chore: use explicit geo_json version

.cargo/config.toml

@@ -1,15 +0,0 @@
-[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",
-]

.config/nextest.toml

@@ -1,3 +0,0 @@
-[profile.default]
-slow-timeout = { period = "60s", terminate-after = 3, grace-period = "30s" }
-retries = { backoff = "exponential", count = 3, delay = "10s", jitter = true }

.dockerignore

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

.env.example

@@ -1,21 +0,0 @@
-# Settings for s3 test
-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

@@ -1,88 +0,0 @@
----
-name: Bug report
-description: Is something not working? Help us fix it!
-labels: [ "bug" ]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Take some time to fill out this bug report. Thank you!
-
-  - type: dropdown
-    id: type
-    attributes:
-      label: What type of bug is this?
-      multiple: true
-      options:
-        - Configuration
-        - Crash
-        - Data corruption
-        - Incorrect result
-        - Locking issue
-        - Performance issue
-        - Unexpected error
-        - Other
-    validations:
-      required: true
-
-  - type: dropdown
-    id: subsystem
-    attributes:
-      label: What subsystems are affected?
-      description: You can pick multiple subsystems.
-      multiple: true
-      options:
-        - Standalone mode
-        - Frontend
-        - Datanode
-        - Meta
-        - Other
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: Minimal reproduce step
-      description: |
-        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.
-    validations:
-      required: true
-
-  - type: textarea
-    id: expected-manner
-    attributes:
-      label: What did you expect to see?
-    validations:
-      required: true
-
-  - type: textarea
-    id: actual-manner
-    attributes:
-      label: What did you see instead?
-    validations:
-      required: true
-
-  - type: input
-    id: os
-    attributes:
-      label: What operating system did you use?
-      description: |
-        Please provide OS, version, and architecture. For example:
-        Windows 10 x64, Ubuntu 21.04 x64, Mac OS X 10.5 ARM, Rasperry
-        Pi i386, etc.
-      placeholder: "Ubuntu 21.04 x64"
-    validations:
-      required: true
-
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output and stack trace
-      description: |
-        Please copy and paste any relevant log output or a stack
-        trace. This will be automatically formatted into code, so no
-        need for backticks.
-      render: bash

.github/ISSUE_TEMPLATE/config.yml

@@ -1,8 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: Greptime Community Slack
-    url: https://greptime.com/slack
-    about: Get free help from the Greptime community
-  - name: Greptime Community Discussion
-    url: https://github.com/greptimeTeam/greptimedb/discussions
-    about: Get free help from the Greptime community

.github/ISSUE_TEMPLATE/enhancement.yml

@@ -1,39 +0,0 @@
----
-name: Enhancement
-description: Suggest an enhancement to existing functionality
-labels: [ "enhancement" ]
-body:
-  - type: dropdown
-    id: type
-    attributes:
-      label: What type of enhancement is this?
-      multiple: true
-      options:
-        - API improvement
-        - Configuration
-        - Performance
-        - Refactor
-        - Tech debt reduction
-        - User experience
-        - Other
-    validations:
-      required: true
-
-  - type: textarea
-    id: what
-    attributes:
-      label: What does the enhancement do?
-      description: |
-        Give a high-level overview of how you
-        suggest improving an existing feature or functionality.
-    validations:
-     required: true
-
-  - type: textarea
-    id: implementation
-    attributes:
-      label: Implementation challenges
-      description: |
-        Share any ideas of how to implement the enhancement.
-    validations:
-      required: false

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,42 +0,0 @@
----
-name: Feature request
-description: Suggest a new feature for GreptimeDB
-labels: [ "feature request" ]
-body:
-  - type: markdown
-    id: info
-    attributes:
-      value: |
-        Only use this template to suggest a new feature that doesn't already exist in GreptimeDB.
-        For enhancements to existing features, use the "Enhancement" issue template. For bugs,
-        use the bug report template.
-
-  - type: textarea
-    id: what
-    attributes:
-      label: What problem does the new feature solve?
-      description: |
-        Describe the problem and why it is important to solve. Did you consider alternative
-        solutions, perhaps outside the database? Why is it better to add the feature to
-        GreptimeDB?
-    validations:
-      required: true
-
-  - type: textarea
-    id: how
-    attributes:
-      label: What does the feature do?
-      description: |
-        Give a high-level overview of what the feature does and how it would work.
-    validations:
-     required: true
-
-  - type: textarea
-    id: implementation
-    attributes:
-      label: Implementation challenges
-      description: |
-        If you have ideas of how to implement the feature, and any particularly
-        challenging issues to overcome, then provide them here.
-    validations:
-      required: false

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

@@ -1,76 +0,0 @@
-name: Build and push dev-builder images
-description: Build and push dev-builder images 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
-  version:
-    description: Version of the dev-builder
-    required: false
-    default: latest
-  build-dev-builder-ubuntu:
-    description: Build dev-builder-ubuntu image
-    required: false
-    default: 'true'
-  build-dev-builder-centos:
-    description: Build dev-builder-centos image
-    required: false
-    default: 'true'
-  build-dev-builder-android:
-    description: Build dev-builder-android image
-    required: false
-    default: 'true'
-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 dev-builder-ubuntu image
-      shell: bash
-      if: ${{ inputs.build-dev-builder-ubuntu == 'true' }}
-      run: |
-        make dev-builder \
-          BASE_IMAGE=ubuntu \
-          BUILDX_MULTI_PLATFORM_BUILD=true \
-          IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
-          IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          IMAGE_TAG=${{ inputs.version }}
-
-    - name: Build and push dev-builder-centos image
-      shell: bash
-      if: ${{ inputs.build-dev-builder-centos == 'true' }}
-      run: |
-        make dev-builder \
-          BASE_IMAGE=centos \
-          BUILDX_MULTI_PLATFORM_BUILD=true \
-          IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
-          IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          IMAGE_TAG=${{ inputs.version }}
-
-    - name: Build and push dev-builder-android image # Only build image for amd64 platform.
-      shell: bash
-      if: ${{ inputs.build-dev-builder-android == 'true' }}
-      run: |
-        make dev-builder \
-          BASE_IMAGE=android \
-          IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
-          IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
-          IMAGE_TAG=${{ inputs.version }} && \
-        
-        docker push ${{ inputs.dockerhub-image-registry }}/${{ inputs.dockerhub-image-namespace }}/dev-builder-android:${{ inputs.version }}

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

@@ -1,63 +0,0 @@
-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
-  working-dir:
-    description: Working directory to build the artifacts
-    required: false
-    default: .
-  build-android-artifacts:
-    description: Build android artifacts
-    required: false
-    default: 'false'
-runs:
-  using: composite
-  steps:
-    - name: Build greptime binary
-      shell: bash
-      if: ${{ inputs.build-android-artifacts == 'false' }}
-      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
-      if: ${{ inputs.build-android-artifacts == 'false' }}
-      with:
-        artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: ./target/${{ inputs.cargo-profile }}/greptime
-        version: ${{ inputs.version }}
-        working-dir: ${{ inputs.working-dir }}
-
-    # TODO(zyy17): We can remove build-android-artifacts flag in the future.
-    - name: Build greptime binary
-      shell: bash
-      if: ${{ inputs.build-android-artifacts == 'true' }}
-      run: |
-        cd ${{ inputs.working-dir }} && make strip-android-bin
-
-    - name: Upload android artifacts
-      uses: ./.github/actions/upload-artifacts
-      if: ${{ inputs.build-android-artifacts == 'true' }}
-      with:
-        artifacts-dir: ${{ inputs.artifacts-dir }}
-        target-file: ./target/aarch64-linux-android/release/greptime
-        version: ${{ inputs.version }}
-        working-dir: ${{ inputs.working-dir }}

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

@@ -1,104 +0,0 @@
-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

@@ -1,62 +0,0 @@
-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

@@ -1,88 +0,0 @@
-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
-  dev-mode:
-    description: Enable dev mode, only build standard greptime
-    required: false
-    default: 'false'
-  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 }}
-        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 }}
-        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 }}
-        working-dir: ${{ inputs.working-dir }}
-
-    - name: Build greptime on android base image
-      uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build android base image on amd64.
-      with:
-        base-image: android
-        artifacts-dir: greptime-android-arm64-${{ inputs.version }}
-        version: ${{ inputs.version }}
-        working-dir: ${{ inputs.working-dir }}
-        build-android-artifacts: true

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

@@ -1,89 +0,0 @@
-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
-  artifacts-dir:
-    description: Directory to store artifacts
-    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 }}

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

@@ -1,80 +0,0 @@
-name: Build Windows artifacts
-description: Build Windows 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
-  artifacts-dir:
-    description: Directory to store artifacts
-    required: true
-runs:
-  using: composite
-  steps:
-    - uses: arduino/setup-protoc@v1
-
-    - name: Install rust toolchain
-      uses: dtolnay/rust-toolchain@master
-      with:
-        toolchain: ${{ inputs.rust-toolchain }}
-        targets: ${{ inputs.arch }}
-        components: llvm-tools-preview
-
-    - name: Rust Cache
-      uses: Swatinem/rust-cache@v2
-
-    - name: Install Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.10'
-
-    - name: Install PyArrow Package
-      shell: pwsh
-      run: pip install pyarrow
-
-    - name: Install WSL distribution
-      uses: Vampire/setup-wsl@v2
-      with:
-        distribution: Ubuntu-22.04
-
-    - 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: pwsh
-      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: ${{ runner.temp }}/greptime-*.log
-        retention-days: 3
-
-    - name: Build greptime binary
-      shell: pwsh
-      run: cargo build --profile ${{ inputs.cargo-profile }} --features ${{ inputs.features }} --target ${{ inputs.arch }}
-
-    - 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 }}

.github/actions/deploy-greptimedb/action.yml

@@ -1,31 +0,0 @@
-name: Deploy GreptimeDB cluster
-description: Deploy GreptimeDB cluster on Kubernetes
-inputs:
-  aws-ci-test-bucket:
-    description: 'AWS S3 bucket name for testing'
-    required: true
-  aws-region:
-    description: 'AWS region for testing'
-    required: true
-  data-root:
-    description: 'Data root for testing'
-    required: true
-  aws-access-key-id:
-    description: 'AWS access key id for testing'
-    required: true
-  aws-secret-access-key:
-    description: 'AWS secret access key for testing'
-    required: true
-runs:
-  using: composite
-  steps:
-    - name: Deploy GreptimeDB by Helm
-      shell: bash
-      env:
-        DATA_ROOT: ${{ inputs.data-root }}
-        AWS_CI_TEST_BUCKET: ${{ inputs.aws-ci-test-bucket }}
-        AWS_REGION: ${{ inputs.aws-region }}
-        AWS_ACCESS_KEY_ID: ${{ inputs.aws-access-key-id }}
-        AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-secret-access-key }}
-      run: |
-        ./.github/scripts/deploy-greptimedb.sh

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

@@ -1,53 +0,0 @@
-name: Publish GitHub release
-description: Publish GitHub release
-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
-          echo "omitBody=true" >> $GITHUB_ENV
-        else
-          echo "prerelease=true" >> $GITHUB_ENV
-          echo "makeLatest=false" >> $GITHUB_ENV
-          echo "generateReleaseNotes=true" >> $GITHUB_ENV
-          echo "omitBody=false" >> $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 }}
-        omitBody: ${{ env.omitBody }} # omitBody is true when the release is a official release.
-        allowUpdates: true
-        artifacts: |
-          **/greptime-*/*

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

@@ -1,138 +0,0 @@
-name: Release CN artifacts
-description: Release artifacts to CN region
-inputs:
-  src-image-registry:
-    description: The source image registry to store the images
-    required: true
-    default: docker.io
-  src-image-namespace:
-    description: The namespace of the source image registry to store the images
-    required: true
-    default: greptime
-  src-image-name:
-    description: The name of the source image
-    required: false
-    default: greptimedb
-  dst-image-registry:
-    description: The destination image registry to store the images
-    required: true
-  dst-image-namespace:
-    description: The namespace of the destination image registry to store the images
-    required: true
-    default: greptime
-  dst-image-registry-username:
-    description: The username to login to the image registry
-    required: true
-  dst-image-registry-password:
-    description: The password to login to the image registry
-    required: true
-  version:
-    description: Version of the artifact
-    required: true
-  dev-mode:
-    description: Enable dev mode, only push standard greptime
-    required: false
-    default: 'false'
-  push-latest-tag:
-    description: Whether to push the latest tag of the image
-    required: false
-    default: 'true'
-  aws-cn-s3-bucket:
-    description: S3 bucket to store released artifacts in CN region
-    required: true
-  aws-cn-access-key-id:
-    description: AWS access key id in CN region
-    required: true
-  aws-cn-secret-access-key:
-    description: AWS secret access key in CN region
-    required: true
-  aws-cn-region:
-    description: AWS region in CN
-    required: true
-  upload-to-s3:
-    description: Upload to S3
-    required: false
-    default: 'true'
-  artifacts-dir:
-    description: Directory to store artifacts
-    required: false
-    default: 'artifacts'
-  update-version-info:
-    description: Update the version info in 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: "30" # minutes
-runs:
-  using: composite
-  steps:
-    - name: Download artifacts
-      uses: actions/download-artifact@v3
-      with:
-        path: ${{ inputs.artifacts-dir }}
-
-    - name: Release artifacts to cn region
-      uses: nick-invision/retry@v2
-      if: ${{ inputs.upload-to-s3 == 'true' }}
-      env:
-        AWS_ACCESS_KEY_ID: ${{ inputs.aws-cn-access-key-id }}
-        AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-cn-secret-access-key }}
-        AWS_DEFAULT_REGION: ${{ inputs.aws-cn-region }}
-        UPDATE_VERSION_INFO: ${{ inputs.update-version-info }}
-      with:
-        max_attempts: ${{ inputs.upload-max-retry-times }}
-        timeout_minutes: ${{ inputs.upload-retry-timeout }}
-        command: |
-          ./.github/scripts/upload-artifacts-to-s3.sh \
-            ${{ inputs.artifacts-dir }} \
-            ${{ inputs.version }} \
-            ${{ inputs.aws-cn-s3-bucket }}
-
-    - name: Push greptimedb image from Dockerhub to ACR
-      shell: bash
-      env:
-        DST_REGISTRY_USERNAME: ${{ inputs.dst-image-registry-username }}
-        DST_REGISTRY_PASSWORD: ${{ inputs.dst-image-registry-password }}
-      run: |
-        ./.github/scripts/copy-image.sh \
-         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}:${{ inputs.version }} \
-         ${{ inputs.dst-image-registry }}/${{ inputs.dst-image-namespace }}
-
-    - name: Push latest greptimedb image from Dockerhub to ACR
-      shell: bash
-      if: ${{ inputs.push-latest-tag == 'true' }}
-      env:
-        DST_REGISTRY_USERNAME: ${{ inputs.dst-image-registry-username }}
-        DST_REGISTRY_PASSWORD: ${{ inputs.dst-image-registry-password }}
-      run: |
-        ./.github/scripts/copy-image.sh \
-         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}:latest \
-         ${{ inputs.dst-image-registry }}/${{ inputs.dst-image-namespace }}
-
-    - name: Push greptimedb-centos image from DockerHub to ACR
-      shell: bash
-      if: ${{ inputs.dev-mode == 'false' }}
-      env:
-        DST_REGISTRY_USERNAME: ${{ inputs.dst-image-registry-username }}
-        DST_REGISTRY_PASSWORD: ${{ inputs.dst-image-registry-password }}
-      run: |
-        ./.github/scripts/copy-image.sh \
-         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}-centos:latest \
-         ${{ inputs.dst-image-registry }}/${{ inputs.dst-image-namespace }}
-
-    - name: Push greptimedb-centos image from DockerHub to ACR
-      shell: bash
-      if: ${{ inputs.dev-mode == 'false' && inputs.push-latest-tag == 'true' }}
-      env:
-        DST_REGISTRY_USERNAME: ${{ inputs.dst-image-registry-username }}
-        DST_REGISTRY_PASSWORD: ${{ inputs.dst-image-registry-password }}
-      run: |
-        ./.github/scripts/copy-image.sh \
-         ${{ inputs.src-image-registry }}/${{ inputs.src-image-namespace }}/${{ inputs.src-image-name }}-centos:latest \
-         ${{ inputs.dst-image-registry }}/${{ inputs.dst-image-namespace }}

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

@@ -1,59 +0,0 @@
-name: Run sqlness test
-description: Run sqlness test on GreptimeDB
-
-inputs:
-  aws-ci-test-bucket:
-    description: 'AWS S3 bucket name for testing'
-    required: true
-  aws-region:
-    description: 'AWS region for testing'
-    required: true
-  data-root:
-    description: 'Data root for testing'
-    required: true
-  aws-access-key-id:
-    description: 'AWS access key id for testing'
-    required: true
-  aws-secret-access-key:
-    description: 'AWS secret access key for testing'
-    required: true
-
-runs:
-  using: composite
-  steps:
-    - name: Deploy GreptimeDB cluster by Helm
-      uses: ./.github/actions/deploy-greptimedb
-      with:
-        data-root: ${{ inputs.data-root }}
-        aws-ci-test-bucket: ${{ inputs.aws-ci-test-bucket }}
-        aws-region: ${{ inputs.aws-region }}
-        aws-access-key-id: ${{ inputs.aws-access-key-id }}
-        aws-secret-access-key: ${{ inputs.aws-secret-access-key }}
-
-    # TODO(zyy17): The following tests will be replaced by the real sqlness test.
-    - name: Run tests on greptimedb cluster
-      shell: bash
-      run: |
-        mysql -h 127.0.0.1 -P 14002 -e "CREATE TABLE IF NOT EXISTS system_metrics (host VARCHAR(255), idc VARCHAR(255), cpu_util DOUBLE, memory_util DOUBLE, disk_util DOUBLE, ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY(host, idc), TIME INDEX(ts));" && \
-        mysql -h 127.0.0.1 -P 14002 -e "SHOW TABLES;"
-
-    - name: Run tests on greptimedb cluster that uses S3
-      shell: bash
-      run: |
-        mysql -h 127.0.0.1 -P 24002 -e "CREATE TABLE IF NOT EXISTS system_metrics (host VARCHAR(255), idc VARCHAR(255), cpu_util DOUBLE, memory_util DOUBLE, disk_util DOUBLE, ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY(host, idc), TIME INDEX(ts));" && \
-        mysql -h 127.0.0.1 -P 24002 -e "SHOW TABLES;"
-
-    - name: Run tests on standalone greptimedb
-      shell: bash
-      run: |
-        mysql -h 127.0.0.1 -P 34002 -e "CREATE TABLE IF NOT EXISTS system_metrics (host VARCHAR(255), idc VARCHAR(255), cpu_util DOUBLE, memory_util DOUBLE, disk_util DOUBLE, ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY(host, idc), TIME INDEX(ts));" && \
-        mysql -h 127.0.0.1 -P 34002 -e "SHOW TABLES;"
-
-    - name: Clean S3 data
-      shell: bash
-      env:
-        AWS_DEFAULT_REGION: ${{ inputs.aws-region }}
-        AWS_ACCESS_KEY_ID: ${{ inputs.aws-access-key-id }}
-        AWS_SECRET_ACCESS_KEY: ${{ inputs.aws-secret-access-key }}
-      run: |
-        aws s3 rm s3://${{ inputs.aws-ci-test-bucket }}/${{ inputs.data-root }} --recursive

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

@@ -1,67 +0,0 @@
-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

@@ -1,41 +0,0 @@
-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

@@ -1,63 +0,0 @@
-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
-  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 }}
-
-    - name: Calculate checksum
-      if: runner.os != 'Windows'
-      working-directory: ${{ inputs.working-dir }}
-      shell: bash
-      run: |
-        echo $(shasum -a 256 ${{ inputs.artifacts-dir }}.tar.gz | cut -f1 -d' ') > ${{ inputs.artifacts-dir }}.sha256sum
-
-    - name: Calculate checksum on Windows
-      if: runner.os == 'Windows'
-      working-directory: ${{ inputs.working-dir }}
-      shell: pwsh
-      run: Get-FileHash ${{ inputs.artifacts-dir }}.tar.gz -Algorithm SHA256 | select -ExpandProperty Hash > ${{ 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

.github/codecov.yml

@@ -1,12 +1,10 @@
 # codecov config
 coverage:
   status:
+    patch: off # disable patch status
     project:
       default:
+        enable: yes
         threshold: 1%
-    patch: off
 ignore:
   - "**/error*.rs" # ignore all error.rs files
-  - "tests/runner/*.rs" # ignore integration test runner
-comment:                  # this is a top-level key
-  layout: "diff"

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

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

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

@@ -1,12 +1,10 @@
 {
-    "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|doc|perf|build|ci|revert)(\\(.*\\))?:.*",
+    "ignoreLabels" : ["ignore-title"]
+  }
 }

.github/pull_request_template.md

@@ -1,19 +0,0 @@
-I hereby agree to the terms of the [GreptimeDB CLA](https://gist.github.com/xtang/6378857777706e568c1949c7578592cc)
-
-## What's changed and what's your intention?
-
-_PLEASE DO NOT LEAVE THIS EMPTY !!!_
-
-Please explain IN DETAIL what the changes are in this PR and why they are needed:
-
-- Summarize your change (**mandatory**)
-- How does this PR work? Need a brief introduction for the changed logic (optional)
-- Describe clearly one logical change and avoid lazy messages (optional)
-- Describe any limitations of the current code (optional)
-
-## Checklist
-
-- [ ]  I have written the necessary rustdoc comments.
-- [ ]  I have added the necessary unit tests and integration tests.
-
-## Refer to a related PR or issue link (optional)

.github/scripts/copy-image.sh

@@ -1,47 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-set -o pipefail
-
-SRC_IMAGE=$1
-DST_REGISTRY=$2
-SKOPEO_STABLE_IMAGE="quay.io/skopeo/stable:latest"
-
-# Check if necessary variables are set.
-function check_vars() {
-  for var in DST_REGISTRY_USERNAME DST_REGISTRY_PASSWORD DST_REGISTRY SRC_IMAGE; do
-    if [ -z "${!var}" ]; then
-      echo "$var is not set or empty."
-      echo "Usage: DST_REGISTRY_USERNAME=<your-dst-registry-username> DST_REGISTRY_PASSWORD=<your-dst-registry-password> $0 <dst-registry> <src-image>"
-      exit 1
-    fi
-  done
-}
-
-# Copies images from DockerHub to the destination registry.
-function copy_images_from_dockerhub() {
-  # Check if docker is installed.
-  if ! command -v docker &> /dev/null; then
-    echo "docker is not installed. Please install docker to continue."
-    exit 1
-  fi
-
-  # Extract the name and tag of the source image.
-  IMAGE_NAME=$(echo "$SRC_IMAGE" | sed "s/.*\///")
-
-  echo "Copying $SRC_IMAGE to $DST_REGISTRY/$IMAGE_NAME"
-
-  docker run "$SKOPEO_STABLE_IMAGE" copy -a docker://"$SRC_IMAGE" \
-    --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-    docker://"$DST_REGISTRY/$IMAGE_NAME"
-}
-
-function main() {
-  check_vars
-  copy_images_from_dockerhub
-}
-
-# Usage example:
-# DST_REGISTRY_USERNAME=123 DST_REGISTRY_PASSWORD=456 \
-#   ./copy-image.sh greptime/greptimedb:v0.4.0 greptime-registry.cn-hangzhou.cr.aliyuncs.com
-main

.github/scripts/create-version.sh

@@ -1,68 +0,0 @@
-#!/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/scripts/deploy-greptimedb.sh

@@ -1,172 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-set -o pipefail
-
-KUBERNETES_VERSION="${KUBERNETES_VERSION:-v1.24.0}"
-ENABLE_STANDALONE_MODE="${ENABLE_STANDALONE_MODE:-true}"
-DEFAULT_INSTALL_NAMESPACE=${DEFAULT_INSTALL_NAMESPACE:-default}
-GREPTIMEDB_IMAGE_TAG=${GREPTIMEDB_IMAGE_TAG:-latest}
-ETCD_CHART="oci://registry-1.docker.io/bitnamicharts/etcd"
-GREPTIME_CHART="https://greptimeteam.github.io/helm-charts/"
-
-# Ceate a cluster with 1 control-plane node and 5 workers.
-function create_kind_cluster() {
-  cat <<EOF | kind create cluster --name "${CLUSTER}" --image kindest/node:"$KUBERNETES_VERSION" --config=-
-kind: Cluster
-apiVersion: kind.x-k8s.io/v1alpha4
-nodes:
-- role: control-plane
-- role: worker
-- role: worker
-- role: worker
-- role: worker
-- role: worker
-EOF
-}
-
-# Add greptime Helm chart repo.
-function add_greptime_chart() {
-  helm repo add greptime "$GREPTIME_CHART"
-  helm repo update
-}
-
-# Deploy a etcd cluster with 3 members.
-function deploy_etcd_cluster() {
-  local namespace="$1"
-
-  helm install etcd "$ETCD_CHART" \
-    --set replicaCount=3 \
-    --set auth.rbac.create=false \
-    --set auth.rbac.token.enabled=false \
-    -n "$namespace"
-
-  # Wait for etcd cluster to be ready.
-  kubectl rollout status statefulset/etcd -n "$namespace"
-}
-
-# Deploy greptimedb-operator.
-function deploy_greptimedb_operator() {
-  # Use the latest chart and image.
-  helm install greptimedb-operator greptime/greptimedb-operator \
-    --set image.tag=latest \
-    -n "$DEFAULT_INSTALL_NAMESPACE"
-
-  # Wait for greptimedb-operator to be ready.
-  kubectl rollout status deployment/greptimedb-operator -n "$DEFAULT_INSTALL_NAMESPACE"
-}
-
-# Deploy greptimedb cluster by using local storage.
-# It will expose cluster service ports as '14000', '14001', '14002', '14003' to local access.
-function deploy_greptimedb_cluster() {
-  local cluster_name=$1
-  local install_namespace=$2
-
-  kubectl create ns "$install_namespace"
-
-  deploy_etcd_cluster "$install_namespace"
-
-  helm install "$cluster_name" greptime/greptimedb-cluster \
-    --set image.tag="$GREPTIMEDB_IMAGE_TAG" \
-    --set meta.etcdEndpoints="etcd.$install_namespace:2379" \
-    -n "$install_namespace"
-
-  # Wait for greptimedb cluster to be ready.
-  while true; do
-    PHASE=$(kubectl -n "$install_namespace" get gtc "$cluster_name" -o jsonpath='{.status.clusterPhase}')
-    if [ "$PHASE" == "Running" ]; then
-      echo "Cluster is ready"
-      break
-    else
-      echo "Cluster is not ready yet: Current phase: $PHASE"
-      sleep 5 # wait for 5 seconds before check again.
-    fi
-  done
-
-  # Expose greptimedb cluster to local access.
-  kubectl -n "$install_namespace" port-forward svc/"$cluster_name"-frontend \
-    14000:4000 \
-    14001:4001 \
-    14002:4002 \
-    14003:4003 > /tmp/connections.out &
-}
-
-# Deploy greptimedb cluster by using S3.
-# It will expose cluster service ports as '24000', '24001', '24002', '24003' to local access.
-function deploy_greptimedb_cluster_with_s3_storage() {
-  local cluster_name=$1
-  local install_namespace=$2
-
-  kubectl create ns "$install_namespace"
-
-  deploy_etcd_cluster "$install_namespace"
-
-  helm install "$cluster_name" greptime/greptimedb-cluster -n "$install_namespace" \
-    --set image.tag="$GREPTIMEDB_IMAGE_TAG" \
-    --set meta.etcdEndpoints="etcd.$install_namespace:2379" \
-    --set storage.s3.bucket="$AWS_CI_TEST_BUCKET" \
-    --set storage.s3.region="$AWS_REGION" \
-    --set storage.s3.root="$DATA_ROOT" \
-    --set storage.s3.secretName=s3-credentials \
-    --set storage.credentials.secretName=s3-credentials \
-    --set storage.credentials.secretCreation.enabled=true \
-    --set storage.credentials.secretCreation.enableEncryption=false \
-    --set storage.credentials.secretCreation.data.access-key-id="$AWS_ACCESS_KEY_ID" \
-    --set storage.credentials.secretCreation.data.secret-access-key="$AWS_SECRET_ACCESS_KEY"
-
-  # Wait for greptimedb cluster to be ready.
-  while true; do
-    PHASE=$(kubectl -n "$install_namespace" get gtc "$cluster_name" -o jsonpath='{.status.clusterPhase}')
-    if [ "$PHASE" == "Running" ]; then
-      echo "Cluster is ready"
-      break
-    else
-      echo "Cluster is not ready yet: Current phase: $PHASE"
-      sleep 5 # wait for 5 seconds before check again.
-    fi
-  done
-
-  # Expose greptimedb cluster to local access.
-  kubectl -n "$install_namespace" port-forward svc/"$cluster_name"-frontend \
-    24000:4000 \
-    24001:4001 \
-    24002:4002 \
-    24003:4003 > /tmp/connections.out &
-}
-
-# Deploy standalone greptimedb.
-# It will expose cluster service ports as '34000', '34001', '34002', '34003' to local access.
-function deploy_standalone_greptimedb() {
-  helm install greptimedb-standalone greptime/greptimedb-standalone \
-    --set image.tag="$GREPTIMEDB_IMAGE_TAG" \
-    -n "$DEFAULT_INSTALL_NAMESPACE"
-
-  # Wait for etcd cluster to be ready.
-  kubectl rollout status statefulset/greptimedb-standalone -n "$DEFAULT_INSTALL_NAMESPACE"
-
-  # Expose greptimedb to local access.
-  kubectl -n "$DEFAULT_INSTALL_NAMESPACE" port-forward svc/greptimedb-standalone \
-    34000:4000 \
-    34001:4001 \
-    34002:4002 \
-    34003:4003 > /tmp/connections.out &
-}
-
-# Entrypoint of the script.
-function main() {
-  create_kind_cluster
-  add_greptime_chart
-
-  # Deploy standalone greptimedb in the same K8s.
-  if [ "$ENABLE_STANDALONE_MODE" == "true" ]; then
-    deploy_standalone_greptimedb
-  fi
-
-  deploy_greptimedb_operator
-  deploy_greptimedb_cluster testcluster testcluster
-  deploy_greptimedb_cluster_with_s3_storage testcluster-s3 testcluster-s3
-}
-
-# Usages:
-# - Deploy greptimedb cluster: ./deploy-greptimedb.sh
-main

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

@@ -1,102 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-set -o pipefail
-
-ARTIFACTS_DIR=$1
-VERSION=$2
-AWS_S3_BUCKET=$3
-RELEASE_DIRS="releases/greptimedb"
-GREPTIMEDB_REPO="GreptimeTeam/greptimedb"
-
-# Check if necessary variables are set.
-function check_vars() {
-  for var in AWS_S3_BUCKET VERSION ARTIFACTS_DIR; do
-    if [ -z "${!var}" ]; then
-      echo "$var is not set or empty."
-      echo "Usage: $0 <artifacts-dir> <version> <aws-s3-bucket>"
-      exit 1
-    fi
-  done
-}
-
-# Uploads artifacts to AWS S3 bucket.
-function upload_artifacts() {
-  # The bucket layout will be:
-  # releases/greptimedb
-  # ├── latest-version.txt
-  # ├── latest-nightly-version.txt
-  # ├── v0.1.0
-  # │   ├── greptime-darwin-amd64-pyo3-v0.1.0.sha256sum
-  # │   └── greptime-darwin-amd64-pyo3-v0.1.0.tar.gz
-  # └── v0.2.0
-  #    ├── greptime-darwin-amd64-pyo3-v0.2.0.sha256sum
-  #    └── greptime-darwin-amd64-pyo3-v0.2.0.tar.gz
-  find "$ARTIFACTS_DIR" -type f \( -name "*.tar.gz" -o -name "*.sha256sum" \) | while IFS= read -r file; do
-    aws s3 cp \
-      "$file" "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/$VERSION/$(basename "$file")"
-  done
-}
-
-# Updates the latest version information in AWS S3 if UPDATE_VERSION_INFO is true.
-function update_version_info() {
-  if [ "$UPDATE_VERSION_INFO" == "true" ]; then
-    # If it's the officail release(like v1.0.0, v1.0.1, v1.0.2, etc.), update latest-version.txt.
-    if [[ "$VERSION" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-      echo "Updating latest-version.txt"
-      echo "$VERSION" > latest-version.txt
-      aws s3 cp \
-        latest-version.txt "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/latest-version.txt"
-    fi
-
-    # If it's the nightly release, update latest-nightly-version.txt.
-    if [[ "$VERSION" == *"nightly"* ]]; then
-      echo "Updating latest-nightly-version.txt"
-      echo "$VERSION" > latest-nightly-version.txt
-      aws s3 cp \
-        latest-nightly-version.txt "s3://$AWS_S3_BUCKET/$RELEASE_DIRS/latest-nightly-version.txt"
-    fi
-  fi
-}
-
-# Downloads artifacts from Github if DOWNLOAD_ARTIFACTS_FROM_GITHUB is true.
-function download_artifacts_from_github() {
-  if [ "$DOWNLOAD_ARTIFACTS_FROM_GITHUB" == "true" ]; then
-    # Check if jq is installed.
-    if ! command -v jq &> /dev/null; then
-      echo "jq is not installed. Please install jq to continue."
-      exit 1
-    fi
-
-    # Get the latest release API response.
-    RELEASES_API_RESPONSE=$(curl -s -H "Accept: application/vnd.github.v3+json" "https://api.github.com/repos/$GREPTIMEDB_REPO/releases/latest")
-
-    # Extract download URLs for the artifacts.
-    # Exclude source code archives which are typically named as 'greptimedb-<version>.zip' or 'greptimedb-<version>.tar.gz'.
-    ASSET_URLS=$(echo "$RELEASES_API_RESPONSE" | jq -r '.assets[] | select(.name | test("greptimedb-.*\\.(zip|tar\\.gz)$") | not) | .browser_download_url')
-
-    # Download each asset.
-    while IFS= read -r url; do
-      if [ -n "$url" ]; then
-        curl -LJO "$url"
-        echo "Downloaded: $url"
-      fi
-    done <<< "$ASSET_URLS"
-  fi
-}
-
-function main() {
-  check_vars
-  download_artifacts_from_github
-  upload_artifacts
-  update_version_info
-}
-
-# Usage example:
-#   AWS_ACCESS_KEY_ID=<your_access_key_id> \
-#   AWS_SECRET_ACCESS_KEY=<your_secret_access_key> \
-#   AWS_DEFAULT_REGION=<your_region> \
-#   UPDATE_VERSION_INFO=true \
-#   DOWNLOAD_ARTIFACTS_FROM_GITHUB=false \
-#     ./upload-artifacts-to-s3.sh <artifacts-dir> <version> <aws-s3-bucket>
-main

.github/workflows/apidoc.yml

@@ -1,42 +0,0 @@
-on:
-  push:
-    branches:
-      - develop
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-
-name: Build API docs
-
-env:
-  RUST_TOOLCHAIN: nightly-2023-10-21
-
-jobs:
-  apidoc:
-    runs-on: ubuntu-20.04
-    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

@@ -0,0 +1,56 @@
+on:
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+  push:
+    branches:
+      - "main"
+      - "develop"
+
+name: Code coverage
+
+env:
+  RUST_TOOLCHAIN: nightly-2022-07-14
+
+jobs:
+  grcov:
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: arduino/setup-protoc@v1
+      - name: Install toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: ${{ env.RUST_TOOLCHAIN }}
+          override: true
+          profile: minimal
+      - name: Rust Cache
+        uses: Swatinem/rust-cache@v2.0.0
+      - name: Cleanup disk
+        uses: curoky/cleanup-disk-action@v2.0
+        with:
+          retain: 'rust'
+      - name: Execute tests
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --workspace
+        env:
+          RUST_BACKTRACE: 1
+          CARGO_INCREMENTAL: 0
+          RUSTFLAGS: "-Zprofile -Ccodegen-units=1 -Cinline-threshold=0 -Clink-dead-code -Coverflow-checks=off -Cpanic=unwind -Zpanic_abort_tests"
+          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: Gather coverage data
+        id: coverage
+        uses: actions-rs/grcov@v0.1
+      - 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

@@ -1,337 +0,0 @@
-# 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-20.04
-          - ubuntu-20.04-8-cores
-          - ubuntu-20.04-16-cores
-          - ubuntu-20.04-32-cores
-          - ubuntu-20.04-64-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-20.04
-    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 }}
-          dev-mode: true # Only build the standard greptime binary.
-          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 }}
-          dev-mode: true # Only build the standard greptime binary.
-          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-20.04
-    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-cn-artifacts:
-    name: Release artifacts to CN region
-    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
-    needs: [
-      allocate-runners,
-      release-images-to-dockerhub,
-    ]
-    runs-on: ubuntu-20.04
-    continue-on-error: true
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Release artifacts to CN region
-        uses: ./.github/actions/release-cn-artifacts
-        with:
-          src-image-registry: docker.io
-          src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: ${{ env.IMAGE_NAME }}
-          dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
-          dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
-          dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
-          dst-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          version: ${{ needs.allocate-runners.outputs.version }}
-          aws-cn-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
-          aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
-          aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
-          aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
-          dev-mode: true                     # Only build the standard images(exclude centos images).
-          push-latest-tag: false             # Don't push the latest tag to registry.
-          update-version-info: false         # Don't update the version info in S3.
-
-  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-20.04
-    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-20.04
-    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-20.04
-    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

@@ -1,197 +1,93 @@
 on:
-  merge_group:
   pull_request:
     types: [opened, synchronize, reopened, ready_for_review]
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-  push:
-    branches:
-      - develop
-      - main
-    paths-ignore:
-      - 'docs/**'
-      - 'config/**'
-      - '**.md'
-      - '.dockerignore'
-      - 'docker/**'
-      - '.gitignore'
-  workflow_dispatch:
 
-name: CI
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
+name: Continuous integration for developing
 
 env:
-  RUST_TOOLCHAIN: nightly-2023-10-21
+  RUST_TOOLCHAIN: nightly-2022-07-14
 
 jobs:
-  typos:
-    name: Spell Check with Typos
-    runs-on: ubuntu-20.04
-    steps:
-      - uses: actions/checkout@v3
-      - uses: crate-ci/typos@v1.13.10
-
   check:
     name: Check
     if: github.event.pull_request.draft == false
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ windows-latest-8-cores, ubuntu-20.04 ]
-    timeout-minutes: 60
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
       - uses: arduino/setup-protoc@v1
+      - uses: actions-rs/toolchain@v1
         with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
+          profile: minimal
           toolchain: ${{ env.RUST_TOOLCHAIN }}
+          override: true
       - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-      - name: Run cargo check
-        run: cargo check --locked --workspace --all-targets
-
-  toml:
-    name: Toml Check
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@master
+        uses: Swatinem/rust-cache@v2.0.0
+      - uses: actions-rs/cargo@v1
         with:
-          toolchain: stable
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-      - name: Install taplo
-        run: cargo +stable install taplo-cli --version ^0.8 --locked
-      - name: Run taplo
-        run: taplo format --check
+          command: check
+          args: --workspace --all-targets
 
-  sqlness:
-    name: Sqlness Test
+  test:
+    name: Test Suite
     if: github.event.pull_request.draft == false
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ ubuntu-20.04-8-cores ]
-    timeout-minutes: 60
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
       - uses: arduino/setup-protoc@v1
+      - uses: actions-rs/toolchain@v1
         with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
+          profile: minimal
           toolchain: ${{ env.RUST_TOOLCHAIN }}
+          override: true
       - 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
+        uses: Swatinem/rust-cache@v2.0.0
+      - uses: actions-rs/cargo@v1
         with:
-          name: sqlness-logs
-          path: ${{ runner.temp }}/greptime-*.log
-          retention-days: 3
+          command: test
+          args: --workspace
+        env:
+          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"
 
   fmt:
     name: Rustfmt
     if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    timeout-minutes: 60
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
       - uses: arduino/setup-protoc@v1
+      - uses: actions-rs/toolchain@v1
         with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
+          profile: minimal
           toolchain: ${{ env.RUST_TOOLCHAIN }}
-          components: rustfmt
+          override: true
       - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-      - name: Run cargo fmt
-        run: cargo fmt --all -- --check
+        uses: Swatinem/rust-cache@v2.0.0
+      - run: rustup component add rustfmt
+      - uses: actions-rs/cargo@v1
+        with:
+          command: fmt
+          args: --all -- --check
 
   clippy:
     name: Clippy
     if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    timeout-minutes: 60
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
       - uses: arduino/setup-protoc@v1
+      - uses: actions-rs/toolchain@v1
         with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
+          profile: minimal
           toolchain: ${{ env.RUST_TOOLCHAIN }}
-          components: clippy
+          override: true
       - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-      - name: Run cargo clippy
-        run: cargo clippy --workspace --all-targets -- -D warnings
-
-  coverage:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04-8-cores
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v3
-      - uses: arduino/setup-protoc@v1
+        uses: Swatinem/rust-cache@v2.0.0
+      - run: rustup component add clippy
+      - uses: actions-rs/cargo@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: Install Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-      - name: Install PyArrow Package
-        run: pip install pyarrow
-      - name: Setup etcd server
-        working-directory: tests-integration/fixtures/etcd
-        run: docker compose -f docker-compose-standalone.yml up -d --wait
-      - name: Run nextest cases
-        run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F pyo3_backend -F dashboard
-        env:
-          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
-          RUST_BACKTRACE: 1
-          CARGO_INCREMENTAL: 0
-          GT_S3_BUCKET: ${{ secrets.S3_BUCKET }}
-          GT_S3_ACCESS_KEY_ID: ${{ secrets.S3_ACCESS_KEY_ID }}
-          GT_S3_ACCESS_KEY: ${{ secrets.S3_ACCESS_KEY }}
-          GT_S3_REGION: ${{ secrets.S3_REGION }}
-          GT_ETCD_ENDPOINTS: http://127.0.0.1:2379
-          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
+          command: clippy
+          args: --workspace --all-targets -- -D warnings -D clippy::print_stdout -D clippy::print_stderr

.github/workflows/doc-issue.yml

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

@@ -1,70 +0,0 @@
-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-20.04
-    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-20.04
-    steps:
-      - run: 'echo "No action required"'
-
-  fmt:
-    name: Rustfmt
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    steps:
-      - run: 'echo "No action required"'
-
-  clippy:
-    name: Clippy
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    steps:
-      - run: 'echo "No action required"'
-
-  coverage:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    steps:
-      - run: 'echo "No action required"'
-
-  sqlness:
-    name: Sqlness Test
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-20.04
-    steps:
-      - run: 'echo "No action required"'

.github/workflows/license.yaml

@@ -1,16 +0,0 @@
-name: License checker
-
-on:
-  push:
-    branches:
-    - develop
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-jobs:
-  license-header-check:
-    runs-on: ubuntu-20.04
-    name: license-header-check
-    steps:
-    - uses: actions/checkout@v2
-    - name: Check License Header
-      uses: korandoru/hawkeye@v3

.github/workflows/nightly-build.yml

@@ -1,309 +0,0 @@
-# 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-20.04
-          - ubuntu-20.04-8-cores
-          - ubuntu-20.04-16-cores
-          - ubuntu-20.04-32-cores
-          - ubuntu-20.04-64-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-20.04
-    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 }}
-
-  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-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-20.04
-    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-cn-artifacts:
-    name: Release artifacts to CN region
-    if: ${{ inputs.release_images || github.event_name == 'schedule' }}
-    needs: [
-      allocate-runners,
-      release-images-to-dockerhub,
-    ]
-    runs-on: ubuntu-20.04
-    # 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: Release artifacts to CN region
-        uses: ./.github/actions/release-cn-artifacts
-        with:
-          src-image-registry: docker.io
-          src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: greptimedb
-          dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
-          dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
-          dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
-          dst-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          version: ${{ needs.allocate-runners.outputs.version }}
-          aws-cn-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
-          aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
-          aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
-          aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
-          dev-mode: false
-          update-version-info: false  # Don't update version info in S3.
-          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-20.04
-    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-20.04
-    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-20.04
-    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/nightly-ci.yml

@@ -1,98 +0,0 @@
-# Nightly CI: runs tests every night for our second tier plaforms (Windows)
-
-on:
-  schedule:
-    - cron: '0 23 * * 1-5'
-  workflow_dispatch:
-
-name: Nightly CI
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  RUST_TOOLCHAIN: nightly-2023-10-21
-
-jobs:
-  sqlness:
-    name: Sqlness Test
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ windows-latest-8-cores ]
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v4.1.0
-      - 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: Notify slack if failed
-        if: failure()
-        uses: slackapi/slack-github-action@v1.23.0
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
-        with:
-          payload: |
-            {"text": "Nightly CI failed for sqlness tests"}
-      - name: Upload sqlness logs
-        if: always()
-        uses: actions/upload-artifact@v3
-        with:
-          name: sqlness-logs
-          path: ${{ runner.temp }}/greptime-*.log
-          retention-days: 3
-
-  test-on-windows:
-    runs-on: windows-latest-8-cores
-    timeout-minutes: 60
-    steps:
-      - run: git config --global core.autocrlf false
-      - uses: actions/checkout@v4.1.0
-      - 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"
-      - name: Notify slack if failed
-        if: failure()
-        uses: slackapi/slack-github-action@v1.23.0
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
-        with:
-          payload: |
-            {"text": "Nightly CI failed for cargo test"}

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

@@ -1,26 +0,0 @@
-name: Nightly functional tests
-
-on:
-  schedule:
-    # At 00:00 on Tuesday.
-    - cron: '0 0 * * 2'
-  workflow_dispatch:
-
-jobs:
-  sqlness-test:
-    name: Run sqlness test
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Run sqlness test
-        uses: ./.github/actions/sqlness-test
-        with:
-          data-root: sqlness-test
-          aws-ci-test-bucket: ${{ vars.AWS_CI_TEST_BUCKET }}
-          aws-region: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
-          aws-access-key-id: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}

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

@@ -10,20 +10,10 @@ on:
 
 jobs:
   check:
-    runs-on: ubuntu-20.04
-    timeout-minutes: 10
+    runs-on: ubuntu-latest
     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-checker-config.json"
-  breaking:
-    runs-on: ubuntu-20.04
-    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-dev-builder-images.yaml

@@ -1,85 +0,0 @@
-name: Release dev-builder images
-
-on:
-  workflow_dispatch: # Allows you to run this workflow manually.
-    inputs:
-      version:
-        description: Version of the dev-builder
-        required: false
-        default: latest
-      release_dev_builder_ubuntu_image:
-        type: boolean
-        description: Release dev-builder-ubuntu image
-        required: false
-        default: false
-      release_dev_builder_centos_image:
-        type: boolean
-        description: Release dev-builder-centos image
-        required: false
-        default: false
-      release_dev_builder_android_image:
-        type: boolean
-        description: Release dev-builder-android image
-        required: false
-        default: false
-
-jobs:
-  release-dev-builder-images:
-    name: Release dev builder images
-    if: ${{ inputs.release_dev_builder_ubuntu_image || inputs.release_dev_builder_centos_image || inputs.release_dev_builder_android_image }} # Only manually trigger this job.
-    runs-on: ubuntu-20.04-16-cores
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Build and push dev builder images
-        uses: ./.github/actions/build-dev-builder-images
-        with:
-          version: ${{ inputs.version }}
-          dockerhub-image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
-          dockerhub-image-registry-token: ${{ secrets.DOCKERHUB_TOKEN }}
-          build-dev-builder-ubuntu: ${{ inputs.release_dev_builder_ubuntu_image }}
-          build-dev-builder-centos: ${{ inputs.release_dev_builder_centos_image }}
-          build-dev-builder-android: ${{ inputs.release_dev_builder_android_image }}
-
-  release-dev-builder-images-cn: # Note: Be careful issue: https://github.com/containers/skopeo/issues/1874 and we decide to use the latest stable skopeo container.
-    name: Release dev builder images to CN region
-    runs-on: ubuntu-20.04
-    needs: [
-      release-dev-builder-images
-    ]
-    steps:
-      - name: Push dev-builder-ubuntu image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_ubuntu_image }}
-        env:
-          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
-          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
-        run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-ubuntu:${{ inputs.version }}
-
-      - name: Push dev-builder-centos image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_centos_image }}
-        env:
-          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
-          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
-        run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-centos:${{ inputs.version }}
-
-      - name: Push dev-builder-android image
-        shell: bash
-        if: ${{ inputs.release_dev_builder_android_image }}
-        env:
-          DST_REGISTRY_USERNAME: ${{ secrets.ALICLOUD_USERNAME }}
-          DST_REGISTRY_PASSWORD: ${{ secrets.ALICLOUD_PASSWORD }}
-        run: |
-          docker run quay.io/skopeo/stable:latest copy -a docker://docker.io/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }} \
-            --dest-creds "$DST_REGISTRY_USERNAME":"$DST_REGISTRY_PASSWORD" \
-            docker://${{ vars.ACR_IMAGE_REGISTRY }}/${{ vars.IMAGE_NAMESPACE }}/dev-builder-android:${{ inputs.version }}

.github/workflows/release.yml

@@ -1,415 +0,0 @@
-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:
-      - "v*.*.*"
-  schedule:
-    # At 00:00 on Monday.
-    - cron: '0 0 * * 1'
-  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-20.04
-          - ubuntu-20.04-8-cores
-          - ubuntu-20.04-16-cores
-          - ubuntu-20.04-32-cores
-          - ubuntu-20.04-64-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
-      build_windows_artifacts:
-        type: boolean
-        description: Build Windows artifacts
-        required: false
-        default: false
-      publish_github_release:
-        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
-
-# Use env variables to control all the release process.
-env:
-  # The arguments of building greptime.
-  RUST_TOOLCHAIN: nightly-2023-10-21
-  CARGO_PROFILE: nightly
-
-  # Controls whether to run tests, include unit-test, integration-test and sqlness.
-  DISABLE_RUN_TESTS: ${{ inputs.skip_test || vars.DEFAULT_SKIP_TEST }}
-
-  # The scheduled version is '${{ 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: v0.5.0
-
-jobs:
-  allocate-runners:
-    name: Allocate runners
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-20.04
-    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 }}
-      windows-runner: windows-latest-8-cores
-
-      # The following EC2 resource id will be used for resource releasing.
-      linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
-      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 }}
-
-  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 }}
-
-  build-macos-artifacts:
-    name: Build macOS artifacts
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - 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:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - uses: ./.github/actions/build-macos-artifacts
-        with:
-          arch: ${{ matrix.arch }}
-          rust-toolchain: ${{ env.RUST_TOOLCHAIN }}
-          cargo-profile: ${{ env.CARGO_PROFILE }}
-          features: ${{ matrix.features }}
-          version: ${{ needs.allocate-runners.outputs.version }}
-          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
-
-  build-windows-artifacts:
-    name: Build Windows artifacts
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - os: ${{ needs.allocate-runners.outputs.windows-runner }}
-            arch: x86_64-pc-windows-msvc
-            features: servers/dashboard
-            artifacts-dir-prefix: greptime-windows-amd64
-          - os: ${{ needs.allocate-runners.outputs.windows-runner }}
-            arch: x86_64-pc-windows-msvc
-            features: pyo3_backend,servers/dashboard
-            artifacts-dir-prefix: greptime-windows-amd64-pyo3
-    runs-on: ${{ matrix.os }}
-    needs: [
-      allocate-runners,
-    ]
-    if: ${{ inputs.build_windows_artifacts || github.event_name == 'push' || github.event_name == 'schedule' }}
-    steps:
-      - run: git config --global core.autocrlf false
-
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - uses: ./.github/actions/build-windows-artifacts
-        with:
-          arch: ${{ matrix.arch }}
-          rust-toolchain: ${{ env.RUST_TOOLCHAIN }}
-          cargo-profile: ${{ env.CARGO_PROFILE }}
-          features: ${{ matrix.features }}
-          version: ${{ needs.allocate-runners.outputs.version }}
-          disable-run-tests: ${{ env.DISABLE_RUN_TESTS }}
-          artifacts-dir: ${{ matrix.artifacts-dir-prefix }}-${{ needs.allocate-runners.outputs.version }}
-
-  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:
-          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 }}
-
-  release-cn-artifacts:
-    name: Release artifacts to CN region
-    if: ${{ inputs.release_images || github.event_name == 'push' || github.event_name == 'schedule' }}
-    needs: [ # The job have to wait for all the artifacts are built.
-      allocate-runners,
-      build-linux-amd64-artifacts,
-      build-linux-arm64-artifacts,
-      build-macos-artifacts,
-      build-windows-artifacts,
-      release-images-to-dockerhub,
-    ]
-    runs-on: ubuntu-20.04
-    # 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: Release artifacts to CN region
-        uses: ./.github/actions/release-cn-artifacts
-        with:
-          src-image-registry: docker.io
-          src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: greptimedb
-          dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
-          dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
-          dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
-          dst-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          version: ${{ needs.allocate-runners.outputs.version }}
-          aws-cn-s3-bucket: ${{ vars.AWS_RELEASE_BUCKET }}
-          aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
-          aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
-          aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
-          dev-mode: false
-          update-version-info: true
-          push-latest-tag: true
-
-  publish-github-release:
-    name: Create GitHub release and upload artifacts
-    if: ${{ inputs.publish_github_release || github.event_name == 'push' || github.event_name == 'schedule' }}
-    needs: [ # The job have to wait for all the artifacts are built.
-      allocate-runners,
-      build-linux-amd64-artifacts,
-      build-linux-arm64-artifacts,
-      build-macos-artifacts,
-      build-windows-artifacts,
-      release-images-to-dockerhub,
-    ]
-    runs-on: ubuntu-20.04
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Publish GitHub release
-        uses: ./.github/actions/publish-github-release
-        with:
-          version: ${{ needs.allocate-runners.outputs.version }}
-
-  ### 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-20.04
-    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-20.04
-    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 }}

.github/workflows/size-label.yml

@@ -1,26 +0,0 @@
-name: size-labeler
-
-on: [pull_request]
-
-jobs:
-  labeler:
-    runs-on: ubuntu-latest
-    name: Label the PR size
-    steps:
-      - uses: codelytv/pr-size-labeler@v1
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          s_label: 'Size: S'
-          s_max_size: '100'
-          m_label: 'Size: M'
-          m_max_size: '500'
-          l_label: 'Size: L'
-          l_max_size: '1000'
-          xl_label: 'Size: XL'
-          fail_if_xl: 'false'
-          message_if_xl: >
-            This PR exceeds the recommended size of 1000 lines.
-            Please make sure you are NOT addressing multiple issues with one PR.
-            Note this PR might be rejected due to its size.
-          github_api_url: 'api.github.com'
-          files_to_ignore: 'Cargo.lock'

.gitignore

@@ -1,8 +1,6 @@
 # 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
@@ -20,29 +18,13 @@ debug/
 
 # JetBrains IDE config directory
 .idea/
-*.iml
-
-# VSCode IDE config directory
-.vscode/
 
 # Logs
 **/__unittest_logs
 logs/
 
+.DS_store
+.gitignore
+
 # cpython's generated python byte code
 **/__pycache__/
-
-# Benchmark dataset
-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

CODE_OF_CONDUCT.md

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

CONTRIBUTING.md

@@ -1,92 +1,23 @@
-# Welcome 👋
+# Contributing to GreptimeDB
 
-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.
+Much appreciate for your interest in contributing to GreptimeDB! This document list some guidelines for contributing to our code base.
 
-Please read the guidelines, and they can help you get started. Communicate with respect to developers maintaining and developing the project. In return, they should reciprocate that respect by addressing your issue, reviewing changes, as well as helping finalize and merge your pull requests.
+To learn about the design of GreptimeDB, please refer to the [design docs](https://github.com/GrepTimeTeam/docs).
 
-Follow our [README](https://github.com/GreptimeTeam/greptimedb#readme) to get the whole picture of the project. To learn about the design of GreptimeDB, please refer to the [design docs](https://github.com/GrepTimeTeam/docs).
-
-## Your First Contribution
-
-It can feel intimidating to contribute to a complex project, but it can also be exciting and fun. These general notes will help everyone participate in this communal activity.
-
-- Follow the [Code of Conduct](https://github.com/GreptimeTeam/greptimedb/blob/develop/CODE_OF_CONDUCT.md)
-- Small changes make huge differences. We will happily accept a PR making a single character change if it helps move forward. Don't wait to have everything working.
-- Check the closed issues before opening your issue.
-- Try to follow the existing style of the code.
-- More importantly, when in doubt, ask away.
-
-Pull requests are great, but we accept all kinds of other help if you like. Such as
-
-- Write tutorials or blog posts. Blog, speak about, or create tutorials about one of GreptimeDB's many features. Mention [@greptime](https://twitter.com/greptime) on Twitter and email info@greptime.com so we can give pointers and tips and help you spread the word by promoting your content on Greptime communication channels.
-- Improve the documentation. [Submit documentation](http://github.com/greptimeTeam/docs/) updates, enhancements, designs, or bug fixes, and fixing any spelling or grammar errors will be very much appreciated.
-- Present at meetups and conferences about your GreptimeDB projects. Your unique challenges and successes in building things with GreptimeDB can provide great speaking material. We'd love to review your talk abstract, so get in touch with us if you'd like some help!
-- Submitting bug reports. To report a bug or a security issue, you can [open a new GitHub issue](https://github.com/GrepTimeTeam/greptimedb/issues/new).
-- Speak up feature requests. Send feedback is a great way for us to understand your different use cases of GreptimeDB better. If you want to share your experience with GreptimeDB, or if you want to discuss any ideas, you can start a discussion on [GitHub discussions](https://github.com/GreptimeTeam/greptimedb/discussions), chat with the Greptime team on [Slack](https://greptime.com/slack), or you can tweet [@greptime](https://twitter.com/greptime) on Twitter.
-
-## Code of Conduct
-
-Also, there are things that we are not looking for because they don't match the goals of the product or benefit the community. Please read [Code of Conduct](https://github.com/GreptimeTeam/greptimedb/blob/develop/CODE_OF_CONDUCT.md); we hope everyone can keep good manners and become an honored member.
-
-## License
-
-GreptimeDB uses the [Apache 2.0 license](https://github.com/GreptimeTeam/greptimedb/blob/master/LICENSE) to strike a balance between open contributions and allowing you to use the software however you want.
-
-## Getting Started
-
-### Submitting Issues
-
-- Check if an issue already exists. Before filing an issue report, see whether it's already covered. Use the search bar and check out existing issues.
-- File an issue:
-  - To report a bug, a security issue, or anything that you think is a problem and that isn't under the radar, go ahead and [open a new GitHub issue](https://github.com/GrepTimeTeam/greptimedb/issues/new).
-  - In the given templates, look for the one that suits you.
-  - If you bump into anything, reach out to our [Slack](https://greptime.com/slack) for a wider audience and ask for help.
-- What happens after:
-  - Once we spot a new issue, we identify and categorize it as soon as possible.
-  - Usually, it gets assigned to other developers. Follow up and see what folks are talking about and how they take care of it.
-  - Please be patient and offer as much information as you can to help reach a solution or a consensus. You are not alone and embrace team power.
+## Pull Requests
 
 ### Before PR
-
-- To ensure that community is free and confident in its ability to use your contributions, please sign the Contributor License Agreement (CLA) which will be incorporated in the pull request process.
-- Make sure all files have proper license header (running `docker run --rm -v $(pwd):/github/workspace ghcr.io/korandoru/hawkeye-native:v3 format` from the project root).
-- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/).
-- Make sure all 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
-
-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 --hook-type pre-push
-        pre-commit installed at .git/hooks/pre-push
-
-Now, `pre-commit` will run automatically on `git commit`.
+- 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`).
 
 ### Title
 
-The titles of pull requests should be prefixed with category names listed in [Conventional Commits specification](https://www.conventionalcommits.org/en/v1.0.0)
-like `feat`/`fix`/`docs`, with a concise summary of code change following. AVOID using the last commit message as pull request title.
+The titles of pull requests should be prefixed with category name listed in [Conventional Commits specification](https://www.conventionalcommits.org/en/v1.0.0) 
+like `feat`/`fix`/`doc`, with a concise summary of code change follows. DO NOT use last commit message as pull request title.
 
 ### Description
 
-- Feel free to go brief if your pull request is small, like a typo fix.
+- If your pull request is small, like a typo fix, feel free to go brief.
 - But if it contains large code change, make sure to state the motivation/design details of this PR so that reviewers can understand what you're trying to do.
 - If the PR contains any breaking change or API change, make sure that is clearly listed in your description.
 
@@ -94,20 +25,11 @@ like `feat`/`fix`/`docs`, with a concise summary of code change following. AVOID
 
 All commit messages SHOULD adhere to the [Conventional Commits specification](https://conventionalcommits.org/).
 
-## Getting Help
+## Getting help
 
 There are many ways to get help when you're stuck. It is recommended to ask for help by opening an issue, with a detailed description
-of what you were trying to do and what went wrong. You can also reach for help in our [Slack channel](https://greptime.com/slack).
+of what you were trying to do and what went wrong. You can also reach for help in our Slack channel.
 
-## Community
 
-The core team will be thrilled if you would like to participate in any way you like. When you are stuck, try to 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://docs.greptime.com/)
-- [Learn GreptimeDB](https://greptime.com/product/db)
-- [Greptime Inc. Website](https://greptime.com)
+## Bug report
+To report a bug or a security issue, you can [open a new GitHub issue](https://github.com/GrepTimeTeam/greptimedb/issues/new). 

Cargo.toml

@@ -1,199 +1,35 @@
 [workspace]
 members = [
-    "benchmarks",
     "src/api",
-    "src/auth",
     "src/catalog",
     "src/client",
     "src/cmd",
     "src/common/base",
-    "src/common/catalog",
-    "src/common/config",
-    "src/common/datasource",
     "src/common/error",
     "src/common/function",
-    "src/common/macro",
-    "src/common/greptimedb-telemetry",
+    "src/common/function-macro",
     "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/decimal",
-    "src/common/version",
     "src/datanode",
     "src/datatypes",
-    "src/file-engine",
     "src/frontend",
     "src/log-store",
-    "src/meta-client",
-    "src/meta-srv",
-    "src/metric-engine",
-    "src/mito2",
+    "src/logical-plans",
     "src/object-store",
-    "src/operator",
-    "src/partition",
-    "src/plugins",
-    "src/promql",
-    "src/puffin",
     "src/query",
     "src/script",
     "src/servers",
-    "src/session",
     "src/sql",
+    "src/storage",
     "src/store-api",
     "src/table",
-    "src/index",
-    "tests-integration",
-    "tests/runner",
+    "src/table-engine",
+    "test-util",
 ]
-resolver = "2"
 
-[workspace.package]
-version = "0.4.4"
-edition = "2021"
-license = "Apache-2.0"
-
-[workspace.dependencies]
-ahash = { version = "0.8", features = ["compile-time-rng"] }
-aquamarine = "0.3"
-arrow = { version = "47.0" }
-arrow-array = "47.0"
-arrow-flight = "47.0"
-arrow-schema = { version = "47.0", features = ["serde"] }
-async-stream = "0.3"
-async-trait = "0.1"
-base64 = "0.21"
-bigdecimal = "0.4.2"
-bitflags = "2.4.1"
-bytemuck = "1.12"
-chrono = { version = "0.4", features = ["serde"] }
-datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion.git", rev = "26e43acac3a96cec8dd4c8365f22dfb1a84306e9" }
-derive_builder = "0.12"
-etcd-client = "0.12"
-fst = "0.4.7"
-futures = "0.3"
-futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "b1d403088f02136bcebde53d604f491c260ca8e2" }
-humantime-serde = "1.1"
-itertools = "0.10"
-lazy_static = "1.4"
-meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "abbd357c1e193cd270ea65ee7652334a150b628f" }
-mockall = "0.11.4"
-moka = "0.12"
-once_cell = "1.18"
-opentelemetry-proto = { git = "https://github.com/waynexia/opentelemetry-rust.git", rev = "33841b38dda79b15f2024952be5f32533325ca02", features = [
-    "gen-tonic",
-    "metrics",
-    "trace",
-] }
-parquet = "47.0"
-paste = "1.0"
-pin-project = "1.0"
-prometheus = { version = "0.13.3", features = ["process"] }
-prost = "0.12"
-raft-engine = { git = "https://github.com/tikv/raft-engine.git", rev = "22dfb426cd994602b57725ef080287d3e53db479" }
-rand = "0.8"
-regex = "1.8"
-regex-automata = { version = "0.1", features = ["transducer"] }
-reqwest = { version = "0.11", default-features = false, features = [
-    "json",
-    "rustls-tls-native-roots",
-    "stream",
-] }
-rust_decimal = "1.33"
-serde = { version = "1.0", features = ["derive"] }
-serde_json = "1.0"
-smallvec = "1"
-snafu = "0.7"
-# on branch v0.38.x
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "6a93567ae38d42be5c8d08b13c8ff4dde26502ef", 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 = "0.10", features = ["tls"] }
-uuid = { version = "1", features = ["serde", "v4", "fast-rng"] }
-
-## 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-config = { path = "src/common/config" }
-common-datasource = { path = "src/common/datasource" }
-common-decimal = { path = "src/common/decimal" }
-common-error = { path = "src/common/error" }
-common-function = { path = "src/common/function" }
-common-greptimedb-telemetry = { path = "src/common/greptimedb-telemetry" }
-common-grpc = { path = "src/common/grpc" }
-common-grpc-expr = { path = "src/common/grpc-expr" }
-common-macro = { path = "src/common/macro" }
-common-mem-prof = { path = "src/common/mem-prof" }
-common-meta = { path = "src/common/meta" }
-common-pprof = { path = "src/common/pprof" }
-common-procedure = { path = "src/common/procedure" }
-common-procedure-test = { path = "src/common/procedure-test" }
-common-query = { path = "src/common/query" }
-common-recordbatch = { path = "src/common/recordbatch" }
-common-runtime = { path = "src/common/runtime" }
-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-engine = { path = "src/file-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" }
-operator = { path = "src/operator" }
-partition = { path = "src/partition" }
-plugins = { path = "src/plugins" }
-promql = { path = "src/promql" }
-query = { path = "src/query" }
-script = { path = "src/script" }
-servers = { path = "src/servers" }
-session = { path = "src/session" }
-sql = { path = "src/sql" }
-store-api = { path = "src/store-api" }
-substrait = { path = "src/common/substrait" }
-table = { path = "src/table" }
-
-[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
+[patch.crates-io]
+sqlparser = { git = "https://github.com/sunng87/sqlparser-rs.git", branch = "feature/argument-for-custom-type-for-v015" }

Cross.toml

@@ -1,7 +0,0 @@
-[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",
-]

LICENSE

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   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.

Makefile

@@ -1,200 +0,0 @@
-# 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
-
-ifneq ($(strip $(CARGO_BUILD_EXTRA_OPTS)),)
-	CARGO_BUILD_OPTS += ${CARGO_BUILD_EXTRA_OPTS}
-endif
-
-##@ Build
-
-.PHONY: build
-build: ## Build debug version greptime.
-	cargo ${CARGO_EXTENSION} build ${CARGO_BUILD_OPTS}
-
-.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_EXTENSION="${CARGO_EXTENSION}" \
-	CARGO_PROFILE=${CARGO_PROFILE} \
-	FEATURES=${FEATURES} \
-	TARGET_DIR=${TARGET_DIR} \
-	TARGET=${TARGET} \
-	RELEASE=${RELEASE} \
-	CARGO_BUILD_EXTRA_OPTS="${CARGO_BUILD_EXTRA_OPTS}"
-
-.PHONY: build-android-bin
-build-android-bin: ## Build greptime binary for android.
-	docker run --network=host \
-	-v ${PWD}:/greptimedb -v ${CARGO_REGISTRY_CACHE}:/root/.cargo/registry \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:latest \
-	make build \
-	CARGO_EXTENSION="ndk --platform 23 -t aarch64-linux-android" \
-	CARGO_PROFILE=release \
-	FEATURES="${FEATURES}" \
-	TARGET_DIR="${TARGET_DIR}" \
-	TARGET="${TARGET}" \
-	RELEASE="${RELEASE}" \
-	CARGO_BUILD_EXTRA_OPTS="--bin greptime --no-default-features"
-
-.PHONY: strip-android-bin
-strip-android-bin: build-android-bin ## Strip greptime binary for android.
-	docker run --network=host \
-	-v ${PWD}:/greptimedb \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-android:latest \
-	bash -c '$${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip /greptimedb/target/aarch64-linux-android/release/greptime'
-
-.PHONY: clean
-clean: ## Clean the project.
-	cargo clean
-
-.PHONY: fmt
-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-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: nextest ## Install nextest tools.
-nextest:
-	cargo --list | grep nextest || cargo install cargo-nextest --locked
-
-.PHONY: sqlness-test
-sqlness-test: ## Run sqlness test.
-	cargo sqlness
-
-.PHONY: check
-check: ## Cargo check all the targets.
-	cargo check --workspace --all-targets --all-features
-
-.PHONY: clippy
-clippy: ## Check clippy rules.
-	cargo clippy --workspace --all-targets --all-features -- -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 $$(docker ps -q --filter ancestor=${ETCD_IMAGE})
-
-.PHONY: run-it-in-container
-run-it-in-container: start-etcd ## Run integration tests in dev-builder.
-	docker run --network=host \
-	-v ${PWD}:/greptimedb -v ${CARGO_REGISTRY_CACHE}:/root/.cargo/registry -v /tmp:/tmp \
-	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:latest \
-	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
-
-##@ General
-
-# The help target prints out all targets with their descriptions organized
-# beneath their categories. The categories are represented by '##@' and the
-# target descriptions by '##'. The awk commands is responsible for reading the
-# entire set of makefiles included in this invocation, looking for lines of the
-# file as xyz: ## something, and then pretty-format the target and help. Then,
-# if there's a line with ##@ something, that gets pretty-printed as a category.
-# More info on the usage of ANSI control characters for terminal formatting:
-# https://en.wikipedia.org/wiki/ANSI_escape_code#SGR_parameters
-# More info on the awk command:
-# https://linuxcommand.org/lc3_adv_awk.php
-
-.PHONY: help
-help: ## Display help messages.
-	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[a-zA-Z_0-9-]+:.*?##/ { printf "  \033[36m%-30s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)

README.md

@@ -1,182 +1,183 @@
-<p align="center">
-  <picture>
-    <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>
+# GreptimeDB
 
+[![codecov](https://codecov.io/gh/GrepTimeTeam/greptimedb/branch/develop/graph/badge.svg?token=FITFDI3J3C)](https://codecov.io/gh/GrepTimeTeam/greptimedb)
 
-<h3 align="center">
-    The next-generation hybrid time-series/analytics processing database in the cloud
-</h3>
+GreptimeDB: the next-generation hybrid timeseries/analytics processing database in the cloud.
 
-<p align="center">
-    <a href="https://codecov.io/gh/GrepTimeTeam/greptimedb"><img src="https://codecov.io/gh/GrepTimeTeam/greptimedb/branch/develop/graph/badge.svg?token=FITFDI3J3C"></img></a>
-    &nbsp;
-    <a href="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml"><img src="https://github.com/GreptimeTeam/greptimedb/actions/workflows/develop.yml/badge.svg" alt="CI"></img></a>
-    &nbsp;
-    <a href="https://github.com/greptimeTeam/greptimedb/blob/develop/LICENSE"><img src="https://img.shields.io/github/license/greptimeTeam/greptimedb"></a>
-</p>
+## Getting Started
 
-<p align="center">
-    <a href="https://twitter.com/greptime"><img src="https://img.shields.io/badge/twitter-follow_us-1d9bf0.svg"></a>
-    &nbsp;
-    <a href="https://www.linkedin.com/company/greptime/"><img src="https://img.shields.io/badge/linkedin-connect_with_us-0a66c2.svg"></a>
-    &nbsp;
-    <a href="https://greptime.com/slack"><img src="https://img.shields.io/badge/slack-GreptimeDB-0abd59?logo=slack" alt="slack" /></a>
-</p>
+### Prerequisites
 
-## What is GreptimeDB
+To compile GreptimeDB from source, you'll need the following:
+- Rust
+- Protobuf
+- OpenSSL
 
-GreptimeDB is an open-source time-series database with a special focus on
-scalability, analytical capabilities and efficiency. It's designed to work on
-infrastructure of the cloud era, and users benefit from its elasticity and commodity
-storage.
+#### Rust
 
-Our core developers have been building time-series data platform
-for years. Based on their best-practices, GreptimeDB is born to give you:
+The easiest way to install Rust is to use [`rustup`](https://rustup.rs/), which will check our `rust-toolchain` file and install correct Rust version for you.
 
-- 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, 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, native PromQL supports
-- Extensible table engine architecture for extensive workloads
+#### Protobuf
 
-## Quick Start
+`protoc` is required for compiling `.proto` files. `protobuf` is available from
+major package manager on macos and linux distributions. You can find an
+installation instructions [here](https://grpc.io/docs/protoc-installation/).
 
-### [GreptimePlay](https://greptime.com/playground)
+#### OpenSSL
 
-Try out the features of GreptimeDB right from your browser.
+For Ubuntu:
+```bash
+sudo apt install libssl-dev
+```
 
-### Build
+For RedHat-based: Fedora, Oracle Linux, etc:
+```bash
+sudo dnf install openssl-devel
+```
 
-#### Build from Source
+For macOS:
+```bash
+brew install openssl
+```
 
-To compile GreptimeDB from source, you'll need:
-
-- C/C++ Toolchain: provides basic tools for compiling and linking. This is
-  available as `build-essential` on ubuntu and similar name on other platforms.
-- Rust: the easiest way to install Rust is to use
-  [`rustup`](https://rustup.rs/), which will check our `rust-toolchain` file and
-  install correct Rust version for you.
-- Protobuf: `protoc` is required for compiling `.proto` files. `protobuf` is
-  available from major package manager on macos and linux distributions. You can
-  find an installation instructions [here](https://grpc.io/docs/protoc-installation/).
-  **Note that `protoc` version needs to be >= 3.15** because we have used the `optional`
-  keyword. You can check it with `protoc --version`.
-- python3-dev or python3-devel(Optional feature, only needed if you want to run scripts
-  in CPython, and also need to enable `pyo3_backend` feature when compiling(by `cargo run -F pyo3_backend` or add `pyo3_backend` to src/script/Cargo.toml 's `features.default` like `default = ["python", "pyo3_backend]`)): this install a Python shared library required for running Python
-  scripting engine(In CPython Mode). This is available as `python3-dev` on
-  ubuntu, you can install it with `sudo apt install python3-dev`, or
-  `python3-devel` on RPM based distributions (e.g. Fedora, Red Hat, SuSE). Mac's
-  `Python3` package should have this shared library by default. More detail for compiling with PyO3 can be found in [PyO3](https://pyo3.rs/v0.18.1/building_and_distribution#configuring-the-python-version)'s documentation.
-
-#### Build with Docker
-
-A docker image with necessary dependencies is provided:
+### Build the Docker Image
 
 ```
 docker build --network host -f docker/Dockerfile -t greptimedb .
 ```
 
-### Run
+## Usage
 
-Start GreptimeDB from source code, in standalone mode:
+### Start Datanode
 
 ```
-cargo run -- standalone start
+// Start datanode with default options.
+cargo run -- datanode start
+
+OR
+
+// Start datanode with `http-addr` option.
+cargo run -- datanode start --http-addr=0.0.0.0:9999
+
+OR
+
+// Start datanode with `log-dir` and `log-level` options.
+cargo run -- --log-dir=logs --log-level=debug datanode start
 ```
 
-Or if you built from docker:
+Start datanode with config file:
 
 ```
-docker run -p 4002:4002 -v "$(pwd):/tmp/greptimedb" greptime/greptimedb standalone start
+cargo run -- --log-dir=logs --log-level=debug datanode start -c ./config/datanode.example.toml
 ```
 
-Please see the online document site for more installation options and [operations info](https://docs.greptime.com/user-guide/operations/overview).
+Start datanode by runing docker container:
 
-### Get started
+```
+docker run -p 3000:3000 \
+-p 3001:3001 \
+-p 3306:3306 \
+greptimedb
+```
 
-Read the [complete getting started guide](https://docs.greptime.com/getting-started/overview) on our [official document site](https://docs.greptime.com/).
+### Start Frontend
 
-To write and query data, GreptimeDB is compatible with multiple [protocols and clients](https://docs.greptime.com/user-guide/clients/overview).
+Frontend should connect to Datanode, so **Datanode must have been started** at first!
 
-## Resources
+```
+// Connects to local Datanode at its default GRPC port: 3001
 
-### Installation
+// Start Frontend with default options.
+cargo run -- frontend start
 
-- [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
+OR
 
-### Documentation
+// Start Frontend with `mysql-addr` option.
+cargo run -- frontend start --mysql-addr=0.0.0.0:9999
 
-- 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)
+OR
 
-### Dashboard
-- [The dashboard UI for GreptimeDB](https://github.com/GreptimeTeam/dashboard)
+// Start datanode with `log-dir` and `log-level` options.
+cargo run -- --log-dir=logs --log-level=debug frontend start
+```
 
-### SDK
+Start datanode with config file:
 
-- [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)
-- [GreptimeDB JavaScript Client](https://github.com/GreptimeTeam/greptime-js-sdk)
+```
+cargo run -- --log-dir=logs --log-level=debug frontend start -c ./config/frontend.example.toml
+```
 
-## Project Status
+### SQL Operations
 
-This project is in its early stage and under heavy development. We move fast and
-break things. Benchmark on development branch may not represent its potential
-performance. We release pre-built binaries constantly for functional
-evaluation. Do not use it in production at the moment.
+1. Connecting DB by [mysql client](https://dev.mysql.com/downloads/mysql/):
 
-For future plans, check out [GreptimeDB roadmap](https://github.com/GreptimeTeam/greptimedb/issues/669).
+   ```
+   # The datanode listen on port 3306 by default.
+   mysql -h 127.0.0.1 -P 3306
+   ```
 
-## Community
+2. Create table:
 
-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:
+   ```SQL
+   CREATE TABLE monitor (
+     host STRING,
+     ts TIMESTAMP,
+     cpu DOUBLE DEFAULT 0,
+     memory DOUBLE,
+     TIME INDEX (ts),
+     PRIMARY KEY(ts,host)) ENGINE=mito WITH(regions=1);
+   ```
 
-- GreptimeDB Community on [Slack](https://greptime.com/slack)
-- GreptimeDB GitHub [Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
-- Greptime official [Website](https://greptime.com)
+3. Insert data:
 
-In addition, you may:
+   ```SQL
+   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host1', 66.6, 1024, 1660897955);
+   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host2', 77.7, 2048, 1660897956);
+   INSERT INTO monitor(host, cpu, memory, ts) VALUES ('host3', 88.8, 4096, 1660897957);
+   ```
 
-- View our official [Blog](https://greptime.com/blogs/index)
-- Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
-- Follow us on [Twitter](https://twitter.com/greptime)
+4. Query data:
 
-## License
+   ```SQL
+   mysql> SELECT * FROM monitor;
+   +-------+------------+------+--------+
+   | host  | ts         | cpu  | memory |
+   +-------+------------+------+--------+
+   | host1 | 1660897955 | 66.6 |   1024 |
+   | host2 | 1660897956 | 77.7 |   2048 |
+   | host3 | 1660897957 | 88.8 |   4096 |
+   +-------+------------+------+--------+
+   3 rows in set (0.01 sec)
+   ```
+   You can delete your data by removing `/tmp/greptimedb`.
 
-GreptimeDB uses the [Apache 2.0 license][1] to strike a balance between
-open contributions and allowing you to use the software however you want.
+## Contribute
 
-[1]: <https://github.com/greptimeTeam/greptimedb/blob/develop/LICENSE>
+1. [Install rust](https://www.rust-lang.org/tools/install)
+2. [Install `pre-commit`](https://pre-commit.com/#plugins) for run hooks on every commit automatically such as `cargo fmt` etc.
 
-## Contributing
+```
+$ pip install pre-commit
 
-Please refer to [contribution guidelines](CONTRIBUTING.md) for more information.
+or
 
-## Acknowledgement
-- GreptimeDB uses [Apache Arrow](https://arrow.apache.org/) as the memory model and [Apache Parquet](https://parquet.apache.org/) as the persistent file format.
-- GreptimeDB's query engine is powered by [Apache Arrow DataFusion](https://github.com/apache/arrow-datafusion).
-- [Apache OpenDAL (incubating)](https://opendal.apache.org) gives GreptimeDB a very general and elegant data access abstraction layer.
-- GreptimeDB's meta service is based on [etcd](https://etcd.io/).
-- GreptimeDB uses [RustPython](https://github.com/RustPython/RustPython) for experimental embedded python scripting.
+$ brew install pre-commit
+$
+```
+
+3. Install the git hook scripts:
+
+```
+$ 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 --hook-type pre-push
+pre-commit installed at .git/hooks/pre-pus
+```
+
+now `pre-commit` will run automatically on `git commit`.
+
+4. Check out branch from `develop` and make your contribution. Follow the [style guide](https://github.com/GreptimeTeam/docs/blob/main/style-guide/zh.md). Create a PR when you are ready, feel free and have fun!

SECURITY.md

@@ -1,19 +0,0 @@
-# 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

@@ -1,16 +0,0 @@
-[package]
-name = "benchmarks"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-arrow.workspace = true
-chrono.workspace = true
-clap = { version = "4.0", features = ["derive"] }
-client.workspace = true
-futures-util.workspace = true
-indicatif = "0.17.1"
-itertools.workspace = true
-parquet.workspace = true
-tokio.workspace = true

benchmarks/src/bin/nyc-taxi.rs

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

component/script/python/example/calc_rv.py

@@ -0,0 +1,71 @@
+import sys
+# for annoying releative import beyond top-level package
+sys.path.insert(0, "../")
+from greptime import mock_tester, coprocessor, greptime as gt_builtin
+from greptime.greptime import interval, vector, log, prev, sqrt, datetime
+import greptime.greptime as greptime
+import json
+import numpy as np
+
+
+def data_sample(k_lines, symbol, density=5 * 30 * 86400):
+    """
+    Only return close data for simplicty for now
+    """
+    k_lines = k_lines["result"] if k_lines["ret_msg"] == "OK" else None
+    if k_lines is None:
+        raise Exception("Expect a `OK`ed message")
+    close = [float(i["close"]) for i in k_lines]
+
+    return interval(close, density, "prev")
+
+
+def as_table(kline: list):
+    col_len = len(kline)
+    ret = {
+        k: vector([fn(row[k]) for row in kline], str(ty))
+        for k, fn, ty in
+        [
+            ("symbol", str, "str"),
+            ("period", str, "str"),
+            ("open_time", int, "int"),
+            ("open", float, "float"),
+            ("high", float, "float"),
+            ("low", float, "float"),
+            ("close", float, "float")
+        ]
+    }
+    return ret
+
+@coprocessor(args=["open_time", "close"], returns=[
+    "rv_7d",
+    "rv_15d",
+    "rv_30d",
+    "rv_60d",
+    "rv_90d",
+    "rv_180d"
+])
+def calc_rvs(open_time, close):
+    from greptime import vector, log, prev, sqrt, datetime, pow, sum, last
+    import greptime as g
+    def calc_rv(close, open_time, time, interval):
+        mask = (open_time < time) & (open_time > time - interval)
+        close = close[mask]
+        open_time = open_time[mask]
+        close = g.interval(open_time, close, datetime("10m"), lambda x:last(x))
+
+        avg_time_interval = (open_time[-1] - open_time[0])/(len(open_time)-1)
+        ref = log(close/prev(close))
+        var = sum(pow(ref, 2)/(len(ref)-1))
+        return sqrt(var/avg_time_interval)
+
+    # how to get env var,
+    # maybe through accessing scope and serde then send to remote?
+    timepoint = open_time[-1]
+    rv_7d = vector([calc_rv(close, open_time, timepoint, datetime("7d"))])
+    rv_15d = vector([calc_rv(close, open_time, timepoint, datetime("15d"))])
+    rv_30d = vector([calc_rv(close, open_time, timepoint, datetime("30d"))])
+    rv_60d = vector([calc_rv(close, open_time, timepoint, datetime("60d"))])
+    rv_90d = vector([calc_rv(close, open_time, timepoint, datetime("90d"))])
+    rv_180d = vector([calc_rv(close, open_time, timepoint, datetime("180d"))])
+    return rv_7d, rv_15d, rv_30d, rv_60d, rv_90d, rv_180d

component/script/python/example/fetch_kline.sh

@@ -0,0 +1 @@
+curl "https://api.bybit.com/v2/public/index-price-kline?symbol=BTCUSD&interval=1&limit=$1&from=1581231260" > kline.json

component/script/python/example/kline.json

@@ -0,0 +1,108 @@
+{
+    "ret_code": 0,
+    "ret_msg": "OK",
+    "ext_code": "",
+    "ext_info": "",
+    "result": [
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 300,
+            "open": "10107",
+            "high": "10109.34",
+            "low": "10106.71",
+            "close": "10106.79"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 900,
+            "open": "10106.79",
+            "high": "10109.27",
+            "low": "10105.92",
+            "close": "10106.09"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 1200,
+            "open": "10106.09",
+            "high": "10108.75",
+            "low": "10104.66",
+            "close": "10108.73"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 1800,
+            "open": "10108.73",
+            "high": "10109.52",
+            "low": "10106.07",
+            "close": "10106.38"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 2400,
+            "open": "10106.38",
+            "high": "10109.48",
+            "low": "10104.81",
+            "close": "10106.95"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 3000,
+            "open": "10106.95",
+            "high": "10109.48",
+            "low": "10106.6",
+            "close": "10107.55"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 3600,
+            "open": "10107.55",
+            "high": "10109.28",
+            "low": "10104.68",
+            "close": "10104.68"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 4200,
+            "open": "10104.68",
+            "high": "10109.18",
+            "low": "10104.14",
+            "close": "10108.8"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 4800,
+            "open": "10108.8",
+            "high": "10117.36",
+            "low": "10108.8",
+            "close": "10115.96"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 5400,
+            "open": "10115.96",
+            "high": "10119.19",
+            "low": "10115.96",
+            "close": "10117.08"
+        },
+        {
+            "symbol": "BTCUSD",
+            "period": "1",
+            "open_time": 6000,
+            "open": "10117.08",
+            "high": "10120.73",
+            "low": "10116.96",
+            "close": "10120.43"
+        }
+    ],
+    "time_now": "1661225351.158190"
+}

component/script/python/greptime/__init__.py

@@ -0,0 +1,4 @@
+from .greptime import coprocessor, copr
+from .greptime import vector, log, prev, next, first, last, sqrt, pow, datetime, sum, interval
+from .mock import mock_tester
+from .cfg import set_conn_addr, get_conn_addr

component/script/python/greptime/cfg.py

@@ -0,0 +1,11 @@
+GREPTIME_DB_CONN_ADDRESS = "localhost:3000"
+"""The Global Variable for address for conntect to database"""
+
+def set_conn_addr(addr: str):
+    """set database address to given `addr`"""
+    global GREPTIME_DB_CONN_ADDRESS
+    GREPTIME_DB_CONN_ADDRESS = addr
+
+def get_conn_addr()->str:
+    global GREPTIME_DB_CONN_ADDRESS
+    return GREPTIME_DB_CONN_ADDRESS

component/script/python/greptime/greptime.py

@@ -0,0 +1,207 @@
+"""
+Be note that this is a mock library, if not connected to database,
+it can only run on mock data and mock function which is supported by numpy
+"""
+import functools
+import numpy as np
+import json
+from urllib import request
+import inspect
+import requests
+
+from .cfg import set_conn_addr, get_conn_addr
+
+log = np.log
+sum = np.nansum
+sqrt = np.sqrt
+pow = np.power
+nan = np.nan
+
+
+class TimeStamp(str):
+    """
+    TODO: impl date time
+    """
+    pass
+
+
+class i32(int):
+    """
+    For Python Coprocessor Type Annotation ONLY
+    A signed 32-bit integer.
+    """
+
+    def __repr__(self) -> str:
+        return "i32"
+
+
+class i64(int):
+    """
+    For Python Coprocessor Type Annotation ONLY
+    A signed 64-bit integer.
+    """
+
+    def __repr__(self) -> str:
+        return "i64"
+
+
+class f32(float):
+    """
+    For Python Coprocessor Type Annotation ONLY
+    A 32-bit floating point number.
+    """
+
+    def __repr__(self) -> str:
+        return "f32"
+
+
+class f64(float):
+    """
+    For Python Coprocessor Type Annotation ONLY
+    A 64-bit floating point number.
+    """
+
+    def __repr__(self) -> str:
+        return "f64"
+
+
+class vector(np.ndarray):
+    """
+    A compact Vector with all elements of same Data type.
+    """
+    _datatype: str | None = None
+
+    def __new__(
+        cls,
+        lst,
+        dtype=None
+    ) -> ...:
+        self = np.asarray(lst).view(cls)
+        self._datatype = dtype
+        return self
+
+    def __str__(self) -> str:
+        return "vector({}, \"{}\")".format(super().__str__(), self.datatype())
+
+    def datatype(self):
+        return self._datatype
+
+    def filter(self, lst_bool):
+        return self[lst_bool]
+
+def last(lst):
+    return lst[-1]
+
+def first(lst):
+    return lst[0]
+
+def prev(lst):
+    ret = np.zeros(len(lst))
+    ret[1:] = lst[0:-1]
+    ret[0] = nan
+    return ret
+
+def next(lst):
+    ret = np.zeros(len(lst))
+    ret[:-1] = lst[1:]
+    ret[-1] = nan
+    return ret
+
+def interval(ts: vector, arr: vector, duration: int, func):
+    """
+    Note that this is a mock function with same functionailty to the actual Python Coprocessor
+    `arr` is a vector of integral or temporal type.
+    """
+    start = np.min(ts)
+    end = np.max(ts)
+    masks = [(ts >= i) & (ts <= (i+duration)) for i in range(start, end, duration)]
+    lst_res = [func(arr[mask]) for mask in masks]
+    return lst_res
+
+
+def factor(unit: str) -> int:
+    if unit == "d":
+        return 24 * 60 * 60
+    elif unit == "h":
+        return 60 * 60
+    elif unit == "m":
+        return 60
+    elif unit == "s":
+        return 1
+    else:
+        raise Exception("Only d,h,m,s, found{}".format(unit))
+
+
+def datetime(input_time: str) -> int:
+    """
+    support `d`(day) `h`(hour) `m`(minute) `s`(second)
+
+    support format:
+    `12s` `7d` `12d2h7m`
+    """
+
+    prev = 0
+    cur = 0
+    state = "Num"
+    parse_res = []
+    for idx, ch in enumerate(input_time):
+        if ch.isdigit():
+            cur = idx
+
+            if state != "Num":
+                parse_res.append((state, input_time[prev:cur], (prev, cur)))
+                prev = idx
+                state = "Num"
+        else:
+            cur = idx
+            if state != "Symbol":
+                parse_res.append((state, input_time[prev:cur], (prev, cur)))
+                prev = idx
+                state = "Symbol"
+    parse_res.append((state, input_time[prev:cur+1], (prev, cur+1)))
+
+    cur_idx = 0
+    res_time = 0
+    while cur_idx < len(parse_res):
+        pair = parse_res[cur_idx]
+        if pair[0] == "Num":
+            val = int(pair[1])
+            nxt = parse_res[cur_idx+1]
+            res_time += val * factor(nxt[1])
+            cur_idx += 2
+        else:
+            raise Exception("Two symbol in a row is impossible")
+
+    return res_time
+
+
+def coprocessor(args=None, returns=None, sql=None):
+    """
+    The actual coprocessor, which will connect to database and update
+    whatever function decorated with `@coprocessor(args=[...], returns=[...], sql=...)`
+    """
+    def decorator_copr(func):
+        @functools.wraps(func)
+        def wrapper_do_actual(*args, **kwargs):
+            if len(args)!=0 or len(kwargs)!=0:
+                raise Exception("Expect call with no arguements(for all args are given by coprocessor itself)")
+            source = inspect.getsource(func)
+            url = "http://{}/v1/scripts".format(get_conn_addr())
+            print("Posting to {}".format(url))
+            data = {
+                    "script": source,
+                    "engine": None,
+                }
+
+            res = requests.post(
+                url,
+                headers={"Content-Type": "application/json"},
+                json=data
+            )
+            return res
+        return wrapper_do_actual
+    return decorator_copr
+
+
+# make a alias for short
+copr = coprocessor

component/script/python/greptime/mock.py

@@ -0,0 +1,82 @@
+"""
+Note this is a mock library, if not connected to database, 
+it can only run on mock data and support by numpy
+"""
+from typing import Any
+import numpy as np
+from .greptime import i32,i64,f32,f64, vector, interval, prev, datetime, log, sum, sqrt, pow, nan, copr, coprocessor
+
+import inspect
+import functools
+import ast
+
+
+
+def mock_tester(
+    func,
+    env:dict, 
+    table=None
+):
+    """
+    Mock tester helper function,
+    What it does is replace `@coprocessor` with `@mock_cpor` and add a keyword `env=env`
+    like `@mock_copr(args=...,returns=...,env=env)`
+    """
+    code = inspect.getsource(func)
+    tree = ast.parse(code)
+    tree = HackyReplaceDecorator("env").visit(tree)
+    new_func = tree.body[0]
+    fn_name = new_func.name
+
+    code_obj = compile(tree, "<embedded>", "exec")
+    exec(code_obj)
+
+    ret = eval("{}()".format(fn_name))
+    return ret
+
+def mock_copr(args, returns, sql=None, env:None|dict=None):
+    """
+    This should not be used directly by user
+    """
+    def decorator_copr(func):
+        @functools.wraps(func)
+        def wrapper_do_actual(*fn_args, **fn_kwargs):
+
+            real_args = [env[name] for name in args]
+            ret = func(*real_args)
+            return ret
+        
+        return wrapper_do_actual
+    return decorator_copr
+
+class HackyReplaceDecorator(ast.NodeTransformer):
+    """
+    This class accept a `env` dict for environment to extract args from,
+    and put `env` dict in the param list of `mock_copr` decorator, i.e:
+
+    a `@copr(args=["a", "b"], returns=["c"])` with call like mock_helper(abc, env={"a":2, "b":3})
+    
+    will be transform into `@mock_copr(args=["a", "b"], returns=["c"], env={"a":2, "b":3})`
+    """
+    def __init__(self, env: str) -> None:
+        # just for add `env` keyword
+        self.env = env
+
+    def visit_FunctionDef(self, node: ast.FunctionDef) -> Any:
+        new_node = node
+        decorator_list = new_node.decorator_list
+        if len(decorator_list)!=1:
+            return node
+
+        deco = decorator_list[0]
+        if deco.func.id!="coprocessor" and deco.func.id !="copr":
+            raise Exception("Expect a @copr or @coprocessor, found {}.".format(deco.func.id))
+        deco.func = ast.Name(id="mock_copr", ctx=ast.Load())
+        new_kw = ast.keyword(arg="env", value=ast.Name(id=self.env, ctx=ast.Load()))
+        deco.keywords.append(new_kw)
+
+        # Tie up loose ends in the AST.
+        ast.copy_location(new_node, node)
+        ast.fix_missing_locations(new_node)
+        self.generic_visit(node)
+        return new_node

component/script/python/test.py

@@ -0,0 +1,60 @@
+from example.calc_rv import as_table, calc_rvs
+from greptime import coprocessor, set_conn_addr, get_conn_addr, mock_tester
+import sys
+import json
+import requests
+'''
+To run this script, you need to first start a http server of greptime, and 
+`
+python3 component/script/python/test.py 地址:端口
+`
+
+'''
+@coprocessor(sql='select number from numbers limit 10', args=['number'], returns=['n'])
+def test(n):
+    return n+2
+
+def init_table(close, open_time):
+    req_init = "/v1/sql?sql=create table k_line (close double, open_time bigint, TIME INDEX (open_time))"
+    print(get_db(req_init).text)
+    for c1, c2 in zip(close, open_time):
+        req = "/v1/sql?sql=INSERT INTO k_line(close, open_time) VALUES ({}, {})".format(c1, c2)
+        print(get_db(req).text)
+    print(get_db("/v1/sql?sql=select * from k_line").text)
+
+def get_db(req:str):
+    return requests.get("http://{}{}".format(get_conn_addr(), req))
+
+if __name__ == "__main__":
+    with open("component/script/python/example/kline.json", "r") as kline_file:
+        kline = json.load(kline_file)
+        table = as_table(kline["result"])
+        close = table["close"]
+        open_time = table["open_time"]
+        env = {"close":close, "open_time": open_time}
+
+        res = mock_tester(calc_rvs, env=env)
+        print("Mock result:", [i[0] for i in res])
+        exit()
+    if len(sys.argv)!=2:
+        raise Exception("Expect only one address as cmd's args")
+    set_conn_addr(sys.argv[1])
+    res = test()
+    print(res.headers)
+    print(res.text)
+    with open("component/script/python/example/kline.json", "r") as kline_file:
+        kline = json.load(kline_file)
+        # vec = vector([1,2,3], int)
+        # print(vec, vec.datatype())
+        table = as_table(kline["result"])
+        # print(table)
+        close = table["close"]
+        open_time = table["open_time"]
+        init_table(close, open_time)
+
+        real = calc_rvs()
+        print(real)
+        try:
+            print(real.text["error"])
+        except:
+            print(real.text)

config/datanode.example.toml

@@ -1,89 +1,14 @@
-# Node running mode, see `standalone.example.toml`.
-mode = "distributed"
-# 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
-# Start services after regions have obtained leases.
-# It will block the datanode start if it can't receive leases in the heartbeat from metasrv.
-require_lease_before_startup = false
+http_addr = '0.0.0.0:3000'
+rpc_addr = '0.0.0.0:3001'
+wal_dir = '/tmp/greptimedb/wal'
 
-[heartbeat]
-# Interval for sending heartbeat messages to the Metasrv, 3 seconds by default.
-interval = "3s"
+mysql_addr = '0.0.0.0:3306'
+mysql_runtime_size = 4
 
-# Metasrv client options.
-[meta_client]
-# Metasrv address list.
-metasrv_addrs = ["127.0.0.1:3002"]
-# Heartbeat timeout, 500 milliseconds by default.
-heartbeat_timeout = "500ms"
-# Operation timeout, 3 seconds by default.
-timeout = "3s"
-# Connect server timeout, 1 second by default.
-connect_timeout = "1s"
-# `TCP_NODELAY` option for accepted connections, true by default.
-tcp_nodelay = true
+# applied when postgres feature enbaled
+postgres_addr = '0.0.0.0:5432'
+postgres_runtime_size = 4
 
-# 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"
-
-# Cache configuration for object storage such as 'S3' etc.
-# The local file cache directory
-# cache_path = "/path/local_cache"
-# The local file cache capacity in bytes.
-# cache_capacity = "256MB"
-
-# Mito engine options
-[[region_engine]]
-[region_engine.mito]
-# Number of region workers
-num_workers = 8
-# Request channel size of each worker
-worker_channel_size = 128
-# Max batch size for a worker to handle requests
-worker_request_batch_size = 64
-# Number of meta action updated to trigger a new checkpoint for the manifest
-manifest_checkpoint_distance = 10
-# Whether to compress manifest and checkpoint file by gzip (default false).
-compress_manifest = false
-# Max number of running background jobs
-max_background_jobs = 4
-# Interval to auto flush a region if it has not flushed yet.
-auto_flush_interval = "1h"
-# Global write buffer size for all regions.
-global_write_buffer_size = "1GB"
-# Global write buffer size threshold to reject write requests (default 2G).
-global_write_buffer_reject_size = "2GB"
-# Cache size for SST metadata (default 128MB). Setting it to 0 to disable the cache.
-sst_meta_cache_size = "128MB"
-# Cache size for vectors and arrow arrays (default 512MB). Setting it to 0 to disable the cache.
-vector_cache_size = "512MB"
-# Cache size for pages of SST row groups (default 512MB). Setting it to 0 to disable the cache.
-page_cache_size = "512MB"
-# Buffer size for SST writing.
-sst_write_buffer_size = "8MB"
-
-# Log options, see `standalone.example.toml`
-# [logging]
-# dir = "/tmp/greptimedb/logs"
-# level = "info"
+type = 'File'
+data_dir = '/tmp/greptimedb/data/'

config/frontend.example.toml

@@ -1,79 +1,4 @@
-# Node running mode, see `standalone.example.toml`.
-mode = "distributed"
-
-[heartbeat]
-# Interval for sending heartbeat task to the Metasrv, 5 seconds by default.
-interval = "5s"
-# Interval for retry sending heartbeat task, 5 seconds by default.
-retry_interval = "5s"
-
-# HTTP server options, see `standalone.example.toml`.
-[http]
-addr = "127.0.0.1:4000"
-timeout = "30s"
-body_limit = "64MB"
-
-# gRPC server options, see `standalone.example.toml`.
-[grpc]
-addr = "127.0.0.1:4001"
-runtime_size = 8
-
-# MySQL server options, see `standalone.example.toml`.
-[mysql]
-enable = true
-addr = "127.0.0.1:4002"
-runtime_size = 2
-
-# MySQL server TLS options, see `standalone.example.toml`.
-[mysql.tls]
-mode = "disable"
-cert_path = ""
-key_path = ""
-
-# PostgresSQL server options, see `standalone.example.toml`.
-[postgres]
-enable = true
-addr = "127.0.0.1:4003"
-runtime_size = 2
-
-# PostgresSQL server TLS options, see `standalone.example.toml`.
-[postgres.tls]
-mode = "disable"
-cert_path = ""
-key_path = ""
-
-# OpenTSDB protocol options, see `standalone.example.toml`.
-[opentsdb]
-enable = true
-addr = "127.0.0.1:4242"
-runtime_size = 2
-
-# InfluxDB protocol options, see `standalone.example.toml`.
-[influxdb]
-enable = true
-
-# Prometheus remote storage options, see `standalone.example.toml`.
-[prom_store]
-enable = true
-
-# Metasrv client options, see `datanode.example.toml`.
-[meta_client]
-metasrv_addrs = ["127.0.0.1:3002"]
-timeout = "3s"
-# DDL timeouts options.
-ddl_timeout = "10s"
-connect_timeout = "1s"
-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
+http_addr = '0.0.0.0:4000'
+grpc_addr = '0.0.0.0:4001'
+mysql_addr = '0.0.0.0:4003'
+mysql_runtime_size = 4

config/metasrv.example.toml

@@ -1,44 +0,0 @@
-# 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 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"
-
-# Failure detectors options.
-[failure_detector]
-threshold = 8.0
-min_std_deviation = "100ms"
-acceptable_heartbeat_pause = "3000ms"
-first_heartbeat_estimate = "1000ms"
-
-# # Datanode options.
-# [datanode]
-# # Datanode client options.
-# [datanode.client_options]
-# timeout = "10s"
-# connect_timeout = "10s"
-# tcp_nodelay = true

config/standalone.example.toml

@@ -1,166 +0,0 @@
-# Node running mode, "standalone" or "distributed".
-mode = "standalone"
-# Whether to enable greptimedb telemetry, true by default.
-enable_telemetry = true
-
-# HTTP server options.
-[http]
-# 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"
-
-# gRPC server options.
-[grpc]
-# 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]
-# Whether to enable
-enable = true
-# 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
-
-# MySQL server TLS options.
-[mysql.tls]
-# TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
-# - "disable" (default value)
-# - "prefer"
-# - "require"
-# - "verify-ca"
-# - "verify-full"
-mode = "disable"
-# Certificate file path.
-cert_path = ""
-# Private key file path.
-key_path = ""
-
-# PostgresSQL server options.
-[postgres]
-# Whether to enable
-enable = true
-# 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
-
-# PostgresSQL server TLS options, see `[mysql_options.tls]` section.
-[postgres.tls]
-# TLS mode.
-mode = "disable"
-# certificate file path.
-cert_path = ""
-# private key file path.
-key_path = ""
-
-# OpenTSDB protocol options.
-[opentsdb]
-# Whether to enable
-enable = true
-# OpenTSDB telnet API server address, "127.0.0.1:4242" by default.
-addr = "127.0.0.1:4242"
-# The number of server worker threads, 2 by default.
-runtime_size = 2
-
-# InfluxDB protocol options.
-[influxdb]
-# Whether to enable InfluxDB protocol in HTTP API, true by default.
-enable = true
-
-# Prometheus remote storage options
-[prom_store]
-# 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
-
-# Metadata storage options.
-[metadata_store]
-# Kv file size in bytes.
-file_size = "256MB"
-# Kv purge threshold.
-purge_threshold = "4GB"
-
-# Procedure storage options.
-[procedure]
-# Procedure max retry time.
-max_retry_times = 3
-# Initial retry delay of procedures, increases exponentially
-retry_delay = "500ms"
-
-# 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"
-# Cache configuration for object storage such as 'S3' etc.
-# cache_path = "/path/local_cache"
-# The local file cache capacity in bytes.
-# cache_capacity = "256MB"
-
-# Mito engine options
-[[region_engine]]
-[region_engine.mito]
-# Number of region workers
-num_workers = 8
-# Request channel size of each worker
-worker_channel_size = 128
-# Max batch size for a worker to handle requests
-worker_request_batch_size = 64
-# Number of meta action updated to trigger a new checkpoint for the manifest
-manifest_checkpoint_distance = 10
-# Whether to compress manifest and checkpoint file by gzip (default false).
-compress_manifest = false
-# Max number of running background jobs
-max_background_jobs = 4
-# Interval to auto flush a region if it has not flushed yet.
-auto_flush_interval = "1h"
-# Global write buffer size for all regions.
-global_write_buffer_size = "1GB"
-# Global write buffer size threshold to reject write requests (default 2G).
-global_write_buffer_reject_size = "2GB"
-# Cache size for SST metadata (default 128MB). Setting it to 0 to disable the cache.
-sst_meta_cache_size = "128MB"
-# Cache size for vectors and arrow arrays (default 512MB). Setting it to 0 to disable the cache.
-vector_cache_size = "512MB"
-# Cache size for pages of SST row groups (default 512MB). Setting it to 0 to disable the cache.
-page_cache_size = "512MB"
-# Buffer size for SST writing.
-sst_write_buffer_size = "8MB"
-
-# Log options
-# [logging]
-# Specify logs directory.
-# dir = "/tmp/greptimedb/logs"
-# Specify the log level [info | debug | error | warn]
-# level = "info"
-# whether enable tracing, default is false
-# enable_otlp_tracing = false
-# tracing exporter endpoint with format `ip:port`, we use grpc oltp as exporter, default endpoint is `localhost:4317`
-# otlp_endpoint = "localhost:4317"
-# The percentage of tracing will be sampled and exported. Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1. ratio > 1 are treated as 1. Fractions < 0 are treated as 0
-# tracing_sample_ratio = 1.0

docker/Dockerfile

@@ -0,0 +1,32 @@
+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/:$PATH
+
+# Build the project in release mode.
+COPY . .
+RUN cargo build --release
+
+# Export the binary to the clean image.
+# TODO(zyy17): Maybe should use the more secure container image.
+FROM ubuntu:22.04 as base
+
+WORKDIR /greptimedb
+COPY --from=builder /greptimedb/target/release/greptime /greptimedb/bin/
+ENV PATH /greptimedb/bin/:$PATH
+
+ENTRYPOINT [ "greptime" ]
+CMD [ "datanode", "start"]

docker/buildx/centos/Dockerfile

@@ -1,54 +0,0 @@
-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

@@ -1,62 +0,0 @@
-FROM ubuntu:20.04 as builder
-
-ARG CARGO_PROFILE
-ARG FEATURES
-ARG OUTPUT_DIR
-
-ENV LANG en_US.utf8
-WORKDIR /greptimedb
-
-# Add PPA for Python 3.10.
-RUN apt-get update && \
-    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa -y
-
-# 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/centos/Dockerfile

@@ -1,16 +0,0 @@
-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

@@ -1,20 +0,0 @@
-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/android/Dockerfile

@@ -1,41 +0,0 @@
-FROM --platform=linux/amd64 saschpe/android-ndk:34-jdk17.0.8_7-ndk25.2.9519653-cmake3.22.1
-
-ENV LANG en_US.utf8
-WORKDIR /greptimedb
-
-# Rename libunwind to libgcc
-RUN cp ${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/lib64/clang/14.0.7/lib/linux/aarch64/libunwind.a ${NDK_ROOT}/toolchains/llvm/prebuilt/linux-x86_64/lib64/clang/14.0.7/lib/linux/aarch64/libgcc.a
-
-# Install dependencies.
-RUN apt-get update && apt-get install -y \
-    libssl-dev \
-    protobuf-compiler \
-    curl \
-    git \
-    build-essential \
-    pkg-config \
-    python3 \
-    python3-dev \
-    python3-pip \
-    && pip3 install --upgrade pip \
-    && pip3 install pyarrow
-
-# Trust workdir
-RUN git config --global --add safe.directory /greptimedb
-
-# Install Rust.
-SHELL ["/bin/bash", "-c"]
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --no-modify-path --default-toolchain none -y
-ENV PATH /root/.cargo/bin/:$PATH
-
-# Add android toolchains
-ARG RUST_TOOLCHAIN
-RUN rustup toolchain install ${RUST_TOOLCHAIN}
-RUN rustup target add aarch64-linux-android
-
-# Install cargo-ndk
-RUN cargo install cargo-ndk
-ENV ANDROID_NDK_HOME $NDK_ROOT
-
-# Builder entrypoint.
-CMD ["cargo", "ndk", "--platform", "23", "-t", "aarch64-linux-android", "build", "--bin", "greptime", "--profile", "release", "--no-default-features"]

docker/dev-builder/centos/Dockerfile

@@ -1,29 +0,0 @@
-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

@@ -1,46 +0,0 @@
-FROM ubuntu:20.04
-
-ENV LANG en_US.utf8
-WORKDIR /greptimedb
-
-# Add PPA for Python 3.10.
-RUN apt-get update && \
-    DEBIAN_FRONTEND=noninteractive apt-get install -y software-properties-common && \
-    add-apt-repository ppa:deadsnakes/ppa -y
-
-# 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
-
-# Remove Python 3.8 and install pip.
-RUN apt-get -y purge python3.8 && \
-    apt-get -y autoremove && \
-    ln -s /usr/bin/python3.10 /usr/bin/python3 && \
-    curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
-
-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/dev-builder/ubuntu/Dockerfile-18.10

@@ -1,47 +0,0 @@
-# Use the legacy glibc 2.28.
-FROM ubuntu:18.10
-
-ENV LANG en_US.utf8
-WORKDIR /greptimedb
-
-# Use old-releases.ubuntu.com to avoid 404s: https://help.ubuntu.com/community/EOLUpgrades.
-RUN echo "deb http://old-releases.ubuntu.com/ubuntu/ cosmic main restricted universe multiverse\n\
-deb http://old-releases.ubuntu.com/ubuntu/ cosmic-updates main restricted universe multiverse\n\
-deb http://old-releases.ubuntu.com/ubuntu/ cosmic-security main restricted universe multiverse" > /etc/apt/sources.list
-
-# Install dependencies.
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-    libssl-dev \
-    tzdata \
-    curl \
-    ca-certificates \
-    git \
-    build-essential \
-    unzip \
-    pkg-config
-
-# Install protoc.
-ENV PROTOC_VERSION=25.1
-RUN if [ "$(uname -m)" = "x86_64" ]; then \
-        PROTOC_ZIP=protoc-${PROTOC_VERSION}-linux-x86_64.zip; \
-    elif [ "$(uname -m)" = "aarch64" ]; then \
-        PROTOC_ZIP=protoc-${PROTOC_VERSION}-linux-aarch_64.zip; \
-    else \
-        echo "Unsupported architecture"; exit 1; \
-    fi && \
-    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/${PROTOC_ZIP} && \
-    unzip -o ${PROTOC_ZIP} -d /usr/local bin/protoc && \
-    unzip -o ${PROTOC_ZIP} -d /usr/local 'include/*' && \
-    rm -f ${PROTOC_ZIP}
-
-# Install Rust.
-SHELL ["/bin/bash", "-c"]
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- --no-modify-path --default-toolchain none -y
-ENV PATH /root/.cargo/bin/:$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

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

docs/benchmarks/tsbs/v0.3.2.md

@@ -1,39 +0,0 @@
-# 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/benchmarks/tsbs/v0.4.0.md

@@ -1,61 +0,0 @@
-# TSBS benchmark - v0.4.0
-
-## Environment
-
-### Local
-|        |                                    |
-| ------ | ---------------------------------- |
-| CPU    | AMD Ryzen 7 7735HS (8 core 3.2GHz) |
-| Memory | 32GB                               |
-| Disk   | SOLIDIGM SSDPFKNU010TZ             |
-| OS     | Ubuntu 22.04.2 LTS                 |
-
-### Aliyun amd64
-
-|         |                |
-| ------- | -------------- |
-| Machine | ecs.g7.4xlarge |
-| CPU     | 16 core        |
-| Memory  | 64GB           |
-| Disk    | 100G           |
-| OS      | Ubuntu  22.04  |
-
-### Aliyun arm64
-
-|         |                   |
-| ------- | ----------------- |
-| Machine | ecs.g8y.4xlarge   |
-| CPU     | 16 core           |
-| Memory  | 64GB              |
-| Disk    | 100G              |
-| OS      | Ubuntu  22.04 ARM |
-
-
-## Write performance
-
-| Environment        | Ingest rate（rows/s） |
-| ------------------ | --------------------- |
-| Local              | 365280.60             |
-| Aliyun g7.4xlarge  | 341368.72             |
-| Aliyun g8y.4xlarge | 320907.29             |
-
-
-## Query performance
-
-| Query type            | Local (ms) | Aliyun g7.4xlarge (ms) | Aliyun g8y.4xlarge (ms) |
-| --------------------- | ---------- | ---------------------- | ----------------------- |
-| cpu-max-all-1         | 50.70      | 31.46                  | 47.61                   |
-| cpu-max-all-8         | 262.16     | 129.26                 | 152.43                  |
-| double-groupby-1      | 2512.71    | 1408.19                | 1586.10                 |
-| double-groupby-5      | 3896.15    | 2304.29                | 2585.29                 |
-| double-groupby-all    | 5404.67    | 3337.61                | 3773.91                 |
-| groupby-orderby-limit | 3786.98    | 2065.72                | 2312.57                 |
-| high-cpu-1            | 71.96      | 37.29                  | 54.01                   |
-| high-cpu-all          | 9468.75    | 7595.69                | 8467.46                 |
-| lastpoint             | 13379.43   | 11253.76               | 12949.40                |
-| single-groupby-1-1-1  | 20.72      | 12.16                  | 13.35                   |
-| single-groupby-1-1-12 | 28.53      | 15.67                  | 21.62                   |
-| single-groupby-1-8-1  | 72.23      | 37.90                  | 43.52                   |
-| single-groupby-5-1-1  | 26.75      | 15.59                  | 17.48                   |
-| single-groupby-5-1-12 | 45.41      | 22.90                  | 31.96                   |
-| single-groupby-5-8-1  | 107.96     | 59.76                  | 69.58                   |

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

@@ -1,74 +0,0 @@
-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/how-to/how-to-write-aggregate-function.md

@@ -55,7 +55,7 @@ The DataFusion basically execute aggregate like this:
 2. Call `update_batch` on each accumulator with partitioned data, to let you update your aggregate calculation.
 3. Call `state` to get each accumulator's internal state, the medial calculation result.
 4. Call `merge_batch` to merge all accumulator's internal state to one.
-5. Execute `evaluate` on the chosen one to get the final calculation result.
+5. Execute `evalute` on the chosen one to get the final calculation result.
 
 Once you know the meaning of each method, you can easily write your accumulator. You can refer to `Median` accumulator or `SUM` accumulator defined in  file `my_sum_udaf_example.rs` for more details.
 
@@ -63,7 +63,7 @@ Once you know the meaning of each method, you can easily write your accumulator.
 
 You can call `register_aggregate_function` method in query engine to register your aggregate function. To do that, you have to new an instance of struct `AggregateFunctionMeta`. The struct has three fields, first is the name of your aggregate function's name. The function name is case-sensitive due to DataFusion's restriction. We strongly recommend using lowercase for your name. If you have to use uppercase name, wrap your aggregate function with quotation marks. For example, if you define an aggregate function named "my_aggr", you can use "`SELECT MY_AGGR(x)`"; if you define "my_AGGR", you have to use "`SELECT "my_AGGR"(x)`".
 
-The second field is arg_counts ,the count of the arguments. Like accumulator `percentile`, calculating the p_number of the column. We need to input the value of column and the value of p to cacalate, and so the count of the arguments is two.
+The second field is arg_counts ,the count of the arguments. Like accumulator `percentile`, caculating the p_number of the column. We need to input the value of column and the value of p to cacalate, and so the count of the arguments is two.
 
 The third field is a function about how to create your accumulator creator that you defined in step 1 above. Create creator, that's a bit intertwined, but it is how we make DataFusion use a newly created aggregate function each time it executes a SQL, preventing the stored input types from affecting each other. The key detail can be starting looking at our `DfContextProviderAdapter` struct's `get_aggregate_meta` method.
 

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

@@ -1,175 +0,0 @@
----
-Feature Name: "promql-in-rust"
-Tracking Issue: https://github.com/GreptimeTeam/greptimedb/issues/596
-Date: 2022-12-20
-Author: "Ruihang Xia <waynestxia@gmail.com>"
----
-
-Rewrite PromQL in Rust
-----------------------
-
-# Summary
-A Rust native implementation of PromQL, for GreptimeDB.
-
-# Motivation
-Prometheus and its query language PromQL prevails in the cloud-native observability area, which is an important scenario for time series database like GreptimeDB. We already have support for its remote read and write protocols. Users can now integrate GreptimeDB as the storage backend to existing Prometheus deployment, but cannot run PromQL query directly on GreptimeDB like SQL.
-
-This RFC proposes to add support for PromQL. Because it was created in Go, we can't use the existing code easily. For interoperability, performance and extendability, porting its logic to Rust is a good choice.
-
-# Details
-
-## Overview
-One of the goals is to make use of our existing basic operators, execution model and runtime to reduce the work. So the entire proposal is built on top of Apache Arrow DataFusion. The rewrote PromQL logic is manifested as `Expr` or `Execution Plan` in DataFusion. And both the intermediate data structure and the result is in the format of `Arrow`'s `RecordBatch`.
-
-The following sections are organized in a top-down manner. Starts with evaluation procedure. Then introduces the building blocks of our new PromQL operation. Follows by an explanation of data model. And end with an example logic plan.
-
-*This RFC is heavily related to Prometheus and PromQL. It won't repeat some basic concepts of them.*
-
-## Evaluation
-
-The original implementation is like an interpreter of parsed PromQL AST. It has two characteristics: (1) Operations are evaluated in place after they are parsed to AST. And some key parameters are separated from the AST because they do not present in the query, but come from other places like another field in the HTTP payload. (2) calculation is performed per timestamp. You can see this pattern many times:
-```go
-for ts := ev.startTimestamp; ts <= ev.endTimestamp; ts += ev.interval {}
-```
-
-These bring out two differences in the proposed implementation. First, to make it more general and clear, the evaluation procedure is reorganized into serval phases (and is the same as DataFusion's). And second, data are evaluated by time series (corresponding to "columnar calculation", if think timestamp as row number).
-
-```
-                                      Logic
-   Query             AST              Plan
- ─────────► Parser ───────► Logical ────────► Physical ────┐
-                            Planner           Planner      │
-                                                           │
- ◄───────────────────────────── Executor  ◄────────────────┘
-        Evaluation Result                     Execution
-                                                Plan
-```
-
-- Parser 
-
-    Provided by [`promql-parser`](https://github.com/GreptimeTeam/promql-parser) crate. Same as the original implementation.
-
-- Logical Planner
-
-    Generates a logical plan with all the needed parameters. It should accept something like `EvalStmt` in Go's implementation, which contains query time range, evaluation interval and lookback range.
-
-    Another important thing done here is assembling the logic plan, with all the operations baked into logically. Like what's the filter and time range to read, how the data then flows through a selector into a binary operation, etc. Or what's the output schema of every single step. The generated logic plan is deterministic without variables, and can be `EXPLAIN`ed clearly.
-
-- Physical Planner
-
-    This step converts a logic plan into evaluatable execution plan. There are not many special things like the previous step. Except when a query is going to be executed distributedly. In this case, a logic plan will be divided into serval parts and sent to serval nodes. One physical planner only sees its own part.
-
-- Executor
-
-    As its name shows, this step calculates data to result. And all new calculation logic, the implementation of PromQL in rust, is placed here. And the rewrote functions are using `RecordBatch` and `Array` from `Arrow` as the intermediate data structure.
-
-    Each "batch" contains only data from single time series. This is from the underlying storage implementation. Though it's not a requirement of this RFC, having this property can simplify some functions.
-    
-    Another thing to mention is the rewrote functions don't aware of timestamp or value columns, they are defined only based on the input data types. For example, `increase()` function in PromQL calculates the unbiased delta of data, its implementation here only does this single thing. Let's compare the signature of two implementations:
-
-    - Go
-        ```go
-        func funcIncrease(vals []parser.Value, args parser.Expressions) Vector {}
-        ```
-    - Rust
-        ```rust
-        fn prom_increase(input: Array) -> Array {}
-        ```
-
-    Some unimportant parameters are omitted. The original Go version only writes the logic for `Point`'s value, either float or histogram. But the proposed rewritten one accepts a generic `Array` as input, which can be any type that suits, from `i8` to `u64` to `TimestampNanosecond`.
-
-## Plan and Expression
-
-They are structures to express logic from PromQL. The proposed implementation is built on top of DataFusion, thus our plan and expression are in form of `ExtensionPlan` and `ScalarUDF`. The only difference between them in this context is the return type: plan returns a record batch while expression returns a single column.
-
-This RFC proposes to add four new plans, they are fundamental building blocks that mainly handle data selection logic in PromQL, for the following calculation expressions. 
-
-- `SeriesNormalize`
-
-    Sort data inside one series on the timestamp column, and bias "offset" if has. This plan usually comes after `TableScan` (or `TableScan` and `Filter`) plan.
-
-- `VectorManipulator` and `MatrixManipulator`
-
-    Corresponding to `InstantSelector` and `RangeSelector`. We don't calculate timestamp by timestamp, thus use "vector" instead of "instant", this image shows the difference. And "matrix" is another name for "range vector", for not confused with our "vector". The following section will detail how they are implemented using Arrow.
-
-    ![instant_and_vector](instant-and-vector.png)
-
-    Due to "interval" parameter in PromQL, data after "selector" (or "manipulator" here) are usually shorter than input. And we have to modify the entire record batch to shorten both timestamp, value and tag columns. So they are formed as plan.
-
-- `PromAggregator`
-
-    The carrier of aggregator expressions. This should not be very different from the DataFusion built-in `Aggregate` plan, except PromQL can use "group without" to do reverse selection.
-
-PromQL has around 70 expressions and functions. But luckily we can reuse lots of them from DataFusion. Like unary expression, binary expression and aggregator. We only need to implement those PromQL-specific expressions, like `rate` or `percentile`. The following table lists some typical functions in PromQL, and their signature in the proposed implementation. Other function should be the same.
-
-| Name               	| In Param(s)                                          	| Out Param(s) 	| Explain            	|
-|--------------------	|------------------------------------------------------	|--------------	|--------------------	|
-| instant_delta      	| Matrix T                                             	| Array T      	| idelta in PromQL   	|
-| increase           	| Matrix T                                             	| Array T      	| increase in PromQL 	|
-| extrapolate_factor 	| - Matrix T<br>- Array Timestamp<br>- Array Timestamp 	| Array T      	| *                   	|
-
-*: *`extrapolate_factor` is one of the "dark sides" in PromQL. In short it's a translation of this [paragraph](https://github.com/prometheus/prometheus/blob/0372e259baf014bbade3134fd79bcdfd8cbdef2c/promql/functions.go#L134-L159)*
-
-To reuse those common calculation logic, we can break them into serval expressions, and assemble in the logic planning phase. Like `rate()` in PromQL can be represented as `increase / extrapolate_factor`.
-
-## Data Model
-
-This part explains how data is represented. Following the data model in GreptimeDB, all the data are stored as table, with tag columns, timestamp column and value column. Table to record batch is very straightforward. So an instant vector can be thought of as a row (though as said before, we don't use instant vectors) in the table. Given four basic types in PromQL: scalar, string, instant vector and range vector, only the last "range vector" need some tricks to adapt our columnar calculation.
-
-Range vector is some sort of matrix, it's consisted of small one-dimension vectors, with each being an input of range function. And, applying range function to a range vector can be thought of kind of convolution.
-
-![range-vector-with-matrix](range-vector-with-matrix.png)
-
-(Left is an illustration of range vector. Notice the Y-axis has no meaning, it's just put different pieces separately. The right side is an imagined "matrix" as range function. Multiplying the left side to it can get a one-dimension "matrix" with four elements. That's the evaluation result of a range vector.)
-
-To adapt this range vector to record batch, it should be represented by a column. This RFC proposes to use `DictionaryArray` from Arrow to represent range vector, or `Matrix`. This is "misusing" `DictionaryArray` to ship some additional information about an array. Because the range vector is sliding over one series, we only need to know the `offset` and `length` of each slides to reconstruct the matrix from an array:
-
-![matrix-from-array](matrix-from-array.png)
-
-The length is not fixed, it depends on the input's timestamp. An PoC implementation of `Matrix` and `increase()` can be found in [this repo](https://github.com/waynexia/corroding-prometheus).
-
-## Example
-
-The logic plan of PromQL query
-```promql
-# start: 2022-12-20T10:00:00
-# end: 2022-12-21T10:00:00
-# interval: 1m
-# lookback: 30s
-sum (rate(request_duration[5m])) by (idc)
-```
-looks like
-
-<!-- title: 'PromAggregator: \naggr = sum, column = idc'
-operator: prom
-inputs:
-- title: 'Matrix Manipulator: \ninterval = 1m, range = 5m, expr = div(increase(value), extrapolate_factor(timestamp))'
-  operator: prom
-  inputs:
-  - title: 'Series Normalize: \noffset = 0'
-    operator: prom
-    inputs:
-    - title: 'Filter: \ntimestamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
-      operator: filter
-      inputs:
-      - title: 'Table Scan: \ntable = request_duration, timestamp > 2022-12-20T10:00:00 && timestamp < 2022-12-21T10:00:00'
-        operator: scan -->
-
-![example](example.png)
-
-# Drawbacks
-
-Human-being is always error-prone. It's harder to endeavor to rewrite from the ground and requires more attention to ensure correctness, than translate line-by-line. And, since the evaluator's architecture are different, it might be painful to catch up with PromQL's breaking update (if any) in the future.
-
-Misusing Arrow's DictionaryVector as Matrix is another point. This hack needs some `unsafe` function call to bypass Arrow's check. And though Arrow's API is stable, this is still an undocumented behavior.
-
-# Alternatives
-
-There are a few alternatives we've considered:
-- Wrap the existing PromQL's implementation via FFI, and import it to GreptimeDB.
-- Translate its evaluator engine line-by-line, rather than rewrite one.
-- Integrate the Prometheus server into GreptimeDB via RPC, making it a detached execution engine for PromQL.
-
-The first and second options are making a separate execution engine in GreptimeDB, they may alleviate the pain during rewriting, but will have negative impacts to afterward evolve like resource management. And introduce another deploy component in the last option will bring a complex deploy architecture.
-
-And all of them are more or less redundant in data transportation that affects performance and resources. The proposed built-in executing procedure is also easy to integrate and expose to the existing SQL interface GreptimeDB currently provides. Some concepts in PromQL like sliding windows (range vector in PromQL) are very convenient and ergonomic in analyzing series data. This makes it not only a PromQL evaluator, but also an enhancement to our query system.

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

@@ -1,151 +0,0 @@
----
-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

@@ -1,92 +0,0 @@
----
-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

@@ -1,196 +0,0 @@
----
-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

@@ -1,174 +0,0 @@
----
-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

@@ -1,137 +0,0 @@
----
-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.