AccessDeniedSnafu, AuthBackendSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
     UserPasswordMismatchSnafu,
 };
 use crate::user_info::DefaultUserInfo;
@@ -49,6 +51,19 @@ 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

@@ -57,6 +57,11 @@ 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>`",
         })?;
-        return match mode {
+        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

@@ -18,6 +18,7 @@ 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;
@@ -33,9 +34,10 @@ impl PermissionChecker for DummyPermissionChecker {
         match req {
             PermissionReq::GrpcRequest(_) => Ok(PermissionResp::Allow),
             PermissionReq::SqlStatement(_) => Ok(PermissionResp::Reject),
-            _ => Err(InternalState {
+            _ => InternalStateSnafu {
                 msg: "testing".to_string(),
-            }),
+            }
+            .fail(),
         }
     }
 }

src/cache/Cargo.toml

@@ -11,4 +11,3 @@ common-macro.workspace = true
 common-meta.workspace = true
 moka.workspace = true
 snafu.workspace = true
-substrait.workspace = true

src/cache/src/lib.rs

@@ -19,9 +19,9 @@ use std::time::Duration;
 
 use catalog::kvbackend::new_table_cache;
 use common_meta::cache::{
-    new_table_flownode_set_cache, new_table_info_cache, new_table_name_cache,
-    new_table_route_cache, new_view_info_cache, CacheRegistry, CacheRegistryBuilder,
-    LayeredCacheRegistryBuilder,
+    new_schema_cache, new_table_flownode_set_cache, new_table_info_cache, new_table_name_cache,
+    new_table_route_cache, new_table_schema_cache, new_view_info_cache, CacheRegistry,
+    CacheRegistryBuilder, LayeredCacheRegistryBuilder,
 };
 use common_meta::kv_backend::KvBackendRef;
 use moka::future::CacheBuilder;
@@ -37,9 +37,47 @@ pub const TABLE_INFO_CACHE_NAME: &str = "table_info_cache";
 pub const VIEW_INFO_CACHE_NAME: &str = "view_info_cache";
 pub const TABLE_NAME_CACHE_NAME: &str = "table_name_cache";
 pub const TABLE_CACHE_NAME: &str = "table_cache";
+pub const SCHEMA_CACHE_NAME: &str = "schema_cache";
+pub const TABLE_SCHEMA_NAME_CACHE_NAME: &str = "table_schema_name_cache";
 pub const TABLE_FLOWNODE_SET_CACHE_NAME: &str = "table_flownode_set_cache";
 pub const TABLE_ROUTE_CACHE_NAME: &str = "table_route_cache";
 
+/// Builds cache registry for datanode, including:
+/// - Schema cache.
+/// - Table id to schema name cache.
+pub fn build_datanode_cache_registry(kv_backend: KvBackendRef) -> CacheRegistry {
+    // Builds table id schema name cache that never expires.
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY).build();
+    let table_id_schema_cache = Arc::new(new_table_schema_cache(
+        TABLE_SCHEMA_NAME_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    // Builds schema cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let schema_cache = Arc::new(new_schema_cache(
+        SCHEMA_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    CacheRegistryBuilder::default()
+        .add_cache(table_id_schema_cache)
+        .add_cache(schema_cache)
+        .build()
+}
+
+/// Builds cache registry for frontend and datanode, including:
+/// - Table info cache
+/// - Table name cache
+/// - Table route cache
+/// - Table flow node cache
+/// - View cache
+/// - Schema cache
 pub fn build_fundamental_cache_registry(kv_backend: KvBackendRef) -> CacheRegistry {
     // Builds table info cache
     let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
@@ -95,12 +133,30 @@ pub fn build_fundamental_cache_registry(kv_backend: KvBackendRef) -> CacheRegist
         kv_backend.clone(),
     ));
 
+    // Builds schema cache
+    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
+        .time_to_live(DEFAULT_CACHE_TTL)
+        .time_to_idle(DEFAULT_CACHE_TTI)
+        .build();
+    let schema_cache = Arc::new(new_schema_cache(
+        SCHEMA_CACHE_NAME.to_string(),
+        cache,
+        kv_backend.clone(),
+    ));
+
+    let table_id_schema_cache = Arc::new(new_table_schema_cache(
+        TABLE_SCHEMA_NAME_CACHE_NAME.to_string(),
+        CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY).build(),
+        kv_backend,
+    ));
     CacheRegistryBuilder::default()
         .add_cache(table_info_cache)
         .add_cache(table_name_cache)
         .add_cache(table_route_cache)
         .add_cache(view_info_cache)
         .add_cache(table_flownode_set_cache)
+        .add_cache(schema_cache)
+        .add_cache(table_id_schema_cache)
         .build()
 }
 

src/catalog/Cargo.toml

@@ -15,22 +15,23 @@ api.workspace = true
 arrow.workspace = true
 arrow-schema.workspace = true
 async-stream.workspace = true
-async-trait = "0.1"
+async-trait.workspace = true
 bytes.workspace = true
 common-catalog.workspace = true
-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
 dashmap.workspace = true
 datafusion.workspace = true
 datatypes.workspace = true
-futures = "0.3"
+futures.workspace = true
 futures-util.workspace = true
 humantime.workspace = true
 itertools.workspace = true
@@ -38,8 +39,9 @@ lazy_static.workspace = true
 meta-client.workspace = true
 moka = { workspace = true, features = ["future", "sync"] }
 partition.workspace = true
-paste = "1.0"
+paste.workspace = true
 prometheus.workspace = true
+rustc-hash.workspace = true
 serde_json.workspace = true
 session.workspace = true
 snafu.workspace = true
@@ -47,6 +49,7 @@ sql.workspace = true
 store-api.workspace = true
 table.workspace = true
 tokio.workspace = true
+tokio-stream.workspace = true
 
 [dev-dependencies]
 cache.workspace = true
@@ -54,7 +57,5 @@ catalog = { workspace = true, features = ["testing"] }
 chrono.workspace = true
 common-meta = { workspace = true, features = ["testing"] }
 common-query = { workspace = true, features = ["testing"] }
-common-test-util.workspace = true
-log-store.workspace = true
 object-store.workspace = true
 tokio.workspace = true

src/catalog/src/error.rs

@@ -50,13 +50,27 @@ pub enum Error {
         source: BoxedError,
     },
 
-    #[snafu(display("Failed to list nodes in cluster: {source}"))]
+    #[snafu(display("Failed to list nodes in cluster"))]
     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 flow stats"))]
+    ListFlowStats {
+        #[snafu(implicit)]
+        location: Location,
+        source: BoxedError,
+    },
+
     #[snafu(display("Failed to list flows in catalog {catalog}"))]
     ListFlows {
         #[snafu(implicit)]
@@ -82,8 +96,27 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display("Failed to re-compile script due to internal error"))]
-    CompileScriptInternal {
+    #[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,
@@ -97,13 +130,6 @@ 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,
@@ -152,6 +178,12 @@ pub enum Error {
         location: Location,
     },
 
+    #[snafu(display("Partition manager not found, it's not expected."))]
+    PartitionManagerNotFound {
+        #[snafu(implicit)]
+        location: Location,
+    },
+
     #[snafu(display("Failed to find table partitions"))]
     FindPartitions { source: partition::error::Error },
 
@@ -186,13 +218,6 @@ 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)]
@@ -280,7 +305,10 @@ impl ErrorExt for Error {
             | Error::FindRegionRoutes { .. }
             | Error::CacheNotFound { .. }
             | Error::CastManager { .. }
-            | Error::Json { .. } => StatusCode::Unexpected,
+            | Error::Json { .. }
+            | Error::GetInformationExtension { .. }
+            | Error::PartitionManagerNotFound { .. }
+            | Error::ProcedureIdNotFound { .. } => StatusCode::Unexpected,
 
             Error::ViewPlanColumnsChanged { .. } => StatusCode::InvalidArguments,
 
@@ -288,8 +316,6 @@ impl ErrorExt for Error {
 
             Error::FlowInfoNotFound { .. } => StatusCode::FlowNotFound,
 
-            Error::SystemCatalog { .. } => StatusCode::StorageUnavailable,
-
             Error::UpgradeWeakCatalogManagerRef { .. } => StatusCode::Internal,
 
             Error::CreateRecordBatch { source, .. } => source.status_code(),
@@ -299,17 +325,18 @@ impl ErrorExt for Error {
             | Error::ListNodes { source, .. }
             | Error::ListSchemas { source, .. }
             | Error::ListTables { source, .. }
-            | Error::ListFlows { source, .. } => source.status_code(),
+            | Error::ListFlows { source, .. }
+            | Error::ListFlowStats { 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(),
 
-            Error::CompileScriptInternal { source, .. } | Error::Internal { source, .. } => {
-                source.status_code()
-            }
+            Error::Internal { source, .. } => source.status_code(),
 
             Error::QueryAccessDenied { .. } => StatusCode::AccessDenied,
             Error::Datafusion { error, .. } => datafusion_status_code::<Self>(error, None),
@@ -338,27 +365,6 @@ 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 {