test: more reduce tests

* feat: add integration-test for interval type.

* chore: add two cases.

* chore: cr

* chore: Field to Column

.cargo/config.toml

@@ -1,2 +1,20 @@
 [target.aarch64-unknown-linux-gnu]
 linker = "aarch64-linux-gnu-gcc"
+
+[alias]
+sqlness = "run --bin sqlness-runner --"
+
+
+[build]
+rustflags = [
+    # lints
+    # TODO: use lint configuration in cargo https://github.com/rust-lang/cargo/issues/5034
+    "-Wclippy::print_stdout",
+    "-Wclippy::print_stderr",
+    "-Wclippy::implicit_clone",
+
+    # It seems clippy has made a false positive decision here when upgrading rust toolchain to
+    # nightly-2023-08-07, we do need it to be borrowed mutably.
+    # Allow it for now; try disallow it when the toolchain is upgraded in the future.
+    "-Aclippy::needless_pass_by_ref_mut",
+]

.config/nextest.toml

@@ -1,2 +1,3 @@
 [profile.default]
 slow-timeout = { period = "60s", terminate-after = 3, grace-period = "30s" }
+retries = { backoff = "exponential", count = 3, delay = "10s", jitter = true }

.dockerignore

@@ -20,6 +20,3 @@ out/
 
 # Rust
 target/
-
-# Git
-.git

.env.example

@@ -2,3 +2,20 @@
 GT_S3_BUCKET=S3 bucket
 GT_S3_ACCESS_KEY_ID=S3 access key id
 GT_S3_ACCESS_KEY=S3 secret access key
+GT_S3_ENDPOINT_URL=S3 endpoint url
+GT_S3_REGION=S3 region
+# Settings for oss test
+GT_OSS_BUCKET=OSS bucket
+GT_OSS_ACCESS_KEY_ID=OSS access key id
+GT_OSS_ACCESS_KEY=OSS access key
+GT_OSS_ENDPOINT=OSS endpoint
+# Settings for azblob test
+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 
+GT_GCS_SCOPE  = GCS scope
+GT_GCS_CREDENTIAL_PATH = GCS credential path 
+GT_GCS_ENDPOINT = GCS end point

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -81,6 +81,5 @@ body:
         Please walk us through and provide steps and details on how
         to reproduce the issue. If possible, provide scripts that we
         can run to trigger the bug.
-      render: bash
     validations:
       required: true

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

@@ -0,0 +1,93 @@
+name: Build and push dev-builder image
+description: Build and push dev-builder image to DockerHub and ACR
+inputs:
+  dockerhub-image-registry:
+    description: The dockerhub image registry to store the images
+    required: false
+    default: docker.io
+  dockerhub-image-registry-username:
+    description: The dockerhub username to login to the image registry
+    required: true
+  dockerhub-image-registry-token:
+    description: The dockerhub token to login to the image registry
+    required: true
+  dockerhub-image-namespace:
+    description: The dockerhub namespace of the image registry to store the images
+    required: false
+    default: greptime
+  acr-image-registry:
+    description: The ACR image registry to store the images
+    required: true
+  acr-image-registry-username:
+    description: The ACR username to login to the image registry
+    required: true
+  acr-image-registry-password:
+    description: The ACR password to login to the image registry
+    required: true
+  acr-image-namespace:
+    description: The ACR namespace of the image registry to store the images
+    required: false
+    default: greptime
+  version:
+    description: Version of the dev-builder
+    required: false
+    default: latest
+runs:
+  using: composite
+  steps:
+    - name: Login to Dockerhub
+      uses: docker/login-action@v2
+      with:
+        registry: ${{ inputs.dockerhub-image-registry }}
+        username: ${{ inputs.dockerhub-image-registry-username }}
+        password: ${{ inputs.dockerhub-image-registry-token }}
+
+    - name: Build and push ubuntu dev builder image to dockerhub
+      shell: bash
+      run:
+        make dev-builder \
+        BASE_IMAGE=ubuntu \
+        BUILDX_MULTI_PLATFORM_BUILD=true \
+        IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
+        IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
+        IMAGE_TAG=${{ inputs.version }}
+
+    - name: Build and push centos dev builder image to dockerhub
+      shell: bash
+      run:
+        make dev-builder \
+        BASE_IMAGE=centos \
+        BUILDX_MULTI_PLATFORM_BUILD=true \
+        IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
+        IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
+        IMAGE_TAG=${{ inputs.version }}
+
+    - name: Login to ACR
+      uses: docker/login-action@v2
+      continue-on-error: true
+      with:
+        registry: ${{ inputs.acr-image-registry }}
+        username: ${{ inputs.acr-image-registry-username }}
+        password: ${{ inputs.acr-image-registry-password }}
+
+    - name: Build and push ubuntu dev builder image to ACR
+      shell: bash
+      continue-on-error: true
+      run: # buildx will cache the images that already built, so it will not take long time to build the images again.
+        make dev-builder \
+        BASE_IMAGE=ubuntu \
+        BUILDX_MULTI_PLATFORM_BUILD=true \
+        IMAGE_REGISTRY=${{ inputs.acr-image-registry }} \
+        IMAGE_NAMESPACE=${{ inputs.acr-image-namespace }} \
+        IMAGE_TAG=${{ inputs.version }}
+
+    - name: Build and push centos dev builder image to ACR
+      shell: bash
+      continue-on-error: true
+      run: # buildx will cache the images that already built, so it will not take long time to build the images again.
+        make dev-builder \
+        BASE_IMAGE=centos \
+        BUILDX_MULTI_PLATFORM_BUILD=true \
+        IMAGE_REGISTRY=${{ inputs.acr-image-registry }} \
+        IMAGE_NAMESPACE=${{ inputs.acr-image-namespace }} \
+        IMAGE_TAG=${{ inputs.version }}

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

@@ -0,0 +1,67 @@
+name: Build greptime binary
+description: Build and upload the single linux artifact
+inputs:
+  base-image:
+    description: Base image to build greptime
+    required: true
+  features:
+    description: Cargo features to build
+    required: true
+  cargo-profile:
+    description: Cargo profile to build
+    required: true
+  artifacts-dir:
+    description: Directory to store artifacts
+    required: true
+  version:
+    description: Version of the artifact
+    required: true
+  release-to-s3-bucket:
+    description: S3 bucket to store released artifacts
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+  upload-to-s3:
+    description: Upload to S3
+    required: false
+    default: 'true'
+  upload-latest-artifacts:
+    description: Upload the latest artifacts to S3
+    required: false
+    default: 'true'
+  working-dir:
+    description: Working directory to build the artifacts
+    required: false
+    default: .
+runs:
+  using: composite
+  steps:
+    - name: Build greptime binary
+      shell: bash
+      run: |
+        cd ${{ inputs.working-dir }} && \
+        make build-by-dev-builder \
+          CARGO_PROFILE=${{ inputs.cargo-profile }} \
+          FEATURES=${{ inputs.features }} \
+          BASE_IMAGE=${{ inputs.base-image }}
+
+    - name: Upload artifacts
+      uses: ./.github/actions/upload-artifacts
+      with:
+        artifacts-dir: ${{ inputs.artifacts-dir }}
+        target-file: ./target/${{ inputs.cargo-profile }}/greptime
+        version: ${{ inputs.version }}
+        release-to-s3-bucket: ${{ inputs.release-to-s3-bucket }}
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+        upload-to-s3: ${{ inputs.upload-to-s3 }}
+        upload-latest-artifacts: ${{ inputs.upload-latest-artifacts }}
+        working-dir: ${{ inputs.working-dir }}

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

@@ -0,0 +1,104 @@
+name: Build greptime images
+description: Build and push greptime images
+inputs:
+  image-registry:
+    description: The image registry to store the images
+    required: true
+  image-registry-username:
+    description: The username to login to the image registry
+    required: true
+  image-registry-password:
+    description: The password to login to the image registry
+    required: true
+  amd64-artifact-name:
+    description: The name of the amd64 artifact for building images
+    required: true
+  arm64-artifact-name:
+    description: The name of the arm64 artifact for building images
+    required: false
+    default: ""
+  image-namespace:
+    description: The namespace of the image registry to store the images
+    required: true
+  image-name:
+    description: The name of the image to build
+    required: true
+  image-tag:
+    description: The tag of the image to build
+    required: true
+  docker-file:
+    description: The path to the Dockerfile to build
+    required: true
+  platforms:
+    description: The supported platforms to build the image
+    required: true
+  push-latest-tag:
+    description: Whether to push the latest tag
+    required: false
+    default: 'true'
+runs:
+  using: composite
+  steps:
+    - name: Login to image registry
+      uses: docker/login-action@v2
+      with:
+        registry: ${{ inputs.image-registry }}
+        username: ${{ inputs.image-registry-username }}
+        password: ${{ inputs.image-registry-password }}
+
+    - name: Set up qemu for multi-platform builds
+      uses: docker/setup-qemu-action@v2
+
+    - name: Set up buildx
+      uses: docker/setup-buildx-action@v2
+
+    - name: Download amd64 artifacts
+      uses: actions/download-artifact@v3
+      with:
+        name: ${{ inputs.amd64-artifact-name }}
+
+    - name: Unzip the amd64 artifacts
+      shell: bash
+      run: |
+        tar xvf ${{ inputs.amd64-artifact-name }}.tar.gz && \
+        rm ${{ inputs.amd64-artifact-name }}.tar.gz && \
+        rm -rf amd64 && \
+        mv ${{ inputs.amd64-artifact-name }} amd64
+
+    - name: Download arm64 artifacts
+      uses: actions/download-artifact@v3
+      if: ${{ inputs.arm64-artifact-name }}
+      with:
+        name: ${{ inputs.arm64-artifact-name }}
+
+    - name: Unzip the arm64 artifacts
+      shell: bash
+      if: ${{ inputs.arm64-artifact-name }}
+      run: |
+        tar xvf ${{ inputs.arm64-artifact-name }}.tar.gz && \
+        rm ${{ inputs.arm64-artifact-name }}.tar.gz && \
+        rm -rf arm64 && \
+        mv ${{ inputs.arm64-artifact-name }} arm64
+
+    - name: Build and push images(without latest) for amd64 and arm64
+      if: ${{ inputs.push-latest-tag == 'false' }}
+      uses: docker/build-push-action@v3
+      with:
+        context: .
+        file: ${{ inputs.docker-file }}
+        push: true
+        platforms: ${{ inputs.platforms }}
+        tags: |
+          ${{ inputs.image-registry }}/${{ inputs.image-namespace }}/${{ inputs.image-name }}:${{ inputs.image-tag }}
+
+    - name: Build and push images for amd64 and arm64
+      if: ${{ inputs.push-latest-tag == 'true' }}
+      uses: docker/build-push-action@v3
+      with:
+        context: .
+        file: ${{ inputs.docker-file }}
+        push: true
+        platforms: ${{ inputs.platforms }}
+        tags: |
+          ${{ inputs.image-registry }}/${{ inputs.image-namespace }}/${{ inputs.image-name }}:latest
+          ${{ inputs.image-registry }}/${{ inputs.image-namespace }}/${{ inputs.image-name }}:${{ inputs.image-tag }}

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

@@ -0,0 +1,62 @@
+name: Group for building greptimedb images
+description: Group for building greptimedb images
+inputs:
+  image-registry:
+    description: The image registry to store the images
+    required: true
+  image-namespace:
+    description: The namespace of the image registry to store the images
+    required: true
+  image-name:
+    description: The name of the image to build
+    required: false
+    default: greptimedb
+  image-registry-username:
+    description: The username to login to the image registry
+    required: true
+  image-registry-password:
+    description: The password to login to the image registry
+    required: true
+  version:
+    description: Version of the artifact
+    required: true
+  push-latest-tag:
+    description: Whether to push the latest tag
+    required: false
+    default: 'true'
+  dev-mode:
+    description: Enable dev mode, only build standard greptime
+    required: false
+    default: 'false'
+runs:
+  using: composite
+  steps:
+    - name: Build and push standard images to dockerhub
+      uses: ./.github/actions/build-greptime-images
+      with: # The image will be used as '${{ inputs.image-registry }}/${{ inputs.image-namespace }}/${{ inputs.image-name }}:${{ inputs.version }}'
+        image-registry: ${{ inputs.image-registry }}
+        image-namespace: ${{ inputs.image-namespace }}
+        image-registry-username: ${{ inputs.image-registry-username }}
+        image-registry-password: ${{ inputs.image-registry-password }}
+        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 }}
+        platforms: linux/amd64,linux/arm64
+        push-latest-tag: ${{ inputs.push-latest-tag }}
+
+    - name: Build and push centos images to dockerhub
+      if: ${{ inputs.dev-mode == 'false' }}
+      uses: ./.github/actions/build-greptime-images
+      with:
+        image-registry: ${{ inputs.image-registry }}
+        image-namespace: ${{ inputs.image-namespace }}
+        image-registry-username: ${{ inputs.image-registry-username }}
+        image-registry-password: ${{ inputs.image-registry-password }}
+        image-name: ${{ inputs.image-name }}-centos
+        image-tag: ${{ inputs.version }}
+        docker-file: docker/ci/centos/Dockerfile
+        amd64-artifact-name: greptime-linux-amd64-centos-${{ inputs.version }}
+        platforms: linux/amd64
+        push-latest-tag: ${{ inputs.push-latest-tag }}

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

@@ -0,0 +1,116 @@
+name: Build linux artifacts
+description: Build linux artifacts
+inputs:
+  arch:
+    description: Architecture to build
+    required: true
+  cargo-profile:
+    description: Cargo profile to build
+    required: true
+  version:
+    description: Version of the artifact
+    required: true
+  disable-run-tests:
+    description: Disable running integration tests
+    required: true
+  release-to-s3-bucket:
+    description: S3 bucket to store released artifacts
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+  dev-mode:
+    description: Enable dev mode, only build standard greptime
+    required: false
+    default: 'false'
+  upload-to-s3:
+    description: Upload to S3
+    required: false
+    default: 'true'
+  upload-latest-artifacts:
+    description: Upload the latest artifacts to S3
+    required: false
+    default: 'true'
+  working-dir:
+    description: Working directory to build the artifacts
+    required: false
+    default: .
+runs:
+  using: composite
+  steps:
+    - name: Run integration test
+      if: ${{ inputs.disable-run-tests == 'false' }}
+      shell: bash
+      # NOTE: If the BUILD_JOBS > 4, it's always OOM in EC2 instance.
+      run: |
+        cd ${{ inputs.working-dir }} && \
+        make run-it-in-container BUILD_JOBS=4
+
+    - name: Upload sqlness logs
+      if: ${{ failure() && inputs.disable-run-tests == 'false' }} # Only upload logs when the integration tests failed.
+      uses: actions/upload-artifact@v3
+      with:
+        name: sqlness-logs
+        path: /tmp/greptime-*.log
+        retention-days: 3
+
+    - name: Build standard greptime
+      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 }}
+        release-to-s3-bucket: ${{ inputs.release-to-s3-bucket }}
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+        upload-to-s3: ${{ inputs.upload-to-s3 }}
+        upload-latest-artifacts: ${{ inputs.upload-latest-artifacts }}
+        working-dir: ${{ inputs.working-dir }}
+
+    - name: Build greptime without pyo3
+      if: ${{ inputs.dev-mode == 'false' }}
+      uses: ./.github/actions/build-greptime-binary
+      with:
+        base-image: ubuntu
+        features: servers/dashboard
+        cargo-profile: ${{ inputs.cargo-profile }}
+        artifacts-dir: greptime-linux-${{ inputs.arch }}-${{ inputs.version }}
+        version: ${{ inputs.version }}
+        release-to-s3-bucket: ${{ inputs.release-to-s3-bucket }}
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+        upload-to-s3: ${{ inputs.upload-to-s3 }}
+        upload-latest-artifacts: ${{ inputs.upload-latest-artifacts }}
+        working-dir: ${{ inputs.working-dir }}
+
+    - 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
+      run: |
+        rm -rf ./target/
+
+    - name: Build greptime on centos base image
+      uses: ./.github/actions/build-greptime-binary
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build centos7 base image for amd64.
+      with:
+        base-image: centos
+        features: servers/dashboard
+        cargo-profile: ${{ inputs.cargo-profile }}
+        artifacts-dir: greptime-linux-${{ inputs.arch }}-centos-${{ inputs.version }}
+        version: ${{ inputs.version }}
+        release-to-s3-bucket: ${{ inputs.release-to-s3-bucket }}
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+        upload-to-s3: ${{ inputs.upload-to-s3 }}
+        upload-latest-artifacts: ${{ inputs.upload-latest-artifacts }}
+        working-dir: ${{ inputs.working-dir }}

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

@@ -0,0 +1,105 @@
+name: Build macos artifacts
+description: Build macos artifacts
+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
+  features:
+    description: Cargo features to build
+    required: true
+  version:
+    description: Version of the artifact
+    required: true
+  disable-run-tests:
+    description: Disable running integration tests
+    required: true
+  release-to-s3-bucket:
+    description: S3 bucket to store released artifacts
+    required: true
+  artifacts-dir:
+    description: Directory to store artifacts
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+runs:
+  using: composite
+  steps:
+    - name: Cache cargo assets
+      id: cache
+      uses: actions/cache@v3
+      with:
+        path: |
+          ~/.cargo/bin/
+          ~/.cargo/registry/index/
+          ~/.cargo/registry/cache/
+          ~/.cargo/git/db/
+          target/
+        key: ${{ inputs.arch }}-build-cargo-${{ hashFiles('**/Cargo.lock') }}
+
+    - name: Install protoc
+      shell: bash
+      run: |
+        brew install protobuf
+
+    - name: Install rust toolchain
+      uses: dtolnay/rust-toolchain@master
+      with:
+        toolchain: ${{ inputs.rust-toolchain }}
+        targets: ${{ inputs.arch }}
+
+    - name: Start etcd # For integration tests.
+      if: ${{ inputs.disable-run-tests == 'false' }}
+      shell: bash
+      run: |
+        brew install etcd && \
+        brew services start etcd
+
+    - name: Install latest nextest release # For integration tests.
+      if: ${{ inputs.disable-run-tests == 'false' }}
+      uses: taiki-e/install-action@nextest
+
+    - name: Run integration tests
+      if: ${{ inputs.disable-run-tests == 'false' }}
+      shell: bash
+      run: |
+        make test sqlness-test
+
+    - name: Upload sqlness logs
+      if: ${{ failure() }} # Only upload logs when the integration tests failed.
+      uses: actions/upload-artifact@v3
+      with:
+        name: sqlness-logs
+        path: /tmp/greptime-*.log
+        retention-days: 3
+
+    - name: Build greptime binary
+      shell: bash
+      run: |
+        make build \
+        CARGO_PROFILE=${{ inputs.cargo-profile }} \
+        FEATURES=${{ inputs.features }} \
+        TARGET=${{ inputs.arch }}
+
+    - name: Upload artifacts
+      uses: ./.github/actions/upload-artifacts
+      with:
+        artifacts-dir: ${{ inputs.artifacts-dir }}
+        target-file: target/${{ inputs.arch }}/${{ inputs.cargo-profile }}/greptime
+        version: ${{ inputs.version }}
+        release-to-s3-bucket: ${{ inputs.release-to-s3-bucket }}
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}

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

@@ -0,0 +1,50 @@
+name: Release artifacts
+description: Release artifacts
+inputs:
+  version:
+    description: Version to release
+    required: true
+runs:
+  using: composite
+  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
+    #   ...
+    - name: Download artifacts
+      uses: actions/download-artifact@v3
+
+    - name: Create git tag for release
+      if: ${{ github.event_name != 'push' }} # Meaning this is a scheduled or manual workflow.
+      shell: bash
+      run: |
+        git tag ${{ inputs.version }}
+
+    # Only publish release when the release tag is like v1.0.0, v1.0.1, v1.0.2, etc.
+    - name: Set release arguments
+      shell: bash
+      run: |
+        if [[ "${{ inputs.version }}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+          echo "prerelease=false" >> $GITHUB_ENV
+          echo "makeLatest=true" >> $GITHUB_ENV
+          echo "generateReleaseNotes=false" >> $GITHUB_ENV
+        else
+          echo "prerelease=true" >> $GITHUB_ENV
+          echo "makeLatest=false" >> $GITHUB_ENV
+          echo "generateReleaseNotes=true" >> $GITHUB_ENV
+        fi
+
+    - name: Publish release
+      uses: ncipollo/release-action@v1
+      with:
+        name: "Release ${{ inputs.version }}"
+        prerelease: ${{ env.prerelease }}
+        makeLatest: ${{ env.makeLatest }}
+        tag: ${{ inputs.version }}
+        generateReleaseNotes: ${{ env.generateReleaseNotes }}
+        allowUpdates: true
+        artifacts: |
+          **/greptime-*/*

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

@@ -0,0 +1,67 @@
+name: Start EC2 runner
+description: Start EC2 runner
+inputs:
+  runner:
+    description: The linux runner name
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+  github-token:
+    description: The GitHub token to clone private repository
+    required: false
+    default: ""
+  image-id:
+    description: The EC2 image id
+    required: true
+  security-group-id:
+    description: The EC2 security group id
+    required: true
+  subnet-id:
+    description: The EC2 subnet id
+    required: true
+outputs:
+  label:
+    description: "label"
+    value: ${{ steps.start-linux-arm64-ec2-runner.outputs.label || inputs.runner }}
+  ec2-instance-id:
+    description: "ec2-instance-id"
+    value: ${{ steps.start-linux-arm64-ec2-runner.outputs.ec2-instance-id }}
+runs:
+  using: composite
+  steps:
+    - name: Configure AWS credentials
+      if: startsWith(inputs.runner, 'ec2')
+      uses: aws-actions/configure-aws-credentials@v2
+      with:
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+
+    # The EC2 runner will use the following format:
+    # <vm-type>-<instance-type>-<arch>
+    # like 'ec2-c6a.4xlarge-amd64'.
+    - name: Get EC2 instance type
+      if: startsWith(inputs.runner, 'ec2')
+      id: get-ec2-instance-type
+      shell: bash
+      run: |
+        echo "instance-type=$(echo ${{ inputs.runner }} | cut -d'-' -f2)" >> $GITHUB_OUTPUT
+
+    - name: Start EC2 runner
+      if: startsWith(inputs.runner, 'ec2')
+      uses: machulav/ec2-github-runner@v2
+      id: start-linux-arm64-ec2-runner
+      with:
+        mode: start
+        ec2-image-id: ${{ inputs.image-id }}
+        ec2-instance-type: ${{ steps.get-ec2-instance-type.outputs.instance-type }}
+        subnet-id: ${{ inputs.subnet-id }}
+        security-group-id: ${{ inputs.security-group-id }}
+        github-token: ${{ inputs.github-token }}

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

@@ -0,0 +1,41 @@
+name: Stop EC2 runner
+description: Stop EC2 runner
+inputs:
+  label:
+    description: The linux runner name
+    required: true
+  ec2-instance-id:
+    description: The EC2 instance id
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+  github-token:
+    description: The GitHub token to clone private repository
+    required: false
+    default: ""
+runs:
+  using: composite
+  steps:
+    - name: Configure AWS credentials
+      if: ${{ inputs.label && inputs.ec2-instance-id }}
+      uses: aws-actions/configure-aws-credentials@v2
+      with:
+        aws-access-key-id: ${{ inputs.aws-access-key-id }}
+        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
+        aws-region: ${{ inputs.aws-region }}
+
+    - name: Stop EC2 runner
+      if: ${{ inputs.label && inputs.ec2-instance-id }}
+      uses: machulav/ec2-github-runner@v2
+      with:
+        mode: stop
+        label: ${{ inputs.label }}
+        ec2-instance-id: ${{ inputs.ec2-instance-id }}
+        github-token: ${{ inputs.github-token }}

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

@@ -0,0 +1,125 @@
+name: Upload artifacts
+description: Upload artifacts
+inputs:
+  artifacts-dir:
+    description: Directory to store artifacts
+    required: true
+  target-file:
+    description: The path of the target artifact
+    required: true
+  version:
+    description: Version of the artifact
+    required: true
+  release-to-s3-bucket:
+    description: S3 bucket to store released artifacts
+    required: true
+  aws-access-key-id:
+    description: AWS access key id
+    required: true
+  aws-secret-access-key:
+    description: AWS secret access key
+    required: true
+  aws-region:
+    description: AWS region
+    required: true
+  upload-to-s3:
+    description: Upload to S3
+    required: false
+    default: 'true'
+  upload-latest-artifacts:
+    description: Upload the latest artifacts to S3
+    required: false
+    default: 'true'
+  upload-max-retry-times:
+    description: Max retry times for uploading artifacts to S3
+    required: false
+    default: "20"
+  upload-retry-timeout:
+    description: Timeout for uploading artifacts to S3
+    required: false
+    default: "10" # minutes
+  working-dir:
+    description: Working directory to upload the artifacts
+    required: false
+    default: .
+runs:
+  using: composite
+  steps:
+    - name: Create artifacts directory
+      working-directory: ${{ inputs.working-dir }}
+      shell: bash
+      run: |
+        mkdir -p ${{ inputs.artifacts-dir }} && \
+        mv ${{ inputs.target-file }} ${{ inputs.artifacts-dir }}
+
+    # 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
+    - name: Compress artifacts and calculate checksum
+      working-directory: ${{ inputs.working-dir }}
+      shell: bash
+      run: |
+        tar -zcvf ${{ inputs.artifacts-dir }}.tar.gz ${{ inputs.artifacts-dir }} && \
+        echo $(shasum -a 256 ${{ inputs.artifacts-dir }}.tar.gz | cut -f1 -d' ') > ${{ inputs.artifacts-dir }}.sha256sum
+
+    # Note: The artifacts will be double zip compressed(related issue: https://github.com/actions/upload-artifact/issues/39).
+    # However, when we use 'actions/download-artifact@v3' to download the artifacts, it will be automatically unzipped.
+    - name: Upload artifacts
+      uses: actions/upload-artifact@v3
+      with:
+        name: ${{ inputs.artifacts-dir }}
+        path: ${{ inputs.working-dir }}/${{ inputs.artifacts-dir }}.tar.gz
+
+    - name: Upload checksum
+      uses: actions/upload-artifact@v3
+      with:
+        name: ${{ inputs.artifacts-dir }}.sha256sum
+        path: ${{ inputs.working-dir }}/${{ inputs.artifacts-dir }}.sha256sum
+
+    - name: Upload artifacts to S3
+      if: ${{ inputs.upload-to-s3 == 'true' }}
+      uses: nick-invision/retry@v2
+      env:
+        AWS_ACCESS_KEY_ID: ${{ inputs.aws-access-key-id }}
+        AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-secret-access-key }}
+        AWS_DEFAULT_REGION: ${{ inputs.aws-region }}
+      with:
+        max_attempts: ${{ inputs.upload-max-retry-times }}
+        timeout_minutes: ${{ inputs.upload-retry-timeout }}
+        # The bucket layout will be:
+        # releases/greptimedb
+        # ├── v0.1.0
+        # │   ├── greptime-darwin-amd64-pyo3-v0.1.0.sha256sum
+        # │   └── greptime-darwin-amd64-pyo3-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
+        command: |
+          cd ${{ inputs.working-dir }} && \
+          aws s3 cp \
+            ${{ inputs.artifacts-dir }}.tar.gz \
+            s3://${{ inputs.release-to-s3-bucket }}/releases/greptimedb/${{ inputs.version }}/${{ inputs.artifacts-dir }}.tar.gz && \
+          aws s3 cp \
+            ${{ inputs.artifacts-dir }}.sha256sum \
+            s3://${{ inputs.release-to-s3-bucket }}/releases/greptimedb/${{ inputs.version }}/${{ inputs.artifacts-dir }}.sha256sum
+
+    - name: Upload latest artifacts to S3
+      if: ${{ inputs.upload-to-s3 == 'true' && inputs.upload-latest-artifacts == 'true' }} # We'll also upload the latest artifacts to S3 in the scheduled and formal release.
+      uses: nick-invision/retry@v2
+      env:
+        AWS_ACCESS_KEY_ID: ${{ inputs.aws-access-key-id }}
+        AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-secret-access-key }}
+        AWS_DEFAULT_REGION: ${{ inputs.aws-region }}
+      with:
+        max_attempts: ${{ inputs.upload-max-retry-times }}
+        timeout_minutes: ${{ inputs.upload-retry-timeout }}
+        command: |
+          cd ${{ inputs.working-dir }} && \
+          aws s3 cp \
+            ${{ inputs.artifacts-dir }}.tar.gz \
+            s3://${{ inputs.release-to-s3-bucket }}/releases/greptimedb/latest/${{ inputs.artifacts-dir }}.tar.gz && \
+          aws s3 cp \
+            ${{ inputs.artifacts-dir }}.sha256sum \
+            s3://${{ inputs.release-to-s3-bucket }}/releases/greptimedb/latest/${{ inputs.artifacts-dir }}.sha256sum

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

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

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

@@ -1,10 +1,12 @@
 {
-  "LABEL": {
-    "name": "Invalid PR Title",
-    "color": "B60205"
-  },
-  "CHECKS": {
-    "regexp": "^(feat|fix|test|refactor|chore|style|docs|perf|build|ci|revert)(\\(.*\\))?:.*",
-    "ignoreLabels" : ["ignore-title"]
-  }
+    "LABEL": {
+        "name": "Invalid PR Title",
+        "color": "B60205"
+    },
+    "CHECKS": {
+        "regexp": "^(feat|fix|test|refactor|chore|style|docs|perf|build|ci|revert)(\\(.*\\))?\\!?:.*",
+        "ignoreLabels": [
+            "ignore-title"
+        ]
+    }
 }

.github/scripts/create-version.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+
+set -e
+
+# - If it's a tag push release, the version is the tag name(${{ github.ref_name }});
+# - If it's a scheduled release, the version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-$buildTime', like 'v0.2.0-nightly-20230313';
+# - If it's a manual release, the version is '${{ env.NEXT_RELEASE_VERSION }}-$(git rev-parse --short HEAD)-YYYYMMDDSS', like 'v0.2.0-e5b243c-2023071245';
+# - If it's a nightly build, the version is 'nightly-YYYYMMDD-$(git rev-parse --short HEAD)', like 'nightly-20230712-e5b243c'.
+# create_version ${GIHUB_EVENT_NAME} ${NEXT_RELEASE_VERSION} ${NIGHTLY_RELEASE_PREFIX}
+function create_version() {
+  # Read from envrionment variables.
+  if [ -z "$GITHUB_EVENT_NAME" ]; then
+      echo "GITHUB_EVENT_NAME is empty"
+      exit 1
+  fi
+
+  if [ -z "$NEXT_RELEASE_VERSION" ]; then
+      echo "NEXT_RELEASE_VERSION is empty"
+      exit 1
+  fi
+
+  if [ -z "$NIGHTLY_RELEASE_PREFIX" ]; then
+      echo "NIGHTLY_RELEASE_PREFIX is empty"
+      exit 1
+  fi
+
+  # Reuse $NEXT_RELEASE_VERSION to identify whether it's a nightly build.
+  # It will be like 'nigtly-20230808-7d0d8dc6'.
+  if [ "$NEXT_RELEASE_VERSION" = nightly ]; then
+    echo "$NIGHTLY_RELEASE_PREFIX-$(date "+%Y%m%d")-$(git rev-parse --short HEAD)"
+    exit 0
+  fi
+
+  # Reuse $NEXT_RELEASE_VERSION to identify whether it's a dev build.
+  # It will be like 'dev-2023080819-f0e7216c'.
+  if [ "$NEXT_RELEASE_VERSION" = dev ]; then
+    if [ -z "$COMMIT_SHA" ]; then
+      echo "COMMIT_SHA is empty in dev build"
+      exit 1
+    fi
+    echo "dev-$(date "+%Y%m%d-%s")-$(echo "$COMMIT_SHA" | cut -c1-8)"
+    exit 0
+  fi
+
+  # Note: Only output 'version=xxx' to stdout when everything is ok, so that it can be used in GitHub Actions Outputs.
+  if [ "$GITHUB_EVENT_NAME" = push ]; then
+    if [ -z "$GITHUB_REF_NAME" ]; then
+      echo "GITHUB_REF_NAME is empty in push event"
+      exit 1
+    fi
+    echo "$GITHUB_REF_NAME"
+  elif [ "$GITHUB_EVENT_NAME" = workflow_dispatch ]; then
+    echo "$NEXT_RELEASE_VERSION-$(git rev-parse --short HEAD)-$(date "+%Y%m%d-%s")"
+  elif [ "$GITHUB_EVENT_NAME" = schedule ]; then
+    echo "$NEXT_RELEASE_VERSION-$NIGHTLY_RELEASE_PREFIX-$(date "+%Y%m%d")"
+  else
+    echo "Unsupported GITHUB_EVENT_NAME: $GITHUB_EVENT_NAME"
+    exit 1
+  fi
+}
+
+# You can run as following examples:
+#  GITHUB_EVENT_NAME=push NEXT_RELEASE_VERSION=v0.4.0 NIGHTLY_RELEASE_PREFIX=nigtly GITHUB_REF_NAME=v0.3.0 ./create-version.sh
+#  GITHUB_EVENT_NAME=workflow_dispatch NEXT_RELEASE_VERSION=v0.4.0 NIGHTLY_RELEASE_PREFIX=nigtly ./create-version.sh
+#  GITHUB_EVENT_NAME=schedule NEXT_RELEASE_VERSION=v0.4.0 NIGHTLY_RELEASE_PREFIX=nigtly ./create-version.sh
+#  GITHUB_EVENT_NAME=schedule NEXT_RELEASE_VERSION=nightly NIGHTLY_RELEASE_PREFIX=nigtly ./create-version.sh
+#  GITHUB_EVENT_NAME=workflow_dispatch COMMIT_SHA=f0e7216c4bb6acce9b29a21ec2d683be2e3f984a NEXT_RELEASE_VERSION=dev NIGHTLY_RELEASE_PREFIX=nigtly ./create-version.sh
+create_version

.github/workflows/apidoc.yml

@@ -0,0 +1,42 @@
+on:
+  push:
+    branches:
+      - develop
+    paths-ignore:
+      - 'docs/**'
+      - 'config/**'
+      - '**.md'
+      - '.dockerignore'
+      - 'docker/**'
+      - '.gitignore'
+
+name: Build API docs
+
+env:
+  RUST_TOOLCHAIN: nightly-2023-08-07
+
+jobs:
+  apidoc:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: arduino/setup-protoc@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+    - uses: dtolnay/rust-toolchain@master
+      with:
+        toolchain: ${{ env.RUST_TOOLCHAIN }}
+    - run: cargo doc --workspace --no-deps --document-private-items
+    - run: |
+        cat <<EOF > target/doc/index.html
+        <!DOCTYPE html>
+        <html>
+        <head>
+        <meta http-equiv="refresh" content="0; url='greptime/'" />
+        </head>
+        <body></body></html>
+        EOF
+    - name: Publish dist directory
+      uses: JamesIves/github-pages-deploy-action@v4
+      with:
+        folder: target/doc

.github/workflows/coverage.yml

@@ -1,70 +0,0 @@
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-  push:
-    branches:
-      - "main"
-      - "develop"
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-  workflow_dispatch:
-
-name: Code coverage
-
-env:
-  RUST_TOOLCHAIN: nightly-2022-12-20
-
-jobs:
-  coverage:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-latest-8-cores
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v3
-      - uses: arduino/setup-protoc@v1
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: KyleMayes/install-llvm-action@v1
-        with:
-          version: "14.0"
-      - name: Install toolchain
-        uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-          components: llvm-tools-preview
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-      - 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: Collect coverage data
-        run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info
-        env:
-          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
-          RUST_BACKTRACE: 1
-          CARGO_INCREMENTAL: 0
-          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
-          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
-          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
-          UNITTEST_LOG_DIR: "__unittest_logs"
-      - name: Codecov upload
-        uses: codecov/codecov-action@v2
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          files: ./lcov.info
-          flags: rust
-          fail_ci_if_error: true
-          verbose: true

.github/workflows/dev-build.yml

@@ -0,0 +1,344 @@
+# Development build only build the debug version of the artifacts manually.
+name: GreptimeDB Development Build
+
+on:
+  workflow_dispatch: # Allows you to run this workflow manually.
+    inputs:
+      repository:
+        description: The public repository to build
+        required: false
+        default: GreptimeTeam/greptimedb
+      commit: # Note: We only pull the source code and use the current workflow to build the artifacts.
+        description: The commit to build
+        required: true
+      linux_amd64_runner:
+        type: choice
+        description: The runner uses to build linux-amd64 artifacts
+        default: ec2-c6i.4xlarge-amd64
+        options:
+          - ubuntu-latest
+          - ubuntu-latest-8-cores
+          - ubuntu-latest-16-cores
+          - ubuntu-latest-32-cores
+          - ubuntu-latest-64-cores
+          - ec2-c6i.xlarge-amd64 # 4C8G
+          - ec2-c6i.2xlarge-amd64 # 8C16G
+          - ec2-c6i.4xlarge-amd64 # 16C32G
+          - ec2-c6i.8xlarge-amd64 # 32C64G
+          - ec2-c6i.16xlarge-amd64 # 64C128G
+      linux_arm64_runner:
+        type: choice
+        description: The runner uses to build linux-arm64 artifacts
+        default: ec2-c6g.4xlarge-arm64
+        options:
+          - ec2-c6g.xlarge-arm64 # 4C8G
+          - ec2-c6g.2xlarge-arm64 # 8C16G
+          - ec2-c6g.4xlarge-arm64 # 16C32G
+          - ec2-c6g.8xlarge-arm64 # 32C64G
+          - ec2-c6g.16xlarge-arm64 # 64C128G
+      skip_test:
+        description: Do not run integration tests during the build
+        type: boolean
+        default: true
+      build_linux_amd64_artifacts:
+        type: boolean
+        description: Build linux-amd64 artifacts
+        required: false
+        default: true
+      build_linux_arm64_artifacts:
+        type: boolean
+        description: Build linux-arm64 artifacts
+        required: false
+        default: true
+      release_images:
+        type: boolean
+        description: Build and push images to DockerHub and ACR
+        required: false
+        default: true
+
+# Use env variables to control all the release process.
+env:
+  CARGO_PROFILE: nightly
+
+  # Controls whether to run tests, include unit-test, integration-test and sqlness.
+  DISABLE_RUN_TESTS: ${{ inputs.skip_test || vars.DEFAULT_SKIP_TEST }}
+
+  # Always use 'dev' to indicate it's the dev build.
+  NEXT_RELEASE_VERSION: dev
+
+  NIGHTLY_RELEASE_PREFIX: nightly
+
+  # Use the different image name to avoid conflict with the release images.
+  IMAGE_NAME: greptimedb-dev
+
+  # The source code will check out in the following path: '${WORKING_DIR}/dev/greptime'.
+  CHECKOUT_GREPTIMEDB_PATH: dev/greptimedb
+
+jobs:
+  allocate-runners:
+    name: Allocate runners
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: ubuntu-latest
+    outputs:
+      linux-amd64-runner: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-arm64-runner: ${{ steps.start-linux-arm64-runner.outputs.label }}
+
+      # The following EC2 resource id will be used for resource releasing.
+      linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-amd64-ec2-runner-instance-id: ${{ steps.start-linux-amd64-runner.outputs.ec2-instance-id }}
+      linux-arm64-ec2-runner-label: ${{ steps.start-linux-arm64-runner.outputs.label }}
+      linux-arm64-ec2-runner-instance-id: ${{ steps.start-linux-arm64-runner.outputs.ec2-instance-id }}
+
+      # The 'version' use as the global tag name of the release workflow.
+      version: ${{ steps.create-version.outputs.version }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Create version
+        id: create-version
+        run: |
+          version=$(./.github/scripts/create-version.sh) && \
+          echo $version && \
+          echo "version=$version" >> $GITHUB_OUTPUT
+        env:
+          GITHUB_EVENT_NAME: ${{ github.event_name }}
+          GITHUB_REF_NAME: ${{ github.ref_name }}
+          COMMIT_SHA: ${{ inputs.commit }}
+          NEXT_RELEASE_VERSION: ${{ env.NEXT_RELEASE_VERSION }}
+          NIGHTLY_RELEASE_PREFIX: ${{ env.NIGHTLY_RELEASE_PREFIX }}
+
+      - name: Allocate linux-amd64 runner
+        if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-amd64-runner
+        with:
+          runner: ${{ inputs.linux_amd64_runner || vars.DEFAULT_AMD64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_AMD64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+      - name: Allocate linux-arm64 runner
+        if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-arm64-runner
+        with:
+          runner: ${{ inputs.linux_arm64_runner || vars.DEFAULT_ARM64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_ARM64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+  build-linux-amd64-artifacts:
+    name: Build linux-amd64 artifacts
+    if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-amd64-runner }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Checkout greptimedb
+        uses: actions/checkout@v3
+        with:
+          repository: ${{ inputs.repository }}
+          ref: ${{ inputs.commit }}
+          path: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: amd64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          dev-mode: true # Only build the standard greptime binary.
+          upload-to-s3: false # No need to upload to S3.
+          working-dir: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+
+  build-linux-arm64-artifacts:
+    name: Build linux-arm64 artifacts
+    if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-arm64-runner }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Checkout greptimedb
+        uses: actions/checkout@v3
+        with:
+          repository: ${{ inputs.repository }}
+          ref: ${{ inputs.commit }}
+          path: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: arm64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          dev-mode: true # Only build the standard greptime binary.
+          upload-to-s3: false # No need to upload to S3.
+          working-dir: ${{ env.CHECKOUT_GREPTIMEDB_PATH }}
+
+  release-images-to-dockerhub:
+    name: Build and push images to DockerHub
+    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-latest
+    outputs:
+      build-result: ${{ steps.set-build-result.outputs.build-result }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - 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-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
+          image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          push-latest-tag: false # Don't push the latest tag to registry.
+          dev-mode: true # Only build the standard images.
+
+      - name: Set build result
+        id: set-build-result
+        run: |
+          echo "build-result=success" >> $GITHUB_OUTPUT
+
+  release-images-to-acr:
+    name: Build and push images to ACR
+    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-latest
+    # When we push to ACR, it's easy to fail due to some unknown network issues.
+    # However, we don't want to fail the whole workflow because of this.
+    # The ACR have daily sync with DockerHub, so don't worry about the image not being updated.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build and push images to ACR
+        uses: ./.github/actions/build-images
+        with:
+          image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
+          image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-name: ${{ env.IMAGE_NAME }}
+          image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
+          image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          push-latest-tag: false # Don't push the latest tag to registry.
+          dev-mode: true # Only build the standard images.
+
+  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
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
+        with:
+          label: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+
+  stop-linux-arm64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
+    name: Stop linux-arm64 runner
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-arm64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
+        with:
+          label: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+
+  notification:
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
+    name: Send notification to Greptime team
+    needs: [
+      release-images-to-dockerhub
+    ]
+    runs-on: ubuntu-latest
+    env:
+      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
+    steps:
+      - name: Notifiy nightly build successful result
+        uses: slackapi/slack-github-action@v1.23.0
+        if: ${{ needs.release-images-to-dockerhub.outputs.build-result == 'success' }}
+        with:
+          payload: |
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
+
+      - name: Notifiy nightly build failed result
+        uses: slackapi/slack-github-action@v1.23.0
+        if: ${{ needs.release-images-to-dockerhub.outputs.build-result != 'success' }}
+        with:
+          payload: |
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

.github/workflows/develop.yml

@@ -1,4 +1,5 @@
 on:
+  merge_group:
   pull_request:
     types: [opened, synchronize, reopened, ready_for_review]
     paths-ignore:
@@ -7,6 +8,7 @@ on:
       - '**.md'
       - '.dockerignore'
       - 'docker/**'
+      - '.gitignore'
   push:
     branches:
       - develop
@@ -22,16 +24,20 @@ on:
 
 name: CI
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
 env:
-  RUST_TOOLCHAIN: nightly-2022-12-20
+  RUST_TOOLCHAIN: nightly-2023-08-07
 
 jobs:
   typos:
     name: Spell Check with Typos
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: crate-ci/typos@v1.0.4
+      - uses: actions/checkout@v3
+      - uses: crate-ci/typos@v1.13.10
 
   check:
     name: Check
@@ -49,7 +55,7 @@ jobs:
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Run cargo check
-        run: cargo check --workspace --all-targets
+        run: cargo check --locked --workspace --all-targets
 
   toml:
     name: Toml Check
@@ -60,55 +66,41 @@ jobs:
       - uses: actions/checkout@v3
       - uses: dtolnay/rust-toolchain@master
         with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
+          toolchain: stable
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Install taplo
-        run: cargo install taplo-cli --version ^0.8 --locked
+        run: cargo +stable install taplo-cli --version ^0.8 --locked
       - name: Run taplo
-        run: taplo format --check --option "indent_string=    "
+        run: taplo format --check
 
-  # Use coverage to run test.
-  # test:
-  #   name: Test Suite
-  #   if: github.event.pull_request.draft == false
-  #   runs-on: ubuntu-latest
-  #   timeout-minutes: 60
-  #   steps:
-  #     - uses: actions/checkout@v3
-  #     - name: Cache LLVM and Clang
-  #       id: cache-llvm
-  #       uses: actions/cache@v3
-  #       with:
-  #         path: ./llvm
-  #         key: llvm
-  #     - uses: arduino/setup-protoc@v1
-  #       with:
-  #         repo-token: ${{ secrets.GITHUB_TOKEN }}
-  #     - uses: KyleMayes/install-llvm-action@v1
-  #       with:
-  #         version: "14.0"
-  #         cached: ${{ steps.cache-llvm.outputs.cache-hit }}
-  #     - uses: dtolnay/rust-toolchain@master
-  #       with:
-  #         toolchain: ${{ env.RUST_TOOLCHAIN }}
-  #     - name: Rust Cache
-  #       uses: Swatinem/rust-cache@v2
-  #     - name: Cleanup disk
-  #       uses: curoky/cleanup-disk-action@v2.0
-  #       with:
-  #         retain: 'rust,llvm'
-  #     - name: Install latest nextest release
-  #       uses: taiki-e/install-action@nextest
-  #     - name: Run tests
-  #       run: cargo nextest run
-  #       env:
-  #         CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
-  #         RUST_BACKTRACE: 1
-  #         GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
-  #         GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
-  #         GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
-  #         UNITTEST_LOG_DIR: "__unittest_logs"
+  sqlness:
+    name: Sqlness Test
+    if: github.event.pull_request.draft == false
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-latest-8-cores, windows-latest-8-cores ]
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v3
+      - uses: arduino/setup-protoc@v1
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2
+      - name: Run sqlness
+        run: cargo sqlness
+      - name: Upload sqlness logs
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: sqlness-logs
+          path: ${{ runner.temp }}/greptime-*.log
+          retention-days: 3
 
   fmt:
     name: Rustfmt
@@ -146,4 +138,93 @@ jobs:
       - name: Rust Cache
         uses: Swatinem/rust-cache@v2
       - name: Run cargo clippy
-        run: cargo clippy --workspace --all-targets -- -D warnings -D clippy::print_stdout -D clippy::print_stderr
+        run: cargo clippy --workspace --all-targets -- -D warnings
+
+  coverage:
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest-8-cores
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v3
+      - uses: arduino/setup-protoc@v1
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - uses: KyleMayes/install-llvm-action@v1
+        with:
+          version: "14.0"
+      - name: Install toolchain
+        uses: dtolnay/rust-toolchain@master
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
+          components: llvm-tools-preview
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2
+      - name: Install latest nextest release
+        uses: taiki-e/install-action@nextest
+      - name: Install Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Install PyArrow Package
+        run: pip install pyarrow
+      - name: Install cargo-llvm-cov
+        uses: taiki-e/install-action@cargo-llvm-cov
+      - name: Collect coverage data
+        run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F pyo3_backend -F dashboard
+        env:
+          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
+          RUST_BACKTRACE: 1
+          CARGO_INCREMENTAL: 0
+          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
+          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
+          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
+          GT_S3_REGION: ${{ secrets.S3_REGION }}
+          UNITTEST_LOG_DIR: "__unittest_logs"
+      - name: Codecov upload
+        uses: codecov/codecov-action@v2
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: ./lcov.info
+          flags: rust
+          fail_ci_if_error: false
+          verbose: true
+
+  test-on-windows:
+    if: github.event.pull_request.draft == false
+    runs-on: windows-latest-8-cores
+    timeout-minutes: 60
+    steps:
+      - run: git config --global core.autocrlf false
+      - uses: actions/checkout@v3
+      - uses: arduino/setup-protoc@v1
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@master
+        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@v4
+        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
+        env:
+          RUST_BACKTRACE: 1
+          CARGO_INCREMENTAL: 0
+          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
+          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
+          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
+          GT_S3_REGION: ${{ secrets.S3_REGION }}
+          UNITTEST_LOG_DIR: "__unittest_logs"

.github/workflows/doc-issue.yml

@@ -1,4 +1,4 @@
-name: Create Issue in docs repo on doc related changes
+name: Create Issue in downstream repos
 
 on:
   issues:
@@ -23,3 +23,17 @@ jobs:
           body: |
             A document change request is generated from
             ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
+  cloud_issue:
+    if: github.event.label.name == 'cloud followup required'
+    runs-on: ubuntu-latest
+    steps:
+      - name: create an issue in cloud repo
+        uses: dacbd/create-issue-action@main
+        with:
+          owner: GreptimeTeam
+          repo: greptimedb-cloud
+          token: ${{ secrets.DOCS_REPO_TOKEN }}
+          title: Followup changes in ${{ github.event.issue.title || github.event.pull_request.title }}
+          body: |
+            A followup request is generated from
+            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}

.github/workflows/docs.yml

@@ -0,0 +1,70 @@
+on:
+  merge_group:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - 'docs/**'
+      - 'config/**'
+      - '**.md'
+      - '.dockerignore'
+      - 'docker/**'
+      - '.gitignore'
+  push:
+    branches:
+      - develop
+      - main
+    paths:
+      - 'docs/**'
+      - 'config/**'
+      - '**.md'
+      - '.dockerignore'
+      - 'docker/**'
+      - '.gitignore'
+  workflow_dispatch:
+
+name: CI
+
+# To pass the required status check, see:
+# https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/defining-the-mergeability-of-pull-requests/troubleshooting-required-status-checks#handling-skipped-but-required-checks
+
+jobs:
+  typos:
+    name: Spell Check with Typos
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: crate-ci/typos@v1.13.10
+
+  check:
+    name: Check
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - run: 'echo "No action required"'
+
+  fmt:
+    name: Rustfmt
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - run: 'echo "No action required"'
+
+  clippy:
+    name: Clippy
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - run: 'echo "No action required"'
+
+  coverage:
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - run: 'echo "No action required"'
+
+  sqlness:
+    name: Sqlness Test
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - run: 'echo "No action required"'

.github/workflows/license.yaml

@@ -13,4 +13,4 @@ jobs:
     steps:
     - uses: actions/checkout@v2
     - name: Check License Header
-      uses: apache/skywalking-eyes/header@main
+      uses: apache/skywalking-eyes/header@df70871af1a8109c9a5b1dc824faaf65246c5236

.github/workflows/nightly-build.yml

@@ -0,0 +1,311 @@
+# Nightly build only do the following things:
+# 1. Run integration tests;
+# 2. Build binaries and images for linux-amd64 and linux-arm64 platform;
+name: GreptimeDB Nightly Build
+
+on:
+  schedule:
+    # Trigger at 00:00(UTC) on every day-of-week from Monday through Friday.
+    - cron: '0 0 * * 1-5'
+  workflow_dispatch: # Allows you to run this workflow manually.
+    inputs:
+      linux_amd64_runner:
+        type: choice
+        description: The runner uses to build linux-amd64 artifacts
+        default: ec2-c6i.2xlarge-amd64
+        options:
+          - ubuntu-latest
+          - ubuntu-latest-8-cores
+          - ubuntu-latest-16-cores
+          - ubuntu-latest-32-cores
+          - ubuntu-latest-64-cores
+          - ec2-c6i.xlarge-amd64 # 4C8G
+          - ec2-c6i.2xlarge-amd64 # 8C16G
+          - ec2-c6i.4xlarge-amd64 # 16C32G
+          - ec2-c6i.8xlarge-amd64 # 32C64G
+          - ec2-c6i.16xlarge-amd64 # 64C128G
+      linux_arm64_runner:
+        type: choice
+        description: The runner uses to build linux-arm64 artifacts
+        default: ec2-c6g.2xlarge-arm64
+        options:
+          - ec2-c6g.xlarge-arm64 # 4C8G
+          - ec2-c6g.2xlarge-arm64 # 8C16G
+          - ec2-c6g.4xlarge-arm64 # 16C32G
+          - ec2-c6g.8xlarge-arm64 # 32C64G
+          - ec2-c6g.16xlarge-arm64 # 64C128G
+      skip_test:
+        description: Do not run integration tests during the build
+        type: boolean
+        default: true
+      build_linux_amd64_artifacts:
+        type: boolean
+        description: Build linux-amd64 artifacts
+        required: false
+        default: false
+      build_linux_arm64_artifacts:
+        type: boolean
+        description: Build linux-arm64 artifacts
+        required: false
+        default: false
+      release_images:
+        type: boolean
+        description: Build and push images to DockerHub and ACR
+        required: false
+        default: false
+
+# Use env variables to control all the release process.
+env:
+  CARGO_PROFILE: nightly
+
+  # Controls whether to run tests, include unit-test, integration-test and sqlness.
+  DISABLE_RUN_TESTS: ${{ inputs.skip_test || vars.DEFAULT_SKIP_TEST }}
+
+  # Always use 'nightly' to indicate it's the nightly build.
+  NEXT_RELEASE_VERSION: nightly
+
+  NIGHTLY_RELEASE_PREFIX: nightly
+
+jobs:
+  allocate-runners:
+    name: Allocate runners
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: ubuntu-latest
+    outputs:
+      linux-amd64-runner: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-arm64-runner: ${{ steps.start-linux-arm64-runner.outputs.label }}
+
+      # The following EC2 resource id will be used for resource releasing.
+      linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-amd64-ec2-runner-instance-id: ${{ steps.start-linux-amd64-runner.outputs.ec2-instance-id }}
+      linux-arm64-ec2-runner-label: ${{ steps.start-linux-arm64-runner.outputs.label }}
+      linux-arm64-ec2-runner-instance-id: ${{ steps.start-linux-arm64-runner.outputs.ec2-instance-id }}
+
+      # The 'version' use as the global tag name of the release workflow.
+      version: ${{ steps.create-version.outputs.version }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Create version
+        id: create-version
+        run: |
+          version=$(./.github/scripts/create-version.sh) && \
+          echo $version && \
+          echo "version=$version" >> $GITHUB_OUTPUT
+        env:
+          GITHUB_EVENT_NAME: ${{ github.event_name }}
+          GITHUB_REF_NAME: ${{ github.ref_name }}
+          NEXT_RELEASE_VERSION: ${{ env.NEXT_RELEASE_VERSION }}
+          NIGHTLY_RELEASE_PREFIX: ${{ env.NIGHTLY_RELEASE_PREFIX }}
+
+      - name: Allocate linux-amd64 runner
+        if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-amd64-runner
+        with:
+          runner: ${{ inputs.linux_amd64_runner || vars.DEFAULT_AMD64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_AMD64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+      - name: Allocate linux-arm64 runner
+        if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-arm64-runner
+        with:
+          runner: ${{ inputs.linux_arm64_runner || vars.DEFAULT_ARM64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_ARM64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+  build-linux-amd64-artifacts:
+    name: Build linux-amd64 artifacts
+    if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-amd64-runner }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: amd64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          upload-latest-artifacts: false
+
+  build-linux-arm64-artifacts:
+    name: Build linux-arm64 artifacts
+    if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-arm64-runner }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: arm64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+          upload-latest-artifacts: false
+
+  release-images-to-dockerhub:
+    name: Build and push images to DockerHub
+    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-latest
+    outputs:
+      nightly-build-result: ${{ steps.set-nightly-build-result.outputs.nightly-build-result }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build and push images to dockerhub
+        uses: ./.github/actions/build-images
+        with:
+          image-registry: docker.io
+          image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
+          image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          push-latest-tag: false # Don't push the latest tag to registry.
+
+      - name: Set nightly build result
+        id: set-nightly-build-result
+        run: |
+          echo "nightly-build-result=success" >> $GITHUB_OUTPUT
+
+  release-images-to-acr:
+    name: Build and push images to ACR
+    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-latest
+    # When we push to ACR, it's easy to fail due to some unknown network issues.
+    # However, we don't want to fail the whole workflow because of this.
+    # The ACR have daily sync with DockerHub, so don't worry about the image not being updated.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build and push images to ACR
+        uses: ./.github/actions/build-images
+        with:
+          image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
+          image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
+          image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          push-latest-tag: false # Don't push the latest tag to registry.
+
+  stop-linux-amd64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
+    name: Stop linux-amd64 runner
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
+        with:
+          label: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+
+  stop-linux-arm64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
+    name: Stop linux-arm64 runner
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-arm64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
+        with:
+          label: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+
+  notification:
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
+    name: Send notification to Greptime team
+    needs: [
+      release-images-to-dockerhub
+    ]
+    runs-on: ubuntu-latest
+    env:
+      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
+    steps:
+      - name: Notifiy nightly build successful result
+        uses: slackapi/slack-github-action@v1.23.0
+        if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result == 'success' }}
+        with:
+          payload: |
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
+
+      - name: Notifiy nightly build failed result
+        uses: slackapi/slack-github-action@v1.23.0
+        if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result != 'success' }}
+        with:
+          payload: |
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

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

@@ -18,3 +18,12 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           pass_on_octokit_error: false
           configuration_path: ".github/pr-title-checker-config.json"
+  breaking:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: thehanimo/pr-title-checker@v1.3.4
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          pass_on_octokit_error: false
+          configuration_path: ".github/pr-title-breaking-change-label-config.json"

.github/workflows/release.yml

@@ -1,3 +1,8 @@
+name: Release
+
+# There are two kinds of formal release:
+# 1. The tag('v*.*.*') push release: the release workflow will be triggered by the tag push event.
+# 2. The scheduled release(the version will be '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD'): the release workflow will be triggered by the schedule event.
 on:
   push:
     tags:
@@ -5,222 +10,386 @@ on:
   schedule:
     # At 00:00 on Monday.
     - cron: '0 0 * * 1'
-  workflow_dispatch:
-
-name: Release
+  workflow_dispatch: # Allows you to run this workflow manually.
+    # Notes: The GitHub Actions ONLY support 10 inputs, and it's already used up.
+    inputs:
+      linux_amd64_runner:
+        type: choice
+        description: The runner uses to build linux-amd64 artifacts
+        default: ec2-c6i.4xlarge-amd64
+        options:
+          - ubuntu-latest
+          - ubuntu-latest-8-cores
+          - ubuntu-latest-16-cores
+          - ubuntu-latest-32-cores
+          - ubuntu-latest-64-cores
+          - ec2-c6i.xlarge-amd64 # 4C8G
+          - ec2-c6i.2xlarge-amd64 # 8C16G
+          - ec2-c6i.4xlarge-amd64 # 16C32G
+          - ec2-c6i.8xlarge-amd64 # 32C64G
+          - ec2-c6i.16xlarge-amd64 # 64C128G
+      linux_arm64_runner:
+        type: choice
+        description: The runner uses to build linux-arm64 artifacts
+        default: ec2-c6g.4xlarge-arm64
+        options:
+          - ec2-c6g.xlarge-arm64 # 4C8G
+          - ec2-c6g.2xlarge-arm64 # 8C16G
+          - ec2-c6g.4xlarge-arm64 # 16C32G
+          - ec2-c6g.8xlarge-arm64 # 32C64G
+          - ec2-c6g.16xlarge-arm64 # 64C128G
+      macos_runner:
+        type: choice
+        description: The runner uses to build macOS artifacts
+        default: macos-latest
+        options:
+          - macos-latest
+      skip_test:
+        description: Do not run integration tests during the build
+        type: boolean
+        default: true
+      build_linux_amd64_artifacts:
+        type: boolean
+        description: Build linux-amd64 artifacts
+        required: false
+        default: false
+      build_linux_arm64_artifacts:
+        type: boolean
+        description: Build linux-arm64 artifacts
+        required: false
+        default: false
+      build_macos_artifacts:
+        type: boolean
+        description: Build macos artifacts
+        required: false
+        default: false
+      release_artifacts:
+        type: boolean
+        description: Create GitHub release and upload artifacts
+        required: false
+        default: false
+      release_images:
+        type: boolean
+        description: Build and push images to DockerHub and ACR
+        required: false
+        default: false
+      release_dev_builder_image:
+        type: boolean
+        description: Release dev-builder image
+        required: false
+        default: false
 
+# Use env variables to control all the release process.
 env:
-  RUST_TOOLCHAIN: nightly-2022-12-20
+  # The arguments of building greptime.
+  RUST_TOOLCHAIN: nightly-2023-08-07
+  CARGO_PROFILE: nightly
 
-  # FIXME(zyy17): Would be better to use `gh release list -L 1 | cut -f 3` to get the latest release version tag, but for a long time, we will stay at 'v0.1.0-alpha-*'.
-  SCHEDULED_BUILD_VERSION_PREFIX: v0.1.0-alpha
+  # Controls whether to run tests, include unit-test, integration-test and sqlness.
+  DISABLE_RUN_TESTS: ${{ inputs.skip_test || vars.DEFAULT_SKIP_TEST }}
 
-  # In the future, we can change SCHEDULED_PERIOD to nightly.
-  SCHEDULED_PERIOD: weekly
+  # 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: v0.4.0
 
 jobs:
-  build:
-    name: Build binary
+  allocate-runners:
+    name: Allocate runners
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: ubuntu-latest
+    outputs:
+      linux-amd64-runner: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-arm64-runner: ${{ steps.start-linux-arm64-runner.outputs.label }}
+      macos-runner: ${{ inputs.macos_runner || vars.DEFAULT_MACOS_RUNNER }}
+
+      # The following EC2 resource id will be used for resource releasing.
+      linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
+      linux-amd64-ec2-runner-instance-id: ${{ steps.start-linux-amd64-runner.outputs.ec2-instance-id }}
+      linux-arm64-ec2-runner-label: ${{ steps.start-linux-arm64-runner.outputs.label }}
+      linux-arm64-ec2-runner-instance-id: ${{ steps.start-linux-arm64-runner.outputs.ec2-instance-id }}
+
+      # The 'version' use as the global tag name of the release workflow.
+      version: ${{ steps.create-version.outputs.version }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      # The create-version will create a global variable named 'version' in the global workflows.
+      # - If it's a tag push release, the version is the tag name(${{ github.ref_name }});
+      # - If it's a scheduled release, the version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-$buildTime', like v0.2.0-nigthly-20230313;
+      # - If it's a manual release, the version is '${{ env.NEXT_RELEASE_VERSION }}-<short-git-sha>-YYYYMMDDSS', like v0.2.0-e5b243c-2023071245;
+      - name: Create version
+        id: create-version
+        run: |
+          echo "version=$(./.github/scripts/create-version.sh)" >> $GITHUB_OUTPUT
+        env:
+          GITHUB_EVENT_NAME: ${{ github.event_name }}
+          GITHUB_REF_NAME: ${{ github.ref_name }}
+          NEXT_RELEASE_VERSION: ${{ env.NEXT_RELEASE_VERSION }}
+          NIGHTLY_RELEASE_PREFIX: ${{ env.NIGHTLY_RELEASE_PREFIX }}
+
+      - name: Allocate linux-amd64 runner
+        if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-amd64-runner
+        with:
+          runner: ${{ inputs.linux_amd64_runner || vars.DEFAULT_AMD64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_AMD64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+      - name: Allocate linux-arm64 runner
+        if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
+        uses: ./.github/actions/start-runner
+        id: start-linux-arm64-runner
+        with:
+          runner: ${{ inputs.linux_arm64_runner || vars.DEFAULT_ARM64_RUNNER }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          image-id: ${{ vars.EC2_RUNNER_LINUX_ARM64_IMAGE_ID }}
+          security-group-id: ${{ vars.EC2_RUNNER_SECURITY_GROUP_ID }}
+          subnet-id: ${{ vars.EC2_RUNNER_SUBNET_ID }}
+
+  build-linux-amd64-artifacts:
+    name: Build linux-amd64 artifacts
+    if: ${{ inputs.build_linux_amd64_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-amd64-runner }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: amd64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+
+  build-linux-arm64-artifacts:
+    name: Build linux-arm64 artifacts
+    if: ${{ inputs.build_linux_arm64_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+    ]
+    runs-on: ${{ needs.allocate-runners.outputs.linux-arm64-runner }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - uses: ./.github/actions/build-linux-artifacts
+        with:
+          arch: arm64
+          cargo-profile: ${{ env.CARGO_PROFILE }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
+
+  build-macos-artifacts:
+    name: Build macOS artifacts
     strategy:
+      fail-fast: false
       matrix:
-        # The file format is greptime-<os>-<arch>
         include:
-          - arch: x86_64-unknown-linux-gnu
-            os: ubuntu-latest-16-cores
-            file: greptime-linux-amd64
-          - arch: aarch64-unknown-linux-gnu
-            os: ubuntu-latest-16-cores
-            file: greptime-linux-arm64
-          - arch: aarch64-apple-darwin
-            os: macos-latest
-            file: greptime-darwin-arm64
-          - arch: x86_64-apple-darwin
-            os: macos-latest
-            file: greptime-darwin-amd64
+          - os: ${{ needs.allocate-runners.outputs.macos-runner }}
+            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 }}
+    needs: [
+      allocate-runners,
+    ]
+    if: ${{ inputs.build_macos_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
     steps:
-      - name: Checkout sources
-        uses: actions/checkout@v3
-
-      - name: Cache cargo assets
-        id: cache
-        uses: actions/cache@v3
+      - uses: actions/checkout@v3
         with:
-          path: |
-            ~/.cargo/bin/
-            ~/.cargo/registry/index/
-            ~/.cargo/registry/cache/
-            ~/.cargo/git/db/
-            target/
-          key: ${{ matrix.arch }}-build-cargo-${{ hashFiles('**/Cargo.lock') }}
+          fetch-depth: 0
 
-      - name: Install Protoc for linux
-        if: contains(matrix.arch, 'linux') && endsWith(matrix.arch, '-gnu')
-        run: | # Make sure the protoc is >= 3.15
-          wget https://github.com/protocolbuffers/protobuf/releases/download/v21.9/protoc-21.9-linux-x86_64.zip
-          unzip protoc-21.9-linux-x86_64.zip -d protoc
-          sudo cp protoc/bin/protoc /usr/local/bin/
-          sudo cp -r protoc/include/google /usr/local/include/
-
-      - name: Install Protoc for macos
-        if: contains(matrix.arch, 'darwin')
-        run: |
-          brew install protobuf
-
-      - name: Install dependencies for linux
-        if: contains(matrix.arch, 'linux') && endsWith(matrix.arch, '-gnu')
-        run: |
-          sudo apt-get -y update
-          sudo apt-get -y install libssl-dev pkg-config g++-aarch64-linux-gnu gcc-aarch64-linux-gnu
-
-      - name: Install rust toolchain
-        uses: dtolnay/rust-toolchain@master
+      - uses: ./.github/actions/build-macos-artifacts
         with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-          targets: ${{ matrix.arch }}
+          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 }}
+          release-to-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
+          artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
+          aws-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
 
-      - name: Output package versions
-        run: protoc --version ; cargo version ; rustc --version ; gcc --version ; g++ --version
-
-      - name: Run cargo build
-        run: cargo build ${{ matrix.opts }} --release --locked --target ${{ matrix.arch }}
-
-      - name: Calculate checksum and rename binary
-        shell: bash
-        run: |
-          cd target/${{ matrix.arch }}/release
-          chmod +x greptime
-          tar -zcvf ${{ matrix.file }}.tgz greptime
-          echo $(shasum -a 256 ${{ matrix.file }}.tgz | cut -f1 -d' ') > ${{ matrix.file }}.sha256sum
-
-      - name: Upload artifacts
-        uses: actions/upload-artifact@v3
+  release-images-to-dockerhub:
+    name: Build and push images to DockerHub
+    if: ${{ inputs.release_images || github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-2004-16-cores
+    steps:
+      - uses: actions/checkout@v3
         with:
-          name: ${{ matrix.file }}
-          path: target/${{ matrix.arch }}/release/${{ matrix.file }}.tgz
+          fetch-depth: 0
 
-      - name: Upload checksum of artifacts
-        uses: actions/upload-artifact@v3
+      - name: Build and push images to dockerhub
+        uses: ./.github/actions/build-images
         with:
-          name: ${{ matrix.file }}.sha256sum
-          path: target/${{ matrix.arch }}/release/${{ matrix.file }}.sha256sum
-  release:
-    name: Release artifacts
-    needs: [build]
+          image-registry: docker.io
+          image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
+          image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+
+  release-images-to-acr:
+    name: Build and push images to ACR
+    if: ${{ inputs.release_images || github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+    ]
+    runs-on: ubuntu-2004-16-cores
+    # When we push to ACR, it's easy to fail due to some unknown network issues.
+    # However, we don't want to fail the whole workflow because of this.
+    # The ACR have daily sync with DockerHub, so don't worry about the image not being updated.
+    continue-on-error: true
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build and push images to ACR
+        uses: ./.github/actions/build-images
+        with:
+          image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
+          image-namespace: ${{ vars.IMAGE_NAMESPACE }}
+          image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
+          image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
+          version: ${{ needs.allocate-runners.outputs.version }}
+
+  release-artifacts:
+    name: Create GitHub release and upload artifacts
+    if: ${{ inputs.release_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+      build-linux-arm64-artifacts,
+      build-macos-artifacts,
+      release-images-to-dockerhub,
+    ]
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout sources
-        uses: actions/checkout@v3
-
-      - name: Download artifacts
-        uses: actions/download-artifact@v3
-
-      - name: Configure scheduled build version # the version would be ${SCHEDULED_BUILD_VERSION_PREFIX}-YYYYMMDD-${SCHEDULED_PERIOD}, like v0.1.0-alpha-20221119-weekly.
-        shell: bash
-        if: github.event_name == 'schedule'
-        run: |
-          buildTime=`date "+%Y%m%d"`
-          SCHEDULED_BUILD_VERSION=${{ env.SCHEDULED_BUILD_VERSION_PREFIX }}-$buildTime-${{ env.SCHEDULED_PERIOD }}
-          echo "SCHEDULED_BUILD_VERSION=${SCHEDULED_BUILD_VERSION}" >> $GITHUB_ENV
-
-      - name: Create scheduled build git tag
-        if: github.event_name == 'schedule'
-        run: |
-          git tag ${{ env.SCHEDULED_BUILD_VERSION }}
-
-      - name: Publish scheduled release # configure the different release title and tags.
-        uses: softprops/action-gh-release@v1
-        if: github.event_name == 'schedule'
+      - uses: actions/checkout@v3
         with:
-          name: "Release ${{ env.SCHEDULED_BUILD_VERSION }}"
-          tag_name: ${{ env.SCHEDULED_BUILD_VERSION }}
-          generate_release_notes: true
-          files: |
-            **/greptime-*
+          fetch-depth: 0
 
-      - name: Publish release
-        uses: softprops/action-gh-release@v1
-        if: github.event_name != 'schedule'
+      - name: Release artifacts
+        uses: ./.github/actions/release-artifacts
         with:
-          name: "Release ${{ github.ref_name }}"
-          files: |
-            **/greptime-*
+          version: ${{ needs.allocate-runners.outputs.version }}
 
-  docker:
-    name: Build docker image
-    needs: [build]
-    runs-on: ubuntu-latest
+  release-dev-builder-image:
+    name: Release dev builder image
+    if: ${{ inputs.release_dev_builder_image }} # Only manually trigger this job.
+    runs-on: ubuntu-latest-16-cores
     steps:
-      - name: Checkout sources
+      - name: Checkout
         uses: actions/checkout@v3
-
-      - name: Download amd64 binary
-        uses: actions/download-artifact@v3
         with:
-          name: greptime-linux-amd64
-          path: amd64
+          fetch-depth: 0
 
-      - name: Unzip the amd64 artifacts
-        run: |
-          cd amd64
-          tar xvf greptime-linux-amd64.tgz
-          rm greptime-linux-amd64.tgz
-
-      - name: Download arm64 binary
-        uses: actions/download-artifact@v3
+      - name: Build and push dev builder image
+        uses: ./.github/actions/build-dev-builder-image
         with:
-          name: greptime-linux-arm64
-          path: arm64
+          dockerhub-image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
+          dockerhub-image-registry-token: ${{ secrets.DOCKERHUB_TOKEN }}
+          acr-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
+          acr-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
+          acr-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
 
-      - name: Unzip the arm64 artifacts
-        run: |
-          cd arm64
-          tar xvf greptime-linux-arm64.tgz
-          rm greptime-linux-arm64.tgz
-
-      - name: Login to UCloud Container Registry
-        uses: docker/login-action@v2
+  ### Stop runners ###
+  # It's very necessary to split the job of releasing runners into 'stop-linux-amd64-runner' and 'stop-linux-arm64-runner'.
+  # Because we can terminate the specified EC2 instance immediately after the job is finished without uncessary waiting.
+  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
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-amd64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
         with:
-          registry: uhub.service.ucloud.cn
-          username: ${{ secrets.UCLOUD_USERNAME }}
-          password: ${{ secrets.UCLOUD_PASSWORD }}
+          fetch-depth: 0
 
-      - name: Login to Dockerhub
-        uses: docker/login-action@v2
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
         with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          label: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-amd64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
-      - name: Configure scheduled build image tag # the tag would be ${SCHEDULED_BUILD_VERSION_PREFIX}-YYYYMMDD-${SCHEDULED_PERIOD}
-        shell: bash
-        if: github.event_name == 'schedule'
-        run: |
-          buildTime=`date "+%Y%m%d"`
-          SCHEDULED_BUILD_VERSION=${{ env.SCHEDULED_BUILD_VERSION_PREFIX }}-$buildTime-${{ env.SCHEDULED_PERIOD }}
-          echo "IMAGE_TAG=${SCHEDULED_BUILD_VERSION:1}" >> $GITHUB_ENV
-
-      - name: Configure tag # If the release tag is v0.1.0, then the image version tag will be 0.1.0.
-        shell: bash
-        if: github.event_name != 'schedule'
-        run: |
-          VERSION=${{ github.ref_name }}
-          echo "IMAGE_TAG=${VERSION:1}" >> $GITHUB_ENV
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
-
-      - name: Set up buildx
-        uses: docker/setup-buildx-action@v2
-
-      - name: Build and push
-        uses: docker/build-push-action@v3
+  stop-linux-arm64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
+    name: Stop linux-arm64 runner
+    # Only run this job when the runner is allocated.
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    needs: [
+      allocate-runners,
+      build-linux-arm64-artifacts,
+    ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
         with:
-          context: .
-          file: ./docker/ci/Dockerfile
-          push: true
-          platforms: linux/amd64,linux/arm64
-          tags: |
-            greptime/greptimedb:latest
-            greptime/greptimedb:${{ env.IMAGE_TAG }}
-            uhub.service.ucloud.cn/greptime/greptimedb:latest
-            uhub.service.ucloud.cn/greptime/greptimedb:${{ env.IMAGE_TAG }}
+          fetch-depth: 0
+
+      - name: Stop EC2 runner
+        uses: ./.github/actions/stop-runner
+        with:
+          label: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-label }}
+          ec2-instance-id: ${{ needs.allocate-runners.outputs.linux-arm64-ec2-runner-instance-id }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.EC2_RUNNER_REGION }}
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}

.gitignore

@@ -1,6 +1,8 @@
 # Generated by Cargo
 # will have compiled files and executables
 /target/
+# also ignore if it's a symbolic link
+/target
 
 # Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
 # More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
@@ -35,3 +37,12 @@ benchmarks/data
 
 # dotenv
 .env
+
+# dashboard files
+!/src/servers/dashboard/VERSION
+/src/servers/dashboard/*
+
+# Vscode workspace
+*.code-workspace
+
+venv/

.pre-commit-config.yaml

@@ -5,11 +5,11 @@ repos:
     -    id: conventional-pre-commit
          stages: [commit-msg]
 
--   repo: https://github.com/DevinR528/cargo-sort
-    rev: e6a795bc6b2c0958f9ef52af4863bbd7cc17238f
-    hooks:
-    -    id: cargo-sort
-         args: ["--workspace"]
+# -   repo: https://github.com/DevinR528/cargo-sort
+#     rev: e6a795bc6b2c0958f9ef52af4863bbd7cc17238f
+#     hooks:
+#     -    id: cargo-sort
+#          args: ["--workspace"]
 
 -   repo: https://github.com/doublify/pre-commit-rust
     rev: v1.0

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Welcome!
+# Welcome 👋
 
 Thanks a lot for considering contributing to GreptimeDB. We believe people like you would make GreptimeDB a great product. We intend to build a community where individuals can have open talks, show respect for one another, and speak with true ❤️. Meanwhile, we are to keep transparency and make your effort count here.
 
@@ -50,34 +50,33 @@ GreptimeDB uses the [Apache 2.0 license](https://github.com/GreptimeTeam/greptim
 
 - To ensure that community is free and confident in its ability to use your contributions, please sign the Contributor License Agreement (CLA) which will be incorporated in the pull request process.
 - Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/).
-- Make sure all unit tests are passed.
-- Make sure all clippy warnings are fixed (you can check it locally by running `cargo clippy --workspace --all-targets -- -D warnings -D clippy::print_stdout -D clippy::print_stderr`).
+- Make sure all unit tests are passed (using `cargo test --workspace` or [nextest](https://nexte.st/index.html) `cargo nextest run`).
+- Make sure all clippy warnings are fixed (you can check it locally by running `cargo clippy --workspace --all-targets -- -D warnings`).
 
 #### `pre-commit` Hooks
+
 You could setup the [`pre-commit`](https://pre-commit.com/#plugins) hooks to run these checks on every commit automatically.
 
 1. Install `pre-commit`
-```
-$ pip install pre-commit
-```
-or
-```
-$ brew install pre-commit
-```
+
+        pip install pre-commit
+
+    or
+
+        brew install pre-commit
 
 2. Install the `pre-commit` hooks
-```
-$ pre-commit install
-pre-commit installed at .git/hooks/pre-commit
 
-$ pre-commit install --hook-type commit-msg
-pre-commit installed at .git/hooks/commit-msg
+        $ pre-commit install
+        pre-commit installed at .git/hooks/pre-commit
 
-$ pre-commit install --hook-type pre-push
-pre-commit installed at .git/hooks/pre-pus
-```
+        $ pre-commit install --hook-type commit-msg
+        pre-commit installed at .git/hooks/commit-msg
 
-now `pre-commit` will run automatically on `git commit`.
+        $ pre-commit install --hook-type pre-push
+        pre-commit installed at .git/hooks/pre-push
+
+Now, `pre-commit` will run automatically on `git commit`.
 
 ### Title
 
@@ -102,10 +101,12 @@ of what you were trying to do and what went wrong. You can also reach for help i
 ## Community
 
 The core team will be thrilled if you participate in any way you like. When you are stuck, try ask for help by filing an issue, with a detailed description of what you were trying to do and what went wrong. If you have any questions or if you would like to get involved in our community, please check out:
+
 - [GreptimeDB Community Slack](https://greptime.com/slack)
 - [GreptimeDB Github Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
 
 Also, see some extra GreptimeDB content:
-- [GreptimeDB Docs](https://greptime.com/docs)
-- [Learn GreptimeDB](https://greptime.com/products/db)
+
+- [GreptimeDB Docs](https://docs.greptime.com/)
+- [Learn GreptimeDB](https://greptime.com/product/db)
 - [Greptime Inc. Website](https://greptime.com)

Cargo.toml

@@ -2,30 +2,42 @@
 members = [
     "benchmarks",
     "src/api",
+    "src/auth",
     "src/catalog",
     "src/client",
     "src/cmd",
     "src/common/base",
     "src/common/catalog",
+    "src/common/datasource",
     "src/common/error",
     "src/common/function",
     "src/common/function-macro",
+    "src/common/greptimedb-telemetry",
     "src/common/grpc",
     "src/common/grpc-expr",
+    "src/common/mem-prof",
+    "src/common/meta",
+    "src/common/procedure",
+    "src/common/procedure-test",
     "src/common/query",
     "src/common/recordbatch",
     "src/common/runtime",
     "src/common/substrait",
     "src/common/telemetry",
+    "src/common/test-util",
     "src/common/time",
+    "src/common/version",
     "src/datanode",
     "src/datatypes",
+    "src/file-table-engine",
     "src/frontend",
     "src/log-store",
     "src/meta-client",
     "src/meta-srv",
     "src/mito",
+    "src/mito2",
     "src/object-store",
+    "src/partition",
     "src/promql",
     "src/query",
     "src/script",
@@ -34,28 +46,124 @@ members = [
     "src/sql",
     "src/storage",
     "src/store-api",
+    "src/flow",
     "src/table",
+    "src/table-procedure",
     "tests-integration",
     "tests/runner",
 ]
+resolver = "2"
 
 [workspace.package]
-version = "0.1.0"
+version = "0.4.0-nightly"
 edition = "2021"
 license = "Apache-2.0"
 
 [workspace.dependencies]
-arrow = "29.0"
-arrow-schema = { version = "29.0", features = ["serde"] }
-# TODO(LFC): Use released Datafusion when it officially dpendent on Arrow 29.0
-datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "4917235a398ae20145c87d20984e6367dc1a0c1e" }
-parquet = "29.0"
-sqlparser = "0.28"
+arrow = { version = "43.0" }
+etcd-client = "0.11"
+arrow-array = "43.0"
+arrow-flight = "43.0"
+arrow-schema = { version = "43.0", features = ["serde"] }
+async-stream = "0.3"
+async-trait = "0.1"
+chrono = { version = "0.4", features = ["serde"] }
+datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "c0b0fca548e99d020c76e1a1cd7132aab26000e1" }
+derive_builder = "0.12"
+futures = "0.3"
+futures-util = "0.3"
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "4a277f27caa035a801d5b9c020a0449777736614" }
+humantime-serde = "1.1"
+itertools = "0.10"
+lazy_static = "1.4"
+once_cell = "1.18"
+opentelemetry-proto = { version = "0.2", features = ["gen-tonic", "metrics"] }
+parquet = "43.0"
+paste = "1.0"
+prost = "0.11"
+rand = "0.8"
+regex = "1.8"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+snafu = { version = "0.7", features = ["backtraces"] }
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "296a4f6c73b129d6f565a42a2e5e53c6bc2b9da4", features = [
+    "visitor",
+] }
+strum = { version = "0.25", features = ["derive"] }
+tempfile = "3"
+tokio = { version = "1.28", features = ["full"] }
+tokio-util = { version = "0.7", features = ["io-util", "compat"] }
+toml = "0.7"
+tonic = { version = "0.9", features = ["tls"] }
+uuid = { version = "1", features = ["serde", "v4", "fast-rng"] }
+metrics = "0.20"
+meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "abbd357c1e193cd270ea65ee7652334a150b628f" }
+## workspaces members
+api = { path = "src/api" }
+auth = { path = "src/auth" }
+catalog = { path = "src/catalog" }
+client = { path = "src/client" }
+cmd = { path = "src/cmd" }
+common-base = { path = "src/common/base" }
+common-catalog = { path = "src/common/catalog" }
+common-datasource = { path = "src/common/datasource" }
+common-error = { path = "src/common/error" }
+common-function = { path = "src/common/function" }
+common-function-macro = { path = "src/common/function-macro" }
+common-greptimedb-telemetry = { path = "src/common/greptimedb-telemetry" }
+common-grpc = { path = "src/common/grpc" }
+common-grpc-expr = { path = "src/common/grpc-expr" }
+common-mem-prof = { path = "src/common/mem-prof" }
+common-meta = { path = "src/common/meta" }
+common-procedure = { path = "src/common/procedure" }
+common-procedure-test = { path = "src/common/procedure-test" }
+common-pprof = { path = "src/common/pprof" }
+common-query = { path = "src/common/query" }
+common-recordbatch = { path = "src/common/recordbatch" }
+common-runtime = { path = "src/common/runtime" }
+substrait = { path = "src/common/substrait" }
+common-telemetry = { path = "src/common/telemetry" }
+common-test-util = { path = "src/common/test-util" }
+common-time = { path = "src/common/time" }
+common-version = { path = "src/common/version" }
+datanode = { path = "src/datanode" }
+datatypes = { path = "src/datatypes" }
+file-table-engine = { path = "src/file-table-engine" }
+frontend = { path = "src/frontend" }
+log-store = { path = "src/log-store" }
+meta-client = { path = "src/meta-client" }
+meta-srv = { path = "src/meta-srv" }
+mito = { path = "src/mito" }
+mito2 = { path = "src/mito2" }
+object-store = { path = "src/object-store" }
+partition = { path = "src/partition" }
+promql = { path = "src/promql" }
+query = { path = "src/query" }
+script = { path = "src/script" }
+servers = { path = "src/servers" }
+session = { path = "src/session" }
+sql = { path = "src/sql" }
+storage = { path = "src/storage" }
+store-api = { path = "src/store-api" }
+table = { path = "src/table" }
+table-procedure = { path = "src/table-procedure" }
+
+[workspace.dependencies.meter-macros]
+git = "https://github.com/GreptimeTeam/greptime-meter.git"
+rev = "abbd357c1e193cd270ea65ee7652334a150b628f"
 
 [profile.release]
 debug = true
+
+[profile.nightly]
+inherits = "release"
+strip = true
+lto = "thin"
+debug = false
+incremental = false

Cross.toml

@@ -0,0 +1,7 @@
+[build]
+pre-build = [
+    "dpkg --add-architecture $CROSS_DEB_ARCH",
+    "apt update && apt install -y unzip zlib1g-dev zlib1g-dev:$CROSS_DEB_ARCH",
+    "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",
+]

Makefile

@@ -1,15 +1,77 @@
-IMAGE_REGISTRY ?= greptimedb
+# The arguments for building images.
+CARGO_PROFILE ?=
+FEATURES ?=
+TARGET_DIR ?=
+TARGET ?=
+CARGO_BUILD_OPTS := --locked
+IMAGE_REGISTRY ?= docker.io
+IMAGE_NAMESPACE ?= greptime
 IMAGE_TAG ?= latest
+BUILDX_MULTI_PLATFORM_BUILD ?= false
+BUILDX_BUILDER_NAME ?= gtbuilder
+BASE_IMAGE ?= ubuntu
+RUST_TOOLCHAIN ?= $(shell cat rust-toolchain.toml | grep channel | cut -d'"' -f2)
+CARGO_REGISTRY_CACHE ?= ${HOME}/.cargo/registry
+ARCH := $(shell uname -m | sed 's/x86_64/amd64/' | sed 's/aarch64/arm64/')
+OUTPUT_DIR := $(shell if [ "$(RELEASE)" = "true" ]; then echo "release"; elif [ ! -z "$(CARGO_PROFILE)" ]; then echo "$(CARGO_PROFILE)" ; else echo "debug"; fi)
+
+# The arguments for running integration tests.
+ETCD_VERSION ?= v3.5.9
+ETCD_IMAGE ?= quay.io/coreos/etcd:${ETCD_VERSION}
+RETRY_COUNT ?= 3
+NEXTEST_OPTS := --retries ${RETRY_COUNT}
+BUILD_JOBS ?= $(shell which nproc 1>/dev/null && expr $$(nproc) / 2) # If nproc is not available, we don't set the build jobs.
+ifeq ($(BUILD_JOBS), 0) # If the number of cores is less than 2, set the build jobs to 1.
+  BUILD_JOBS := 1
+endif
+
+ifneq ($(strip $(BUILD_JOBS)),)
+	NEXTEST_OPTS += --build-jobs=${BUILD_JOBS}
+endif
+
+ifneq ($(strip $(CARGO_PROFILE)),)
+	CARGO_BUILD_OPTS += --profile ${CARGO_PROFILE}
+endif
+
+ifneq ($(strip $(FEATURES)),)
+	CARGO_BUILD_OPTS += --features ${FEATURES}
+endif
+
+ifneq ($(strip $(TARGET_DIR)),)
+	CARGO_BUILD_OPTS += --target-dir ${TARGET_DIR}
+endif
+
+ifneq ($(strip $(TARGET)),)
+	CARGO_BUILD_OPTS += --target ${TARGET}
+endif
+
+ifneq ($(strip $(RELEASE)),)
+	CARGO_BUILD_OPTS += --release
+endif
+
+ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), true)
+	BUILDX_MULTI_PLATFORM_BUILD_OPTS := --platform linux/amd64,linux/arm64 --push
+else
+	BUILDX_MULTI_PLATFORM_BUILD_OPTS := -o type=docker
+endif
 
 ##@ Build
 
 .PHONY: build
 build: ## Build debug version greptime.
-	cargo build
+	cargo build ${CARGO_BUILD_OPTS}
 
-.PHONY: release
-release:  ## Build release version greptime.
-	cargo build --release
+.POHNY: build-by-dev-builder
+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-${BASE_IMAGE}:latest \
+	make build \
+	CARGO_PROFILE=${CARGO_PROFILE} \
+	FEATURES=${FEATURES} \
+	TARGET_DIR=${TARGET_DIR} \
+	TARGET=${TARGET} \
+	RELEASE=${RELEASE}
 
 .PHONY: clean
 clean: ## Clean the project.
@@ -19,23 +81,52 @@ clean: ## Clean the project.
 fmt: ## Format all the Rust code.
 	cargo fmt --all
 
+.PHONY: fmt-toml
+fmt-toml: ## Format all TOML files.
+	taplo format
+
+.PHONY: check-toml
+check-toml: ## Check all TOML files.
+	taplo format --check
+
 .PHONY: docker-image
-docker-image: ## Build docker image.
-	docker build --network host -f docker/Dockerfile -t ${IMAGE_REGISTRY}:${IMAGE_TAG} .
+docker-image: build-by-dev-builder ## Build docker image.
+	mkdir -p ${ARCH} && \
+	cp ./target/${OUTPUT_DIR}/greptime ${ARCH}/greptime && \
+	docker build -f docker/ci/${BASE_IMAGE}/Dockerfile -t ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/greptimedb:${IMAGE_TAG} . && \
+	rm -r ${ARCH}
+
+.PHONY: docker-image-buildx
+docker-image-buildx: multi-platform-buildx ## Build docker image by buildx.
+	docker buildx build --builder ${BUILDX_BUILDER_NAME} \
+	  --build-arg="CARGO_PROFILE=${CARGO_PROFILE}" \
+	  --build-arg="FEATURES=${FEATURES}" \
+	  --build-arg="OUTPUT_DIR=${OUTPUT_DIR}" \
+	  -f docker/buildx/${BASE_IMAGE}/Dockerfile \
+	  -t ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/greptimedb:${IMAGE_TAG} ${BUILDX_MULTI_PLATFORM_BUILD_OPTS} .
+
+.PHONY: dev-builder
+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} .
+
+.PHONY: multi-platform-buildx
+multi-platform-buildx: ## Create buildx multi-platform builder.
+	docker buildx inspect ${BUILDX_BUILDER_NAME} || docker buildx create --name ${BUILDX_BUILDER_NAME} --driver docker-container --bootstrap --use
 
 ##@ Test
+test: nextest ## Run unit and integration tests.
+	cargo nextest run ${NEXTEST_OPTS}
 
-.PHONY: unit-test
-unit-test: ## Run unit test.
-	cargo test --workspace
-
-.PHONY: integration-test
-integration-test: ## Run integation test.
-	cargo test integration
+.PHONY: nextest ## Install nextest tools.
+nextest:
+	cargo --list | grep nextest || cargo install cargo-nextest --locked
 
 .PHONY: sqlness-test
 sqlness-test: ## Run sqlness test.
-	cargo run --bin sqlness-runner
+	cargo sqlness
 
 .PHONY: check
 check: ## Cargo check all the targets.
@@ -43,12 +134,27 @@ check: ## Cargo check all the targets.
 
 .PHONY: clippy
 clippy: ## Check clippy rules.
-	cargo clippy --workspace --all-targets -- -D warnings -D clippy::print_stdout -D clippy::print_stderr
+	cargo clippy --workspace --all-targets -F pyo3_backend -- -D warnings
 
 .PHONY: fmt-check
 fmt-check: ## Check code format.
 	cargo fmt --all -- --check
 
+.PHONY: start-etcd
+start-etcd: ## Start single node etcd for testing purpose.
+	docker run --rm -d --network=host -p 2379-2380:2379-2380 ${ETCD_IMAGE}
+
+.PHONY: stop-etcd
+stop-etcd: ## Stop single node etcd for testing purpose.
+	docker stop $$(docker ps -q --filter ancestor=${ETCD_IMAGE})
+
+.PHONY: run-it-in-container
+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-${BASE_IMAGE}:latest \
+	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
+
 ##@ General
 
 # The help target prints out all targets with their descriptions organized
@@ -64,4 +170,4 @@ fmt-check: ## Check code format.
 
 .PHONY: help
 help: ## Display help messages.
-	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[a-zA-Z_0-9-]+:.*?##/ { printf "  \033[36m%-20s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)
+	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[a-zA-Z_0-9-]+:.*?##/ { printf "  \033[36m%-30s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)

README.md

@@ -1,14 +1,14 @@
 <p align="center">
   <picture>
-    <source media="(prefers-color-scheme: light)" srcset="/docs/logo-text-padding.png">
-    <source media="(prefers-color-scheme: dark)" srcset="/docs/logo-text-padding-dark.png">
-    <img alt="GreptimeDB Logo" src="/docs/logo-text-padding.png" width="400px">
+    <source media="(prefers-color-scheme: light)" srcset="https://cdn.jsdelivr.net/gh/GreptimeTeam/greptimedb@develop/docs/logo-text-padding.png">
+    <source media="(prefers-color-scheme: dark)" srcset="https://cdn.jsdelivr.net/gh/GreptimeTeam/greptimedb@develop/docs/logo-text-padding-dark.png">
+    <img alt="GreptimeDB Logo" src="https://cdn.jsdelivr.net/gh/GreptimeTeam/greptimedb@develop/docs/logo-text-padding.png" width="400px">
   </picture>
 </p>
 
 
 <h3 align="center">
-    The next-generation hybrid timeseries/analytics processing database in the cloud
+    The next-generation hybrid time-series/analytics processing database in the cloud
 </h3>
 
 <p align="center">
@@ -23,6 +23,8 @@
     <a href="https://twitter.com/greptime"><img src="https://img.shields.io/badge/twitter-follow_us-1d9bf0.svg"></a>
     &nbsp;
     <a href="https://www.linkedin.com/company/greptime/"><img src="https://img.shields.io/badge/linkedin-connect_with_us-0a66c2.svg"></a>
+    &nbsp;
+    <a href="https://greptime.com/slack"><img src="https://img.shields.io/badge/slack-GreptimeDB-0abd59?logo=slack" alt="slack" /></a>
 </p>
 
 ## What is GreptimeDB
@@ -36,15 +38,19 @@ Our core developers have been building time-series data platform
 for years. Based on their best-practices, GreptimeDB is born to give you:
 
 - A standalone binary that scales to highly-available distributed cluster, providing a transparent experience for cluster users
-- Optimized columnar layout for handling time-series data; compacted, compressed, stored on various storage backends
-- Flexible index options, tackling high cardinality issues down
+- Optimized columnar layout for handling time-series data; compacted, compressed, and stored on various storage backends
+- Flexible indexes, tackling high cardinality issues down
 - Distributed, parallel query execution, leveraging elastic computing resource
 - Native SQL, and Python scripting for advanced analytical scenarios
-- Widely adopted database protocols and APIs
+- Widely adopted database protocols and APIs, native PromQL supports
 - Extensible table engine architecture for extensive workloads
 
 ## Quick Start
 
+### [GreptimePlay](https://greptime.com/playground)
+
+Try out the features of GreptimeDB right from your browser.
+
 ### Build
 
 #### Build from Source
@@ -61,6 +67,12 @@ To compile GreptimeDB from source, you'll need:
   find an installation instructions [here](https://grpc.io/docs/protoc-installation/).
   **Note that `protoc` version needs to be >= 3.15** because we have used the `optional`
   keyword. You can check it with `protoc --version`.
+- python3-dev or python3-devel(Optional feature, only needed if you want to run scripts
+  in CPython, and also need to enable `pyo3_backend` feature when compiling(by `cargo run -F pyo3_backend` or add `pyo3_backend` to src/script/Cargo.toml 's `features.default` like `default = ["python", "pyo3_backend]`)): this install a Python shared library required for running Python
+  scripting engine(In CPython Mode). This is available as `python3-dev` on
+  ubuntu, you can install it with `sudo apt install python3-dev`, or
+  `python3-devel` on RPM based distributions (e.g. Fedora, Red Hat, SuSE). Mac's
+  `Python3` package should have this shared library by default. More detail for compiling with PyO3 can be found in [PyO3](https://pyo3.rs/v0.18.1/building_and_distribution#configuring-the-python-version)'s documentation.
 
 #### Build with Docker
 
@@ -84,79 +96,45 @@ Or if you built from docker:
 docker run -p 4002:4002 -v "$(pwd):/tmp/greptimedb" greptime/greptimedb standalone start
 ```
 
-For more startup options, greptimedb's **distributed mode** and information
-about Kubernetes deployment, check our [docs](https://docs.greptime.com/).
+Please see [the online document site](https://docs.greptime.com/getting-started/overview#install-greptimedb) for more installation options and [operations info](https://docs.greptime.com/user-guide/operations/overview).
 
-### Connect
+### Get started
 
-1. Connect to GreptimeDB via standard [MySQL
-   client](https://dev.mysql.com/downloads/mysql/):
+Read the [complete getting started guide](https://docs.greptime.com/getting-started/overview#connect) on our [official document site](https://docs.greptime.com/).
 
-   ```
-   # The standalone instance listen on port 4002 by default.
-   mysql -h 127.0.0.1 -P 4002
-   ```
-
-2. Create table:
-
-   ```SQL
-   CREATE TABLE monitor (
-     host STRING,
-     ts TIMESTAMP,
-     cpu DOUBLE DEFAULT 0,
-     memory DOUBLE,
-     TIME INDEX (ts),
-     PRIMARY KEY(host)) ENGINE=mito WITH(regions=1);
-   ```
-
-3. Insert some data:
-
-   ```SQL
-   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host1', 66.6, 1024, 1660897955000);
-   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host2', 77.7, 2048, 1660897956000);
-   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host3', 88.8, 4096, 1660897957000);
-   ```
-
-4. Query the data:
-
-   ```SQL
-   SELECT * FROM monitor;
-   ```
-
-   ```TEXT
-   +-------+---------------------+------+--------+
-   | host  | ts                  | cpu  | memory |
-   +-------+---------------------+------+--------+
-   | host1 | 2022-08-19 08:32:35 | 66.6 |   1024 |
-   | host2 | 2022-08-19 08:32:36 | 77.7 |   2048 |
-   | host3 | 2022-08-19 08:32:37 | 88.8 |   4096 |
-   +-------+---------------------+------+--------+
-   3 rows in set (0.01 sec)
-   ```
-
-You can always cleanup test database by removing `/tmp/greptimedb`.
+To write and query data, GreptimeDB is compatible with multiple [protocols and clients](https://docs.greptime.com/user-guide/clients/overview).
 
 ## Resources
 
 ### Installation
 
-- [Pre-built Binaries](https://github.com/GreptimeTeam/greptimedb/releases):
-  downloadable pre-built binaries for Linux and MacOS
-- [Docker Images](https://hub.docker.com/r/greptime/greptimedb): pre-built
-  Docker images
+- [Pre-built Binaries](https://greptime.com/download):
+  For Linux and macOS, you can easily download pre-built binaries including official releases and nightly builds that are ready to use. 
+  In most cases, downloading the version without PyO3 is sufficient. However, if you plan to run scripts in CPython (and use Python packages like NumPy and Pandas), you will need to download the version with PyO3 and install a Python with the same version as the Python in the PyO3 version.
+  We recommend using virtualenv for the installation process to manage multiple Python versions.
+- [Docker Images](https://hub.docker.com/r/greptime/greptimedb)(**recommended**): pre-built
+  Docker images, this is the easiest way to try GreptimeDB. By default it runs CPython script with `pyo3_backend` enabled.
 - [`gtctl`](https://github.com/GreptimeTeam/gtctl): the command-line tool for
   Kubernetes deployment
 
 ### Documentation
 
-- GreptimeDB [User Guide](https://docs.greptime.com/user-guide/concepts.html)
+- GreptimeDB [User Guide](https://docs.greptime.com/user-guide/concepts/overview)
 - GreptimeDB [Developer
   Guide](https://docs.greptime.com/developer-guide/overview.html)
+- GreptimeDB [internal code document](https://greptimedb.rs)
+
+### Dashboard
+- [The dashboard UI for GreptimeDB](https://github.com/GreptimeTeam/dashboard)
 
 ### SDK
 
-- [GreptimeDB Java
-  Client](https://github.com/GreptimeTeam/greptimedb-client-java)
+- [GreptimeDB C++ Client](https://github.com/GreptimeTeam/greptimedb-client-cpp)
+- [GreptimeDB Erlang Client](https://github.com/GreptimeTeam/greptimedb-client-erl)
+- [GreptimeDB Go Client](https://github.com/GreptimeTeam/greptimedb-client-go)
+- [GreptimeDB Java Client](https://github.com/GreptimeTeam/greptimedb-client-java)
+- [GreptimeDB Python Client](https://github.com/GreptimeTeam/greptimedb-client-py) (WIP)
+- [GreptimeDB Rust Client](https://github.com/GreptimeTeam/greptimedb-client-rust)
 
 ## Project Status
 
@@ -169,7 +147,7 @@ For future plans, check out [GreptimeDB roadmap](https://github.com/GreptimeTeam
 
 ## Community
 
-Our core team is thrilled too see you participate in any ways you like. When you are stuck, try to
+Our core team is thrilled to see you participate in any ways you like. When you are stuck, try to
 ask for help by filling an issue with a detailed description of what you were trying to do
 and what went wrong. If you have any questions or if you would like to get involved in our
 community, please check out:

SECURITY.md

@@ -0,0 +1,19 @@
+# Security Policy
+
+## Supported Versions
+
+| Version | Supported          |
+| ------- | ------------------ |
+| >= v0.1.0 | :white_check_mark: |
+| < v0.1.0   | :x:                |
+
+## Reporting a Vulnerability
+
+We place great importance on the security of GreptimeDB code, software, 
+and cloud platform. If you come across a security vulnerability in GreptimeDB, 
+we kindly request that you inform us immediately. We will thoroughly investigate
+all valid reports and make every effort to resolve the issue promptly.
+
+To report any issues or vulnerabilities, please email us at info@greptime.com, rather than 
+posting publicly on GitHub. Be sure to provide us with the version identifier as well as details
+on how the vulnerability can be exploited.

benchmarks/Cargo.toml

@@ -7,8 +7,8 @@ license.workspace = true
 [dependencies]
 arrow.workspace = true
 clap = { version = "4.0", features = ["derive"] }
-client = { path = "../src/client" }
+client = { workspace = true }
 indicatif = "0.17.1"
-itertools = "0.10.5"
+itertools.workspace = true
 parquet.workspace = true
-tokio = { version = "1.21", features = ["full"] }
+tokio.workspace = true

benchmarks/src/bin/nyc-taxi.rs

@@ -1,10 +1,10 @@
-// Copyright 2022 Greptime Team
+// 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
+//     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,
@@ -21,19 +21,19 @@ use std::collections::HashMap;
 use std::path::{Path, PathBuf};
 use std::time::Instant;
 
-use arrow::array::{ArrayRef, PrimitiveArray, StringArray, TimestampNanosecondArray};
+use arrow::array::{ArrayRef, PrimitiveArray, StringArray, TimestampMicrosecondArray};
 use arrow::datatypes::{DataType, Float64Type, Int64Type};
 use arrow::record_batch::RecordBatch;
 use clap::Parser;
-use client::admin::Admin;
 use client::api::v1::column::Values;
-use client::api::v1::{Column, ColumnDataType, ColumnDef, CreateTableExpr, InsertExpr, TableId};
-use client::{Client, Database, Select};
+use client::api::v1::{
+    Column, ColumnDataType, ColumnDef, CreateTableExpr, InsertRequest, InsertRequests,
+};
+use client::{Client, Database, DEFAULT_CATALOG_NAME, DEFAULT_SCHEMA_NAME};
 use indicatif::{MultiProgress, ProgressBar, ProgressStyle};
 use parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder;
 use tokio::task::JoinSet;
 
-const DATABASE_NAME: &str = "greptime";
 const CATALOG_NAME: &str = "greptime";
 const SCHEMA_NAME: &str = "public";
 const TABLE_NAME: &str = "nyc_taxi";
@@ -63,7 +63,7 @@ struct Args {
     #[arg(long = "skip-read")]
     skip_read: bool,
 
-    #[arg(short, long, default_value_t = String::from("127.0.0.1:3001"))]
+    #[arg(short, long, default_value_t = String::from("127.0.0.1:4001"))]
     endpoint: String,
 }
 
@@ -99,16 +99,22 @@ async fn write_data(
 
     for record_batch in record_batch_reader {
         let record_batch = record_batch.unwrap();
+        if !is_record_batch_full(&record_batch) {
+            continue;
+        }
         let (columns, row_count) = convert_record_batch(record_batch);
-        let insert_expr = InsertExpr {
-            schema_name: "public".to_string(),
+        let request = InsertRequest {
             table_name: TABLE_NAME.to_string(),
             region_number: 0,
             columns,
             row_count,
         };
+        let requests = InsertRequests {
+            inserts: vec![request],
+        };
+
         let now = Instant::now();
-        db.insert(insert_expr).await.unwrap();
+        let _ = db.insert(requests).await.unwrap();
         let elapsed = now.elapsed();
         total_rpc_elapsed_ms += elapsed.as_millis();
         progress_bar.inc(row_count as _);
@@ -125,11 +131,17 @@ fn convert_record_batch(record_batch: RecordBatch) -> (Vec<Column>, u32) {
     let mut columns = vec![];
 
     for (array, field) in record_batch.columns().iter().zip(fields.iter()) {
-        let values = build_values(array);
+        let (values, datatype) = build_values(array);
+
         let column = Column {
-            column_name: field.name().to_owned(),
+            column_name: field.name().clone(),
             values: Some(values),
-            null_mask: vec![],
+            null_mask: array
+                .to_data()
+                .nulls()
+                .map(|bitmap| bitmap.buffer().as_slice().to_vec())
+                .unwrap_or_default(),
+            datatype: datatype.into(),
             // datatype and semantic_type are set to default
             ..Default::default()
         };
@@ -139,7 +151,7 @@ fn convert_record_batch(record_batch: RecordBatch) -> (Vec<Column>, u32) {
     (columns, row_count as _)
 }
 
-fn build_values(column: &ArrayRef) -> Values {
+fn build_values(column: &ArrayRef) -> (Values, ColumnDataType) {
     match column.data_type() {
         DataType::Int64 => {
             let array = column
@@ -147,10 +159,13 @@ fn build_values(column: &ArrayRef) -> Values {
                 .downcast_ref::<PrimitiveArray<Int64Type>>()
                 .unwrap();
             let values = array.values();
-            Values {
-                i64_values: values.to_vec(),
-                ..Default::default()
-            }
+            (
+                Values {
+                    i64_values: values.to_vec(),
+                    ..Default::default()
+                },
+                ColumnDataType::Int64,
+            )
         }
         DataType::Float64 => {
             let array = column
@@ -158,29 +173,38 @@ fn build_values(column: &ArrayRef) -> Values {
                 .downcast_ref::<PrimitiveArray<Float64Type>>()
                 .unwrap();
             let values = array.values();
-            Values {
-                f64_values: values.to_vec(),
-                ..Default::default()
-            }
+            (
+                Values {
+                    f64_values: values.to_vec(),
+                    ..Default::default()
+                },
+                ColumnDataType::Float64,
+            )
         }
         DataType::Timestamp(_, _) => {
             let array = column
                 .as_any()
-                .downcast_ref::<TimestampNanosecondArray>()
+                .downcast_ref::<TimestampMicrosecondArray>()
                 .unwrap();
             let values = array.values();
-            Values {
-                i64_values: values.to_vec(),
-                ..Default::default()
-            }
+            (
+                Values {
+                    ts_microsecond_values: values.to_vec(),
+                    ..Default::default()
+                },
+                ColumnDataType::TimestampMicrosecond,
+            )
         }
         DataType::Utf8 => {
             let array = column.as_any().downcast_ref::<StringArray>().unwrap();
             let values = array.iter().filter_map(|s| s.map(String::from)).collect();
-            Values {
-                string_values: values,
-                ..Default::default()
-            }
+            (
+                Values {
+                    string_values: values,
+                    ..Default::default()
+                },
+                ColumnDataType::String,
+            )
         }
         DataType::Null
         | DataType::Boolean
@@ -207,14 +231,19 @@ fn build_values(column: &ArrayRef) -> Values {
         | DataType::FixedSizeList(_, _)
         | DataType::LargeList(_)
         | DataType::Struct(_)
-        | DataType::Union(_, _, _)
+        | DataType::Union(_, _)
         | DataType::Dictionary(_, _)
         | DataType::Decimal128(_, _)
         | DataType::Decimal256(_, _)
+        | DataType::RunEndEncoded(_, _)
         | DataType::Map(_, _) => todo!(),
     }
 }
 
+fn is_record_batch_full(batch: &RecordBatch) -> bool {
+    batch.columns().iter().all(|col| col.null_count() == 0)
+}
+
 fn create_table_expr() -> CreateTableExpr {
     CreateTableExpr {
         catalog_name: CATALOG_NAME.to_string(),
@@ -230,13 +259,13 @@ fn create_table_expr() -> CreateTableExpr {
             },
             ColumnDef {
                 name: "tpep_pickup_datetime".to_string(),
-                datatype: ColumnDataType::Int64 as i32,
+                datatype: ColumnDataType::TimestampMicrosecond as i32,
                 is_nullable: true,
                 default_constraint: vec![],
             },
             ColumnDef {
                 name: "tpep_dropoff_datetime".to_string(),
-                datatype: ColumnDataType::Int64 as i32,
+                datatype: ColumnDataType::TimestampMicrosecond as i32,
                 is_nullable: true,
                 default_constraint: vec![],
             },
@@ -341,34 +370,30 @@ fn create_table_expr() -> CreateTableExpr {
         primary_keys: vec!["VendorID".to_string()],
         create_if_not_exists: false,
         table_options: Default::default(),
-        region_ids: vec![0],
-        table_id: Some(TableId { id: 0 }),
+        region_numbers: vec![0],
+        table_id: None,
+        engine: "mito".to_string(),
     }
 }
 
 fn query_set() -> HashMap<String, String> {
-    let mut ret = HashMap::new();
-
-    ret.insert(
-        "count_all".to_string(),
-        format!("SELECT COUNT(*) FROM {TABLE_NAME};"),
-    );
-
-    ret.insert(
-        "fare_amt_by_passenger".to_string(),
-        format!("SELECT passenger_count, MIN(fare_amount), MAX(fare_amount), SUM(fare_amount) FROM {TABLE_NAME} GROUP BY passenger_count")
-    );
-
-    ret
+    HashMap::from([
+        (
+            "count_all".to_string(), 
+            format!("SELECT COUNT(*) FROM {TABLE_NAME};"),
+        ),
+        (
+            "fare_amt_by_passenger".to_string(),
+            format!("SELECT passenger_count, MIN(fare_amount), MAX(fare_amount), SUM(fare_amount) FROM {TABLE_NAME} GROUP BY passenger_count"),
+        )
+    ])
 }
 
-async fn do_write(args: &Args, client: &Client) {
-    let admin = Admin::new("admin", client.clone());
-
+async fn do_write(args: &Args, db: &Database) {
     let mut file_list = get_file_list(args.path.clone().expect("Specify data path in argument"));
     let mut write_jobs = JoinSet::new();
 
-    let create_table_result = admin.create(create_table_expr()).await;
+    let create_table_result = db.create(create_table_expr()).await;
     println!("Create table result: {create_table_result:?}");
 
     let progress_bar_style = ProgressStyle::with_template(
@@ -383,19 +408,21 @@ async fn do_write(args: &Args, client: &Client) {
     let batch_size = args.batch_size;
     for _ in 0..args.thread_num {
         if let Some(path) = file_list.pop() {
-            let db = Database::new(DATABASE_NAME, client.clone());
+            let db = db.clone();
             let mpb = multi_progress_bar.clone();
             let pb_style = progress_bar_style.clone();
-            write_jobs.spawn(async move { write_data(batch_size, &db, path, mpb, pb_style).await });
+            let _ = write_jobs
+                .spawn(async move { write_data(batch_size, &db, path, mpb, pb_style).await });
         }
     }
     while write_jobs.join_next().await.is_some() {
         file_progress.inc(1);
         if let Some(path) = file_list.pop() {
-            let db = Database::new(DATABASE_NAME, client.clone());
+            let db = db.clone();
             let mpb = multi_progress_bar.clone();
             let pb_style = progress_bar_style.clone();
-            write_jobs.spawn(async move { write_data(batch_size, &db, path, mpb, pb_style).await });
+            let _ = write_jobs
+                .spawn(async move { write_data(batch_size, &db, path, mpb, pb_style).await });
         }
     }
 }
@@ -405,7 +432,7 @@ async fn do_query(num_iter: usize, db: &Database) {
         println!("Running query: {query}");
         for i in 0..num_iter {
             let now = Instant::now();
-            let _res = db.select(Select::Sql(query.clone())).await.unwrap();
+            let _res = db.sql(&query).await.unwrap();
             let elapsed = now.elapsed();
             println!(
                 "query {}, iteration {}: {}ms",
@@ -427,13 +454,13 @@ fn main() {
         .unwrap()
         .block_on(async {
             let client = Client::with_urls(vec![&args.endpoint]);
+            let db = Database::new(DEFAULT_CATALOG_NAME, DEFAULT_SCHEMA_NAME, client);
 
             if !args.skip_write {
-                do_write(&args, &client).await;
+                do_write(&args, &db).await;
             }
 
             if !args.skip_read {
-                let db = Database::new(DATABASE_NAME, client.clone());
                 do_query(args.iter_num, &db).await;
             }
         })

codecov.yml

@@ -8,3 +8,5 @@ coverage:
 ignore:
   - "**/error*.rs" # ignore all error.rs files
   - "tests/runner/*.rs" # ignore integration test runner
+comment:                  # this is a top-level key
+  layout: "diff"

config/datanode.example.toml

@@ -1,18 +1,84 @@
-node_id = 42
-mode = 'distributed'
-rpc_addr = '127.0.0.1:3001'
-wal_dir = '/tmp/greptimedb/wal'
-rpc_runtime_size = 8
-mysql_addr = '127.0.0.1:4406'
-mysql_runtime_size = 4
+# Node running mode, see `standalone.example.toml`.
+mode = "distributed"
+# Whether to use in-memory catalog, see `standalone.example.toml`.
 enable_memory_catalog = false
+# The datanode identifier, should be unique.
+node_id = 42
+# gRPC server address, "127.0.0.1:3001" by default.
+rpc_addr = "127.0.0.1:3001"
+# Hostname of this node.
+rpc_hostname = "127.0.0.1"
+# The number of gRPC server worker threads, 8 by default.
+rpc_runtime_size = 8
 
-[storage]
-type = 'File'
-data_dir = '/tmp/greptimedb/data/'
+[heartbeat]
+# Interval for sending heartbeat messages to the Metasrv in milliseconds, 5000 by default.
+interval_millis = 5000
 
-[meta_client_opts]
-metasrv_addrs = ['127.0.0.1:3002']
+# Metasrv client options.
+[meta_client_options]
+# Metasrv address list.
+metasrv_addrs = ["127.0.0.1:3002"]
+# Operation timeout in milliseconds, 3000 by default.
 timeout_millis = 3000
+# Connect server timeout in milliseconds, 5000 by default.
 connect_timeout_millis = 5000
-tcp_nodelay = false
+# `TCP_NODELAY` option for accepted connections, true by default.
+tcp_nodelay = true
+
+# WAL options, see `standalone.example.toml`.
+[wal]
+# WAL data directory
+# dir = "/tmp/greptimedb/wal"
+file_size = "256MB"
+purge_threshold = "4GB"
+purge_interval = "10m"
+read_batch_size = 128
+sync_write = false
+
+# Storage options, see `standalone.example.toml`.
+[storage]
+# The working home directory.
+data_home = "/tmp/greptimedb/"
+type = "File"
+# TTL for all tables. Disabled by default.
+# global_ttl = "7d"
+
+# Compaction options, see `standalone.example.toml`.
+[storage.compaction]
+max_inflight_tasks = 4
+max_files_in_level0 = 8
+max_purge_tasks = 32
+
+# Storage manifest options
+[storage.manifest]
+# Region checkpoint actions margin.
+# Create a checkpoint every <checkpoint_margin> actions.
+checkpoint_margin = 10
+# Region manifest logs and checkpoints gc execution duration
+gc_duration = '10m'
+
+# Storage flush options
+[storage.flush]
+# Max inflight flush tasks.
+max_flush_tasks = 8
+# Default write buffer size for a region.
+region_write_buffer_size = "32MB"
+# Interval to check whether a region needs flush.
+picker_schedule_interval = "5m"
+# Interval to auto flush a region if it has not flushed yet.
+auto_flush_interval = "1h"
+# Global write buffer size for all regions.
+global_write_buffer_size = "1GB"
+
+# Procedure storage options, see `standalone.example.toml`.
+[procedure]
+max_retry_times = 3
+retry_delay = "500ms"
+
+# Log options
+# [logging]
+# Specify logs directory.
+# dir = "/tmp/greptimedb/logs"
+# Specify the log level [info | debug | error | warn]
+# level = "info"

config/frontend.example.toml

@@ -1,12 +1,76 @@
-mode = 'distributed'
-datanode_rpc_addr = '127.0.0.1:3001'
+# Node running mode, see `standalone.example.toml`.
+mode = "distributed"
 
+[heartbeat]
+# Interval for sending heartbeat task to the Metasrv in milliseconds, 5000 by default.
+interval_millis = 5000
+# Interval for retry sending heartbeat task in milliseconds, 5000 by default.
+retry_interval_millis = 5000
+
+# HTTP server options, see `standalone.example.toml`.
 [http_options]
-addr = '127.0.0.1:4000'
+addr = "127.0.0.1:4000"
 timeout = "30s"
+body_limit = "64MB"
 
-[meta_client_opts]
-metasrv_addrs = ['127.0.0.1:3002']
+# gRPC server options, see `standalone.example.toml`.
+[grpc_options]
+addr = "127.0.0.1:4001"
+runtime_size = 8
+
+# MySQL server options, see `standalone.example.toml`.
+[mysql_options]
+addr = "127.0.0.1:4002"
+runtime_size = 2
+
+# MySQL server TLS options, see `standalone.example.toml`.
+[mysql_options.tls]
+mode = "disable"
+cert_path = ""
+key_path = ""
+
+# PostgresSQL server options, see `standalone.example.toml`.
+[postgres_options]
+addr = "127.0.0.1:4003"
+runtime_size = 2
+
+# PostgresSQL server TLS options, see `standalone.example.toml`.
+[postgres_options.tls]
+mode = "disable"
+cert_path = ""
+key_path = ""
+
+# OpenTSDB protocol options, see `standalone.example.toml`.
+[opentsdb_options]
+addr = "127.0.0.1:4242"
+runtime_size = 2
+
+# InfluxDB protocol options, see `standalone.example.toml`.
+[influxdb_options]
+enable = true
+
+# Prometheus remote storage options, see `standalone.example.toml`.
+[prom_store_options]
+enable = true
+
+# Metasrv client options, see `datanode.example.toml`.
+[meta_client_options]
+metasrv_addrs = ["127.0.0.1:3002"]
 timeout_millis = 3000
+# DDL timeouts options.
+ddl_timeout_millis = 10000
 connect_timeout_millis = 5000
-tcp_nodelay = false
+tcp_nodelay = true
+
+# Log options, see `standalone.example.toml`
+# [logging]
+# dir = "/tmp/greptimedb/logs"
+# level = "info"
+
+# Datanode options.
+[datanode]
+# Datanode client options.
+[datanode.client]
+timeout = "10s"
+connect_timeout = "10s"
+tcp_nodelay = true

config/metasrv.example.toml

@@ -1,4 +1,39 @@
-bind_addr = '127.0.0.1:3002'
-server_addr = '127.0.0.1:3002'
-store_addr = '127.0.0.1:2379'
+# The working home directory.
+data_home = "/tmp/metasrv/"
+# The bind address of metasrv, "127.0.0.1:3002" by default.
+bind_addr = "127.0.0.1:3002"
+# The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost.
+server_addr = "127.0.0.1:3002"
+# Etcd server address, "127.0.0.1:2379" by default.
+store_addr = "127.0.0.1:2379"
+# Datanode lease in seconds, 15 seconds by default.
 datanode_lease_secs = 15
+# Datanode selector type.
+# - "LeaseBased" (default value).
+# - "LoadBased"
+# For details, please see "https://docs.greptime.com/developer-guide/meta/selector".
+selector = "LeaseBased"
+# Store data in memory, false by default.
+use_memory_store = false
+# Whether to enable greptimedb telemetry, true by default.
+enable_telemetry = true
+
+# Log options, see `standalone.example.toml`
+# [logging]
+# dir = "/tmp/greptimedb/logs"
+# level = "info"
+
+# Procedure storage options.
+[procedure]
+# Procedure max retry time.
+max_retry_times = 12
+# Initial retry delay of procedures, increases exponentially
+retry_delay = "500ms"
+
+# # Datanode options.
+# [datanode]
+# # Datanode client options.
+# [datanode.client_options]
+# timeout_millis = 10000
+# connect_timeout_millis = 10000
+# tcp_nodelay = true

config/standalone.example.toml

@@ -1,36 +1,145 @@
-node_id = 0
-mode = 'standalone'
-wal_dir = '/tmp/greptimedb/wal/'
+# Node running mode, "standalone" or "distributed".
+mode = "standalone"
+# Whether to use in-memory catalog, `false` by default.
 enable_memory_catalog = false
+# Whether to enable greptimedb telemetry, true by default.
+enable_telemetry = true
 
+# HTTP server options.
 [http_options]
-addr = '127.0.0.1:4000'
+# Server address, "127.0.0.1:4000" by default.
+addr = "127.0.0.1:4000"
+# HTTP request timeout, 30s by default.
 timeout = "30s"
+# HTTP request body limit, 64Mb by default.
+# the following units are supported: B, KB, KiB, MB, MiB, GB, GiB, TB, TiB, PB, PiB
+body_limit = "64MB"
 
-[storage]
-type = 'File'
-data_dir = '/tmp/greptimedb/data/'
-
+# gRPC server options.
 [grpc_options]
-addr = '127.0.0.1:4001'
+# Server address, "127.0.0.1:4001" by default.
+addr = "127.0.0.1:4001"
+# The number of server worker threads, 8 by default.
 runtime_size = 8
 
+# MySQL server options.
 [mysql_options]
-addr = '127.0.0.1:4002'
+# Server address, "127.0.0.1:4002" by default.
+addr = "127.0.0.1:4002"
+# The number of server worker threads, 2 by default.
 runtime_size = 2
 
-[influxdb_options]
-enable = true
-
-[opentsdb_options]
-addr = '127.0.0.1:4242'
-enable = true
-runtime_size = 2
-
-[prometheus_options]
-enable = true
+# MySQL server TLS options.
+[mysql_options.tls]
+# TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
+# - "disable" (default value)
+# - "prefer"
+# - "require"
+# - "verify-ca"
+# - "verify-full"
+mode = "disable"
+# Certificate file path.
+cert_path = ""
+# Private key file path.
+key_path = ""
 
+# PostgresSQL server options.
 [postgres_options]
-addr = '127.0.0.1:4003'
+# Server address, "127.0.0.1:4003" by default.
+addr = "127.0.0.1:4003"
+# The number of server worker threads, 2 by default.
 runtime_size = 2
-check_pwd = false
+
+# PostgresSQL server TLS options, see `[mysql_options.tls]` section.
+[postgres_options.tls]
+# TLS mode.
+mode = "disable"
+# certificate file path.
+cert_path = ""
+# private key file path.
+key_path = ""
+
+# OpenTSDB protocol options.
+[opentsdb_options]
+# OpenTSDB telnet API server address, "127.0.0.1:4242" by default.
+addr = "127.0.0.1:4242"
+# The number of server worker threads, 2 by default.
+runtime_size = 2
+
+# InfluxDB protocol options.
+[influxdb_options]
+# Whether to enable InfluxDB protocol in HTTP API, true by default.
+enable = true
+
+# Prometheus remote storage options
+[prom_store_options]
+# Whether to enable Prometheus remote write and read in HTTP API, true by default.
+enable = true
+
+# WAL options.
+[wal]
+# WAL data directory
+# dir = "/tmp/greptimedb/wal"
+# WAL file size in bytes.
+file_size = "256MB"
+# WAL purge threshold.
+purge_threshold = "4GB"
+# WAL purge interval in seconds.
+purge_interval = "10m"
+# WAL read batch size.
+read_batch_size = 128
+# Whether to sync log file after every write.
+sync_write = false
+
+# Storage options.
+[storage]
+# The working home directory.
+data_home = "/tmp/greptimedb/"
+# Storage type.
+type = "File"
+# TTL for all tables. Disabled by default.
+# global_ttl = "7d"
+
+# Compaction options.
+[storage.compaction]
+# Max task number that can concurrently run.
+max_inflight_tasks = 4
+# Max files in level 0 to trigger compaction.
+max_files_in_level0 = 8
+# Max task number for SST purge task after compaction.
+max_purge_tasks = 32
+
+# Storage manifest options
+[storage.manifest]
+# Region checkpoint actions margin.
+# Create a checkpoint every <checkpoint_margin> actions.
+checkpoint_margin = 10
+# Region manifest logs and checkpoints gc execution duration
+gc_duration = '10m'
+
+# Storage flush options
+[storage.flush]
+# Max inflight flush tasks.
+max_flush_tasks = 8
+# Default write buffer size for a region.
+region_write_buffer_size = "32MB"
+# Interval to check whether a region needs flush.
+picker_schedule_interval = "5m"
+# Interval to auto flush a region if it has not flushed yet.
+auto_flush_interval = "1h"
+# Global write buffer size for all regions.
+global_write_buffer_size = "1GB"
+
+# Procedure storage options.
+[procedure]
+# Procedure max retry time.
+max_retry_times = 3
+# Initial retry delay of procedures, increases exponentially
+retry_delay = "500ms"
+
+# Log options
+# [logging]
+# Specify logs directory.
+# dir = "/tmp/greptimedb/logs"
+# Specify the log level [info | debug | error | warn]
+# level = "info"

docker/Dockerfile

@@ -1,31 +0,0 @@
-FROM ubuntu:22.04 as builder
-
-ENV LANG en_US.utf8
-WORKDIR /greptimedb
-
-# Install dependencies.
-RUN apt-get update && apt-get install -y \
-    libssl-dev \
-    protobuf-compiler \
-    curl \
-    build-essential \
-    pkg-config
-
-# 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 /root/.cargo/bin/:$PATH
-
-# Build the project in release mode.
-COPY . .
-RUN cargo build --release
-
-# Export the binary to the clean image.
-# TODO(zyy17): Maybe should use the more secure container image.
-FROM ubuntu:22.04 as base
-
-WORKDIR /greptime
-COPY --from=builder /greptimedb/target/release/greptime /greptime/bin/
-ENV PATH /greptime/bin/:$PATH
-
-ENTRYPOINT ["greptime"]

docker/buildx/centos/Dockerfile

@@ -0,0 +1,54 @@
+FROM centos:7 as builder
+
+ARG CARGO_PROFILE
+ARG FEATURES
+ARG OUTPUT_DIR
+
+ENV LANG en_US.utf8
+WORKDIR /greptimedb
+
+# Install dependencies
+RUN ulimit -n 1024000 && yum groupinstall -y 'Development Tools'
+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/
+
+# 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/:$PATH
+
+# Build the project in release mode.
+RUN --mount=target=.,rw \
+    --mount=type=cache,target=/root/.cargo/registry \
+    make build \
+    CARGO_PROFILE=${CARGO_PROFILE} \
+    FEATURES=${FEATURES} \
+    TARGET_DIR=/out/target
+
+# Export the binary to the clean image.
+FROM centos:7 as base
+
+ARG OUTPUT_DIR
+
+RUN yum install -y epel-release \
+    openssl \
+    openssl-devel  \
+    centos-release-scl  \
+    rh-python38  \
+    rh-python38-python-devel \
+    which
+
+WORKDIR /greptime
+COPY --from=builder /out/target/${OUTPUT_DIR}/greptime /greptime/bin/
+ENV PATH /greptime/bin/:$PATH
+
+ENTRYPOINT ["greptime"]

docker/buildx/ubuntu/Dockerfile

@@ -0,0 +1,57 @@
+FROM ubuntu:22.04 as builder
+
+ARG CARGO_PROFILE
+ARG FEATURES
+ARG OUTPUT_DIR
+
+ENV LANG en_US.utf8
+WORKDIR /greptimedb
+
+# Install dependencies.
+RUN --mount=type=cache,target=/var/cache/apt \
+    apt-get update && apt-get install -y \
+    libssl-dev \
+    protobuf-compiler \
+    curl \
+    git \
+    build-essential \
+    pkg-config \
+    python3.10 \
+    python3.10-dev \
+    python3-pip
+
+# 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 /root/.cargo/bin/:$PATH
+
+# Build the project in release mode.
+RUN --mount=target=. \
+    --mount=type=cache,target=/root/.cargo/registry \
+    make build \
+    CARGO_PROFILE=${CARGO_PROFILE} \
+    FEATURES=${FEATURES} \
+    TARGET_DIR=/out/target
+
+# Export the binary to the clean image.
+# TODO(zyy17): Maybe should use the more secure container image.
+FROM ubuntu:22.04 as base
+
+ARG OUTPUT_DIR
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get \
+    -y install ca-certificates \
+    python3.10 \
+    python3.10-dev \
+    python3-pip \
+    curl
+
+COPY ./docker/python/requirements.txt /etc/greptime/requirements.txt
+
+RUN python3 -m pip install -r /etc/greptime/requirements.txt
+
+WORKDIR /greptime
+COPY --from=builder /out/target/${OUTPUT_DIR}/greptime /greptime/bin/
+ENV PATH /greptime/bin/:$PATH
+
+ENTRYPOINT ["greptime"]

docker/ci/Dockerfile

@@ -1,9 +0,0 @@
-FROM ubuntu:22.04
-
-ARG TARGETARCH
-
-ADD $TARGETARCH/greptime /greptime/bin/
-
-ENV PATH /greptime/bin/:$PATH
-
-ENTRYPOINT ["greptime"]

docker/ci/centos/Dockerfile

@@ -0,0 +1,16 @@
+FROM centos:7
+
+RUN yum install -y epel-release \
+    openssl \
+    openssl-devel  \
+    centos-release-scl  \
+    rh-python38  \
+    rh-python38-python-devel
+
+ARG TARGETARCH
+
+ADD $TARGETARCH/greptime /greptime/bin/
+
+ENV PATH /greptime/bin/:$PATH
+
+ENTRYPOINT ["greptime"]

docker/ci/ubuntu/Dockerfile

@@ -0,0 +1,20 @@
+FROM ubuntu:22.04
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
+    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
+
+ARG TARGETARCH
+
+ADD $TARGETARCH/greptime /greptime/bin/
+
+ENV PATH /greptime/bin/:$PATH
+
+ENTRYPOINT ["greptime"]

docker/dev-builder/centos/Dockerfile

@@ -0,0 +1,29 @@
+FROM centos:7 as builder
+
+ENV LANG en_US.utf8
+
+# Install dependencies
+RUN ulimit -n 1024000 && yum groupinstall -y 'Development Tools'
+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/
+
+# 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
+
+# Install Rust toolchains.
+ARG RUST_TOOLCHAIN
+RUN rustup toolchain install ${RUST_TOOLCHAIN}
+
+# Install nextest.
+RUN cargo install cargo-nextest --locked

docker/dev-builder/ubuntu/Dockerfile

@@ -0,0 +1,36 @@
+FROM ubuntu:22.04
+
+ENV LANG en_US.utf8
+WORKDIR /greptimedb
+
+# Install dependencies.
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
+    libssl-dev \
+    tzdata \
+    protobuf-compiler \
+    curl \
+    ca-certificates \
+    git \
+    build-essential \
+    pkg-config \
+    python3.10 \
+    python3.10-dev \
+    python3-pip
+
+RUN git config --global --add safe.directory /greptimedb
+
+# Install Python dependencies.
+COPY ./docker/python/requirements.txt /etc/greptime/requirements.txt
+RUN python3 -m pip install -r /etc/greptime/requirements.txt
+
+# 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 /root/.cargo/bin/:$PATH
+
+# Install Rust toolchains.
+ARG RUST_TOOLCHAIN
+RUN rustup toolchain install ${RUST_TOOLCHAIN}
+
+# Install nextest.
+RUN cargo install cargo-nextest --locked

docker/python/requirements.txt

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

docs/benchmarks/tsbs/v0.3.2.md

@@ -0,0 +1,39 @@
+# TSBS benchmark - v0.3.2
+
+## Environment
+
+|     |     |
+| --- | --- |
+| CPU | AMD Ryzen 7 7735HS (8 core 3.2GHz) |
+| Memory | 32GB |
+| Disk | SOLIDIGM SSDPFKNU010TZ |
+| OS | Ubuntu 22.04.2 LTS |
+
+
+## Write performance
+
+| Write buffer size | Ingest rate（rows/s） |
+| --- | --- |
+| 512M | 139583.04 |
+| 32M | 279250.52 |
+
+
+## Query performance
+
+| Query type  | v0.3.2 write buffer 32M (ms) | v0.3.2 write buffer 512M (ms) | v0.3.1 write buffer 32M (ms) |
+| --- | --- | --- | --- |
+| cpu-max-all-1 | 921.12 | 241.23 | 553.63 |
+| cpu-max-all-8 | 2657.66 | 502.78 | 3308.41 |
+| double-groupby-1 | 28238.85 | 27367.42 | 52148.22 |
+| double-groupby-5 | 33094.65 | 32421.89 | 56762.37 |
+| double-groupby-all | 38565.89 | 38635.52 | 59596.80 |
+| groupby-orderby-limit | 23321.60 | 22423.55 | 53983.23 |
+| high-cpu-1 | 1167.04 | 254.15 | 832.41 |
+| high-cpu-all | 32814.08 | 29906.94 | 62853.12 |
+| lastpoint | 192045.05 | 153575.42 | NA   |
+| single-groupby-1-1-1 | 63.97 | 87.35 | 92.66 |
+| single-groupby-1-1-12 | 666.24 | 326.98 | 781.50 |
+| single-groupby-1-8-1 | 225.29 | 137.97 |281.95 |
+| single-groupby-5-1-1 | 70.40 | 81.64 | 86.15 |
+| single-groupby-5-1-12 | 722.75 | 356.01 | 805.18 |
+| single-groupby-5-8-1 | 285.60 | 115.88 | 326.29 |

docs/how-to/how-to-implement-sql-statement.md

@@ -0,0 +1,74 @@
+This document introduces how to implement SQL statements in GreptimeDB.
+
+The execution entry point for SQL statements locates at Frontend Instance. You can see it has
+implemented `SqlQueryHandler`:
+
+```rust
+impl SqlQueryHandler for Instance {
+    type Error = Error;
+
+    async fn do_query(&self, query: &str, query_ctx: QueryContextRef) -> Vec<Result<Output>> {
+        // ...
+    }
+}
+```
+
+Normally, when a SQL query arrives at GreptimeDB, the `do_query` method will be called. After some parsing work, the SQL
+will be feed into `StatementExecutor`:
+
+```rust
+// in Frontend Instance:
+self.statement_executor.execute_sql(stmt, query_ctx).await
+```
+
+That's where we handle our SQL statements. You can just create a new match arm for your statement there, then the
+statement is implemented for both GreptimeDB Standalone and Cluster. You can see how `DESCRIBE TABLE` is implemented as
+an example.
+
+Now, what if the statements should be handled differently for GreptimeDB Standalone and Cluster? You can see there's
+a `SqlStatementExecutor` field in `StatementExecutor`. Each GreptimeDB Standalone and Cluster has its own implementation
+of `SqlStatementExecutor`. If you are going to implement the statements differently in the two mode (
+like `CREATE TABLE`), you have to implement them in their own `SqlStatementExecutor`s.
+
+Summarize as the diagram below:
+
+```text
+                             SQL query                            
+                                |                                
+                                v                                
+                  +---------------------------+                  
+                  | SqlQueryHandler::do_query |                  
+                  +---------------------------+                  
+                                |                                
+                                | SQL parsing                    
+                                v                                
+               +--------------------------------+                
+               | StatementExecutor::execute_sql |                
+               +--------------------------------+                
+                                |                                
+                                | SQL execution                    
+                                v                                
+               +----------------------------------+                
+               | commonly handled statements like |
+               | "plan_exec" for selection or     |
+               +----------------------------------+                
+                       |                |                        
+        For Standalone |                | For Cluster          
+                       v                v                        
++---------------------------+      +---------------------------+ 
+| SqlStatementExecutor impl |      | SqlStatementExecutor impl | 
+| in Datanode Instance      |      | in Frontend DistInstance  | 
++---------------------------+      +---------------------------+ 
+```
+
+Note that some SQL statements can be executed in our QueryEngine, in the form of `LogicalPlan`. You can follow the
+invocation path down to the `QueryEngine` implementation from `StatementExecutor::plan_exec`. For now, there's only
+one `DatafusionQueryEngine` for both GreptimeDB Standalone and Cluster. That lone query engine works for both modes is
+because GreptimeDB read/write data through `Table` trait, and each mode has its own `Table` implementation.
+
+We don't have any bias towards whether statements should be handled in query engine or `StatementExecutor`. You can
+implement one kind of statement in both places. For example, `Insert` with selection is handled in query engine, because
+we can easily do the query part there. However, `Insert` without selection is not, for the cost of parsing statement
+to `LogicalPlan` is not neglectable. So generally if the SQL query is simple enough, you can handle it
+in `StatementExecutor`; otherwise if it is complex or has some part of selection, it should be parsed to `LogicalPlan`
+and handled in query engine.  

docs/rfcs/2022-12-20-promql-in-rust/rfc.md

@@ -149,10 +149,10 @@ inputs:
   - title: 'Series Normalize: \noffset = 0'
     operator: prom
     inputs:
-    - title: 'Filter: \ntimetamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
+    - title: 'Filter: \ntimestamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
       operator: filter
       inputs:
-      - title: 'Table Scan: \ntable = request_duration, timetamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
+      - title: 'Table Scan: \ntable = request_duration, timestamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
         operator: scan -->
 
 ![example](example.png)

docs/rfcs/2023-01-03-procedure-framework.md

@@ -0,0 +1,151 @@
+---
+Feature Name: "procedure-framework"
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/286
+Date: 2023-01-03
+Author: "Yingwen <realevenyag@gmail.com>"
+---
+
+Procedure Framework
+----------------------
+
+# Summary
+A framework for executing operations in a fault-tolerant manner.
+
+# Motivation
+Some operations in GreptimeDB require multiple steps to implement. For example, creating a table needs:
+1. Check whether the table exists
+2. Create the table in the table engine
+  1. Create a region for the table in the storage engine
+  2. Persist the metadata of the table to the table manifest
+3. Add the table to the catalog manager
+
+If the node dies or restarts in the middle of creating a table, it could leave the system in an inconsistent state. The procedure framework, inspired by [Apache HBase's ProcedureV2 framework](https://github.com/apache/hbase/blob/bfc9fc9605de638785435e404430a9408b99a8d0/src/main/asciidoc/_chapters/pv2.adoc) and [Apache Accumulo’s FATE framework](https://accumulo.apache.org/docs/2.x/administration/fate), aims to provide a unified way to implement multi-step operations that is tolerant to failure.
+
+# Details
+## Overview
+The procedure framework consists of the following primary components:
+- A `Procedure` represents an operation or a set of operations to be performed step-by-step
+- `ProcedureManager`, the runtime to run `Procedures`. It executes the submitted procedures, stores procedures' states to the `ProcedureStore` and restores procedures from `ProcedureStore` while the database restarts.
+- `ProcedureStore` is a storage layer for persisting the procedure state
+
+
+## Procedures
+The `ProcedureManager` keeps calling `Procedure::execute()` until the Procedure is done, so the operation of the Procedure should be [idempotent](https://developer.mozilla.org/en-US/docs/Glossary/Idempotent): it needs to be able to undo or replay a partial execution of itself.
+
+```rust
+trait Procedure {
+    fn execute(&mut self, ctx: &Context) -> Result<Status>;
+
+    fn dump(&self) -> Result<String>;
+
+    fn rollback(&self) -> Result<()>;
+
+    // other methods...
+}
+```
+
+The `Status` is an enum that has the following variants:
+```rust
+enum Status {
+    Executing {
+        persist: bool,
+    },
+    Suspended {
+        subprocedures: Vec<ProcedureWithId>,
+        persist: bool,
+    },
+    Done,
+}
+```
+
+A call to `execute()` can result in the following possibilities:
+- `Ok(Status::Done)`: we are done
+- `Ok(Status::Executing { .. })`: there are remaining steps to do
+- `Ok(Status::Suspend { sub_procedure, .. })`: execution is suspended and can be resumed later after the sub-procedure is done.
+- `Err(e)`: error occurs during execution and the procedure is unable to proceed anymore.
+
+Users need to assign a unique `ProcedureId` to the procedure and the procedure can get this id via the `Context`. The `ProcedureId` is typically a UUID.
+
+```rust
+struct Context {
+    id: ProcedureId,
+    // other fields ...
+}
+```
+
+The `ProcedureManager` calls `Procedure::dump()` to serialize the internal state of the procedure and writes to the `ProcedureStore`. The `Status` has a field `persist` to tell the `ProcedureManager` whether it needs persistence.
+
+## Sub-procedures
+A procedure may need to create some sub-procedures to process its subtasks. For example, creating a distributed table with multiple regions (partitions) needs to set up the regions in each node, thus the parent procedure should instantiate a sub-procedure for each region. The `ProcedureManager` makes sure that the parent procedure does not proceed till all sub-procedures are successfully finished.
+
+The procedure can submit sub-procedures to the `ProcedureManager` by returning `Status::Suspended`. It needs to assign a procedure id to each procedure manually so it can track the status of the sub-procedures.
+```rust
+struct ProcedureWithId {
+    id: ProcedureId,
+    procedure: BoxedProcedure,
+}
+```
+
+## ProcedureStore
+We might need to provide two different ProcedureStore implementations:
+- In standalone mode, it stores data on the local disk.
+- In distributed mode, it stores data on the meta server or the object store service.
+
+These implementations should share the same storage structure. They store each procedure's state in a unique path based on the procedure id:
+
+```
+Sample paths:
+
+/procedures/{PROCEDURE_ID}/000001.step
+/procedures/{PROCEDURE_ID}/000002.step
+/procedures/{PROCEDURE_ID}/000003.commit
+```
+
+`ProcedureStore` behaves like a WAL. Before performing each step, the `ProcedureManager` can write the procedure's current state to the ProcedureStore, which stores the state in the `.step` file. The `000001` in the path is a monotonic increasing sequence of the step. After the procedure is done, the `ProcedureManager` puts a `.commit` file to indicate the procedure is finished (committed).
+
+The `ProcedureManager` can remove the procedure's files once the procedure is done, but it needs to leave the `.commit` as the last file to remove in case of failure during removal.
+
+## ProcedureManager
+`ProcedureManager` executes procedures submitted to it.
+
+```rust
+trait ProcedureManager {
+    fn register_loader(&self, name: &str, loader: BoxedProcedureLoader) -> Result<()>;
+
+    async fn submit(&self, procedure: ProcedureWithId) -> Result<()>;
+}
+```
+
+It supports the following operations:
+- Register a `ProcedureLoader` by the type name of the `Procedure`.
+- Submit a `Procedure` to the manager and execute it.
+
+When `ProcedureManager` starts, it loads procedures from the `ProcedureStore` and restores the procedures by the `ProcedureLoader`. The manager stores the type name from `Procedure::type_name()` with the data from `Procedure::dump()` in the `.step` file and uses the type name to find a `ProcedureLoader` to recover the procedure from its data.
+
+```rust
+type BoxedProcedureLoader = Box<dyn Fn(&str) -> Result<BoxedProcedure> + Send>;
+```
+
+## Rollback
+The rollback step is supposed to clean up the resources created during the execute() step. When a procedure has failed, the `ProcedureManager` puts a `rollback` file and calls the `Procedure::rollback()` method.
+
+
+```text
+/procedures/{PROCEDURE_ID}/000001.step
+/procedures/{PROCEDURE_ID}/000002.rollback
+```
+
+Rollback is complicated to implement so some procedures might not support rollback or only provide a best-efforts approach.
+
+## Locking
+The `ProcedureManager` can provide a locking mechanism that gives a procedure read/write access to a database object such as a table so other procedures are unable to modify the same table while the current one is executing.
+
+# Drawbacks
+The `Procedure` framework introduces additional complexity and overhead to our database.
+- To execute a `Procedure`, we need to write to the `ProcedureStore` multiple times, which may slow down the server
+- We need to rewrite the logic of creating/dropping/altering a table using the procedure framework
+
+# Alternatives
+Another approach is to tolerate failure during execution and allow users to retry the operation until it succeeds. But we still need to:
+- Make each step idempotent
+- Record the status in some place to check whether we are done

docs/rfcs/2023-02-01-table-compaction.md

@@ -0,0 +1,92 @@
+---
+Feature Name: "table-compaction"
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/930
+Date: 2023-02-01
+Author: "Lei, HUANG <mrsatangel@gmail.com>"
+---
+
+# Table Compaction
+
+--- 
+
+## Background
+
+GreptimeDB uses an LSM-tree based storage engine that flushes memtables to SSTs for persistence. 
+But currently it only supports level 0. SST files in level 0 does not guarantee to contain only rows with disjoint time ranges. 
+That is to say, different SST files in level 0 may contain overlapped timestamps. 
+The consequence is, in order to retrieve rows in some time range, all files need to be scanned, which brings a lot of IO overhead.
+
+Also, just like other LSMT engines, delete/update to existing primary keys are converted to new rows with delete/update mark and appended to SSTs on flushing. 
+We need to merge the operations to same primary keys so that we don't have to go through all SST files to find the final state of these primary keys.  
+
+## Goal
+
+Implement a compaction framework to: 
+- maintain SSTs in timestamp order to accelerate queries with timestamp condition;
+- merge rows with same primary key;
+- purge expired SSTs;
+- accommodate other tasks like data rollup/indexing.
+
+
+## Overview
+
+Table compaction involves following components:
+- Compaction scheduler: run compaction tasks, limit the consumed resources;
+- Compaction strategy: find the SSTs to compact and determine the output files of compaction.
+- Compaction task: read the rows from input SSTs and write to the output files.
+
+## Implementation
+
+### Compaction scheduler
+
+`CompactionScheduler` is an executor that continuously polls and executes compaction request from a task queue. 
+
+```rust
+#[async_trait]
+pub trait CompactionScheduler {
+    /// Schedules a compaction task.
+    async fn schedule(&self, task: CompactionRequest) -> Result<()>;
+
+    /// Stops compaction scheduler.
+    async fn stop(&self) -> Result<()>;
+}
+```
+
+
+
+### Compaction triggering
+
+Currently, we can check whether to compact tables when memtable is flushed to SST.
+
+https://github.com/GreptimeTeam/greptimedb/blob/4015dd80752e1e6aaa3d7cacc3203cb67ed9be6d/src/storage/src/flush.rs#L245
+
+
+### Compaction strategy
+
+`CompactionStrategy` defines how to pick SSTs in all levels for compaction.   
+
+```rust
+pub trait CompactionStrategy {
+    fn pick(
+        &self,
+        ctx: CompactionContext,
+        levels: &LevelMetas,
+    ) -> Result<CompactionTask>;
+}
+```
+
+The most suitable compaction strategy for time-series scenario would be 
+a hybrid strategy that combines time window compaction with size-tired compaction, just like [Cassandra](https://cassandra.apache.org/doc/latest/cassandra/operating/compaction/twcs.html) and [ScyllaDB](https://docs.scylladb.com/stable/architecture/compaction/compaction-strategies.html#time-window-compaction-strategy-twcs) does.
+
+We can first group SSTs in level n into buckets according to some predefined time window. Within that window, 
+SSTs are compacted in a size-tired manner (find SSTs with similar size and compact them to level n+1). 
+SSTs from different time windows are neven compacted together.
+That strategy guarantees SSTs in each level are mainly sorted in timestamp order which boosts queries with 
+explicit timestamp condition, while size-tired compaction minimizes the impact to foreground writes. 
+
+### Alternatives
+
+Currently, GreptimeDB's storage engine [only support two levels](https://github.com/GreptimeTeam/greptimedb/blob/43aefc5d74dfa73b7819cae77b7eb546d8534a41/src/storage/src/sst.rs#L32).
+For level 0, we can start with a simple time-window based leveled compaction, which reads from all SSTs in level 0, 
+align them to time windows with a fixed duration, merge them with SSTs in level 1 within the same time window 
+to ensure there is only one sorted run in level 1.

docs/rfcs/2023-03-08-region-fault-tolerance.md

@@ -0,0 +1,196 @@
+---
+Feature Name: "Fault Tolerance for Region"
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/1126
+Date: 2023-03-08
+Author: "Luo Fucong <luofucong@greptime.com>"
+---
+
+Fault Tolerance for Region
+----------------------
+
+# Summary
+
+This RFC proposes a method to achieve fault tolerance for regions in GreptimeDB's distributed mode. Or, put it in another way, achieving region high availability("HA") for GreptimeDB cluster. 
+
+In this RFC, we mainly describe two aspects of region HA: how region availability is detected, and what recovery process is need to be taken. We also discuss some alternatives and future work.
+
+When this feature is done, our users could expect a GreptimeDB cluster that can always handle their requests to regions, despite some requests may failed during the region failover. The optimization to reduce the MTTR(Mean Time To Recovery) is not a concern of this RPC, and is left for future work.
+
+# Motivation
+
+Fault tolerance for regions is a critical feature for our clients to use the GreptimeDB cluster confidently. High availability for users to interact with their stored data is a "must have" for any TSDB products, that include our GreptimeDB cluster.
+
+# Details
+
+## Background
+
+Some backgrounds about region in distributed mode:
+
+- A table is logically split into multiple regions. Each region stores a part of non-overlapping table data.
+- Regions are distributed in Datanodes, the mappings are not static, are assigned and governed by Metasrv.
+- In distributed mode, client requests are scoped in regions. To be more specific, when a request that needs to scan multiple regions arrived in Frontend, Frontend splits the request into multiple sub-requests, each of which scans one region only, and submits them to Datanodes that hold corresponding regions. 
+
+In conclusion, as long as regions remain available, and regions could regain availability when failures do occur, the overall region HA could be achieved. With this in mind, let's see how region failures are detected first. 
+
+## Failure Detection
+
+We detect region failures in Metasrv, and do it both passively and actively. Passively means that Metasrv do not fire some "are you healthy" requests to regions. Instead, we carry region healthy information in the heartbeat requests that are submit to Metasrv by Datanodes. 
+
+Datanode already carries its regions stats in the heartbeat request (the non-relevant fields are omitted):
+
+```protobuf
+message HeartbeatRequest {
+  ...
+  // Region stats on this node
+  repeated RegionStat region_stats = 6;
+  ...
+}
+
+message RegionStat {
+  uint64 region_id = 1;
+  TableName table_name = 2;
+  ...
+}
+```
+
+For the sake of simplicity, we don't add another field `bool available = 3` to the `RegionStat` message; instead, if the region were unavailable in the view of the Datanode that contains it, the Datanode just not includes the `RegionStat` of it in the heartbeat request. Or, if the Datanode itself is not unavailable, the heartbeat request is not submitted, effectively the same with not carrying the `RegionStat`.
+
+> The heartbeat interval is now hardcoded to five seconds.
+
+Metasrv gathers the heartbeat requests, extracts the `RegionStat`s, and treat them as region heartbeat. In this way, Metasrv maintains all regions healthy information. If some region's heartbeats were not received in a period of time, Metasrv speculates the region might be unavailable. To make the decision whether a region is failed or not, Metasrv uses a failure detection algorithm called the "[Phi φ Accrual Failure Detection](https://medium.com/@arpitbhayani/phi-%CF%86-accrual-failure-detection-79c21ce53a7a)". Basically, the algorithm calculates a value called "phi" to represent the possibility of a region's unavailability, based on the historical heartbeats' arrived rate. Once the "phi" is above some pre-defined threshold, Metasrv knows the region is failed.
+
+> This algorithm has been widely adopted in some well known products, like Akka and Cassandra.
+
+When Metasrv decides some region is failed from heartbeats, it's not the final decision. Here comes the "actively" detection. Before Metasrv decides to do region failover, it actively invokes the healthy check interface of the Datanode that the failure region resides. Only this healthy check is failed does Metasrv actually start doing failover upon the region.
+
+To conclude, the failure detection pseudo-codes are like this:
+
+```rust
+// in Metasrv:
+fn failure_detection() {
+    loop {
+        // passive detection
+        let failed_regions = all_regions.iter().filter(|r| r.estimated_failure_possibility() > config.phi).collect();
+
+        // find the datanodes that contains the failed regions
+        let datanodes_and_regions = find_region_resides_datanodes(failed_regions);
+
+        // active detection  
+        for (datanode, regions) in datanodes_and_regions {
+            if !datanode.is_healthy(regions) {
+                do_failover(datanode, regions);
+            }
+        }
+
+        sleep(config.detect_interval);
+    }
+}
+```
+
+Some design considerations:
+
+- Why active detecting while we have passively detection? Because it could be happened that the network is singly connectable sometimes (especially in the complex Cloud environment), then the Datanode's heartbeats cannot reach Metasrv, while Metasrv could request Datanode. Active detecting avoid this false positive situation.
+- Why the detection works on region instead of Datanode? Because we might face the possibility that only part of the regions in the Datanode are not available, not ALL regions. Especially the situation that Datanodes are used by multiple tenants. If this is the case, it's better to do failover upon the designated regions instead of the whole regions that reside on the Datanode. All in all, we want a more subtle control over region failover. 
+
+So we detect some regions are not available. How to regain the availability back?
+
+## Region Failover
+
+Region Failover largely relies on remote WAL, aka "[Bunshin](https://github.com/GreptimeTeam/bunshin)". I'm not including any of the details of it in this RFC, let's just assume we already have it.
+
+In general, region failover is fairly simple. Once Metasrv decides to do failover upon some regions, it first chooses one or more Datanodes to hold the failed region. This can be done easily, as the Metasrv already has the whole picture of Datanodes: it knows which Datanode has the minimum regions, what Datanode historically had the lowest CPU usage and IO rate, and how the Datanodes are assigned to tenants, among other information that can all help the Metasrv choose the most suitable Datanodes. Let's call these chosen Datanodes as "candidates".
+
+> The strategy to choose the most suitable candidates required careful design, but it's another RFC.
+
+Then, Metasrv sets the states of these failed regions as "passive". We should add a field to `Region`:
+
+```protobuf
+message Region {
+  uint64 id = 1;
+  string name = 2;
+  Partition partition = 3;
+  
+  message State {
+    Active,
+    Passive,
+  }
+  State state = 4;
+  
+  map<string, string> attrs = 100;
+}
+```
+
+Here `Region` is used in message `RegionRoute`, which indicates how the write request is split among regions. When a region is set as "passive", Frontend knows the write to it should be rejected at the moment (the region read is not blocked, however).
+
+> Making a region "passive" here is effectively blocking the write to it. It's ok in the failover situation, the region is failed anyway. However, when dealing with active maintenance operations, region state requires more refined design. But that's another story. 
+
+Third, Metasrv fires the "close region" requests to the failed Datanodes, and fires the "open region" requests to those candidates. "Close region" requests might be failed due to the unavailability of Datanodes, but that's fine, it's just a best-effort attempt to reduce the chance of any in-flight writes got handled unintentionally after the region is set as "passive". The "open region" requests must have succeeded though. Datanodes open regions from remote WAL.
+
+> Currently the "close region" is undefined in Datanode. It could be a local cache clean up of region data or other resources tidy up.
+
+Finally, when a candidate successfully opens its region, it calls back to Metasrv, indicating it is ready to handle region. "call back" here is backed by its heartbeat to Metasrv. Metasrv updates the region's state to "active", so as to let Frontend lifts the restrictions of region writes (again, the read part of region is untouched).
+
+All the above steps should be managed by remote procedure framework. It's another implementation challenge in the region failover feature. (One is the remote WAL of course.)
+
+A picture is worth a 1000 words:
+
+```text
+                                    +-------------------------+                                        
+                                    | Metasrv detects region  |                                        
+                                    | failure                 |                                        
+                                    +-------------------------+                                        
+                                                 |                                                     
+                                                 v                                                     
+                                    +----------------------------+                                        
+                                    | Metasrv chooses candidates |                                        
+                                    | to hold failed regions     |                                        
+                                    +----------------------------+                                        
+                                                 |                                                     
+                                                 v                                                     
+                                    +-------------------------+       +-------------------------+      
+                                    | Metasrv "passive" the   |------>| Frontend rejects writes |      
+                                    | failed regions          |       | to "passive" regions    |      
+                                    +-------------------------+       +-------------------------+      
+                                                 |                                                     
+                                                 v                                                     
++--------------------------+        +---------------------------+                                        
+| Candidate Datanodes open |<-------| Metasrv fires "close" and |                                        
+| regions from remote WAL  |        | "open" region requests    |                                        
++--------------------------+        +---------------------------+                                        
+             |                                                                                         
+             |                                                                                         
+             |                      +-------------------------+       +-------------------------+      
+             +--------------------->| Metasrv "active" the    |------>| Frontend lifts write    |      
+                                    | failed regions          |       | restriction to regions  |      
+                                    +-------------------------+       +-------------------------+      
+                                                 |                                                     
+                                                 v                                                     
+                                    +-------------------------+                                        
+                                    | Region failover done,   |                                        
+                                    | HA regain               |                                        
+                                    +-------------------------+                                        
+```
+
+# Alternatives
+
+## The "Neon" Way
+
+Remote WAL raises a problem that could harm the write throughput of GreptimeDB cluster: each write request has to do at least two remote call, one is from Frontend to Datanode, and one is from Datanode to remote WAL. What if we do it the "[Neon](https://github.com/neondatabase/neon)" way, making remote WAL sits in between the Frontend and Datanode, couldn't that improve our write throughput? It could, though there're some consistency issues like "read-your-writes" to solve.
+
+However, the main concerns we don't adopt this method are two-fold:
+
+1. Remote WAL is planned to be quorum based, it can be efficiently written;
+2. More importantly, we are planning to make the remote WAL an option that users could choose not to enable it (at the cost of some reliability reduction).
+
+## No WAL, Replication instead
+
+This method replicates region across Datanodes directly, like the common way in shared-nothing database. Were the main region failed, a standby region in the replicate group is elected as new "main" and take the read/write requests. The main concern to this method is the incompatibility to our current architecture and code structure. It requires a major redesign, but gains no significant advantage over the remote WAL method. 
+
+However, the replication does have its own advantage that we can learn from to optimize this failover procedure.
+
+# Future Work
+
+Some optimizations we could take:
+
+- To reduce the MTTR, we could make Metasrv chooses the candidate to each region at normal time. The candidate does some preparation works to reduce the open region time, effectively accelerate the failover procedure.
+- We can adopt the replication method, to the degree that region replicas are used as the fast catch-up candidates. The data difference among replicas is minor, region failover does not need to load or exchange too much data, greatly reduced the region failover time.

docs/rfcs/2023-03-29-file-external-table/rfc.md

@@ -0,0 +1,174 @@
+---
+Feature Name: "File external table"
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/1041
+Date: 2023-03-08
+Author: "Xu Wenkang <wenymedia@gmail.com>"
+---
+
+File external table
+
+---
+
+# Summary
+
+Allows users to perform SQL queries on files
+
+# Motivation
+
+User data may already exist in other storages, i.g., file systems/s3, etc. in CSV, parquet, JSON format, etc. We can provide users the ability to perform SQL queries on these files.
+
+
+# Details
+
+## Overview
+
+The file external table providers users ability to perform SQL queries on these files.
+
+For example, a user has a CSV file on the local file system `/var/data/city.csv`:
+
+```
+Rank , Name , State , 2023 Population , 2020 Census , Annual Change , Density (mi²)
+1 , New York City , New York , 8,992,908 , 8,804,190 , 0.7% , 29,938
+2 , Los Angeles , California , 3,930,586 , 3,898,747 , 0.27% , 8,382
+3 , Chicago , Illinois , 2,761,625 , 2,746,388 , 0.18% , 12,146
+.....
+```
+
+Then user can create a file external table with:
+
+```sql
+CREATE EXTERNAL TABLE city with(location='/var/data/city.csv', format="CSV", field_delimiter = ',', record_delimiter = '\n', skip_header = 1);
+```
+
+Then query the external table with:
+
+```bash
+MySQL> select * from city;
+```
+
+| Rank | Name          | State      | 2023 Population | 2020 Census | Annual Change | Density (mi²) |
+| :--- | :------------ | :--------- | :-------------- | :---------- | :------------ | :------------ |
+| 1    | New York City | New York   | 8,992,908       | 8,804,190   | 0.7%          | 29,938        |
+| 2    | Los Angeles   | California | 3,930,586       | 3,898,747   | 0.27%         | 8,382         |
+| 3    | Chicago       | Illinois   | 2,761,625       | 2,746,388   | 0.18%         | 12,146        |
+
+Drop the external table, if needs with:
+
+```sql
+DROP EXTERNAL TABLE city
+```
+
+
+### Syntax
+
+```
+CREATE EXTERNAL [<database>.]<table_name>
+[
+ (
+    <col_name> <col_type> [NULL | NOT NULL] [COMMENT "<comment>"]
+ )
+]
+[ WITH
+ (
+     LOCATION = 'url'
+   [,FIELD_DELIMITER =  'delimiter' ]
+   [,RECORD_DELIMITER =  'delimiter' ]
+   [,SKIP_HEADER =  '<number>' ]
+   [,FORMAT =  { csv | json | parquet } ]
+   [,PATTERN = '<regex_pattern>' ]
+   [,ENDPOINT = '<uri>' ]
+   [,ACCESS_KEY_ID = '<key_id>' ]
+   [,SECRET_ACCESS_KEY = '<access_key>' ]
+   [,SESSION_TOKEN = '<token>' ]
+   [,REGION = '<region>' ]
+   [,ENABLE_VIRTUAL_HOST_STYLE = '<boolean>']
+   ..
+ )
+]
+```
+
+### Supported File Format
+
+The external file table supports multiple formats; We divide formats into row format and columnar format.
+
+Row formats:
+
+- CSV, JSON
+
+Columnar formats:
+
+- Parquet
+
+Some of these formats support filter pushdown, and others don't. If users use very large files, that format doesn't support pushdown, which might consume a lot of IO for scanning full files and cause a long running query.
+
+### File Table Engine
+
+![overview](external-table-engine-overview.png)
+
+We implement a file table engine that creates an external table by accepting user-specified file paths and treating all records as immutable.
+
+1. File Format Decoder: decode files to the `RecordBatch` stream.
+2. File Table Engine: implement the `TableProvider` trait, store necessary metadata in memory, and provide scan ability.
+
+Our implementation is better for small files. For large files(i.g., a GB-level CSV file), suggests our users import data to the database.
+
+## Drawbacks
+
+- Some formats don't support filter pushdown
+- Hard to support indexing
+
+## Life cycle
+
+### Register a table
+
+1. Write metadata to manifest.
+2. Create the table via file table engine.
+3. Register table to `CatalogProvider` and register table to `SystemCatalog`(persist tables to disk).
+
+### Deregister a table (Drop a table)
+
+1. Fetch the target table info (figure out table engine type).
+2. Deregister the target table in `CatalogProvider` and `SystemCatalog`.
+3. Find the target table engine.
+4. Drop the target table.
+
+### Recover a table when restarting
+
+1. Collect tables name and engine type info.
+2. Find the target tables in different engines.
+3. Open and register tables.
+
+# Alternatives
+
+## Using DataFusion API
+
+We can use datafusion API to register a file table:
+
+```rust
+let ctx = SessionContext::new();
+
+ctx.register_csv("example", "tests/data/example.csv", CsvReadOptions::new()).await?;
+
+// create a plan
+let df = ctx.sql("SELECT a, MIN(b) FROM example WHERE a <= b GROUP BY a LIMIT 100").await?;
+```
+
+### Drawbacks
+
+The DataFusion implements its own `Object Store` abstraction and supports parsing the partitioned directories, which can push down the filter and skips some directories. However, this makes it impossible to use our's `LruCacheLayer`(The parsing of the partitioned directories required paths as input). If we want to manage memory entirely, we should implement our own `TableProvider` or `Table`.
+
+- Impossible to use `CacheLayer`
+
+## Introduce an intermediate representation layer
+
+![overview](external-table-engine-way-2.png)
+
+We convert all files into `parquet` as an intermediate representation. Then we only need to implement a `parquet` file table engine, and we already have a similar one. Also, it supports limited filter pushdown via the `parquet` row group stats.
+
+### Drawbacks
+
+- Computing overhead
+- Storage overhead
+
+
+

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

@@ -0,0 +1,137 @@
+---
+Feature Name: distributed-planner
+Tracking Issue: TBD
+Date: 2023-05-09
+Author: "Ruihang Xia <waynestxia@gmail.com>"
+---
+
+Distributed Planner
+-------------------
+# Summary
+Enhance the logical planner with aware of distributed, multi-region table topology. To achieve "push computation down" execution rather than the current "pull data up" manner.
+
+# Motivation
+Query distributively can leverage the advantage of GreptimeDB's architecture to process large dataset that exceeds the capacity of a single node, or accelerate the query execution by executing it in parallel. This task includes two sub-tasks
+  - Be able to transform the plan that can push as much as possible computation down to data source.
+  - Be able to handle pipeline breaker (like `Join` or `Sort`) on multiple computation nodes.
+This is a relatively complex topic. To keep this RFC concentrated I'll focus on the first one.
+
+# Details
+## Background: Partition and Region
+GreptimeDB supports table partitioning, where the partition rule is set during table creation. Each partition can be further divided into one or more physical storage units known as "regions". Both partitions and regions are divided based on rows:
+``` text
+┌────────────────────────────────────┐
+│                                    │
+│               Table                │
+│                                    │
+└─────┬────────────┬────────────┬────┘
+      │            │            │
+      │            │            │
+┌─────▼────┐ ┌─────▼────┐ ┌─────▼────┐
+│ Region 1 │ │ Region 2 │ │ Region 3 │
+└──────────┘ └──────────┘ └──────────┘
+  Row 1~10     Row 11~20    Row 21~30
+```
+General speaking, region is the minimum element of data distribution, and we can also use it as the unit to distribute computation. This can greatly simplify the routing logic of this distributed planner, by always schedule the computation to the node that currently opening the corresponding region. And is also easy to scale more node for computing since GreptimeDB's data is persisted on shared storage backend like S3. But this is a bit beyond the scope of this specific topic.
+## Background: Commutativity
+Commutativity is an attribute that describes whether two operation can exchange their apply order: $P1(P2(R)) \Leftrightarrow P2(P1(R))$. If the equation keeps, we can transform one expression into another form without changing its result. This is useful on rewriting SQL expression, and is the theoretical basis of this RFC.
+
+Take this SQL as an example
+
+``` sql
+SELECT a FROM t WHERE a > 10;
+```
+
+As we know projection and filter are commutative (todo: latex), it can be translated to the following two identical plan trees:
+
+```text
+┌─────────────┐       ┌─────────────┐
+│Projection(a)│       │Filter(a>10) │
+└──────▲──────┘       └──────▲──────┘
+       │                     │
+┌──────┴──────┐       ┌──────┴──────┐
+│Filter(a>10) │       │Projection(a)│
+└──────▲──────┘       └──────▲──────┘
+       │                     │
+┌──────┴──────┐       ┌──────┴──────┐
+│  TableScan  │       │  TableScan  │
+└─────────────┘       └─────────────┘
+```
+
+## Merge Operation
+
+This RFC proposes to add a new expression node `MergeScan` to merge result from several regions in the frontend. It wrap the abstraction of remote data and execution, and expose a `TableScan` interface to upper level.
+
+``` text
+        ▲
+        │
+┌───────┼───────┐
+│       │       │
+│    ┌──┴──┐    │
+│    └──▲──┘    │
+│       │       │
+│    ┌──┴──┐    │
+│    └──▲──┘    │    ┌─────────────────────────────┐
+│       │       │    │                             │
+│  ┌────┴────┐  │    │ ┌──────────┐ ┌───┐    ┌───┐ │
+│  │MergeScan◄──┼────┤ │ Region 1 │ │   │ .. │   │ │
+│  └─────────┘  │    │ └──────────┘ └───┘    └───┘ │
+│               │    │                             │
+└─Frontend──────┘    └─Remote-Sources──────────────┘
+```
+This merge operation simply chains all the the underlying remote data sources and return `RecordBatch`, just like a coalesce op. And each remote sources is a gRPC query to datanode via the substrait logical plan interface. The plan is transformed and divided from the original query that comes to frontend.
+
+## Commutativity of MergeScan
+
+Obviously, The position of `MergeScan` is the key of the distributed plan. The more closer to the underlying `TableScan`, the less computation is taken by datanodes. Thus the goal is to pull the `MergeScan` up as more as possible. The word "pull up" means exchange `MergeScan` with its parent node in the plan tree, which means we should check the commutativity between the existing expression nodes and the `MergeScan`. Here I classify all the possibility into five categories:
+
+- Commutative: $P1(P2(R)) \Leftrightarrow P2(P1(R))$
+  - filter
+  - projection
+  - operations that match the partition key
+- Partial Commutative: $P1(P2(R)) \Leftrightarrow P1(P2(P1(R)))$
+  - $min(R) \rightarrow min(MERGE(min(R)))$
+  - $max(R) \rightarrow max(MERGE(max(R)))$
+- Conditional Commutative: $P1(P2(R)) \Leftrightarrow P3(P2(P1(R)))$
+  - $count(R) \rightarrow sum(count(R))$
+- Transformed Commutative: $P1(P2(R)) \Leftrightarrow P1(P3(R)) \Leftrightarrow P3(P1(R))$
+  - $avg(R) \rightarrow sum(R)/count(R)$
+- Non-commutative
+  - sort
+  - join
+  - percentile
+## Steps to plan
+After establishing the set of commutative relations for all expressions, we can begin transforming the logical plan. There are four steps:
+
+  - Add a merge node before table scan
+  - Evaluate commutativity in a bottom-up way, stop at the first non-commutative node
+  - Divide the TableScan to scan over partitions
+  - Execute
+
+First insert the `MergeScan` on top of the bottom `TableScan` node. Then examine the commutativity start from the `MergeScan` node transform the plan tree based on the result. Stop this process on the first non-commutative node.
+``` text
+                  ┌─────────────┐   ┌─────────────┐
+                  │    Sort     │   │    Sort     │
+                  └──────▲──────┘   └──────▲──────┘
+                         │                 │
+┌─────────────┐   ┌──────┴──────┐   ┌──────┴──────┐
+│    Sort     │   │Projection(a)│   │  MergeScan  │
+└──────▲──────┘   └──────▲──────┘   └──────▲──────┘
+       │                 │                 │
+┌──────┴──────┐   ┌──────┴──────┐   ┌──────┴──────┐
+│Projection(a)│   │  MergeScan  │   │Projection(a)│
+└──────▲──────┘   └──────▲──────┘   └──────▲──────┘
+       │                 │                 │
+┌──────┴──────┐   ┌──────┴──────┐   ┌──────┴──────┐
+│  TableScan  │   │  TableScan  │   │  TableScan  │
+└─────────────┘   └─────────────┘   └─────────────┘
+      (a)               (b)               (c)
+```
+Then in the physical planning phase, convert the sub-tree below `MergeScan` into a remote query request and dispatch to all the regions. And let the `MergeScan` to receive the results and feed to it parent node.
+
+To simplify the overall complexity, any error in the procedure will lead to a failure to the entire query, and cancel all other parts.
+# Alternatives
+## Spill
+If only consider the ability of processing large dataset, we can enable DataFusion's spill ability to temporary persist intermediate data into disk, like the "swap" memory. But this will lead to a super slow performance and very large write amplification.
+# Future Work
+As described in the `Motivation` section we can further explore the distributed planner on the physical execution level, by introducing mechanism like Spark's shuffle to improve parallelism and reduce intermediate pipeline breaker's stage.

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

@@ -0,0 +1,303 @@
+---
+Feature Name: table-engine-refactor
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/1869
+Date: 2023-07-06
+Author: "Yingwen <realevenyag@gmail.com>"
+---
+
+Refactor Table Engine
+----------------------
+
+# Summary
+Refactor table engines to address several historical tech debts.
+
+# Motivation
+Both `Frontend` and `Datanode` have to deal with multiple regions in a table. This results in code duplication and additional burden to the `Datanode`.
+
+Before:
+
+
+```mermaid
+graph TB
+
+subgraph Frontend["Frontend"]
+    subgraph MyTable
+        A("region 0, 2 -> Datanode0")
+        B("region 1, 3 -> Datanode1")
+    end
+end
+
+MyTable --> MetaSrv
+MetaSrv --> ETCD
+
+MyTable-->TableEngine0
+MyTable-->TableEngine1
+
+subgraph Datanode0
+    Procedure0("procedure")
+    TableEngine0("table engine")
+    region0
+    region2
+    mytable0("my_table")
+
+    Procedure0-->mytable0
+    TableEngine0-->mytable0
+    mytable0-->region0
+    mytable0-->region2
+end
+
+
+subgraph Datanode1
+    Procedure1("procedure")
+    TableEngine1("table engine")
+    region1
+    region3
+    mytable1("my_table")
+
+    Procedure1-->mytable1
+    TableEngine1-->mytable1
+    mytable1-->region1
+    mytable1-->region3
+end
+
+
+subgraph manifest["table manifest"]
+    M0("my_table")
+    M1("regions: [0, 1, 2, 3]")
+end
+
+mytable1-->manifest
+mytable0-->manifest
+
+RegionManifest0("region manifest 0")
+RegionManifest1("region manifest 1")
+RegionManifest2("region manifest 2")
+RegionManifest3("region manifest 3")
+region0-->RegionManifest0
+region1-->RegionManifest1
+region2-->RegionManifest2
+region3-->RegionManifest3
+```
+
+`Datanodes` can update the same manifest file for a table as regions are assigned to different nodes in the cluster. We also have to run procedures on `Datanode` to ensure the table manifest is consistent with region manifests. "Table" in a `Datanode` is a subset of the table's regions. The `Datanode` is much closer to `RegionServer` in `HBase` which only deals with regions.
+
+In cluster mode, we store table metadata in etcd and table manifest. The table manifest becomes redundant. We can remove the table manifest if we refactor the table engines to region engines that only care about regions. What's more, we don't need to run those procedures on `Datanode`.
+
+After:
+```mermaid
+graph TB
+
+subgraph Frontend["Frontend"]
+    direction LR
+    subgraph MyTable
+        A("region 0, 2 -> Datanode0")
+        B("region 1, 3 -> Datanode1")
+    end
+end
+
+MyTable --> MetaSrv
+MetaSrv --> ETCD
+
+MyTable-->RegionEngine
+MyTable-->RegionEngine1
+
+subgraph Datanode0
+    RegionEngine("region engine")
+    region0
+    region2
+    RegionEngine-->region0
+    RegionEngine-->region2
+end
+
+
+subgraph Datanode1
+    RegionEngine1("region engine")
+    region1
+    region3
+    RegionEngine1-->region1
+    RegionEngine1-->region3
+end
+
+RegionManifest0("region manifest 0")
+RegionManifest1("region manifest 1")
+RegionManifest2("region manifest 2")
+RegionManifest3("region manifest 3")
+region0-->RegionManifest0
+region1-->RegionManifest1
+region2-->RegionManifest2
+region3-->RegionManifest3
+```
+This RFC proposes to refactor table engines into region engines as a first step to make the `Datanode` acts like a `RegionServer`.
+
+
+# Details
+## Overview
+
+We plan to refactor the `TableEngine` trait into `RegionEngine` gradually. This RFC focuses on the `mito` engine as it is the default table engine and the most complicated engine.
+
+Currently, we built `MitoEngine` upon `StorageEngine` that manages regions of the `mito` engine. Since `MitoEngine` becomes a region engine, we could combine `StorageEngine` with `MitoEngine` to simplify our code structure.
+
+The chart below shows the overall architecture of the `MitoEngine`.
+
+```mermaid
+classDiagram
+class MitoEngine~LogStore~ {
+    -WorkerGroup workers
+}
+class MitoRegion {
+    +VersionControlRef version_control
+    -RegionId region_id
+    -String manifest_dir
+    -AtomicI64 last_flush_millis
+    +region_id() RegionId
+    +scan() ChunkReaderImpl
+}
+class RegionMap {
+    -HashMap&lt;RegionId, MitoRegionRef&gt; regions
+}
+class ChunkReaderImpl
+
+class WorkerGroup {
+    -Vec~RegionWorker~ workers
+}
+class RegionWorker {
+    -RegionMap regions
+    -Sender sender
+    -JoinHandle handle
+}
+class RegionWorkerThread~LogStore~ {
+    -RegionMap regions
+    -Receiver receiver
+    -Wal~LogStore~ wal
+    -ObjectStore object_store
+    -MemtableBuilderRef memtable_builder
+    -FlushSchedulerRef~LogStore~ flush_scheduler
+    -FlushStrategy flush_strategy
+    -CompactionSchedulerRef~LogStore~ compaction_scheduler
+    -FilePurgerRef file_purger
+}
+class Wal~LogStore~ {
+    -LogStore log_store
+}
+class MitoConfig
+
+MitoEngine~LogStore~ o-- MitoConfig
+MitoEngine~LogStore~ o-- MitoRegion
+MitoEngine~LogStore~ o-- WorkerGroup
+MitoRegion o-- VersionControl
+MitoRegion -- ChunkReaderImpl
+WorkerGroup o-- RegionWorker
+RegionWorker o-- RegionMap
+RegionWorker -- RegionWorkerThread~LogStore~
+RegionWorkerThread~LogStore~ o-- RegionMap
+RegionWorkerThread~LogStore~ o-- Wal~LogStore~
+```
+
+We replace the `RegionWriter` with `RegionWorker` to process write requests and DDL requests.
+
+
+## Metadata
+We also merge region's metadata with table's metadata. It should make metadata much easier to maintain.
+```mermaid
+classDiagram
+class VersionControl {
+    -CowCell~Version~ version
+    -AtomicU64 committed_sequence
+}
+class Version {
+    -RegionMetadataRef metadata
+    -MemtableVersionRef memtables
+    -LevelMetasRef ssts
+    -SequenceNumber flushed_sequence
+    -ManifestVersion manifest_version
+}
+class MemtableVersion {
+    -MemtableRef mutable
+    -Vec~MemtableRef~ immutables
+    +mutable_memtable() MemtableRef
+    +immutable_memtables() &[MemtableRef]
+    +freeze_mutable(MemtableRef new_mutable) MemtableVersion
+}
+class LevelMetas {
+    -LevelMetaVec levels
+    -AccessLayerRef sst_layer
+    -FilePurgerRef file_purger
+    -Option~i64~ compaction_time_window
+}
+class LevelMeta {
+    -Level level
+    -HashMap&lt;FileId, FileHandle&gt; files
+}
+class FileHandle {
+    -FileMeta meta
+    -bool compacting
+    -AtomicBool deleted
+    -AccessLayerRef sst_layer
+    -FilePurgerRef file_purger
+}
+class FileMeta {
+    +RegionId region_id
+    +FileId file_id
+    +Option&lt;Timestamp, Timestamp&gt; time_range
+    +Level level
+    +u64 file_size
+}
+
+VersionControl o-- Version
+Version o-- RegionMetadata
+Version o-- MemtableVersion
+Version o-- LevelMetas
+LevelMetas o-- LevelMeta
+LevelMeta o-- FileHandle
+FileHandle o-- FileMeta
+
+class RegionMetadata {
+    +RegionId region_id
+    +VersionNumber version
+    +SchemaRef table_schema
+    +Vec~usize~ primary_key_indices
+    +Vec~usize~ value_indices
+    +ColumnId next_column_id
+    +TableOptions region_options
+    +DateTime~Utc~ created_on
+    +RegionSchemaRef region_schema
+}
+class RegionSchema {
+    -SchemaRef user_schema
+    -StoreSchemaRef store_schema
+    -ColumnsMetadataRef columns
+}
+class Schema
+class StoreSchema {
+    -Vec~ColumnMetadata~ columns
+    -SchemaRef schema
+    -usize row_key_end
+    -usize user_column_end
+}
+class ColumnsMetadata {
+    -Vec~ColumnMetadata~ columns
+    -HashMap&lt;String, usize&gt; name_to_col_index
+    -usize row_key_end
+    -usize timestamp_key_index
+    -usize user_column_end
+}
+class ColumnMetadata
+
+RegionMetadata o-- RegionSchema
+RegionMetadata o-- Schema
+RegionSchema o-- StoreSchema
+RegionSchema o-- Schema
+RegionSchema o-- ColumnsMetadata
+StoreSchema o-- ColumnsMetadata
+StoreSchema o-- Schema
+StoreSchema o-- ColumnMetadata
+ColumnsMetadata o-- ColumnMetadata
+```
+
+# Drawback
+This is a breaking change.
+
+# Future Work
+- Rename `TableEngine` to `RegionEngine`
+- Simplify schema relationship in the `mito` engine
+- Refactor the `Datanode` into a `RegionServer`.

docs/rfcs/2023-07-10-metric-engine.md

@@ -0,0 +1,202 @@
+---
+Feature Name: metric-engine
+Tracking Issue: TBD
+Date: 2023-07-10
+Author: "Ruihang Xia <waynestxia@gmail.com>"
+---
+
+# Summary
+
+A new metric engine that can significantly enhance our ability to handle the tremendous number of small tables in scenarios like Prometheus metrics, by leveraging a synthetic wide table that offers storage and metadata multiplexing capabilities over the existing engine.
+
+# Motivation
+
+The concept "Table" in GreptimeDB is a bit "heavy" compared to other time-series storage like Prometheus or VictoriaMetrics. This has lots of disadvantages in aspects from performance, footprint, and storage to cost.
+
+# Details
+
+## Top level description
+
+- User Interface
+
+    This feature will add a new type of storage engine. It might be available to be an option like `with ENGINE=mito` or an internal interface like auto create table on Prometheus remote write. From the user side, there is no difference from tables in mito engine. All the DDL like `CREATE`, `ALTER` and DML like `SELECT` should be supported.
+
+- Implementation Overlook
+
+    This new engine doesn't re-implement low level components like file R/W etc. It's a wrapper layer over the existing mito engine, with extra storage and metadata multiplexing capabilities. I.e., it expose multiple table based on one mito engine table like this:
+	``` plaintext
+	   ┌───────────────┐ ┌───────────────┐ ┌───────────────┐
+	   │ Metric Engine │ │ Metric Engine │ │ Metric Engine │
+	   │   Table 1     │ │   Table 2     │ │   Table 3     │
+	   └───────────────┘ └───────────────┘ └───────────────┘
+	           ▲               ▲                   ▲
+	           │               │                   │
+	           └───────────────┼───────────────────┘
+	                           │
+	                 ┌─────────┴────────┐
+	                 │ Metric Region    │
+	                 │   Engine         │
+	                 │    ┌─────────────┤
+	                 │    │ Mito Region │
+	                 │    │   Engine    │
+	                 └────▲─────────────┘
+	                      │
+	                      │
+	                ┌─────┴───────────────┐
+	                │                     │
+	                │  Mito Engine Table  │
+	                │                     │
+	                └─────────────────────┘
+	```
+
+The following parts will describe these implementation details:
+    - How to route these metric region tables and how those table are distributed
+    - How to maintain the schema and other metadata of the underlying mito engine table
+    - How to maintain the schema of metric engine table
+    - How the query goes
+
+## Routing
+
+Before this change, the region route rule was based on a group of partition keys. Relation of physical table to region is one-to-many.
+
+``` rust
+  pub struct PartitionDef {
+      partition_columns: Vec<String>,
+      partition_bounds: Vec<PartitionBound>,
+  }
+```
+
+And for metric engine tables, the key difference is we split the concept of "physical table" and "logical table". Like the previous ASCII chart, multiple logical tables are based on one physical table. The relationship of logical table to region becomes many-to-many. Thus, we must include the table name (of logical table) into partition rules.
+
+Consider the partition/route interface is a generic map of string array to region id, all we need to do is to insert logical table name into the request:
+
+``` rust
+  fn route(request: Vec<String>) -> RegionId;
+```
+
+The next question is, where to do this conversion? The basic idea is to dispatch different routing behavior based on the engine type. Since we have all the necessary information in frontend, it's a good place to do that. And can leave meta server untouched. The essential change is to associate engine type with route rule.
+
+## Physical Region Schema
+
+The idea "physical wide table" is to perform column-level multiplexing. I.e., map all logical columns to physical columns by their names.
+
+```
+   ┌────────────┐      ┌────────────┐         ┌────────────┐
+   │   Table 1  │      │   Table 2  │         │   Table 3  │
+   ├───┬────┬───┤      ├───┬────┬───┤         ├───┬────┬───┤
+   │C1 │ C2 │ C3│      │C1 │ C3 │ C5├──────┐  │C2 │ C4 │ C6│
+   └─┬─┴──┬─┴─┬─┘ ┌────┴───┴──┬─┴───┘      │  └─┬─┴──┬─┴─┬─┘
+     │    │   │   │           │            │    │    │   │
+     │    │   │   │           └──────────┐ │    │    │   │
+     │    │   │   │                      │ │    │    │   │
+     │    │   │   │  ┌─────────────────┐ │ │    │    │   │
+     │    │   │   │  │ Physical Table  │ │ │    │    │   │
+     │    │   │   │  ├──┬──┬──┬──┬──┬──┘ │ │    │    │   │
+     └────x───x───┴─►│C1│C2│C3│C4│C5│C6◄─┼─x────x────x───┘
+          │   │      └──┘▲─┘▲─┴─▲└─▲└──┘ │ │    │    │
+          │   │          │  │   │  │     │ │    │    │
+          ├───x──────────┘  ├───x──x─────┘ │    │    │
+          │   │             │   │  │       │    │    │
+          │   └─────────────┘   │  └───────┘    │    │
+          │                     │               │    │
+          └─────────────────────x───────────────┘    │
+                                │                    │
+                                └────────────────────┘
+```
+
+This approach is very straightforward but has one problem. It only works when two columns have different semantic type (time index, tag or field) or data types but with the same name. E.g., `CREATE TABLE t1 (c1 timestamp(3) TIME INDEX)` and `CREATE TABLE t2 (c1 STRING PRIMARY KEY)`.
+
+One possible workaround is to prefix each column with its data type and semantic type, like `_STRING_PK_c1`. However, considering the primary goal at present is to support data from monitoring metrics like Prometheus remote write, it's acceptable not to support this at first because data types are often simple and limited here.
+
+
+The next point is changing the physical table's schema. This is only needed when creating a new logical table or altering the existing table. Typically speaking, table creating and altering are explicit. We only need to emit an add column request to underlying physical table on processing logical table's DDL. GreptimeDB can create or alter table automatically on some protocols, but the internal logic is the same.
+
+Also for simplicity, we don't support shrinking the underlying table at first. This can be achieved by introducing mechanism on the physical column.
+
+Frontend needs not to keep physical table's schema.
+
+## Metadata of physical regions
+
+Those metric engine regions need to store extra metadata like the schema of logical table or all logical table's name. That information is relatively simple and can be stored in a format like key-value pair. For now, we have to use another physical mito region for metadata. This involves an issue with region scheduling. Since we don't have the ability to perform affinity scheduling, the initial version will just assume the data region and metadata region are in the same instance. See alternatives - other storage for physical region's metadata for possible future improvement.
+
+Here is the schema of metadata region and how we would use it. The `CREATE TABLE` clause of metadata region looks like the following. Notice that it wouldn't be actually created by SQL.
+
+``` sql
+  CREATE TABLE metadata(
+  	ts timestamp time index,
+    	key string primary key,
+    	value string
+  );
+```
+
+The `ts` field is just a placeholder -- for the constraints that a mito region must contain a time index field. It will always be `0`. The other two fields `key` and `value` will be used as a k-v storage. It contains two group of key
+    - `__table_<TABLE_NAME>` is used for marking table existence. It doesn't have value.
+    - `__column_<TABLE_NAME>_<COLUMN_NAME>` is used for marking table existence, the value is column's semantic type.
+
+## Physical region implementation
+
+This RFC proposes to add a new region implementation named "MetricRegion". As showed in the first chart, it's wrapped over the existing mito region. This section will describe the implementation details. Firstly, here is a chart shows how the region hierarchy looks like:
+
+```plaintext
+ ┌───────────────────────┐
+ │ Metric Region         │
+ │                       │
+ │   ┌────────┬──────────┤
+ │   │ Mito   │ Mito     │
+ │   │ Region │ Region   │
+ │   │ for    │ for      │
+ │   │ Data   │ Metadata │
+ └───┴────────┴──────────┘
+```
+
+All upper levels only see the Metric Region. E.g., Meta Server schedules on this region, or Frontend routes requests to this Metrics Region's id. To be scheduled (open or close etc.), Metric Region needs to implement its own procedures. Most of those procedures can be simply assembled from underlying Mito Regions', but those related to data like alter or drop will have its own new logic.
+
+Another point is region id. Since the region id is used widely from meta server to persisted state, it's better to keep it unchanged. This means we can't use the same id for two regions, but one for each. To achieve this, this RFC proposes a concept named "region id group". A region id group is a group of region ids that are bound for different purposes. Like the two underlying regions here. 
+
+This preserves the first 8 bits of the `u32` region number for grouping. Each group has one main id (the first one) and other sub ids (the rest non-zero ids). All components other than the region implementation itself doesn't aware of the existence of region id group. They only see the main id. The region implementation is in response of managing and using the region id group.
+
+```plaintext
+63                                  31         23                  0
+┌────────────────────────────────────┬──────────┬──────────────────┐
+│          Table Id(32)              │ Group(8) │ Region Number(24)│
+└────────────────────────────────────┴──────────┴──────────────────┘
+                                            Region Id(32)
+```
+
+## Routing in meta server
+
+From previous sections, we can conclude the following points about routing:
+- Each "logical table" has its own, universe unique table id.
+- Logical table doesn't have physical region, they share the same physical region with other logical tables.
+- Route rule of logical table's is a strict subset of physical table's.
+
+To associate the logical table with physical region, we need to specify necessary information in the create table request. Specifically, the table type and its parent table. This require to change our gRPC proto's definition. And once meta recognize the table to create is a logical table, it will use the parent table's region to create route entry.
+
+And to reduce the consumption of region failover (which need to update the physical table route info), we'd better to split the current route table structure into two parts:
+
+```rust
+region_route: Map<TableName, [RegionId]>,
+node_route: Map<RegionId, NodeId>,
+```
+
+By doing this on each failover the meta server only needs to update the second `node_route` map and leave the first one untouched.
+
+## Query
+
+Like other existing components, a user query always starts in the frontend. In the planning phase, frontend needs to fetch related schemas of the queried table. This part is the same. I.e., changes in this RFC don't affect components above the `Table` abstraction.
+
+# Alternatives
+
+## Other routing method
+
+We can also do this "special" route rule in the meta server. But there is no difference with the proposed method.
+
+## Other storage for physical region's metadata
+
+Once we have implemented the "region family" that allows multiple physical schemas exist in one region, we can store the metadata and table data into one region.
+
+Before that, we can also let the `MetricRegion` holds a `KvBackend` to access the storage layer directly. But this breaks the abstraction in some way.
+
+# Drawbacks
+
+Since the physical storage is mixed together. It's hard to do fine-grained operations in table level. Like configuring TTL, memtable size or compaction strategy in table level. Or define different partition rules for different tables. For scenarios like this, it's better to move the table out of metrics engine and "upgrade" it to a normal mito engine table. This requires a migration process in a low cost. And we have to ensure data consistency during the migration, which may require a out-of-service period.

docs/rfcs/2023-08-04-tabie-trait-refactor.md

@@ -0,0 +1,175 @@
+---
+Feature Name: table-trait-refactor
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/2065
+Date: 2023-08-04
+Author: "Ruihang Xia <waynestxia@gmail.com>"
+---
+
+Refactor Table Trait
+--------------------
+
+# Summary
+Refactor `Table` trait to adapt the new region server architecture and make code more straightforward.
+
+# Motivation
+The `Table` is designed in the background of both frontend and datanode keeping the same concepts. And all the operations are served by a `Table`. However, in our practice, we found that not all the operations are suitable to be served by a `Table`. For example, the `Table` doesn't hold actual physical data itself, thus operations like write or alter are simply a proxy over underlying regions. And in the recent refactor to datanode ([rfc table-engine-refactor](./2023-07-06-table-engine-refactor.md)), we are changing datanode to region server that is only aware of `Region` things. This also calls for a refactor to the `Table` trait.
+
+# Details
+
+## Definitions
+
+The current `Table` trait contains the following methods:
+```rust
+pub trait Table {
+    /// Get a reference to the schema for this table
+    fn schema(&self) -> SchemaRef;
+
+    /// Get a reference to the table info.
+    fn table_info(&self) -> TableInfoRef;
+
+    /// Get the type of this table for metadata/catalog purposes.
+    fn table_type(&self) -> TableType;
+
+    /// Insert values into table.
+    ///
+    /// Returns number of inserted rows.
+    async fn insert(&self, _request: InsertRequest) -> Result<usize>;
+
+    /// Generate a record batch stream for querying.
+    async fn scan_to_stream(&self, request: ScanRequest) -> Result<SendableRecordBatchStream>;
+
+    /// Tests whether the table provider can make use of any or all filter expressions
+    /// to optimise data retrieval.
+    fn supports_filters_pushdown(&self, filters: &[&Expr]) -> Result<Vec<FilterPushDownType>>;
+
+    /// Alter table.
+    async fn alter(&self, _context: AlterContext, _request: &AlterTableRequest) -> Result<()>;
+
+    /// Delete rows in the table.
+    ///
+    /// Returns number of deleted rows.
+    async fn delete(&self, _request: DeleteRequest) -> Result<usize>;
+
+    /// Flush table.
+    ///
+    /// Options:
+    /// - region_number: specify region to flush.
+    /// - wait: Whether to wait until flush is done.
+    async fn flush(&self, region_number: Option<RegionNumber>, wait: Option<bool>) -> Result<()>;
+
+    /// Close the table.
+    async fn close(&self, _regions: &[RegionNumber]) -> Result<()>;
+
+    /// Get region stats in this table.
+    fn region_stats(&self) -> Result<Vec<RegionStat>>;
+
+    /// Return true if contains the region
+    fn contains_region(&self, _region: RegionNumber) -> Result<bool>;
+
+    /// Get statistics for this table, if available
+    fn statistics(&self) -> Option<TableStatistics>;
+
+    async fn compact(&self, region_number: Option<RegionNumber>, wait: Option<bool>) -> Result<()>;
+}
+```
+
+We can divide those methods into three categories from the perspective of functionality:
+
+|     Retrieve Metadata      | Manipulate Data |    Read Data     |
+| :------------------------: | :-------------: | :--------------: |
+|          `schema`          |    `insert`     | `scan_to_stream` |
+|        `table_info`        |     `alter`     |                  |
+|        `table_type`        |    `delete`     |                  |
+| `supports_filter_pushdown` |     `flush`     |                  |
+|       `region_stats`       |     `close`     |                  |
+|     `contains_region`      |    `compact`    |                  |
+|        `statistics`        |                 |                  |
+
+And considering most of the access to metadata happens in frontend, like route or query; and all the persisted data are stored in regions; while only the query engine needs to read data. We can divide the `Table` trait into three concepts:
+
+- struct `Table` provides metadata:
+    ```rust
+    impl Table {
+        /// Get a reference to the schema for this table
+        fn schema(&self) -> SchemaRef;
+
+        /// Get a reference to the table info.
+        fn table_info(&self) -> TableInfoRef;
+
+        /// Get the type of this table for metadata/catalog purposes.
+        fn table_type(&self) -> TableType;
+
+        /// Get statistics for this table, if available
+        fn statistics(&self) -> Option<TableStatistics>;
+
+        fn to_data_source(&self) -> DataSourceRef;
+    }
+    ```
+- Requests to region server
+  - `InsertRequest`
+  - `AlterRequest`
+  - `DeleteRequest`
+  - `FlushRequest`
+  - `CompactRequest`
+  - `CloseRequest`
+
+- trait `DataSource` provides data (`RecordBatch`)
+    ```rust
+    trait DataSource {
+        fn get_stream(&self, request: ScanRequest) -> Result<SendableRecordBatchStream>;
+    }
+    ```
+
+## Use `Table`
+
+`Table` will only be used in frontend. It's constructed from the `OpenTableRequest` or `CreateTableRequest`.
+
+`Table` also provides a method `to_data_source` to generate a `DataSource` from itself. But this method is only for non-`TableType::Base` tables (i.e., `TableType::View` and `TableType::Temporary`) because `TableType::Base` table doesn't hold actual data itself. Its `DataSource` should be constructed from the `Region` directly (in other words, it's a remote query).
+
+And it requires some extra information to construct a `DataSource`, named `TableSourceProvider`:
+
+```rust
+type TableFactory = Arc<dyn Fn() -> DataSourceRef>;
+
+pub enum TableSourceProvider {
+    Base,
+    View(LogicalPlan),
+    Temporary(TableFactory),
+}
+```
+
+## Use `DataSource`
+
+`DataSource` will be adapted to the `TableProvider` from DataFusion that can be `scan()`ed in a `TableScan` plan.
+
+In frontend this is done in the planning phase. And datanode will have one implementation for `Region` to generate record batch stream.
+
+## Interact with RegionServer
+
+Previously, persisted state change operations were through the old `Table` trait, like said before. Now they will come from the action source, like the procedure or protocol handler directly to the region server. E.g., on alter table, the corresponding procedure will generate its `AlterRequest` and send it to regions. Or write request will be split in frontend handler, and sent to regions. `Table` only provides necessary metadata like route information if needed, but not the necessary part anymore.
+
+## Implement temporary table
+
+Temporary table is a special table that doesn't revolves to any persistent physical region. Examples are:
+- the `Numbers` table for testing, which produces a record batch that contains 0-100 integers.
+- tables in information schema. It is an interface for querying catalog's metadata. The contents are generated on the fly with information from `CatalogManager`. The `CatalogManager` can be held in `TableFactory`.
+- Function table that produces data generated by a formula or a function. Like something that always `sin(current_timestamp())`.
+
+## Relationship among those components
+
+Here is a diagram to show the relationship among those components, and how they interact with each other.
+
+```mermaid
+erDiagram
+    CatalogManager ||--|{ Table : manages
+    Table ||--|{ DataStream : generates
+    Table ||--|{ Region : routes
+    Region ||--|{ DataStream : implements
+    DataStream }|..|| QueryEngine : adapts-to
+    Procedure ||--|{ Region : requests
+    Protocol ||--|{ Region : writes
+    Protocol ||--|{ QueryEngine : queries
+```
+
+# Drawback
+This is a breaking change.

docs/rfcs/2023-08-13-metadata-txn.md

@@ -0,0 +1,90 @@
+---
+Feature Name: Update Metadata in single transaction
+Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/1715
+Date: 2023-08-13
+Author: "Feng Yangsen <fengys1996@gmail.com>, Xu Wenkang <wenymedia@gmail.com>"
+---
+
+# Summary
+Update Metadata in single transaction.
+
+# Motivation
+Currently, multiple transactions are involved during the procedure. This implementation is inefficient, and it's hard to make data consistent. Therefore, We can update multiple metadata in a single transaction.
+
+# Details 
+Now we have the following table metadata keys:
+
+**TableInfo** 
+```rust
+// __table_info/{table_id}
+pub struct TableInfoKey {
+    table_id: TableId,
+}
+
+pub struct TableInfoValue {
+    pub table_info: RawTableInfo,
+    version: u64,
+}
+```
+
+**TableRoute** 
+```rust
+// __table_route/{table_id}
+pub struct NextTableRouteKey {
+    table_id: TableId,
+}
+
+pub struct TableRoute {
+    pub region_routes: Vec<RegionRoute>,
+}
+```
+**DatanodeTable**
+```rust
+// __table_route/{datanode_id}/{table_id}
+pub struct DatanodeTableKey {
+    datanode_id: DatanodeId,
+    table_id: TableId,
+}
+
+pub struct DatanodeTableValue {
+    pub table_id: TableId,
+    pub regions: Vec<RegionNumber>,
+    version: u64,
+}
+```
+
+**TableNameKey**
+```rust
+// __table_name/{CatalogName}/{SchemaName}/{TableName}
+pub struct TableNameKey<'a> {
+    pub catalog: &'a str,
+    pub schema: &'a str,
+    pub table: &'a str,
+}
+
+pub struct TableNameValue {
+    table_id: TableId,
+}
+```
+
+These table metadata only updates in the following operations.
+
+## Region Failover
+It needs to update `TableRoute` key and `DatanodeTable` keys. If the `TableRoute` equals the Snapshot of `TableRoute` submitting the Failover task, then we can safely update these keys.
+
+After submitting Failover tasks to acquire locks for execution, the `TableRoute` may be updated by another task. After acquiring the lock, we can get the latest `TableRoute` again and then execute it if needed.
+
+## Create Table DDL
+Creates all of the above keys. `TableRoute`, `TableInfo`, should be empty.
+
+The **TableNameKey**'s lock will be held by the procedure framework.
+## Drop Table DDL
+
+`TableInfoKey` and `NextTableRouteKey` will be added with  `__removed-` prefix, and the other above keys will be deleted.  The transaction will not compare any keys.
+## Alter Table DDL
+
+1. Rename table, updates `TableInfo` and `TableName`. Compares `TableInfo`, and the new `TableNameKey` should be empty, and TableInfo should equal the Snapshot when submitting DDL.
+
+The old and new **TableNameKey**'s lock will be held by the procedure framework.
+
+2. Alter table, updates `TableInfo`. `TableInfo` should equal the Snapshot when submitting DDL.

docs/schema-structs.md

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

rust-toolchain

@@ -1 +0,0 @@
-nightly-2022-12-20

rust-toolchain.toml

@@ -0,0 +1,2 @@
+[toolchain]
+channel = "nightly-2023-08-07"

scripts/fetch-dashboard-assets.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+# This script is used to download built dashboard assets from the "GreptimeTeam/dashboard" repository.
+
+set -e -x
+
+declare -r SCRIPT_DIR=$(cd $(dirname ${0}) >/dev/null 2>&1 && pwd)
+declare -r ROOT_DIR=$(dirname ${SCRIPT_DIR})
+declare -r STATIC_DIR="$ROOT_DIR/src/servers/dashboard"
+OUT_DIR="${1:-$SCRIPT_DIR}"
+
+RELEASE_VERSION="$(cat $STATIC_DIR/VERSION | tr -d '\t\r\n ')"
+
+echo "Downloading assets to dir: $OUT_DIR"
+cd $OUT_DIR
+# Download the SHA256 checksum attached to the release. To verify the integrity
+# of the download, this checksum will be used to check the download tar file
+# containing the built dashboard assets.
+curl -Ls https://github.com/GreptimeTeam/dashboard/releases/download/$RELEASE_VERSION/sha256.txt --output sha256.txt
+
+# Download the tar file containing the built dashboard assets.
+curl -L https://github.com/GreptimeTeam/dashboard/releases/download/$RELEASE_VERSION/build.tar.gz --output build.tar.gz
+
+# Verify the checksums match; exit if they don't.
+case "$(uname -s)" in
+    FreeBSD | Darwin)
+        echo "$(cat sha256.txt)" | shasum --algorithm 256 --check \
+            || { echo "Checksums did not match for downloaded dashboard assets!"; exit 1; } ;;
+    Linux)
+        echo "$(cat sha256.txt)" | sha256sum --check -- \
+            || { echo "Checksums did not match for downloaded dashboard assets!"; exit 1; } ;;
+    *)
+        echo "The '$(uname -s)' operating system is not supported as a build host for the dashboard" >&2
+        exit 1
+esac
+
+# Extract the assets and clean up.
+tar -xzf build.tar.gz -C "$STATIC_DIR"
+rm sha256.txt
+rm build.tar.gz
+
+echo "Successfully download dashboard assets to $STATIC_DIR"

scripts/install.sh

@@ -51,13 +51,26 @@ get_os_type
 get_arch_type
 
 if [ -n "${OS_TYPE}" ] && [ -n "${ARCH_TYPE}" ]; then
-    echo "Downloading ${BIN}, OS: ${OS_TYPE}, Arch: ${ARCH_TYPE}, Version: ${VERSION}"
-
+    # Use the latest nightly version.
     if [ "${VERSION}" = "latest" ]; then
-        wget "https://github.com/${GITHUB_ORG}/${GITHUB_REPO}/releases/latest/download/${BIN}-${OS_TYPE}-${ARCH_TYPE}.tgz"
-    else
-        wget "https://github.com/${GITHUB_ORG}/${GITHUB_REPO}/releases/download/${VERSION}/${BIN}-${OS_TYPE}-${ARCH_TYPE}.tgz"
+        VERSION=$(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
+        fi
     fi
 
-    tar xvf ${BIN}-${OS_TYPE}-${ARCH_TYPE}.tgz && rm ${BIN}-${OS_TYPE}-${ARCH_TYPE}.tgz && echo "Run '${BIN} --help' to get started"
+    echo "Downloading ${BIN}, OS: ${OS_TYPE}, Arch: ${ARCH_TYPE}, Version: ${VERSION}"
+    PACKAGE_NAME="${BIN}-${OS_TYPE}-${ARCH_TYPE}-${VERSION}.tar.gz"
+
+    if [ -n "${PACKAGE_NAME}" ]; then
+      wget "https://github.com/${GITHUB_ORG}/${GITHUB_REPO}/releases/download/${VERSION}/${PACKAGE_NAME}"
+
+      # Extract the binary and clean the rest.
+      tar xvf "${PACKAGE_NAME}" && \
+      mv "${PACKAGE_NAME%.tar.gz}/${BIN}" "${PWD}" && \
+      rm -r "${PACKAGE_NAME}" && \
+      rm -r "${PACKAGE_NAME%.tar.gz}" && \
+      echo "Run './${BIN} --help' to get started"
+    fi
 fi

src/api/Cargo.toml

@@ -5,13 +5,17 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-common-base = { path = "../common/base" }
-common-error = { path = "../common/error" }
-common-time = { path = "../common/time" }
-datatypes = { path = "../datatypes" }
-prost = "0.11"
+common-base = { workspace = true }
+common-error = { workspace = true }
+common-time = { workspace = true }
+datatypes = { workspace = true }
+greptime-proto.workspace = true
+prost.workspace = true
 snafu = { version = "0.7", features = ["backtraces"] }
-tonic = "0.8"
+tonic.workspace = true
 
 [build-dependencies]
-tonic-build = "0.8"
+tonic-build = "0.9"
+
+[dev-dependencies]
+paste = "1.0"

src/api/build.rs

@@ -1,34 +0,0 @@
-// Copyright 2022 Greptime Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use std::path::PathBuf;
-
-fn main() {
-    let default_out_dir = PathBuf::from(std::env::var("OUT_DIR").unwrap());
-    tonic_build::configure()
-        .file_descriptor_set_path(default_out_dir.join("greptime_fd.bin"))
-        .compile(
-            &[
-                "greptime/v1/select.proto",
-                "greptime/v1/greptime.proto",
-                "greptime/v1/meta/common.proto",
-                "greptime/v1/meta/heartbeat.proto",
-                "greptime/v1/meta/route.proto",
-                "greptime/v1/meta/store.proto",
-                "prometheus/remote/remote.proto",
-            ],
-            &["."],
-        )
-        .expect("compile proto");
-}

src/api/greptime/v1/admin.proto

@@ -1,88 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1;
-
-import "greptime/v1/column.proto";
-import "greptime/v1/common.proto";
-
-message AdminRequest {
-  string name = 1;
-  repeated AdminExpr exprs = 2;
-}
-
-message AdminResponse {
-  repeated AdminResult results = 1;
-}
-
-message AdminExpr {
-  ExprHeader header = 1;
-  oneof expr {
-    CreateTableExpr create_table = 2;
-    AlterExpr alter = 3;
-    CreateDatabaseExpr create_database = 4;
-    DropTableExpr drop_table = 5;
-  }
-}
-
-message AdminResult {
-  ResultHeader header = 1;
-  oneof result {
-    MutateResult mutate = 2;
-  }
-}
-
-message CreateTableExpr {
-  string catalog_name = 1;
-  string schema_name = 2;
-  string table_name = 3;
-  string desc = 4;
-  repeated ColumnDef column_defs = 5;
-  string time_index = 6;
-  repeated string primary_keys = 7;
-  bool create_if_not_exists = 8;
-  map<string, string> table_options = 9;
-  TableId table_id = 10;
-  repeated uint32 region_ids = 11;
-}
-
-message AlterExpr {
-  string catalog_name = 1;
-  string schema_name = 2;
-  string table_name = 3;
-  oneof kind {
-    AddColumns add_columns = 4;
-    DropColumns drop_columns = 5;
-  }
-}
-
-message DropTableExpr {
-  string catalog_name = 1;
-  string schema_name = 2;
-  string table_name = 3;
-}
-
-message CreateDatabaseExpr {
-  //TODO(hl): maybe rename to schema_name?
-  string database_name = 1;
-}
-
-message AddColumns {
-  repeated AddColumn add_columns = 1;
-}
-
-message DropColumns {
-  repeated DropColumn drop_columns = 1;
-}
-
-message AddColumn {
-  ColumnDef column_def = 1;
-  bool is_key = 2;
-}
-
-message DropColumn {
-  string name = 1;
-}
-
-message TableId {
-  uint32 id = 1;
-}

src/api/greptime/v1/column.proto

@@ -1,85 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1;
-
-message Column {
-  string column_name = 1;
-
-  enum SemanticType {
-    TAG = 0;
-    FIELD = 1;
-    TIMESTAMP = 2;
-  }
-  SemanticType semantic_type = 2;
-
-  message Values {
-    repeated int32 i8_values = 1;
-    repeated int32 i16_values = 2;
-    repeated int32 i32_values = 3;
-    repeated int64 i64_values = 4;
-
-    repeated uint32 u8_values = 5;
-    repeated uint32 u16_values = 6;
-    repeated uint32 u32_values = 7;
-    repeated uint64 u64_values = 8;
-
-    repeated float f32_values = 9;
-    repeated double f64_values = 10;
-
-    repeated bool bool_values = 11;
-    repeated bytes binary_values = 12;
-    repeated string string_values = 13;
-
-    repeated int32 date_values = 14;
-    repeated int64 datetime_values = 15;
-    repeated int64 ts_second_values = 16;
-    repeated int64 ts_millisecond_values = 17;
-    repeated int64 ts_microsecond_values = 18;
-    repeated int64 ts_nanosecond_values = 19;
-  }
-  // The array of non-null values in this column.
-  //
-  // For example: suppose there is a column "foo" that contains some int32 values (1, 2, 3, 4, 5, null, 7, 8, 9, null);
-  //   column:
-  //     column_name: foo
-  //     semantic_type: Tag
-  //     values: 1, 2, 3, 4, 5, 7, 8, 9
-  //     null_masks: 00100000 00000010
-  Values values = 3;
-
-  // Mask maps the positions of null values.
-  // If a bit in null_mask is 1, it indicates that the column value at that position is null.
-  bytes null_mask = 4;
-
-  // Helpful in creating vector from column.
-  ColumnDataType datatype = 5;
-}
-
-message ColumnDef {
-  string name = 1;
-  ColumnDataType datatype = 2;
-  bool is_nullable = 3;
-  bytes default_constraint = 4;
-}
-
-enum ColumnDataType {
-  BOOLEAN = 0;
-  INT8 = 1;
-  INT16 = 2;
-  INT32 = 3;
-  INT64 = 4;
-  UINT8 = 5;
-  UINT16 = 6;
-  UINT32 = 7;
-  UINT64 = 8;
-  FLOAT32 = 9;
-  FLOAT64 = 10;
-  BINARY = 11;
-  STRING = 12;
-  DATE = 13;
-  DATETIME = 14;
-  TIMESTAMP_SECOND = 15;
-  TIMESTAMP_MILLISECOND = 16;
-  TIMESTAMP_MICROSECOND = 17;
-  TIMESTAMP_NANOSECOND = 18;
-}

src/api/greptime/v1/common.proto

@@ -1,22 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1;
-
-message RequestHeader {
-  string tenant = 1;
-}
-
-message ExprHeader {
-  uint32 version = 1;
-}
-
-message ResultHeader {
-  uint32 version = 1;
-  uint32 code = 2;
-  string err_msg = 3;
-}
-
-message MutateResult {
-  uint32 success = 1;
-  uint32 failure = 2;
-}

src/api/greptime/v1/database.proto

@@ -1,66 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1;
-
-import "greptime/v1/column.proto";
-import "greptime/v1/common.proto";
-
-message DatabaseRequest {
-  string name = 1;
-  repeated ObjectExpr exprs = 2;
-}
-
-message DatabaseResponse {
-  repeated ObjectResult results = 1;
-}
-
-message ObjectExpr {
-  ExprHeader header = 1;
-  oneof expr {
-    InsertExpr insert = 2;
-    SelectExpr select = 3;
-    UpdateExpr update = 4;
-    DeleteExpr delete = 5;
-  }
-}
-
-// TODO(fys): Only support sql now, and will support promql etc in the future
-message SelectExpr {
-  oneof expr {
-    string sql = 1;
-    bytes logical_plan = 2;
-  }
-}
-
-message InsertExpr {
-  string schema_name = 1;
-  string table_name = 2;
-
-  // Data is represented here.
-  repeated Column columns = 3;
-
-  // The row_count of all columns, which include null and non-null values.
-  //
-  // Note: the row_count of all columns in a InsertExpr must be same.
-  uint32 row_count = 4;
-
-  // The region number of current insert request.
-  uint32 region_number = 5;
-}
-
-// TODO(jiachun)
-message UpdateExpr {}
-// TODO(jiachun)
-message DeleteExpr {}
-
-message ObjectResult {
-  ResultHeader header = 1;
-  oneof result {
-    SelectResult select = 2;
-    MutateResult mutate = 3;
-  }
-}
-
-message SelectResult {
-  bytes raw_data = 1;
-}

src/api/greptime/v1/greptime.proto

@@ -1,22 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1;
-
-import "greptime/v1/admin.proto";
-import "greptime/v1/common.proto";
-import "greptime/v1/database.proto";
-
-service Greptime {
-  rpc Batch(BatchRequest) returns (BatchResponse) {}
-}
-
-message BatchRequest {
-  RequestHeader header = 1;
-  repeated AdminRequest admins = 2;
-  repeated DatabaseRequest databases = 3;
-}
-
-message BatchResponse {
-  repeated AdminResponse admins = 1;
-  repeated DatabaseResponse databases = 2;
-}

src/api/greptime/v1/meta/common.proto

@@ -1,48 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1.meta;
-
-message RequestHeader {
-  uint64 protocol_version = 1;
-  // cluster_id is the ID of the cluster which be sent to.
-  uint64 cluster_id = 2;
-  // member_id is the ID of the sender server.
-  uint64 member_id = 3;
-}
-
-message ResponseHeader {
-  uint64 protocol_version = 1;
-  // cluster_id is the ID of the cluster which sent the response.
-  uint64 cluster_id = 2;
-  Error error = 3;
-}
-
-message Error {
-  int32 code = 1;
-  string err_msg = 2;
-}
-
-message Peer {
-  uint64 id = 1;
-  string addr = 2;
-}
-
-message TableName {
-  string catalog_name = 1;
-  string schema_name = 2;
-  string table_name = 3;
-}
-
-message TimeInterval {
-  // The unix timestamp in millis of the start of this period.
-  uint64 start_timestamp_millis = 1;
-  // The unix timestamp in millis of the end of this period.
-  uint64 end_timestamp_millis = 2;
-}
-
-message KeyValue {
-  // key is the key in bytes. An empty key is not allowed.
-  bytes key = 1;
-  // value is the value held by the key, in bytes.
-  bytes value = 2;
-}

src/api/greptime/v1/meta/heartbeat.proto

@@ -1,92 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1.meta;
-
-import "greptime/v1/meta/common.proto";
-
-service Heartbeat {
-  // Heartbeat, there may be many contents of the heartbeat, such as:
-  // 1. Metadata to be registered to meta server and discoverable by other nodes.
-  // 2. Some performance metrics, such as Load, CPU usage, etc.
-  // 3. The number of computing tasks being executed.
-  rpc Heartbeat(stream HeartbeatRequest) returns (stream HeartbeatResponse) {}
-
-  // Ask leader's endpoint.
-  rpc AskLeader(AskLeaderRequest) returns (AskLeaderResponse) {}
-}
-
-message HeartbeatRequest {
-  RequestHeader header = 1;
-
-  // Self peer
-  Peer peer = 2;
-  // Leader node
-  bool is_leader = 3;
-  // Actually reported time interval
-  TimeInterval report_interval = 4;
-  // Node stat
-  NodeStat node_stat = 5;
-  // Region stats in this node
-  repeated RegionStat region_stats = 6;
-  // Follower nodes and stats, empty on follower nodes
-  repeated ReplicaStat replica_stats = 7;
-}
-
-message NodeStat {
-  // The read capacity units during this period
-  uint64 rcus = 1;
-  // The write capacity units during this period
-  uint64 wcus = 2;
-  // Table number in this node
-  uint64 table_num = 3;
-  // Region number in this node
-  uint64 region_num = 4;
-
-  double cpu_usage = 5;
-  double load = 6;
-  // Read disk I/O in the node
-  double read_io_rate = 7;
-  // Write disk I/O in the node
-  double write_io_rate = 8;
-
-  // Others
-  map<string, string> attrs = 100;
-}
-
-message RegionStat {
-  uint64 region_id = 1;
-  TableName table_name = 2;
-  // The read capacity units during this period
-  uint64 rcus = 3;
-  // The write capacity units during this period
-  uint64 wcus = 4;
-  // Approximate region size
-  uint64 approximate_size = 5;
-  // Approximate number of rows
-  uint64 approximate_rows = 6;
-
-  // Others
-  map<string, string> attrs = 100;
-}
-
-message ReplicaStat {
-  Peer peer = 1;
-  bool in_sync = 2;
-  bool is_learner = 3;
-}
-
-message HeartbeatResponse {
-  ResponseHeader header = 1;
-
-  repeated bytes payload = 2;
-}
-
-message AskLeaderRequest {
-  RequestHeader header = 1;
-}
-
-message AskLeaderResponse {
-  ResponseHeader header = 1;
-
-  Peer leader = 2;
-}

src/api/greptime/v1/meta/route.proto

@@ -1,98 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1.meta;
-
-import "greptime/v1/meta/common.proto";
-
-service Router {
-  rpc Create(CreateRequest) returns (RouteResponse) {}
-
-  // Fetch routing information for tables. The smallest unit is the complete
-  // routing information(all regions) of a table.
-  // 
-  // ```text
-  // table_1
-  //    table_name
-  //    table_schema
-  //    regions
-  //      region_1
-  //        leader_peer
-  //        follower_peer_1, follower_peer_2
-  //      region_2
-  //        leader_peer
-  //        follower_peer_1, follower_peer_2, follower_peer_3
-  //      region_xxx
-  // table_2
-  //    ...
-  // ```
-  //
-  rpc Route(RouteRequest) returns (RouteResponse) {}
-
-  rpc Delete(DeleteRequest) returns (RouteResponse) {}
-}
-
-message CreateRequest {
-  RequestHeader header = 1;
-
-  TableName table_name = 2;
-  repeated Partition partitions = 3;
-}
-
-message RouteRequest {
-  RequestHeader header = 1;
-
-  repeated TableName table_names = 2;
-}
-
-message DeleteRequest {
-  RequestHeader header = 1;
-
-  TableName table_name = 2; 
-}
-
-message RouteResponse {
-  ResponseHeader header = 1;
-
-  repeated Peer peers = 2;
-  repeated TableRoute table_routes = 3;
-}
-
-message TableRoute {
-  Table table = 1;
-  repeated RegionRoute region_routes = 2;
-}
-
-message RegionRoute {
-  Region region = 1;
-  // single leader node for write task
-  uint64 leader_peer_index = 2;
-  // multiple follower nodes for read task
-  repeated uint64 follower_peer_indexes = 3;
-}
-
-message Table {
-  uint64 id = 1;
-  TableName table_name = 2;
-  bytes table_schema = 3;
-}
-
-message Region {
-  // TODO(LFC): Maybe use message RegionNumber?
-  uint64 id = 1;
-  string name = 2;
-  Partition partition = 3;
-  
-  map<string, string> attrs = 100;
-}
-
-// PARTITION `region_name` VALUES LESS THAN (value_list)
-message Partition {
-  repeated bytes column_list = 1;
-  repeated bytes value_list = 2;
-}
-
-// This message is only for saving into store.
-message TableRouteValue {
-  repeated Peer peers = 1; 
-  TableRoute table_route = 2;
-}

src/api/greptime/v1/meta/store.proto

@@ -1,159 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1.meta;
-
-import "greptime/v1/meta/common.proto";
-
-service Store {
-  // Range gets the keys in the range from the key-value store.
-  rpc Range(RangeRequest) returns (RangeResponse);
-
-  // Put puts the given key into the key-value store.
-  rpc Put(PutRequest) returns (PutResponse);
-
-  // BatchPut atomically puts the given keys into the key-value store.
-  rpc BatchPut(BatchPutRequest) returns (BatchPutResponse);
-
-  // CompareAndPut atomically puts the value to the given updated
-  // value if the current value == the expected value.
-  rpc CompareAndPut(CompareAndPutRequest) returns (CompareAndPutResponse);
-
-  // DeleteRange deletes the given range from the key-value store.
-  rpc DeleteRange(DeleteRangeRequest) returns (DeleteRangeResponse);
-
-  // MoveValue atomically renames the key to the given updated key.
-  rpc MoveValue(MoveValueRequest) returns (MoveValueResponse);
-}
-
-message RangeRequest {
-  RequestHeader header = 1;
-
-  // key is the first key for the range, If range_end is not given, the
-  // request only looks up key.
-  bytes key = 2;
-  // range_end is the upper bound on the requested range [key, range_end).
-  // If range_end is '\0', the range is all keys >= key.
-  // If range_end is key plus one (e.g., "aa"+1 == "ab", "a\xff"+1 == "b"),
-  // then the range request gets all keys prefixed with key.
-  // If both key and range_end are '\0', then the range request returns all
-  // keys.
-  bytes range_end = 3;
-  // limit is a limit on the number of keys returned for the request. When
-  // limit is set to 0, it is treated as no limit.
-  int64 limit = 4;
-  // keys_only when set returns only the keys and not the values.
-  bool keys_only = 5;
-}
-
-message RangeResponse {
-  ResponseHeader header = 1;
-  
-  // kvs is the list of key-value pairs matched by the range request.
-  repeated KeyValue kvs = 2;
-  // more indicates if there are more keys to return in the requested range.
-  bool more = 3;
-}
-
-message PutRequest {
-  RequestHeader header = 1;
-
-  // key is the key, in bytes, to put into the key-value store.
-  bytes key = 2;
-  // value is the value, in bytes, to associate with the key in the
-  // key-value store.
-  bytes value = 3;
-  // If prev_kv is set, gets the previous key-value pair before changing it.
-  // The previous key-value pair will be returned in the put response.
-  bool prev_kv = 4;
-}
-
-message PutResponse {
-  ResponseHeader header = 1;
-
-  // If prev_kv is set in the request, the previous key-value pair will be
-  // returned.
-  KeyValue prev_kv = 2;
-}
-
-message BatchPutRequest {
-  RequestHeader header = 1;
-
-  repeated KeyValue kvs = 2;
-  // If prev_kv is set, gets the previous key-value pairs before changing it.
-  // The previous key-value pairs will be returned in the batch put response.
-  bool prev_kv = 3;
-}
-
-message BatchPutResponse {
-  ResponseHeader header = 1;
-
-  // If prev_kv is set in the request, the previous key-value pairs will be
-  // returned.
-  repeated KeyValue prev_kvs = 2;
-}
-
-message CompareAndPutRequest {
-  RequestHeader header = 1;
-
-  // key is the key, in bytes, to put into the key-value store.
-  bytes key = 2;
-  // expect is the previous value, in bytes
-  bytes expect = 3;
-  // value is the value, in bytes, to associate with the key in the
-  // key-value store.
-  bytes value = 4; 
-}
-
-message CompareAndPutResponse {
-  ResponseHeader header = 1;
-
-  bool success = 2;
-  KeyValue prev_kv = 3;
-}
-
-message DeleteRangeRequest {
-  RequestHeader header = 1;
-
-  // key is the first key to delete in the range.
-  bytes key = 2;
-  // range_end is the key following the last key to delete for the range
-  // [key, range_end).
-  // If range_end is not given, the range is defined to contain only the key
-  // argument.
-  // If range_end is one bit larger than the given key, then the range is all
-  // the keys with the prefix (the given key).
-  // If range_end is '\0', the range is all keys greater than or equal to the
-  // key argument.
-  bytes range_end = 3;
-  // If prev_kv is set, gets the previous key-value pairs before deleting it.
-  // The previous key-value pairs will be returned in the delete response.
-  bool prev_kv = 4;
-}
-
-message DeleteRangeResponse {
-  ResponseHeader header = 1;
-
-  // deleted is the number of keys deleted by the delete range request.
-  int64 deleted = 2;
-  // If prev_kv is set in the request, the previous key-value pairs will be
-  // returned.
-  repeated KeyValue prev_kvs = 3;
-}
-
-message MoveValueRequest {
-  RequestHeader header = 1;
-
-  // If from_key dose not exist, return the value of to_key (if it exists).
-  // If from_key exists, move the value of from_key to to_key (i.e. rename),
-  // and return the value.
-  bytes from_key = 2;
-  bytes to_key = 3;
-}
-
-message MoveValueResponse {
-  ResponseHeader header = 1;
-
-  // If from_key dose not exist, return the value of to_key (if it exists).
-  // If from_key exists, return the value of from_key.
-  KeyValue kv = 2;
-}

src/api/greptime/v1/select.proto

@@ -1,10 +0,0 @@
-syntax = "proto3";
-
-package greptime.v1.codec;
-
-import "greptime/v1/column.proto";
-
-message SelectResult {
-  repeated Column columns = 1;
-  uint32 row_count = 2;
-}

src/api/prometheus/remote/remote.proto

@@ -1,85 +0,0 @@
-// Copyright 2016 Prometheus 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.
-
-syntax = "proto3";
-package prometheus;
-
-option go_package = "prompb";
-
-import "prometheus/remote/types.proto";
-
-message WriteRequest {
-  repeated prometheus.TimeSeries timeseries = 1;
-  // Cortex uses this field to determine the source of the write request.
-  // We reserve it to avoid any compatibility issues.
-  reserved  2;
-  repeated prometheus.MetricMetadata metadata = 3;
-}
-
-// ReadRequest represents a remote read request.
-message ReadRequest {
-  repeated Query queries = 1;
-
-  enum ResponseType {
-    // Server will return a single ReadResponse message with matched series that includes list of raw samples.
-    // It's recommended to use streamed response types instead.
-    //
-    // Response headers:
-    // Content-Type: "application/x-protobuf"
-    // Content-Encoding: "snappy"
-    SAMPLES = 0;
-    // Server will stream a delimited ChunkedReadResponse message that contains XOR encoded chunks for a single series.
-    // Each message is following varint size and fixed size bigendian uint32 for CRC32 Castagnoli checksum.
-    //
-    // Response headers:
-    // Content-Type: "application/x-streamed-protobuf; proto=prometheus.ChunkedReadResponse"
-    // Content-Encoding: ""
-    STREAMED_XOR_CHUNKS = 1;
-  }
-
-  // accepted_response_types allows negotiating the content type of the response.
-  //
-  // Response types are taken from the list in the FIFO order. If no response type in `accepted_response_types` is
-  // implemented by server, error is returned.
-  // For request that do not contain `accepted_response_types` field the SAMPLES response type will be used.
-  repeated ResponseType accepted_response_types = 2;
-}
-
-// ReadResponse is a response when response_type equals SAMPLES.
-message ReadResponse {
-  // In same order as the request's queries.
-  repeated QueryResult results = 1;
-}
-
-message Query {
-  int64 start_timestamp_ms = 1;
-  int64 end_timestamp_ms = 2;
-  repeated prometheus.LabelMatcher matchers = 3;
-  prometheus.ReadHints hints = 4;
-}
-
-message QueryResult {
-  // Samples within a time series must be ordered by time.
-  repeated prometheus.TimeSeries timeseries = 1;
-}
-
-// ChunkedReadResponse is a response when response_type equals STREAMED_XOR_CHUNKS.
-// We strictly stream full series after series, optionally split by time. This means that a single frame can contain
-// partition of the single series, but once a new series is started to be streamed it means that no more chunks will
-// be sent for previous one. Series are returned sorted in the same way TSDB block are internally.
-message ChunkedReadResponse {
-  repeated prometheus.ChunkedSeries chunked_series = 1;
-
-  // query_index represents an index of the query from ReadRequest.queries these chunks relates to.
-  int64 query_index = 2;
-}

src/api/prometheus/remote/types.proto

@@ -1,117 +0,0 @@
-// Copyright 2017 Prometheus 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.
-
-syntax = "proto3";
-package prometheus;
-
-option go_package = "prompb";
-
-message MetricMetadata {
-  enum MetricType {
-    UNKNOWN        = 0;
-    COUNTER        = 1;
-    GAUGE          = 2;
-    HISTOGRAM      = 3;
-    GAUGEHISTOGRAM = 4;
-    SUMMARY        = 5;
-    INFO           = 6;
-    STATESET       = 7;
-  }
-
-  // Represents the metric type, these match the set from Prometheus.
-  // Refer to model/textparse/interface.go for details.
-  MetricType type = 1;
-  string metric_family_name = 2;
-  string help = 4;
-  string unit = 5;
-}
-
-message Sample {
-  double value    = 1;
-  // timestamp is in ms format, see model/timestamp/timestamp.go for
-  // conversion from time.Time to Prometheus timestamp.
-  int64 timestamp = 2;
-}
-
-message Exemplar {
-  // Optional, can be empty.
-  repeated Label labels = 1;
-  double value = 2;
-  // timestamp is in ms format, see model/timestamp/timestamp.go for
-  // conversion from time.Time to Prometheus timestamp.
-  int64 timestamp = 3;
-}
-
-// TimeSeries represents samples and labels for a single time series.
-message TimeSeries {
-  // For a timeseries to be valid, and for the samples and exemplars
-  // to be ingested by the remote system properly, the labels field is required.
-  repeated Label labels   = 1;
-  repeated Sample samples = 2;
-  repeated Exemplar exemplars = 3;
-}
-
-message Label {
-  string name  = 1;
-  string value = 2;
-}
-
-message Labels {
-  repeated Label labels = 1;
-}
-
-// Matcher specifies a rule, which can match or set of labels or not.
-message LabelMatcher {
-  enum Type {
-    EQ  = 0;
-    NEQ = 1;
-    RE  = 2;
-    NRE = 3;
-  }
-  Type type    = 1;
-  string name  = 2;
-  string value = 3;
-}
-
-message ReadHints {
-  int64 step_ms = 1;  // Query step size in milliseconds.
-  string func = 2;    // String representation of surrounding function or aggregation.
-  int64 start_ms = 3; // Start time in milliseconds.
-  int64 end_ms = 4;   // End time in milliseconds.
-  repeated string grouping = 5; // List of label names used in aggregation.
-  bool by = 6; // Indicate whether it is without or by.
-  int64 range_ms = 7; // Range vector selector range in milliseconds.
-}
-
-// Chunk represents a TSDB chunk.
-// Time range [min, max] is inclusive.
-message Chunk {
-  int64 min_time_ms = 1;
-  int64 max_time_ms = 2;
-
-  // We require this to match chunkenc.Encoding.
-  enum Encoding {
-    UNKNOWN = 0;
-    XOR     = 1;
-  }
-  Encoding type  = 3;
-  bytes data     = 4;
-}
-
-// ChunkedSeries represents single, encoded time series.
-message ChunkedSeries {
-  // Labels should be sorted.
-  repeated Label labels = 1;
-  // Chunks will be in start time order and may overlap.
-  repeated Chunk chunks = 2;
-}

src/api/src/error.rs

@@ -1,10 +1,10 @@
-// Copyright 2022 Greptime Team
+// 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
+//     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,
@@ -15,10 +15,10 @@
 use std::any::Any;
 
 use common_error::ext::ErrorExt;
-use common_error::prelude::StatusCode;
+use common_error::status_code::StatusCode;
 use datatypes::prelude::ConcreteDataType;
 use snafu::prelude::*;
-use snafu::{Backtrace, ErrorCompat};
+use snafu::Location;
 
 pub type Result<T> = std::result::Result<T, Error>;
 
@@ -26,12 +26,12 @@ pub type Result<T> = std::result::Result<T, Error>;
 #[snafu(visibility(pub))]
 pub enum Error {
     #[snafu(display("Unknown proto column datatype: {}", datatype))]
-    UnknownColumnDataType { datatype: i32, backtrace: Backtrace },
+    UnknownColumnDataType { datatype: i32, location: Location },
 
     #[snafu(display("Failed to create column datatype from {:?}", from))]
     IntoColumnDataType {
         from: ConcreteDataType,
-        backtrace: Backtrace,
+        location: Location,
     },
 
     #[snafu(display(
@@ -41,7 +41,7 @@ pub enum Error {
     ))]
     ConvertColumnDefaultConstraint {
         column: String,
-        #[snafu(backtrace)]
+        location: Location,
         source: datatypes::error::Error,
     },
 
@@ -52,7 +52,7 @@ pub enum Error {
     ))]
     InvalidColumnDefaultConstraint {
         column: String,
-        #[snafu(backtrace)]
+        location: Location,
         source: datatypes::error::Error,
     },
 }
@@ -66,9 +66,6 @@ impl ErrorExt for Error {
             | Error::InvalidColumnDefaultConstraint { source, .. } => source.status_code(),
         }
     }
-    fn backtrace_opt(&self) -> Option<&Backtrace> {
-        ErrorCompat::backtrace(self)
-    }
 
     fn as_any(&self) -> &dyn Any {
         self

src/api/src/lib.rs

@@ -1,10 +1,10 @@
-// Copyright 2022 Greptime Team
+// 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
+//     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,
@@ -14,9 +14,14 @@
 
 pub mod error;
 pub mod helper;
-pub mod prometheus;
-pub mod result;
-pub mod serde;
+
+pub mod prom_store {
+    pub mod remote {
+        pub use greptime_proto::prometheus::remote::*;
+    }
+}
+
 pub mod v1;
 
+pub use greptime_proto;
 pub use prost::DecodeError;

src/api/src/result.rs

@@ -1,203 +0,0 @@
-// Copyright 2022 Greptime Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use common_error::prelude::ErrorExt;
-
-use crate::v1::codec::SelectResult;
-use crate::v1::{
-    admin_result, object_result, AdminResult, MutateResult, ObjectResult, ResultHeader,
-    SelectResult as SelectResultRaw,
-};
-
-pub const PROTOCOL_VERSION: u32 = 1;
-
-pub type Success = u32;
-pub type Failure = u32;
-
-#[derive(Default)]
-pub struct ObjectResultBuilder {
-    version: u32,
-    code: u32,
-    err_msg: Option<String>,
-    result: Option<Body>,
-}
-
-pub enum Body {
-    Mutate((Success, Failure)),
-    Select(SelectResult),
-}
-
-impl ObjectResultBuilder {
-    pub fn new() -> Self {
-        Self {
-            version: PROTOCOL_VERSION,
-            ..Default::default()
-        }
-    }
-
-    #[allow(dead_code)]
-    pub fn version(mut self, version: u32) -> Self {
-        self.version = version;
-        self
-    }
-
-    pub fn status_code(mut self, code: u32) -> Self {
-        self.code = code;
-        self
-    }
-
-    pub fn err_msg(mut self, err_msg: String) -> Self {
-        self.err_msg = Some(err_msg);
-        self
-    }
-
-    pub fn mutate_result(mut self, success: u32, failure: u32) -> Self {
-        self.result = Some(Body::Mutate((success, failure)));
-        self
-    }
-
-    pub fn select_result(mut self, select_result: SelectResult) -> Self {
-        self.result = Some(Body::Select(select_result));
-        self
-    }
-
-    pub fn build(self) -> ObjectResult {
-        let header = Some(ResultHeader {
-            version: self.version,
-            code: self.code,
-            err_msg: self.err_msg.unwrap_or_default(),
-        });
-
-        let result = match self.result {
-            Some(Body::Mutate((success, failure))) => {
-                Some(object_result::Result::Mutate(MutateResult {
-                    success,
-                    failure,
-                }))
-            }
-            Some(Body::Select(select)) => Some(object_result::Result::Select(SelectResultRaw {
-                raw_data: select.into(),
-            })),
-            None => None,
-        };
-
-        ObjectResult { header, result }
-    }
-}
-
-pub fn build_err_result(err: &impl ErrorExt) -> ObjectResult {
-    ObjectResultBuilder::new()
-        .status_code(err.status_code() as u32)
-        .err_msg(err.to_string())
-        .build()
-}
-
-#[derive(Debug)]
-pub struct AdminResultBuilder {
-    version: u32,
-    code: u32,
-    err_msg: Option<String>,
-    mutate: Option<(Success, Failure)>,
-}
-
-impl AdminResultBuilder {
-    pub fn status_code(mut self, code: u32) -> Self {
-        self.code = code;
-        self
-    }
-
-    pub fn err_msg(mut self, err_msg: String) -> Self {
-        self.err_msg = Some(err_msg);
-        self
-    }
-
-    pub fn mutate_result(mut self, success: u32, failure: u32) -> Self {
-        self.mutate = Some((success, failure));
-        self
-    }
-
-    pub fn build(self) -> AdminResult {
-        let header = Some(ResultHeader {
-            version: self.version,
-            code: self.code,
-            err_msg: self.err_msg.unwrap_or_default(),
-        });
-
-        let result = if let Some((success, failure)) = self.mutate {
-            Some(admin_result::Result::Mutate(MutateResult {
-                success,
-                failure,
-            }))
-        } else {
-            None
-        };
-
-        AdminResult { header, result }
-    }
-}
-
-impl Default for AdminResultBuilder {
-    fn default() -> Self {
-        Self {
-            version: PROTOCOL_VERSION,
-            code: 0,
-            err_msg: None,
-            mutate: None,
-        }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use common_error::status_code::StatusCode;
-
-    use super::*;
-    use crate::error::UnknownColumnDataTypeSnafu;
-    use crate::v1::{object_result, MutateResult};
-
-    #[test]
-    fn test_object_result_builder() {
-        let obj_result = ObjectResultBuilder::new()
-            .version(101)
-            .status_code(500)
-            .err_msg("Failed to read this file!".to_string())
-            .mutate_result(100, 20)
-            .build();
-        let header = obj_result.header.unwrap();
-        assert_eq!(101, header.version);
-        assert_eq!(500, header.code);
-        assert_eq!("Failed to read this file!", header.err_msg);
-
-        let result = obj_result.result.unwrap();
-        assert_eq!(
-            object_result::Result::Mutate(MutateResult {
-                success: 100,
-                failure: 20,
-            }),
-            result
-        );
-    }
-
-    #[test]
-    fn test_build_err_result() {
-        let err = UnknownColumnDataTypeSnafu { datatype: 1 }.build();
-        let err_result = build_err_result(&err);
-        let header = err_result.header.unwrap();
-        let result = err_result.result;
-
-        assert_eq!(PROTOCOL_VERSION, header.version);
-        assert_eq!(StatusCode::InvalidArguments as u32, header.code);
-        assert!(result.is_none());
-    }
-}

src/api/src/serde.rs

@@ -1,115 +0,0 @@
-// Copyright 2022 Greptime Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-pub use prost::DecodeError;
-use prost::Message;
-
-use crate::v1::codec::SelectResult;
-use crate::v1::meta::TableRouteValue;
-
-macro_rules! impl_convert_with_bytes {
-    ($data_type: ty) => {
-        impl From<$data_type> for Vec<u8> {
-            fn from(entity: $data_type) -> Self {
-                entity.encode_to_vec()
-            }
-        }
-
-        impl TryFrom<&[u8]> for $data_type {
-            type Error = DecodeError;
-
-            fn try_from(value: &[u8]) -> Result<Self, Self::Error> {
-                <$data_type>::decode(value.as_ref())
-            }
-        }
-    };
-}
-
-impl_convert_with_bytes!(SelectResult);
-impl_convert_with_bytes!(TableRouteValue);
-
-#[cfg(test)]
-mod tests {
-    use std::ops::Deref;
-
-    use crate::v1::codec::*;
-    use crate::v1::{column, Column};
-
-    const SEMANTIC_TAG: i32 = 0;
-
-    #[test]
-    fn test_convert_select_result() {
-        let select_result = mock_select_result();
-
-        let bytes: Vec<u8> = select_result.into();
-        let result: SelectResult = bytes.deref().try_into().unwrap();
-
-        assert_eq!(8, result.row_count);
-        assert_eq!(1, result.columns.len());
-
-        let column = &result.columns[0];
-        assert_eq!("foo", column.column_name);
-        assert_eq!(SEMANTIC_TAG, column.semantic_type);
-        assert_eq!(vec![1], column.null_mask);
-        assert_eq!(
-            vec![2, 3, 4, 5, 6, 7, 8],
-            column.values.as_ref().unwrap().i32_values
-        );
-    }
-
-    #[should_panic]
-    #[test]
-    fn test_convert_select_result_wrong() {
-        let select_result = mock_select_result();
-
-        let mut bytes: Vec<u8> = select_result.into();
-
-        // modify some bytes
-        bytes[0] = 0b1;
-        bytes[1] = 0b1;
-
-        let result: SelectResult = bytes.deref().try_into().unwrap();
-
-        assert_eq!(8, result.row_count);
-        assert_eq!(1, result.columns.len());
-
-        let column = &result.columns[0];
-        assert_eq!("foo", column.column_name);
-        assert_eq!(SEMANTIC_TAG, column.semantic_type);
-        assert_eq!(vec![1], column.null_mask);
-        assert_eq!(
-            vec![2, 3, 4, 5, 6, 7, 8],
-            column.values.as_ref().unwrap().i32_values
-        );
-    }
-
-    fn mock_select_result() -> SelectResult {
-        let values = column::Values {
-            i32_values: vec![2, 3, 4, 5, 6, 7, 8],
-            ..Default::default()
-        };
-        let null_mask = vec![1];
-        let column = Column {
-            column_name: "foo".to_string(),
-            semantic_type: SEMANTIC_TAG,
-            values: Some(values),
-            null_mask,
-            ..Default::default()
-        };
-        SelectResult {
-            columns: vec![column],
-            row_count: 8,
-        }
-    }
-}

src/api/src/v1.rs

@@ -1,10 +1,10 @@
-// Copyright 2022 Greptime Team
+// 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
+//     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,
@@ -12,14 +12,10 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-#![allow(clippy::derive_partial_eq_without_eq)]
-tonic::include_proto!("greptime.v1");
+pub mod column_def;
 
-pub const GREPTIME_FD_SET: &[u8] = tonic::include_file_descriptor_set!("greptime_fd");
-
-pub mod codec {
-    tonic::include_proto!("greptime.v1.codec");
+pub mod meta {
+    pub use greptime_proto::v1::meta::*;
 }
 
-mod column_def;
-pub mod meta;
+pub use greptime_proto::v1::*;

src/api/src/v1/column_def.rs

@@ -1,10 +1,10 @@
-// Copyright 2022 Greptime Team
+// 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
+//     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,
@@ -19,21 +19,24 @@ use crate::error::{self, Result};
 use crate::helper::ColumnDataTypeWrapper;
 use crate::v1::ColumnDef;
 
-impl ColumnDef {
-    pub fn try_as_column_schema(&self) -> Result<ColumnSchema> {
-        let data_type = ColumnDataTypeWrapper::try_new(self.datatype)?;
+pub fn try_as_column_schema(column_def: &ColumnDef) -> Result<ColumnSchema> {
+    let data_type = ColumnDataTypeWrapper::try_new(column_def.datatype)?;
 
-        let constraint = if self.default_constraint.is_empty() {
-            None
-        } else {
-            Some(
-                ColumnDefaultConstraint::try_from(self.default_constraint.as_slice())
-                    .context(error::ConvertColumnDefaultConstraintSnafu { column: &self.name })?,
-            )
-        };
+    let constraint = if column_def.default_constraint.is_empty() {
+        None
+    } else {
+        Some(
+            ColumnDefaultConstraint::try_from(column_def.default_constraint.as_slice()).context(
+                error::ConvertColumnDefaultConstraintSnafu {
+                    column: &column_def.name,
+                },
+            )?,
+        )
+    };
 
-        ColumnSchema::new(&self.name, data_type.into(), self.is_nullable)
-            .with_default_constraint(constraint)
-            .context(error::InvalidColumnDefaultConstraintSnafu { column: &self.name })
-    }
+    ColumnSchema::new(&column_def.name, data_type.into(), column_def.is_nullable)
+        .with_default_constraint(constraint)
+        .context(error::InvalidColumnDefaultConstraintSnafu {
+            column: &column_def.name,
+        })
 }

src/api/src/v1/meta.rs

@@ -1,209 +0,0 @@
-// Copyright 2022 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.
-
-tonic::include_proto!("greptime.v1.meta");
-
-use std::collections::HashMap;
-use std::hash::{Hash, Hasher};
-
-pub const PROTOCOL_VERSION: u64 = 1;
-
-#[derive(Default)]
-pub struct PeerDict {
-    peers: HashMap<Peer, usize>,
-    index: usize,
-}
-
-impl PeerDict {
-    pub fn get_or_insert(&mut self, peer: Peer) -> usize {
-        let index = self.peers.entry(peer).or_insert_with(|| {
-            let v = self.index;
-            self.index += 1;
-            v
-        });
-
-        *index
-    }
-
-    pub fn into_peers(self) -> Vec<Peer> {
-        let mut array = vec![Peer::default(); self.index];
-        for (p, i) in self.peers {
-            array[i] = p;
-        }
-        array
-    }
-}
-
-#[allow(clippy::derive_hash_xor_eq)]
-impl Hash for Peer {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        self.id.hash(state);
-        self.addr.hash(state);
-    }
-}
-
-impl Eq for Peer {}
-
-impl RequestHeader {
-    #[inline]
-    pub fn new((cluster_id, member_id): (u64, u64)) -> Self {
-        Self {
-            protocol_version: PROTOCOL_VERSION,
-            cluster_id,
-            member_id,
-        }
-    }
-}
-
-impl ResponseHeader {
-    #[inline]
-    pub fn success(cluster_id: u64) -> Self {
-        Self {
-            protocol_version: PROTOCOL_VERSION,
-            cluster_id,
-            ..Default::default()
-        }
-    }
-
-    #[inline]
-    pub fn failed(cluster_id: u64, error: Error) -> Self {
-        Self {
-            protocol_version: PROTOCOL_VERSION,
-            cluster_id,
-            error: Some(error),
-        }
-    }
-
-    #[inline]
-    pub fn is_not_leader(&self) -> bool {
-        if let Some(error) = &self.error {
-            if error.code == ErrorCode::NotLeader as i32 {
-                return true;
-            }
-        }
-        false
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum ErrorCode {
-    NoActiveDatanodes = 1,
-    NotLeader = 2,
-}
-
-impl Error {
-    #[inline]
-    pub fn no_active_datanodes() -> Self {
-        Self {
-            code: ErrorCode::NoActiveDatanodes as i32,
-            err_msg: "No active datanodes".to_string(),
-        }
-    }
-
-    #[inline]
-    pub fn is_not_leader() -> Self {
-        Self {
-            code: ErrorCode::NotLeader as i32,
-            err_msg: "Current server is not leader".to_string(),
-        }
-    }
-}
-
-impl HeartbeatResponse {
-    #[inline]
-    pub fn is_not_leader(&self) -> bool {
-        if let Some(header) = &self.header {
-            return header.is_not_leader();
-        }
-        false
-    }
-}
-
-macro_rules! gen_set_header {
-    ($req: ty) => {
-        impl $req {
-            #[inline]
-            pub fn set_header(&mut self, (cluster_id, member_id): (u64, u64)) {
-                self.header = Some(RequestHeader::new((cluster_id, member_id)));
-            }
-        }
-    };
-}
-
-gen_set_header!(HeartbeatRequest);
-gen_set_header!(RouteRequest);
-gen_set_header!(CreateRequest);
-gen_set_header!(RangeRequest);
-gen_set_header!(DeleteRequest);
-gen_set_header!(PutRequest);
-gen_set_header!(BatchPutRequest);
-gen_set_header!(CompareAndPutRequest);
-gen_set_header!(DeleteRangeRequest);
-gen_set_header!(MoveValueRequest);
-
-#[cfg(test)]
-mod tests {
-    use std::vec;
-
-    use super::*;
-
-    #[test]
-    fn test_peer_dict() {
-        let mut dict = PeerDict::default();
-
-        dict.get_or_insert(Peer {
-            id: 1,
-            addr: "111".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 2,
-            addr: "222".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 1,
-            addr: "111".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 1,
-            addr: "111".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 1,
-            addr: "111".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 1,
-            addr: "111".to_string(),
-        });
-        dict.get_or_insert(Peer {
-            id: 2,
-            addr: "222".to_string(),
-        });
-
-        assert_eq!(2, dict.index);
-        assert_eq!(
-            vec![
-                Peer {
-                    id: 1,
-                    addr: "111".to_string(),
-                },
-                Peer {
-                    id: 2,
-                    addr: "222".to_string(),
-                }
-            ],
-            dict.into_peers()
-        );
-    }
-}

src/auth/Cargo.toml

@@ -0,0 +1,26 @@
+[package]
+name = "auth"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[features]
+default = []
+testing = []
+
+[dependencies]
+api.workspace = true
+async-trait.workspace = true
+common-error.workspace = true
+digest = "0.10"
+hex = { version = "0.4" }
+secrecy = { version = "0.8", features = ["serde", "alloc"] }
+sha1 = "0.10"
+snafu.workspace = true
+sql.workspace = true
+tokio.workspace = true
+
+[dev-dependencies]
+common-test-util.workspace = true

src/auth/src/common.rs

@@ -0,0 +1,147 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::sync::Arc;
+
+use digest::Digest;
+use secrecy::SecretString;
+use sha1::Sha1;
+use snafu::{ensure, OptionExt};
+
+use crate::error::{IllegalParamSnafu, InvalidConfigSnafu, Result, UserPasswordMismatchSnafu};
+use crate::user_info::DefaultUserInfo;
+use crate::user_provider::static_user_provider::{StaticUserProvider, STATIC_USER_PROVIDER};
+use crate::{UserInfoRef, UserProviderRef};
+
+pub(crate) const DEFAULT_USERNAME: &str = "greptime";
+
+/// construct a [`UserInfo`] impl with name
+/// use default username `greptime` if None is provided
+pub fn userinfo_by_name(username: Option<String>) -> UserInfoRef {
+    DefaultUserInfo::with_name(username.unwrap_or_else(|| DEFAULT_USERNAME.to_string()))
+}
+
+pub fn user_provider_from_option(opt: &String) -> Result<UserProviderRef> {
+    let (name, content) = opt.split_once(':').context(InvalidConfigSnafu {
+        value: opt.to_string(),
+        msg: "UserProviderOption must be in format `<option>:<value>`",
+    })?;
+    match name {
+        STATIC_USER_PROVIDER => {
+            let provider =
+                StaticUserProvider::try_from(content).map(|p| Arc::new(p) as UserProviderRef)?;
+            Ok(provider)
+        }
+        _ => InvalidConfigSnafu {
+            value: name.to_string(),
+            msg: "Invalid UserProviderOption",
+        }
+        .fail(),
+    }
+}
+
+type Username<'a> = &'a str;
+type HostOrIp<'a> = &'a str;
+
+#[derive(Debug, Clone)]
+pub enum Identity<'a> {
+    UserId(Username<'a>, Option<HostOrIp<'a>>),
+}
+
+pub type HashedPassword<'a> = &'a [u8];
+pub type Salt<'a> = &'a [u8];
+
+/// Authentication information sent by the client.
+pub enum Password<'a> {
+    PlainText(SecretString),
+    MysqlNativePassword(HashedPassword<'a>, Salt<'a>),
+    PgMD5(HashedPassword<'a>, Salt<'a>),
+}
+
+pub fn auth_mysql(
+    auth_data: HashedPassword,
+    salt: Salt,
+    username: &str,
+    save_pwd: &[u8],
+) -> Result<()> {
+    ensure!(
+        auth_data.len() == 20,
+        IllegalParamSnafu {
+            msg: "Illegal mysql password length"
+        }
+    );
+    // ref: https://github.com/mysql/mysql-server/blob/a246bad76b9271cb4333634e954040a970222e0a/sql/auth/password.cc#L62
+    let hash_stage_2 = double_sha1(save_pwd);
+    let tmp = sha1_two(salt, &hash_stage_2);
+    // xor auth_data and tmp
+    let mut xor_result = [0u8; 20];
+    for i in 0..20 {
+        xor_result[i] = auth_data[i] ^ tmp[i];
+    }
+    let candidate_stage_2 = sha1_one(&xor_result);
+    if candidate_stage_2 == hash_stage_2 {
+        Ok(())
+    } else {
+        UserPasswordMismatchSnafu {
+            username: username.to_string(),
+        }
+        .fail()
+    }
+}
+
+fn sha1_two(input_1: &[u8], input_2: &[u8]) -> Vec<u8> {
+    let mut hasher = Sha1::new();
+    hasher.update(input_1);
+    hasher.update(input_2);
+    hasher.finalize().to_vec()
+}
+
+fn sha1_one(data: &[u8]) -> Vec<u8> {
+    let mut hasher = Sha1::new();
+    hasher.update(data);
+    hasher.finalize().to_vec()
+}
+
+fn double_sha1(data: &[u8]) -> Vec<u8> {
+    sha1_one(&sha1_one(data))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_sha() {
+        let sha_1_answer: Vec<u8> = vec![
+            124, 74, 141, 9, 202, 55, 98, 175, 97, 229, 149, 32, 148, 61, 194, 100, 148, 248, 148,
+            27,
+        ];
+        let sha_1 = sha1_one("123456".as_bytes());
+        assert_eq!(sha_1, sha_1_answer);
+
+        let double_sha1_answer: Vec<u8> = vec![
+            107, 180, 131, 126, 183, 67, 41, 16, 94, 228, 86, 141, 218, 125, 198, 126, 210, 202,
+            42, 217,
+        ];
+        let double_sha1 = double_sha1("123456".as_bytes());
+        assert_eq!(double_sha1, double_sha1_answer);
+
+        let sha1_2_answer: Vec<u8> = vec![
+            132, 115, 215, 211, 99, 186, 164, 206, 168, 152, 217, 192, 117, 47, 240, 252, 142, 244,
+            37, 204,
+        ];
+        let sha1_2 = sha1_two("123456".as_bytes(), "654321".as_bytes());
+        assert_eq!(sha1_2, sha1_2_answer);
+    }
+}

src/auth/src/error.rs

@@ -0,0 +1,90 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use common_error::ext::{BoxedError, ErrorExt};
+use common_error::status_code::StatusCode;
+use snafu::{Location, Snafu};
+
+#[derive(Debug, Snafu)]
+#[snafu(visibility(pub))]
+pub enum Error {
+    #[snafu(display("Invalid config value: {}, {}", value, msg))]
+    InvalidConfig { value: String, msg: String },
+
+    #[snafu(display("Illegal param: {}", msg))]
+    IllegalParam { msg: String },
+
+    #[snafu(display("Internal state error: {}", msg))]
+    InternalState { msg: String },
+
+    #[snafu(display("IO error, source: {}", source))]
+    Io {
+        source: std::io::Error,
+        location: Location,
+    },
+
+    #[snafu(display("Auth failed, source: {}", source))]
+    AuthBackend {
+        location: Location,
+        source: BoxedError,
+    },
+
+    #[snafu(display("User not found, username: {}", username))]
+    UserNotFound { username: String },
+
+    #[snafu(display("Unsupported password type: {}", password_type))]
+    UnsupportedPasswordType { password_type: String },
+
+    #[snafu(display("Username and password does not match, username: {}", username))]
+    UserPasswordMismatch { username: String },
+
+    #[snafu(display(
+        "Access denied for user '{}' to database '{}-{}'",
+        username,
+        catalog,
+        schema
+    ))]
+    AccessDenied {
+        catalog: String,
+        schema: String,
+        username: String,
+    },
+
+    #[snafu(display("User is not authorized to perform this action"))]
+    PermissionDenied { location: Location },
+}
+
+impl ErrorExt for Error {
+    fn status_code(&self) -> StatusCode {
+        match self {
+            Error::InvalidConfig { .. } => StatusCode::InvalidArguments,
+            Error::IllegalParam { .. } => StatusCode::InvalidArguments,
+            Error::InternalState { .. } => StatusCode::Unexpected,
+            Error::Io { .. } => StatusCode::Internal,
+            Error::AuthBackend { .. } => StatusCode::Internal,
+
+            Error::UserNotFound { .. } => StatusCode::UserNotFound,
+            Error::UnsupportedPasswordType { .. } => StatusCode::UnsupportedPasswordType,
+            Error::UserPasswordMismatch { .. } => StatusCode::UserPasswordMismatch,
+            Error::AccessDenied { .. } => StatusCode::AccessDenied,
+            Error::PermissionDenied { .. } => StatusCode::PermissionDenied,
+        }
+    }
+
+    fn as_any(&self) -> &dyn std::any::Any {
+        self
+    }
+}
+
+pub type Result<T> = std::result::Result<T, Error>;

src/auth/src/lib.rs

@@ -0,0 +1,34 @@
+// 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.
+
+mod common;
+pub mod error;
+mod permission;
+mod user_info;
+mod user_provider;
+
+#[cfg(feature = "testing")]
+pub mod tests;
+
+pub use common::{
+    auth_mysql, user_provider_from_option, userinfo_by_name, HashedPassword, Identity, Password,
+};
+pub use permission::{PermissionChecker, PermissionReq, PermissionResp};
+pub use user_info::UserInfo;
+pub use user_provider::UserProvider;
+
+/// pub type alias
+pub type UserInfoRef = std::sync::Arc<dyn UserInfo>;
+pub type UserProviderRef = std::sync::Arc<dyn UserProvider>;
+pub type PermissionCheckerRef = std::sync::Arc<dyn PermissionChecker>;

src/auth/src/permission.rs

@@ -0,0 +1,64 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::fmt::Debug;
+
+use api::v1::greptime_request::Request;
+use sql::statements::statement::Statement;
+
+use crate::error::{PermissionDeniedSnafu, Result};
+use crate::{PermissionCheckerRef, UserInfoRef};
+
+#[derive(Debug, Clone)]
+pub enum PermissionReq<'a> {
+    GrpcRequest(&'a Request),
+    SqlStatement(&'a Statement),
+    PromQuery,
+    Opentsdb,
+    LineProtocol,
+    PromStoreWrite,
+    PromStoreRead,
+    Otlp,
+}
+
+#[derive(Debug)]
+pub enum PermissionResp {
+    Allow,
+    Reject,
+}
+
+pub trait PermissionChecker: Send + Sync {
+    fn check_permission(
+        &self,
+        user_info: Option<UserInfoRef>,
+        req: PermissionReq,
+    ) -> Result<PermissionResp>;
+}
+
+impl PermissionChecker for Option<&PermissionCheckerRef> {
+    fn check_permission(
+        &self,
+        user_info: Option<UserInfoRef>,
+        req: PermissionReq,
+    ) -> Result<PermissionResp> {
+        match self {
+            Some(checker) => match checker.check_permission(user_info, req) {
+                Ok(PermissionResp::Reject) => PermissionDeniedSnafu.fail(),
+                Ok(PermissionResp::Allow) => Ok(PermissionResp::Allow),
+                Err(e) => Err(e),
+            },
+            None => Ok(PermissionResp::Allow),
+        }
+    }
+}

src/auth/src/tests.rs

@@ -0,0 +1,193 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+use secrecy::ExposeSecret;
+
+use crate::error::{
+    AccessDeniedSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,
+    UserPasswordMismatchSnafu,
+};
+use crate::user_info::DefaultUserInfo;
+use crate::{auth_mysql, Identity, Password, UserInfoRef, UserProvider};
+
+pub struct DatabaseAuthInfo<'a> {
+    pub catalog: &'a str,
+    pub schema: &'a str,
+    pub username: &'a str,
+}
+
+pub struct MockUserProvider {
+    pub catalog: String,
+    pub schema: String,
+    pub username: String,
+}
+
+impl Default for MockUserProvider {
+    fn default() -> Self {
+        MockUserProvider {
+            catalog: "greptime".to_owned(),
+            schema: "public".to_owned(),
+            username: "greptime".to_owned(),
+        }
+    }
+}
+
+impl MockUserProvider {
+    pub fn set_authorization_info(&mut self, info: DatabaseAuthInfo) {
+        self.catalog = info.catalog.to_owned();
+        self.schema = info.schema.to_owned();
+        self.username = info.username.to_owned();
+    }
+}
+
+#[async_trait::async_trait]
+impl UserProvider for MockUserProvider {
+    fn name(&self) -> &str {
+        "mock_user_provider"
+    }
+
+    async fn authenticate(&self, id: Identity<'_>, password: Password<'_>) -> Result<UserInfoRef> {
+        match id {
+            Identity::UserId(username, _host) => match password {
+                Password::PlainText(password) => {
+                    if username == "greptime" {
+                        if password.expose_secret() == "greptime" {
+                            Ok(DefaultUserInfo::with_name("greptime"))
+                        } else {
+                            UserPasswordMismatchSnafu {
+                                username: username.to_string(),
+                            }
+                            .fail()
+                        }
+                    } else {
+                        UserNotFoundSnafu {
+                            username: username.to_string(),
+                        }
+                        .fail()
+                    }
+                }
+                Password::MysqlNativePassword(auth_data, salt) => {
+                    auth_mysql(auth_data, salt, username, "greptime".as_bytes())
+                        .map(|_| DefaultUserInfo::with_name(username))
+                }
+                _ => UnsupportedPasswordTypeSnafu {
+                    password_type: "mysql_native_password",
+                }
+                .fail(),
+            },
+        }
+    }
+
+    async fn authorize(&self, catalog: &str, schema: &str, user_info: &UserInfoRef) -> Result<()> {
+        if catalog == self.catalog && schema == self.schema && user_info.username() == self.username
+        {
+            Ok(())
+        } else {
+            AccessDeniedSnafu {
+                catalog: catalog.to_string(),
+                schema: schema.to_string(),
+                username: user_info.username().to_string(),
+            }
+            .fail()
+        }
+    }
+}
+
+#[tokio::test]
+async fn test_auth_by_plain_text() {
+    use crate::error;
+
+    let user_provider = MockUserProvider::default();
+    assert_eq!("mock_user_provider", user_provider.name());
+
+    // auth success
+    let auth_result = user_provider
+        .authenticate(
+            Identity::UserId("greptime", None),
+            Password::PlainText("greptime".to_string().into()),
+        )
+        .await
+        .unwrap();
+    assert_eq!("greptime", auth_result.username());
+
+    // auth failed, unsupported password type
+    let auth_result = user_provider
+        .authenticate(
+            Identity::UserId("greptime", None),
+            Password::PgMD5(b"hashed_value", b"salt"),
+        )
+        .await;
+    assert!(auth_result.is_err());
+    assert!(matches!(
+        auth_result.err().unwrap(),
+        error::Error::UnsupportedPasswordType { .. }
+    ));
+
+    // auth failed, err: user not exist.
+    let auth_result = user_provider
+        .authenticate(
+            Identity::UserId("not_exist_username", None),
+            Password::PlainText("greptime".to_string().into()),
+        )
+        .await;
+    assert!(auth_result.is_err());
+    assert!(matches!(
+        auth_result.err().unwrap(),
+        error::Error::UserNotFound { .. }
+    ));
+
+    // auth failed, err: wrong password
+    let auth_result = user_provider
+        .authenticate(
+            Identity::UserId("greptime", None),
+            Password::PlainText("wrong_password".to_string().into()),
+        )
+        .await;
+    assert!(auth_result.is_err());
+    assert!(matches!(
+        auth_result.err().unwrap(),
+        error::Error::UserPasswordMismatch { .. }
+    ))
+}
+
+#[tokio::test]
+async fn test_schema_validate() {
+    let mut validator = MockUserProvider::default();
+    validator.set_authorization_info(DatabaseAuthInfo {
+        catalog: "greptime",
+        schema: "public",
+        username: "test_user",
+    });
+
+    let right_user = DefaultUserInfo::with_name("test_user");
+    let wrong_user = DefaultUserInfo::with_name("greptime");
+
+    // check catalog
+    let re = validator
+        .authorize("greptime_wrong", "public", &right_user)
+        .await;
+    assert!(re.is_err());
+    // check schema
+    let re = validator
+        .authorize("greptime", "public_wrong", &right_user)
+        .await;
+    assert!(re.is_err());
+    // check username
+    let re = validator.authorize("greptime", "public", &wrong_user).await;
+    assert!(re.is_err());
+    // check ok
+    validator
+        .authorize("greptime", "public", &right_user)
+        .await
+        .unwrap();
+}