Merge branch 'main' into create-view

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

.env.example

@@ -24,7 +24,3 @@ GT_KAFKA_ENDPOINTS = localhost:9092
 
 # Setting for fuzz tests
 GT_MYSQL_ADDR = localhost:4002
-
-# Setting for unstable fuzz tests
-GT_FUZZ_BINARY_PATH=/path/to/
-GT_FUZZ_INSTANCE_ROOT_DIR=/tmp/unstable_greptime

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,7 +1,7 @@
 ---
 name: Bug report
 description: Is something not working? Help us fix it!
-labels: [ "C-bug" ]
+labels: [ "bug" ]
 body:
   - type: markdown
     attributes:

.github/ISSUE_TEMPLATE/config.yml

@@ -4,5 +4,5 @@ contact_links:
     url: https://greptime.com/slack
     about: Get free help from the Greptime community
   - name: Greptime Community Discussion
-    url: https://github.com/greptimeTeam/discussions
+    url: https://github.com/greptimeTeam/greptimedb/discussions
     about: Get free help from the Greptime community

.github/ISSUE_TEMPLATE/enhancement.yml

@@ -1,7 +1,7 @@
 ---
 name: Enhancement
 description: Suggest an enhancement to existing functionality
-labels: [ "C-enhancement" ]
+labels: [ "enhancement" ]
 body:
   - type: dropdown
     id: type

.github/ISSUE_TEMPLATE/feature_request.yml

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

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

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

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

@@ -22,15 +22,15 @@ inputs:
   build-dev-builder-ubuntu:
     description: Build dev-builder-ubuntu image
     required: false
-    default: "true"
+    default: 'true'
   build-dev-builder-centos:
     description: Build dev-builder-centos image
     required: false
-    default: "true"
+    default: 'true'
   build-dev-builder-android:
     description: Build dev-builder-android image
     required: false
-    default: "true"
+    default: 'true'
 runs:
   using: composite
   steps:
@@ -47,7 +47,7 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=ubuntu \
-          BUILDX_MULTI_PLATFORM_BUILD=all \
+          BUILDX_MULTI_PLATFORM_BUILD=true \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
           IMAGE_TAG=${{ inputs.version }}
@@ -58,7 +58,7 @@ runs:
       run: |
         make dev-builder \
           BASE_IMAGE=centos \
-          BUILDX_MULTI_PLATFORM_BUILD=amd64 \
+          BUILDX_MULTI_PLATFORM_BUILD=true \
           IMAGE_REGISTRY=${{ inputs.dockerhub-image-registry }} \
           IMAGE_NAMESPACE=${{ inputs.dockerhub-image-namespace }} \
           IMAGE_TAG=${{ inputs.version }}
@@ -72,5 +72,5 @@ runs:
           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

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

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

@@ -16,7 +16,7 @@ inputs:
   dev-mode:
     description: Enable dev mode, only build standard greptime
     required: false
-    default: "false"
+    default: 'false'
   working-dir:
     description: Working directory to build the artifacts
     required: false
@@ -30,9 +30,7 @@ runs:
       # NOTE: If the BUILD_JOBS > 4, it's always OOM in EC2 instance.
       run: |
         cd ${{ inputs.working-dir }} && \
-        make run-it-in-container BUILD_JOBS=4 \
-        IMAGE_NAMESPACE=i8k6a5e1/greptime \
-        IMAGE_REGISTRY=public.ecr.aws
+        make run-it-in-container BUILD_JOBS=4
 
     - name: Upload sqlness logs
       if: ${{ failure() && inputs.disable-run-tests == 'false' }} # Only upload logs when the integration tests failed.
@@ -51,8 +49,6 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-pyo3-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime        
 
     - name: Build greptime without pyo3
       if: ${{ inputs.dev-mode == 'false' }}
@@ -64,8 +60,6 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime
 
     - 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
@@ -74,7 +68,7 @@ runs:
 
     - name: Build greptime on centos base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds greptime for centos if the host machine is amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build centos7 base image for amd64.
       with:
         base-image: centos
         features: servers/dashboard
@@ -82,17 +76,13 @@ runs:
         artifacts-dir: greptime-linux-${{ inputs.arch }}-centos-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime
 
     - name: Build greptime on android base image
       uses: ./.github/actions/build-greptime-binary
-      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds arm64 greptime binary for android if the host machine amd64.
+      if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Only build android base image on amd64.
       with:
         base-image: android
         artifacts-dir: greptime-android-arm64-${{ inputs.version }}
         version: ${{ inputs.version }}
         working-dir: ${{ inputs.working-dir }}
         build-android-artifacts: true
-        image-registry: public.ecr.aws
-        image-namespace: i8k6a5e1/greptime

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

@@ -59,15 +59,9 @@ runs:
       if: ${{ inputs.disable-run-tests == 'false' }}
       uses: taiki-e/install-action@nextest
 
-    # Get proper backtraces in mac Sonoma. Currently there's an issue with the new
-    # linker that prevents backtraces from getting printed correctly.
-    #
-    # <https://github.com/rust-lang/rust/issues/113783> 
     - name: Run integration tests
       if: ${{ inputs.disable-run-tests == 'false' }}
       shell: bash
-      env: 
-        CARGO_BUILD_RUSTFLAGS: "-Clink-arg=-Wl,-ld_classic"
       run: |
         make test sqlness-test
 
@@ -81,8 +75,6 @@ runs:
 
     - name: Build greptime binary
       shell: bash
-      env: 
-        CARGO_BUILD_RUSTFLAGS: "-Clink-arg=-Wl,-ld_classic"
       run: |
         make build \
         CARGO_PROFILE=${{ inputs.cargo-profile }} \

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

@@ -26,6 +26,8 @@ runs:
   using: composite
   steps:
     - uses: arduino/setup-protoc@v3
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
 
     - name: Install rust toolchain
       uses: dtolnay/rust-toolchain@master
@@ -59,9 +61,6 @@ runs:
       if: ${{ inputs.disable-run-tests == 'false' }}
       shell: pwsh
       run: make test sqlness-test
-      env:
-        RUSTUP_WINDOWS_PATH_ADD_BIN: 1 # Workaround for https://github.com/nextest-rs/nextest/issues/1493
-        RUST_BACKTRACE: 1
 
     - name: Upload sqlness logs
       if: ${{ failure() }} # Only upload logs when the integration tests failed.

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

@@ -3,17 +3,11 @@ description: 'Fuzz test given setup and service'
 inputs:
   target:
     description: "The fuzz target to test"
-    required: true
-  max-total-time:
-    description: "Max total time(secs)"
-    required: true
-  unstable:
-    default: 'false'
-    description: "Enable unstable feature"
 runs:
   using: composite
   steps:
   - name: Run Fuzz Test
     shell: bash
-    run: cargo fuzz run ${{ inputs.target }} --fuzz-dir tests-fuzz -D -s none ${{ inputs.unstable == 'true' && '--features=unstable' || '' }} -- -max_total_time=${{ inputs.max-total-time }}
-
+    run: cargo fuzz run ${{ inputs.target }} --fuzz-dir tests-fuzz -D -s none -- -max_total_time=120
+    env:
+      GT_MYSQL_ADDR: 127.0.0.1:4002

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

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

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

@@ -1,16 +0,0 @@
-name: Setup cyborg environment
-description: Setup cyborg environment
-runs:
-  using: composite
-  steps:
-    - uses: actions/setup-node@v4
-      with:
-        node-version: 22
-    - uses: pnpm/action-setup@v3
-      with:
-        package_json_file: 'cyborg/package.json'
-        run_install: true
-    - name: Describe the Environment
-      working-directory: cyborg
-      shell: bash
-      run: pnpm tsx -v

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

@@ -1,25 +0,0 @@
-name: Setup Etcd cluster
-description: Deploy Etcd cluster on Kubernetes
-inputs:
-  etcd-replicas:
-    default: 3
-    description: "Etcd replicas"
-  namespace:
-    default: "etcd-cluster"
-
-runs:
-  using: composite
-  steps:
-  - name: Install Etcd cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install etcd oci://registry-1.docker.io/bitnamicharts/etcd \
-        --set replicaCount=${{ inputs.etcd-replicas }} \
-        --set resources.requests.cpu=50m \
-        --set resources.requests.memory=128Mi \
-        --set auth.rbac.create=false \
-        --set auth.rbac.token.enabled=false \
-        --set persistence.size=2Gi \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

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

@@ -1,91 +0,0 @@
-name: Setup GreptimeDB cluster
-description: Deploy GreptimeDB cluster on Kubernetes
-inputs:
-  frontend-replicas:
-    default: 2
-    description: "Number of Frontend replicas"
-  datanode-replicas:
-    default: 2
-    description: "Number of Datanode replicas"
-  meta-replicas:
-    default: 3
-    description: "Number of Metasrv replicas"
-  image-registry: 
-    default: "docker.io"
-    description: "Image registry"
-  image-repository: 
-    default: "greptime/greptimedb"
-    description: "Image repository"
-  image-tag: 
-    default: "latest"
-    description: 'Image tag'
-  etcd-endpoints:
-    default: "etcd.etcd-cluster.svc.cluster.local:2379"
-    description: "Etcd endpoints"
-  values-filename:
-    default: "with-minio.yaml"
-  enable-region-failover:
-    default: false
-
-runs:
-  using: composite
-  steps:
-  - name: Install GreptimeDB operator
-    shell: bash
-    run: |
-      helm repo add greptime https://greptimeteam.github.io/helm-charts/ 
-      helm repo update
-      helm upgrade \
-        --install \
-        --create-namespace \
-        greptimedb-operator greptime/greptimedb-operator \
-        -n greptimedb-admin \
-        --wait \
-        --wait-for-jobs
-  - name: Install GreptimeDB cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install my-greptimedb \
-        --set meta.etcdEndpoints=${{ inputs.etcd-endpoints }} \
-        --set meta.enableRegionFailover=${{ inputs.enable-region-failover }} \
-        --set image.registry=${{ inputs.image-registry }} \
-        --set image.repository=${{ inputs.image-repository }}  \
-        --set image.tag=${{ inputs.image-tag }} \
-        --set base.podTemplate.main.resources.requests.cpu=50m \
-        --set base.podTemplate.main.resources.requests.memory=256Mi \
-        --set base.podTemplate.main.resources.limits.cpu=1000m \
-        --set base.podTemplate.main.resources.limits.memory=2Gi \
-        --set frontend.replicas=${{ inputs.frontend-replicas }} \
-        --set datanode.replicas=${{ inputs.datanode-replicas }} \
-        --set meta.replicas=${{ inputs.meta-replicas }} \
-        greptime/greptimedb-cluster \
-        --create-namespace \
-        -n my-greptimedb \
-        --values ./.github/actions/setup-greptimedb-cluster/${{ inputs.values-filename }} \
-        --wait \
-        --wait-for-jobs
-  - name: Wait for GreptimeDB
-    shell: bash
-    run: |
-      while true; do 
-        PHASE=$(kubectl -n my-greptimedb get gtc my-greptimedb -o jsonpath='{.status.clusterPhase}')
-        if [ "$PHASE" == "Running" ]; then
-          echo "Cluster is ready"
-          break
-        else
-          echo "Cluster is not ready yet: Current phase: $PHASE"
-          kubectl get pods -n my-greptimedb
-          sleep 5 # wait for 5 seconds before check again.
-        fi
-      done
-  - name: Print GreptimeDB info
-    if: always()
-    shell: bash
-    run: | 
-      kubectl get all --show-labels -n my-greptimedb
-  - name: Describe Nodes
-    if: always()
-    shell: bash
-    run: | 
-      kubectl describe nodes

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

@@ -1,18 +0,0 @@
-meta:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-datanode:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-frontend:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8

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

@@ -1,38 +0,0 @@
-meta:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-    
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-    
-    [storage]
-    cache_path = "/data/greptimedb/s3cache"
-    cache_capacity = "256MB"
-frontend:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123

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

@@ -1,34 +0,0 @@
-meta:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-    
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-frontend:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123

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

@@ -1,45 +0,0 @@
-meta:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-    
-    [wal]
-    provider = "kafka"
-    broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
-    num_topics = 3
-
-        
-    [datanode]
-    [datanode.client]
-    timeout = "60s"
-datanode:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-
-    [wal]
-    provider = "kafka"
-    broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
-    linger = "2ms"
-frontend:
-  config: |-
-    [runtime]
-    read_rt_size = 8
-    write_rt_size = 8
-    bg_rt_size = 8
-
-    [meta_client]
-    ddl_timeout = "60s"
-objectStorage:
-  s3:
-    bucket: default
-    region: us-west-2
-    root: test-root
-    endpoint: http://minio.minio.svc.cluster.local 
-  credentials:
-    accessKeyId: rootuser
-    secretAccessKey: rootpass123

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

@@ -1,24 +0,0 @@
-name: Setup Kafka cluster
-description: Deploy Kafka cluster on Kubernetes
-inputs:
-  controller-replicas:
-    default: 3
-    description: "Kafka controller replicas"
-  namespace:
-    default: "kafka-cluster"
-
-runs:
-  using: composite
-  steps:
-  - name: Install Kafka cluster
-    shell: bash
-    run: | 
-      helm upgrade \
-        --install kafka oci://registry-1.docker.io/bitnamicharts/kafka \
-        --set controller.replicaCount=${{ inputs.controller-replicas }} \
-        --set controller.resources.requests.cpu=50m \
-        --set controller.resources.requests.memory=128Mi \
-        --set listeners.controller.protocol=PLAINTEXT \
-        --set listeners.client.protocol=PLAINTEXT \
-        --create-namespace \
-        -n ${{ inputs.namespace }}

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

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

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

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

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

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

.github/doc-label-config.yml

@@ -0,0 +1,4 @@
+Doc not needed:
+    - '- \[x\]  This PR does not require documentation updates.'
+Doc update required:
+    - '- \[ \]  This PR does not require documentation updates.'

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

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

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

@@ -0,0 +1,12 @@
+{
+    "LABEL": {
+        "name": "Invalid PR Title",
+        "color": "B60205"
+    },
+    "CHECKS": {
+        "regexp": "^(feat|fix|test|refactor|chore|style|docs|perf|build|ci|revert)(\\(.*\\))?\\!?:.*",
+        "ignoreLabels": [
+            "ignore-title"
+        ]
+    }
+}

.github/pull_request_template.md

@@ -15,6 +15,6 @@ Please explain IN DETAIL what the changes are in this PR and why they are needed
 
 ## Checklist
 
-- [ ] I have written the necessary rustdoc comments.
-- [ ] I have added the necessary unit tests and integration tests.
-- [ ] This PR requires documentation updates.
+- [ ]  I have written the necessary rustdoc comments.
+- [ ]  I have added the necessary unit tests and integration tests.
+- [x]  This PR does not require documentation updates.

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

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

.github/workflows/apidoc.yml

@@ -13,7 +13,7 @@ on:
 name: Build API docs
 
 env:
-  RUST_TOOLCHAIN: nightly-2024-04-20
+  RUST_TOOLCHAIN: nightly-2024-04-18
 
 jobs:
   apidoc:

.github/workflows/dev-build.yml

@@ -82,9 +82,6 @@ env:
   # The source code will check out in the following path: '${WORKING_DIR}/dev/greptime'.
   CHECKOUT_GREPTIMEDB_PATH: dev/greptimedb
 
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -324,7 +321,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub
@@ -333,25 +330,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.build-result == 'success' }}
-      - name: Notify dev build successful result
+      - name: Notifiy dev build successful result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
 
-      - name: Notify dev build failed result
+      - name: Notifiy dev build failed result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

.github/workflows/develop.yml

@@ -30,7 +30,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  RUST_TOOLCHAIN: nightly-2024-04-20
+  RUST_TOOLCHAIN: nightly-2024-04-18
 
 jobs:
   check-typos-and-docs:
@@ -38,26 +38,19 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
-      - uses: crate-ci/typos@master
+      - uses: crate-ci/typos@v1.13.10
       - name: Check the config docs
         run: |
           make config-docs && \
           git diff --name-only --exit-code ./config/config.md  \
           || (echo "'config/config.md' is not up-to-date, please run 'make config-docs'." && exit 1)
 
-  license-header-check:
-    runs-on: ubuntu-20.04
-    name: Check License Header
-    steps:
-      - uses: actions/checkout@v4
-      - uses: korandoru/hawkeye@v5
-
   check:
     name: Check
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ windows-2022, ubuntu-20.04 ]
+        os: [ windows-latest, ubuntu-20.04 ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
@@ -114,13 +107,9 @@ jobs:
         with:
           # Shares across multiple jobs
           shared-key: "build-binaries"
-      - name: Install cargo-gc-bin
-        shell: bash
-        run: cargo install cargo-gc-bin
       - name: Build greptime binaries
         shell: bash
-        # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc -- --bin greptime --bin sqlness-runner
+        run: cargo build --bin greptime --bin sqlness-runner
       - name: Pack greptime binaries
         shell: bash
         run: |
@@ -141,54 +130,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        target: [ "fuzz_create_table", "fuzz_alter_table", "fuzz_create_database", "fuzz_create_logical_table", "fuzz_alter_logical_table", "fuzz_insert", "fuzz_insert_logical_table" ]
-    steps:
-      - uses: actions/checkout@v4
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
-      - name: Set Rust Fuzz
-        shell: bash
-        run: |
-          sudo apt-get install -y libfuzzer-14-dev
-          rustup install nightly
-          cargo +nightly install cargo-fuzz cargo-gc-bin
-      - name: Download pre-built binaries
-        uses: actions/download-artifact@v4
-        with:
-          name: bins
-          path: .
-      - name: Unzip binaries
-        run: | 
-          tar -xvf ./bins.tar.gz
-          rm ./bins.tar.gz
-      - name: Run GreptimeDB
-        run: |
-          ./bins/greptime standalone start&
-      - name: Fuzz Test
-        uses: ./.github/actions/fuzz-test
-        env:
-          CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
-          GT_MYSQL_ADDR: 127.0.0.1:4002
-        with:
-          target: ${{ matrix.target }}
-          max-total-time: 120
-
-  unstable-fuzztest:
-    name: Unstable Fuzz Test
-    needs: build-greptime-ci
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        target: [ "unstable_fuzz_create_table_standalone" ]
+        target: [ "fuzz_create_table", "fuzz_alter_table", "fuzz_create_database" ]
     steps:
       - uses: actions/checkout@v4
       - uses: arduino/setup-protoc@v3
@@ -206,349 +148,31 @@ jobs:
         shell: bash
         run: |
           sudo apt update && sudo apt install -y libfuzzer-14-dev
-          cargo install cargo-fuzz cargo-gc-bin
-      - name: Download pre-built binariy
+          cargo install cargo-fuzz
+      - name: Download pre-built binaries
         uses: actions/download-artifact@v4
         with:
-          name: bin
+          name: bins
           path: .
-      - name: Unzip bianry
+      - name: Unzip binaries
+        run: tar -xvf ./bins.tar.gz
+      - name: Run GreptimeDB
         run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Run Fuzz Test
-        uses: ./.github/actions/fuzz-test
-        env:
-          CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
-          GT_MYSQL_ADDR: 127.0.0.1:4002
-          GT_FUZZ_BINARY_PATH: ./bin/greptime
-          GT_FUZZ_INSTANCE_ROOT_DIR: /tmp/unstable-greptime/
-        with:
-          target: ${{ matrix.target }}
-          max-total-time: 120
-          unstable: 'true'
-      - name: Upload unstable fuzz test logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: unstable-fuzz-logs
-          path: /tmp/unstable-greptime/
-          retention-days: 3
-
-  build-greptime-ci:
-    name: Build GreptimeDB binary (profile-CI)
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [ ubuntu-20.04 ]
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v4
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "build-greptime-ci"
-      - name: Install cargo-gc-bin
-        shell: bash
-        run: cargo install cargo-gc-bin
-      - name: Build greptime bianry
-        shell: bash
-        # `cargo gc` will invoke `cargo build` with specified args
-        run: cargo gc --profile ci -- --bin greptime 
-      - name: Pack greptime binary
-        shell: bash
-        run: |
-          mkdir bin && \
-          mv ./target/ci/greptime bin
-      - name: Print greptime binaries info
-        run: ls -lh bin
-      - name: Upload artifacts
-        uses: ./.github/actions/upload-artifacts
-        with:
-          artifacts-dir: bin
-          version: current
-
-  distributed-fuzztest: 
-    name: Fuzz Test (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
-    runs-on: ubuntu-latest
-    needs:  build-greptime-ci
-    strategy:
-      matrix:
-        target: [ "fuzz_create_table", "fuzz_alter_table", "fuzz_create_database", "fuzz_create_logical_table", "fuzz_alter_logical_table", "fuzz_insert", "fuzz_insert_logical_table" ]
-        mode: 
-          - name: "Disk"
-            minio: false
-            kafka: false
-            values: "with-disk.yaml"
-          - name: "Minio"
-            minio: true
-            kafka: false
-            values: "with-minio.yaml"
-          - name: "Minio with Cache"
-            minio: true
-            kafka: false
-            values: "with-minio-and-cache.yaml"
-          - name: "Remote WAL"
-            minio: true
-            kafka: true
-            values: "with-remote-wal.yaml"
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup Kind
-        uses: ./.github/actions/setup-kind
-      - if: matrix.mode.minio
-        name: Setup Minio
-        uses: ./.github/actions/setup-minio
-      - if: matrix.mode.kafka
-        name: Setup Kafka cluser
-        uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluser
-        uses: ./.github/actions/setup-etcd-cluster
-      # Prepares for fuzz tests
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
-      - name: Set Rust Fuzz
-        shell: bash
-        run: |
-          sudo apt-get install -y libfuzzer-14-dev
-          rustup install nightly
-          cargo +nightly install cargo-fuzz cargo-gc-bin
-      # Downloads ci image
-      - name: Download pre-built binariy
-        uses: actions/download-artifact@v4
-        with:
-          name: bin
-          path: .
-      - name: Unzip binary
-        run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Build and push GreptimeDB image
-        uses: ./.github/actions/build-and-push-ci-image
-      - name: Wait for etcd
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=etcd \
-            --timeout=120s \
-            -n etcd-cluster
-      - if: matrix.mode.minio
-        name: Wait for minio
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app=minio \
-            --timeout=120s \
-            -n minio
-      - if: matrix.mode.kafka
-        name: Wait for kafka
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=kafka \
-            --timeout=120s \
-            -n kafka-cluster
-      - name: Print etcd info
-        shell: bash
-        run: kubectl get all --show-labels -n etcd-cluster
-      # Setup cluster for test
-      - name: Setup GreptimeDB cluster
-        uses: ./.github/actions/setup-greptimedb-cluster
-        with:
-          image-registry: localhost:5001
-          values-filename: ${{ matrix.mode.values }}
-      - name: Port forward (mysql)
-        run: |
-          kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
+          ./bins/greptime standalone start&
       - name: Fuzz Test
         uses: ./.github/actions/fuzz-test
         env:
           CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
-          GT_MYSQL_ADDR: 127.0.0.1:4002
         with:
           target: ${{ matrix.target }}
-          max-total-time: 120
-      - name: Describe Nodes
-        if: failure()
-        shell: bash
-        run: | 
-          kubectl describe nodes      
-      - name: Export kind logs
-        if: failure()
-        shell: bash
-        run: | 
-          kind export logs /tmp/kind
-      - name: Upload logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: fuzz-tests-kind-logs-${{ matrix.mode.name }}-${{ matrix.target }}
-          path: /tmp/kind
-          retention-days: 3
-      - name: Delete cluster
-        if: success()
-        shell: bash
-        run: | 
-          kind delete cluster
-          docker stop $(docker ps -a -q)
-          docker rm $(docker ps -a -q)
-          docker system prune -f
-
-  distributed-fuzztest-with-chaos: 
-    name: Fuzz Test with Chaos (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
-    runs-on: ubuntu-latest
-    needs:  build-greptime-ci
-    strategy:
-      matrix:
-        target: ["fuzz_failover_mito_regions"]
-        mode: 
-          - name: "Remote WAL"
-            minio: true
-            kafka: true
-            values: "with-remote-wal.yaml"
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup Kind
-        uses: ./.github/actions/setup-kind
-      - name: Setup Chaos Mesh
-        uses: ./.github/actions/setup-chaos
-      - if: matrix.mode.minio
-        name: Setup Minio
-        uses: ./.github/actions/setup-minio
-      - if: matrix.mode.kafka
-        name: Setup Kafka cluser
-        uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluser
-        uses: ./.github/actions/setup-etcd-cluster
-      # Prepares for fuzz tests
-      - uses: arduino/setup-protoc@v3
-        with:
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: dtolnay/rust-toolchain@master
-        with:
-          toolchain: ${{ env.RUST_TOOLCHAIN }}
-      - name: Rust Cache
-        uses: Swatinem/rust-cache@v2
-        with:
-          # Shares across multiple jobs
-          shared-key: "fuzz-test-targets"
-      - name: Set Rust Fuzz
-        shell: bash
-        run: |
-          sudo apt-get install -y libfuzzer-14-dev
-          rustup install nightly
-          cargo +nightly install cargo-fuzz cargo-gc-bin
-      # Downloads ci image
-      - name: Download pre-built binariy
-        uses: actions/download-artifact@v4
-        with:
-          name: bin
-          path: .
-      - name: Unzip binary
-        run: |
-          tar -xvf ./bin.tar.gz
-          rm ./bin.tar.gz
-      - name: Build and push GreptimeDB image
-        uses: ./.github/actions/build-and-push-ci-image
-      - name: Wait for etcd
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=etcd \
-            --timeout=120s \
-            -n etcd-cluster
-      - if: matrix.mode.minio
-        name: Wait for minio
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app=minio \
-            --timeout=120s \
-            -n minio
-      - if: matrix.mode.kafka
-        name: Wait for kafka
-        run: |
-          kubectl wait \
-            --for=condition=Ready \
-            pod -l app.kubernetes.io/instance=kafka \
-            --timeout=120s \
-            -n kafka-cluster
-      - name: Print etcd info
-        shell: bash
-        run: kubectl get all --show-labels -n etcd-cluster
-      # Setup cluster for test
-      - name: Setup GreptimeDB cluster
-        uses: ./.github/actions/setup-greptimedb-cluster
-        with:
-          image-registry: localhost:5001
-          values-filename: ${{ matrix.mode.values }}
-          enable-region-failover: true
-      - name: Port forward (mysql)
-        run: |
-          kubectl port-forward service/my-greptimedb-frontend 4002:4002 -n my-greptimedb&
-      - name: Fuzz Test
-        uses: ./.github/actions/fuzz-test
-        env:
-          CUSTOM_LIBFUZZER_PATH: /usr/lib/llvm-14/lib/libFuzzer.a
-          GT_MYSQL_ADDR: 127.0.0.1:4002
-        with:
-          target: ${{ matrix.target }}
-          max-total-time: 120
-      - name: Describe Nodes
-        if: failure()
-        shell: bash
-        run: | 
-          kubectl describe nodes      
-      - name: Export kind logs
-        if: failure()
-        shell: bash
-        run: | 
-          kind export logs /tmp/kind
-      - name: Upload logs
-        if: failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: fuzz-tests-kind-logs-${{ matrix.mode.name }}-${{ matrix.target }}
-          path: /tmp/kind
-          retention-days: 3
-      - name: Delete cluster
-        if: success()
-        shell: bash
-        run: | 
-          kind delete cluster
-          docker stop $(docker ps -a -q)
-          docker rm $(docker ps -a -q)
-          docker system prune -f
 
   sqlness:
-    name: Sqlness Test (${{ matrix.mode.name }})
+    name: Sqlness Test
     needs: build
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ ubuntu-20.04 ]
-        mode:
-          - name: "Basic"
-            opts: ""
-            kafka: false
-          - name: "Remote WAL"
-            opts: "-w kafka -k 127.0.0.1:9092"
-            kafka: true
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
@@ -559,18 +183,44 @@ jobs:
           path: .
       - name: Unzip binaries
         run: tar -xvf ./bins.tar.gz
-      - if: matrix.mode.kafka
-        name: Setup kafka server
+      - name: Run sqlness
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -c ./tests/cases --bins-dir ./bins
+      - name: Upload sqlness logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: sqlness-logs
+          path: /tmp/greptime-*.log
+          retention-days: 3
+
+  sqlness-kafka-wal:
+    name: Sqlness Test with Kafka Wal
+    needs: build
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-20.04 ]
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v4
+      - name: Download pre-built binaries
+        uses: actions/download-artifact@v4
+        with:
+          name: bins
+          path: .
+      - name: Unzip binaries
+        run: tar -xvf ./bins.tar.gz
+      - name: Setup kafka server
         working-directory: tests-integration/fixtures/kafka
         run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Run sqlness
-        run: RUST_BACKTRACE=1 ./bins/sqlness-runner ${{ matrix.mode.opts }} -c ./tests/cases --bins-dir ./bins --preserve-state
+        run: RUST_BACKTRACE=1 ./bins/sqlness-runner -w kafka -k 127.0.0.1:9092 -c ./tests/cases --bins-dir ./bins
       - name: Upload sqlness logs
-        if: failure()
+        if: always()
         uses: actions/upload-artifact@v4
         with:
-          name: sqlness-logs-${{ matrix.mode.name }}
-          path: /tmp/sqlness*
+          name: sqlness-logs-with-kafka-wal
+          path: /tmp/greptime-*.log
           retention-days: 3
 
   fmt:
@@ -614,7 +264,7 @@ jobs:
           # Shares with `Check` job
           shared-key: "check-lint"
       - name: Run cargo clippy
-        run: make clippy
+        run: cargo clippy --workspace --all-targets -- -D warnings
 
   coverage:
     if: github.event.pull_request.draft == false
@@ -658,9 +308,6 @@ jobs:
       - name: Setup kafka server
         working-directory: tests-integration/fixtures/kafka
         run: docker compose -f docker-compose-standalone.yml up -d --wait
-      - name: Setup minio
-        working-directory: tests-integration/fixtures/minio
-        run: docker compose -f docker-compose-standalone.yml up -d --wait
       - name: Run nextest cases
         run: cargo llvm-cov nextest --workspace --lcov --output-path lcov.info -F pyo3_backend -F dashboard
         env:
@@ -671,11 +318,6 @@ jobs:
           GT_S3_ACCESS_KEY_ID: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
           GT_S3_ACCESS_KEY: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
           GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
-          GT_MINIO_BUCKET: greptime
-          GT_MINIO_ACCESS_KEY_ID: superpower_ci_user
-          GT_MINIO_ACCESS_KEY: superpower_password
-          GT_MINIO_REGION: us-west-2
-          GT_MINIO_ENDPOINT_URL: http://127.0.0.1:9000
           GT_ETCD_ENDPOINTS: http://127.0.0.1:2379
           GT_KAFKA_ENDPOINTS: 127.0.0.1:9092
           UNITTEST_LOG_DIR: "__unittest_logs"
@@ -688,20 +330,20 @@ jobs:
           fail_ci_if_error: false
           verbose: true
 
-  # compat:
-  #   name: Compatibility Test
-  #   needs: build
-  #   runs-on: ubuntu-20.04
-  #   timeout-minutes: 60
-  #   steps:
-  #     - uses: actions/checkout@v4
-  #     - name: Download pre-built binaries
-  #       uses: actions/download-artifact@v4
-  #       with:
-  #         name: bins
-  #         path: .
-  #     - name: Unzip binaries
-  #       run: |
-  #         mkdir -p ./bins/current
-  #         tar -xvf ./bins.tar.gz --strip-components=1 -C ./bins/current
-  #     - run: ./tests/compat/test-compat.sh 0.6.0
+  compat:
+    name: Compatibility Test
+    needs: build
+    runs-on: ubuntu-20.04
+    timeout-minutes: 60
+    steps:
+      - uses: actions/checkout@v4
+      - name: Download pre-built binaries
+        uses: actions/download-artifact@v4
+        with:
+          name: bins
+          path: .
+      - name: Unzip binaries
+        run: |
+          mkdir -p ./bins/current
+          tar -xvf ./bins.tar.gz --strip-components=1 -C ./bins/current
+      - run: ./tests/compat/test-compat.sh 0.6.0

.github/workflows/doc-issue.yml

@@ -0,0 +1,39 @@
+name: Create Issue in downstream repos
+
+on:
+  issues:
+    types:
+      - labeled
+  pull_request_target:
+    types:
+      - labeled
+
+jobs:
+  doc_issue:
+    if: github.event.label.name == 'doc update required'
+    runs-on: ubuntu-20.04
+    steps:
+      - name: create an issue in doc repo
+        uses: dacbd/create-issue-action@v1.2.1
+        with:
+          owner: GreptimeTeam
+          repo: docs
+          token: ${{ secrets.DOCS_REPO_TOKEN }}
+          title: Update docs for ${{ github.event.issue.title || github.event.pull_request.title }}
+          body: |
+            A document change request is generated from
+            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
+  cloud_issue:
+    if: github.event.label.name == 'cloud followup required'
+    runs-on: ubuntu-20.04
+    steps:
+      - name: create an issue in cloud repo
+        uses: dacbd/create-issue-action@v1.2.1
+        with:
+          owner: GreptimeTeam
+          repo: greptimedb-cloud
+          token: ${{ secrets.DOCS_REPO_TOKEN }}
+          title: Followup changes in ${{ github.event.issue.title || github.event.pull_request.title }}
+          body: |
+            A followup request is generated from
+            ${{ github.event.issue.html_url || github.event.pull_request.html_url }}

.github/workflows/doc-label.yml

@@ -0,0 +1,36 @@
+name: "PR Doc Labeler"
+on:
+  pull_request_target:
+    types: [opened, edited, synchronize, ready_for_review, auto_merge_enabled, labeled, unlabeled]
+
+permissions:
+  pull-requests: write
+  contents: read
+
+jobs:
+  triage:
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: ubuntu-latest
+    steps:
+    - uses: github/issue-labeler@v3.4
+      with:
+        configuration-path: .github/doc-label-config.yml
+        enable-versioned-regex: false
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        sync-labels: 1
+    - name: create an issue in doc repo
+      uses: dacbd/create-issue-action@v1.2.1
+      if: ${{ github.event.action == 'opened' && contains(github.event.pull_request.body, '- [ ]  This PR does not require documentation updates.') }}
+      with:
+        owner: GreptimeTeam
+        repo: docs
+        token: ${{ secrets.DOCS_REPO_TOKEN }}
+        title: Update docs for ${{ github.event.issue.title || github.event.pull_request.title }}
+        body: |
+          A document change request is generated from
+          ${{ github.event.issue.html_url || github.event.pull_request.html_url }}
+    - name: Check doc labels
+      uses: docker://agilepathway/pull-request-label-checker:latest
+      with:
+        one_of: Doc update required,Doc not needed
+        repo_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docbot.yml

@@ -1,22 +0,0 @@
-name: Follow Up Docs
-on:
-  pull_request_target:
-    types: [opened, edited]
-
-permissions:
-  pull-requests: write
-  contents: read
-
-jobs:
-  docbot:
-    runs-on: ubuntu-20.04
-    timeout-minutes: 10
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Maybe Follow Up Docs Issue
-        working-directory: cyborg
-        run: pnpm tsx bin/follow-up-docs-issue.ts
-        env:
-          DOCS_REPO_TOKEN: ${{ secrets.DOCS_REPO_TOKEN }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs.yml

@@ -34,14 +34,7 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
-      - uses: crate-ci/typos@master
-
-  license-header-check:
-    runs-on: ubuntu-20.04
-    name: Check License Header
-    steps:
-      - uses: actions/checkout@v4
-      - uses: korandoru/hawkeye@v5
+      - uses: crate-ci/typos@v1.13.10
 
   check:
     name: Check
@@ -67,13 +60,19 @@ jobs:
       - run: 'echo "No action required"'
 
   sqlness:
-    name: Sqlness Test (${{ matrix.mode.name }})
+    name: Sqlness Test
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ ubuntu-20.04 ]
+    steps:
+      - run: 'echo "No action required"'
+
+  sqlness-kafka-wal:
+    name: Sqlness Test with Kafka Wal
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ ubuntu-20.04 ]
-        mode:
-          - name: "Basic"
-          - name: "Remote WAL"
     steps:
       - run: 'echo "No action required"'

.github/workflows/license.yaml

@@ -0,0 +1,16 @@
+name: License checker
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+jobs:
+  license-header-check:
+    runs-on: ubuntu-20.04
+    name: license-header-check
+    steps:
+    - uses: actions/checkout@v4
+    - name: Check License Header
+      uses: korandoru/hawkeye@v5

.github/workflows/nightly-build.yml

@@ -66,13 +66,6 @@ env:
 
   NIGHTLY_RELEASE_PREFIX: nightly
 
-  # Use the different image name to avoid conflict with the release images.
-  # The DockerHub image will be greptime/greptimedb-nightly.
-  IMAGE_NAME: greptimedb-nightly
-
-permissions:
-  issues: write
-
 jobs:
   allocate-runners:
     name: Allocate runners
@@ -195,7 +188,6 @@ jobs:
         with:
           image-registry: docker.io
           image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          image-name: ${{ env.IMAGE_NAME }}
           image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           image-registry-password: ${{ secrets.DOCKERHUB_TOKEN }}
           version: ${{ needs.allocate-runners.outputs.version }}
@@ -228,7 +220,7 @@ jobs:
         with:
           src-image-registry: docker.io
           src-image-namespace: ${{ vars.IMAGE_NAMESPACE }}
-          src-image-name: ${{ env.IMAGE_NAME }}
+          src-image-name: greptimedb
           dst-image-registry-username: ${{ secrets.ALICLOUD_USERNAME }}
           dst-image-registry-password: ${{ secrets.ALICLOUD_PASSWORD }}
           dst-image-registry: ${{ vars.ACR_IMAGE_REGISTRY }}
@@ -293,7 +285,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub
@@ -302,25 +294,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result == 'success' }}
-      - name: Notify nightly build successful result
+      - name: Notifiy nightly build successful result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has completed successfully."}
 
-      - name: Notify nightly build failed result
+      - name: Notifiy nightly build failed result
         uses: slackapi/slack-github-action@v1.23.0
         if: ${{ needs.release-images-to-dockerhub.outputs.nightly-build-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's ${{ env.NEXT_RELEASE_VERSION }} build has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/${{ env.NEXT_RELEASE_VERSION }}-build.yml'."}

.github/workflows/nightly-ci.yml

@@ -1,6 +1,8 @@
+# Nightly CI: runs tests every night for our second tier plaforms (Windows)
+
 on:
   schedule:
-    - cron: "0 23 * * 1-5"
+    - cron: '0 23 * * 1-5'
   workflow_dispatch:
 
 name: Nightly CI
@@ -10,38 +12,19 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  RUST_TOOLCHAIN: nightly-2024-04-20
-
-permissions:
-  issues: write
+  RUST_TOOLCHAIN: nightly-2024-04-18
 
 jobs:
-  sqlness-test:
-    name: Run sqlness test
+  sqlness:
+    name: Sqlness Test
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-      - name: 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 }}
-
-  sqlness-windows:
-    name: Sqlness tests on Windows
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: windows-2022-8-cores
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ windows-latest-8-cores ]
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
@@ -52,6 +35,14 @@ jobs:
         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@v4
@@ -61,20 +52,15 @@ jobs:
           retention-days: 3
 
   test-on-windows:
-    name: Run tests on Windows
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: windows-2022-8-cores
+    runs-on: windows-latest-8-cores
     timeout-minutes: 60
     steps:
       - run: git config --global core.autocrlf false
       - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
       - uses: arduino/setup-protoc@v3
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-      - uses: KyleMayes/install-llvm-action@v1
-        with:
-          version: "14.0"
       - name: Install Rust toolchain
         uses: dtolnay/rust-toolchain@master
         with:
@@ -87,7 +73,7 @@ jobs:
       - name: Install Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: '3.10'
       - name: Install PyArrow Package
         run: pip install pyarrow
       - name: Install WSL distribution
@@ -97,62 +83,18 @@ jobs:
       - name: Running tests
         run: cargo nextest run -F pyo3_backend,dashboard
         env:
-          CARGO_BUILD_RUSTFLAGS: "-C linker=lld-link"
           RUST_BACKTRACE: 1
           CARGO_INCREMENTAL: 0
-          RUSTUP_WINDOWS_PATH_ADD_BIN: 1 # Workaround for https://github.com/nextest-rs/nextest/issues/1493
           GT_S3_BUCKET: ${{ vars.AWS_CI_TEST_BUCKET }}
           GT_S3_ACCESS_KEY_ID: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
           GT_S3_ACCESS_KEY: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}
           GT_S3_REGION: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
           UNITTEST_LOG_DIR: "__unittest_logs"
-
-  check-status:
-    name: Check status
-    needs: [
-      sqlness-test,
-      sqlness-windows,
-      test-on-windows,
-    ]
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    runs-on: ubuntu-20.04
-    outputs:
-      check-result: ${{ steps.set-check-result.outputs.check-result }}
-    steps:
-      - name: Set check result
-        id: set-check-result
-        run: |
-          echo "check-result=success" >> $GITHUB_OUTPUT
-
-  notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && always() }} # Not requiring successful dependent jobs, always run.
-    name: Send notification to Greptime team
-    needs: [
-      check-status
-    ]
-    runs-on: ubuntu-20.04
-    env:
-      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
+      - name: Notify slack if failed
+        if: failure()
+        uses: slackapi/slack-github-action@v1.23.0
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.check-status.outputs.check-result == 'success' }}
-      - name: Notify dev build successful result
-        uses: slackapi/slack-github-action@v1.23.0
-        if: ${{ needs.check-status.outputs.check-result == 'success' }}
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
         with:
           payload: |
-            {"text": "Nightly CI has completed successfully."}
-
-      - name: Notify dev build failed result
-        uses: slackapi/slack-github-action@v1.23.0
-        if: ${{ needs.check-status.outputs.check-result != 'success' }}
-        with:
-          payload: |
-            {"text": "Nightly CI failed has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "Nightly CI failed for cargo test"}

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

@@ -0,0 +1,27 @@
+name: Nightly functional tests
+
+on:
+  schedule:
+    # At 00:00 on Tuesday.
+    - cron: '0 0 * * 2'
+  workflow_dispatch:
+
+jobs:
+  sqlness-test:
+    name: Run sqlness test
+    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Run sqlness test
+        uses: ./.github/actions/sqlness-test
+        with:
+          data-root: sqlness-test
+          aws-ci-test-bucket: ${{ vars.AWS_CI_TEST_BUCKET }}
+          aws-region: ${{ vars.AWS_CI_TEST_BUCKET_REGION }}
+          aws-access-key-id: ${{ secrets.AWS_CI_TEST_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_CI_TEST_SECRET_ACCESS_KEY }}

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

@@ -0,0 +1,29 @@
+name: "PR Title Checker"
+on:
+  pull_request_target:
+    types:
+      - opened
+      - edited
+      - synchronize
+      - labeled
+      - unlabeled
+
+jobs:
+  check:
+    runs-on: ubuntu-20.04
+    timeout-minutes: 10
+    steps:
+      - uses: thehanimo/pr-title-checker@v1.4.2
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          pass_on_octokit_error: false
+          configuration_path: ".github/pr-title-checker-config.json"
+  breaking:
+    runs-on: ubuntu-20.04
+    timeout-minutes: 10
+    steps:
+      - uses: thehanimo/pr-title-checker@v1.4.2
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          pass_on_octokit_error: false
+          configuration_path: ".github/pr-title-breaking-change-label-config.json"

.github/workflows/release.yml

@@ -82,7 +82,7 @@ on:
 # Use env variables to control all the release process.
 env:
   # The arguments of building greptime.
-  RUST_TOOLCHAIN: nightly-2024-04-20
+  RUST_TOOLCHAIN: nightly-2024-04-18
   CARGO_PROFILE: nightly
 
   # Controls whether to run tests, include unit-test, integration-test and sqlness.
@@ -91,12 +91,7 @@ env:
   # The scheduled version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD', like v0.2.0-nigthly-20230313;
   NIGHTLY_RELEASE_PREFIX: nightly
   # Note: The NEXT_RELEASE_VERSION should be modified manually by every formal release.
-  NEXT_RELEASE_VERSION: v0.9.0
-
-# Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
-permissions:
-  issues: write # Allows the action to create issues for cyborg.
-  contents: write # Allows the action to create a release.
+  NEXT_RELEASE_VERSION: v0.8.0
 
 jobs:
   allocate-runners:
@@ -107,7 +102,7 @@ jobs:
       linux-amd64-runner: ${{ steps.start-linux-amd64-runner.outputs.label }}
       linux-arm64-runner: ${{ steps.start-linux-arm64-runner.outputs.label }}
       macos-runner: ${{ inputs.macos_runner || vars.DEFAULT_MACOS_RUNNER }}
-      windows-runner: windows-2022-8-cores
+      windows-runner: windows-latest-8-cores
 
       # The following EC2 resource id will be used for resource releasing.
       linux-amd64-ec2-runner-label: ${{ steps.start-linux-amd64-runner.outputs.label }}
@@ -250,7 +245,7 @@ jobs:
       - name: Set build macos result
         id: set-build-macos-result
         run: |
-          echo "build-macos-result=success" >> $GITHUB_OUTPUT
+          echo "build-macos-result=success" >> $GITHUB_OUTPUT    
 
   build-windows-artifacts:
     name: Build Windows artifacts
@@ -323,7 +318,7 @@ jobs:
       - name: Set build image result
         id: set-build-image-result
         run: |
-          echo "build-image-result=success" >> $GITHUB_OUTPUT
+          echo "build-image-result=success" >> $GITHUB_OUTPUT    
 
   release-cn-artifacts:
     name: Release artifacts to CN region
@@ -441,7 +436,7 @@ jobs:
           github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
 
   notification:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && (github.event_name == 'push' || github.event_name == 'schedule') && always() }}
+    if: ${{ always() }} # Not requiring successful dependent jobs, always run.
     name: Send notification to Greptime team
     needs: [
       release-images-to-dockerhub,
@@ -452,25 +447,16 @@ jobs:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_DEVELOP_CHANNEL }}
     steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Report CI status
-        id: report-ci-status
-        working-directory: cyborg
-        run: pnpm tsx bin/report-ci-failure.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CI_REPORT_STATUS: ${{ needs.release-images-to-dockerhub.outputs.build-image-result == 'success' && needs.build-windows-artifacts.outputs.build-windows-result == 'success' && needs.build-macos-artifacts.outputs.build-macos-result == 'success' }}
-      - name: Notify release successful result
+      - name: Notifiy release successful result
         uses: slackapi/slack-github-action@v1.25.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-image-result == 'success' && needs.build-windows-artifacts.outputs.build-windows-result == 'success' && needs.build-macos-artifacts.outputs.build-macos-result == 'success' }}
         with:
           payload: |
             {"text": "GreptimeDB's release version has completed successfully."}
 
-      - name: Notify release failed result
+      - name: Notifiy release failed result
         uses: slackapi/slack-github-action@v1.25.0
         if: ${{ needs.release-images-to-dockerhub.outputs.build-image-result != 'success' || needs.build-windows-artifacts.outputs.build-windows-result != 'success' || needs.build-macos-artifacts.outputs.build-macos-result != 'success' }}
         with:
           payload: |
-            {"text": "GreptimeDB's release version has failed, please check ${{ steps.report-ci-status.outputs.html_url }}."}
+            {"text": "GreptimeDB's release version has failed, please check 'https://github.com/GreptimeTeam/greptimedb/actions/workflows/release.yml'."}

.github/workflows/schedule.yml

@@ -1,24 +0,0 @@
-name: Schedule Management
-on:
-  schedule:
-    - cron: '4 2 * * *'
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  issues: write
-  pull-requests: write
-
-jobs:
-  maintenance:
-    name: Periodic Maintenance
-    runs-on: ubuntu-latest
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Do Maintenance
-        working-directory: cyborg
-        run: pnpm tsx bin/schedule.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}

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

@@ -1,21 +0,0 @@
-name: "Semantic Pull Request"
-
-on:
-  pull_request_target:
-    types:
-      - opened
-      - reopened
-      - edited
-
-jobs:
-  check:
-    runs-on: ubuntu-20.04
-    timeout-minutes: 10
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/setup-cyborg
-      - name: Check Pull Request
-        working-directory: cyborg
-        run: pnpm tsx bin/check-pull-request.ts
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/unassign.yml

@@ -0,0 +1,21 @@
+name: Auto Unassign
+on:
+  schedule:
+    - cron: '4 2 * * *'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  issues: write
+  pull-requests: write
+
+jobs:
+  auto-unassign:
+    name: Auto Unassign
+    runs-on: ubuntu-latest
+    steps:
+      - name: Auto Unassign
+        uses: tisonspieces/auto-unassign@main
+        with:
+          token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          repository: ${{ github.repository }}

CONTRIBUTING.md

@@ -2,14 +2,7 @@
 
 Thanks a lot for considering contributing to GreptimeDB. We believe people like you would make GreptimeDB a great product. We intend to build a community where individuals can have open talks, show respect for one another, and speak with true ❤️. Meanwhile, we are to keep transparency and make your effort count here.
 
-You can find our contributors at https://github.com/GreptimeTeam/greptimedb/graphs/contributors. When you dedicate to GreptimeDB for a few months and keep bringing high-quality contributions (code, docs, advocate, etc.), you will be a candidate of a committer.
-
-A committer will be granted both read & write access to GreptimeDB repos. Here is a list of current committers except GreptimeDB team members:
-
-* [Eugene Tolbakov](https://github.com/etolbakov): PromQL support, SQL engine, InfluxDB APIs, and more.
-* [@NiwakaDev](https://github.com/NiwakaDev): SQL engine and storage layer.
-
-Please read the guidelines, and they can help you get started. Communicate respectfully with the developers maintaining and developing the project. In return, they should reciprocate that respect by addressing your issue, reviewing changes, as well as helping finalize and merge your pull requests.
+Please read the guidelines, and they can help you get started. Communicate with respect to developers maintaining and developing the project. In return, they should reciprocate that respect by addressing your issue, reviewing changes, as well as helping finalize and merge your pull requests.
 
 Follow our [README](https://github.com/GreptimeTeam/greptimedb#readme) to get the whole picture of the project. To learn about the design of GreptimeDB, please refer to the [design docs](https://github.com/GrepTimeTeam/docs).
 
@@ -57,7 +50,7 @@ GreptimeDB uses the [Apache 2.0 license](https://github.com/GreptimeTeam/greptim
 
 - To ensure that community is free and confident in its ability to use your contributions, please sign the Contributor License Agreement (CLA) which will be incorporated in the pull request process.
 - Make sure all files have proper license header (running `docker run --rm -v $(pwd):/github/workspace ghcr.io/korandoru/hawkeye-native:v3 format` from the project root).
-- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/) and [style guide](docs/style-guide.md).
+- Make sure all your codes are formatted and follow the [coding style](https://pingcap.github.io/style-guide/rust/) and [style guide](http://github.com/greptimeTeam/docs/style-guide.md).
 - 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`).
 

Cargo.toml

@@ -1,9 +1,9 @@
 [workspace]
 members = [
+    "benchmarks",
     "src/api",
     "src/auth",
     "src/catalog",
-    "src/cache",
     "src/client",
     "src/cmd",
     "src/common/base",
@@ -11,7 +11,6 @@ members = [
     "src/common/config",
     "src/common/datasource",
     "src/common/error",
-    "src/common/frontend",
     "src/common/function",
     "src/common/macro",
     "src/common/greptimedb-telemetry",
@@ -45,7 +44,6 @@ members = [
     "src/object-store",
     "src/operator",
     "src/partition",
-    "src/pipeline",
     "src/plugins",
     "src/promql",
     "src/puffin",
@@ -64,14 +62,13 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.8.2"
+version = "0.7.2"
 edition = "2021"
 license = "Apache-2.0"
 
 [workspace.lints]
 clippy.print_stdout = "warn"
 clippy.print_stderr = "warn"
-clippy.dbg_macro = "warn"
 clippy.implicit_clone = "warn"
 clippy.readonly_write_lock = "allow"
 rust.unknown_lints = "deny"
@@ -101,18 +98,15 @@ bytemuck = "1.12"
 bytes = { version = "1.5", features = ["serde"] }
 chrono = { version = "0.4", features = ["serde"] }
 clap = { version = "4.4", features = ["derive"] }
-config = "0.13.0"
-crossbeam-utils = "0.8"
 dashmap = "5.4"
-datafusion = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-common = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-expr = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-functions = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-optimizer = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-physical-expr = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-physical-plan = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-sql = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
-datafusion-substrait = { git = "https://github.com/apache/datafusion.git", rev = "729b356ef543ffcda6813c7b5373507a04ae0109" }
+datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-common = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-functions = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-physical-expr = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-sql = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
+datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion.git", rev = "34eda15b73a9e278af8844b30ed2f1c21c10359c" }
 derive_builder = "0.12"
 dotenv = "0.15"
 # TODO(LFC): Wait for https://github.com/etcdv3/etcd-client/pull/76
@@ -120,7 +114,7 @@ etcd-client = { git = "https://github.com/MichaelScofield/etcd-client.git", rev
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "a70a6af9c69e40f9a918936a48717343402b4393" }
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "73ac0207ab71dfea48f30259ffdb611501b5ecb8" }
 humantime = "2.1"
 humantime-serde = "1.1"
 itertools = "0.10"
@@ -140,31 +134,28 @@ parquet = { version = "51.0.0", default-features = false, features = ["arrow", "
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-promql-parser = { version = "0.4" }
 prost = "0.12"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
 regex = "1.8"
 regex-automata = { version = "0.4" }
-reqwest = { version = "0.12", default-features = false, features = [
+reqwest = { version = "0.11", default-features = false, features = [
     "json",
     "rustls-tls-native-roots",
     "stream",
     "multipart",
 ] }
 rskafka = "0.5"
-rstest = "0.21"
-rstest_reuse = "0.7"
 rust_decimal = "1.33"
 schemars = "0.8"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = { version = "1.0", features = ["float_roundtrip"] }
 serde_with = "3"
 smallvec = { version = "1", features = ["serde"] }
-snafu = "0.8"
+snafu = "0.7"
 sysinfo = "0.30"
 # on branch v0.44.x
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "54a267ac89c09b11c0c88934690530807185d3e7", features = [
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "c919990bf62ad38d2b0c0a3bc90b26ad919d51b0", features = [
     "visitor",
 ] }
 strum = { version = "0.25", features = ["derive"] }
@@ -173,15 +164,13 @@ tokio = { version = "1.36", features = ["full"] }
 tokio-stream = { version = "0.1" }
 tokio-util = { version = "0.7", features = ["io-util", "compat"] }
 toml = "0.8.8"
-tonic = { version = "0.11", features = ["tls", "gzip", "zstd"] }
-tower = { version = "0.4" }
+tonic = { version = "0.11", features = ["tls"] }
 uuid = { version = "1.7", features = ["serde", "v4", "fast-rng"] }
 zstd = "0.13"
 
 ## workspaces members
 api = { path = "src/api" }
 auth = { path = "src/auth" }
-cache = { path = "src/cache" }
 catalog = { path = "src/catalog" }
 client = { path = "src/client" }
 cmd = { path = "src/cmd" }
@@ -191,7 +180,6 @@ common-config = { path = "src/common/config" }
 common-datasource = { path = "src/common/datasource" }
 common-decimal = { path = "src/common/decimal" }
 common-error = { path = "src/common/error" }
-common-frontend = { path = "src/common/frontend" }
 common-function = { path = "src/common/function" }
 common-greptimedb-telemetry = { path = "src/common/greptimedb-telemetry" }
 common-grpc = { path = "src/common/grpc" }
@@ -213,7 +201,6 @@ common-wal = { path = "src/common/wal" }
 datanode = { path = "src/datanode" }
 datatypes = { path = "src/datatypes" }
 file-engine = { path = "src/file-engine" }
-flow = { path = "src/flow" }
 frontend = { path = "src/frontend" }
 index = { path = "src/index" }
 log-store = { path = "src/log-store" }
@@ -224,7 +211,6 @@ mito2 = { path = "src/mito2" }
 object-store = { path = "src/object-store" }
 operator = { path = "src/operator" }
 partition = { path = "src/partition" }
-pipeline = { path = "src/pipeline" }
 plugins = { path = "src/plugins" }
 promql = { path = "src/promql" }
 puffin = { path = "src/puffin" }
@@ -250,15 +236,3 @@ strip = true
 lto = "thin"
 debug = false
 incremental = false
-
-[profile.ci]
-inherits = "dev"
-strip = true
-
-[profile.dev.package.sqlness-runner]
-debug = false
-strip = true
-
-[profile.dev.package.tests-fuzz]
-debug = false
-strip = true

Makefile

@@ -54,10 +54,8 @@ ifneq ($(strip $(RELEASE)),)
 	CARGO_BUILD_OPTS += --release
 endif
 
-ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), all)
+ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), true)
 	BUILDX_MULTI_PLATFORM_BUILD_OPTS := --platform linux/amd64,linux/arm64 --push
-else ifeq ($(BUILDX_MULTI_PLATFORM_BUILD), amd64)
-	BUILDX_MULTI_PLATFORM_BUILD_OPTS := --platform linux/amd64 --push
 else
 	BUILDX_MULTI_PLATFORM_BUILD_OPTS := -o type=docker
 endif
@@ -163,17 +161,6 @@ nextest: ## Install nextest tools.
 sqlness-test: ## Run sqlness test.
 	cargo sqlness
 
-# Run fuzz test ${FUZZ_TARGET}.
-RUNS ?= 1
-FUZZ_TARGET ?= fuzz_alter_table
-.PHONY: fuzz
-fuzz:
-	cargo fuzz run ${FUZZ_TARGET} --fuzz-dir tests-fuzz -D -s none -- -runs=${RUNS}
-
-.PHONY: fuzz-ls
-fuzz-ls:
-	cargo fuzz list --fuzz-dir tests-fuzz 
-
 .PHONY: check
 check: ## Cargo check all the targets.
 	cargo check --workspace --all-targets --all-features
@@ -205,16 +192,12 @@ run-it-in-container: start-etcd ## Run integration tests in dev-builder.
 	-w /greptimedb ${IMAGE_REGISTRY}/${IMAGE_NAMESPACE}/dev-builder-${BASE_IMAGE}:latest \
 	make test sqlness-test BUILD_JOBS=${BUILD_JOBS}
 
-.PHONY: run-cluster-with-etcd
-run-cluster-with-etcd: ## Run greptime cluster with etcd in docker-compose.
-	 docker compose -f ./docker/docker-compose/cluster-with-etcd.yaml up
-
 ##@ Docs
 config-docs: ## Generate configuration documentation from toml files.
 	docker run --rm \
     -v ${PWD}:/greptimedb \
     -w /greptimedb/config \
-    toml2docs/toml2docs:v0.1.1 \
+    toml2docs/toml2docs:latest \
     -p '##' \
     -t ./config-docs-template.md \
     -o ./config.md

benchmarks/Cargo.toml

@@ -0,0 +1,38 @@
+[package]
+name = "benchmarks"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[lints]
+workspace = true
+
+[dependencies]
+api.workspace = true
+arrow.workspace = true
+chrono.workspace = true
+clap.workspace = true
+client.workspace = true
+common-base.workspace = true
+common-telemetry.workspace = true
+common-wal.workspace = true
+dotenv.workspace = true
+futures.workspace = true
+futures-util.workspace = true
+humantime.workspace = true
+humantime-serde.workspace = true
+indicatif = "0.17.1"
+itertools.workspace = true
+lazy_static.workspace = true
+log-store.workspace = true
+mito2.workspace = true
+num_cpus.workspace = true
+parquet.workspace = true
+prometheus.workspace = true
+rand.workspace = true
+rskafka.workspace = true
+serde.workspace = true
+store-api.workspace = true
+tokio.workspace = true
+toml.workspace = true
+uuid.workspace = true

benchmarks/README.md

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

benchmarks/config/wal_bench.example.toml

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

benchmarks/src/bin/nyc-taxi.rs

@@ -0,0 +1,513 @@
+// 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, OutputData, 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,
+            )
+        }
+        _ => unimplemented!(),
+    }
+}
+
+fn is_record_batch_full(batch: &RecordBatch) -> bool {
+    batch.columns().iter().all(|col| col.null_count() == 0)
+}
+
+fn create_table_expr(table_name: &str) -> CreateTableExpr {
+    CreateTableExpr {
+        catalog_name: CATALOG_NAME.to_string(),
+        schema_name: SCHEMA_NAME.to_string(),
+        table_name: table_name.to_string(),
+        desc: String::default(),
+        column_defs: vec![
+            ColumnDef {
+                name: "VendorID".to_string(),
+                data_type: ColumnDataType::Int64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Tag as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "tpep_pickup_datetime".to_string(),
+                data_type: ColumnDataType::TimestampMicrosecond as i32,
+                is_nullable: false,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Timestamp as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "tpep_dropoff_datetime".to_string(),
+                data_type: ColumnDataType::TimestampMicrosecond as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "passenger_count".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "trip_distance".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "RatecodeID".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "store_and_fwd_flag".to_string(),
+                data_type: ColumnDataType::String as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "PULocationID".to_string(),
+                data_type: ColumnDataType::Int64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "DOLocationID".to_string(),
+                data_type: ColumnDataType::Int64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "payment_type".to_string(),
+                data_type: ColumnDataType::Int64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "fare_amount".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "extra".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "mta_tax".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "tip_amount".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "tolls_amount".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "improvement_surcharge".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "total_amount".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "congestion_surcharge".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+            ColumnDef {
+                name: "airport_fee".to_string(),
+                data_type: ColumnDataType::Float64 as i32,
+                is_nullable: true,
+                default_constraint: vec![],
+                semantic_type: SemanticType::Field as i32,
+                comment: String::new(),
+                ..Default::default()
+            },
+        ],
+        time_index: "tpep_pickup_datetime".to_string(),
+        primary_keys: vec!["VendorID".to_string()],
+        create_if_not_exists: true,
+        table_options: Default::default(),
+        table_id: None,
+        engine: "mito".to_string(),
+    }
+}
+
+fn query_set(table_name: &str) -> HashMap<String, String> {
+    HashMap::from([
+        (
+            "count_all".to_string(),
+            format!("SELECT COUNT(*) FROM {table_name};"),
+        ),
+        (
+            "fare_amt_by_passenger".to_string(),
+            format!("SELECT passenger_count, MIN(fare_amount), MAX(fare_amount), SUM(fare_amount) FROM {table_name} GROUP BY passenger_count"),
+        )
+    ])
+}
+
+async fn do_write(args: &Args, db: &Database, table_name: &str) {
+    let mut file_list = get_file_list(args.path.clone().expect("Specify data path in argument"));
+    let mut write_jobs = JoinSet::new();
+
+    let create_table_result = db.create(create_table_expr(table_name)).await;
+    println!("Create table result: {create_table_result:?}");
+
+    let progress_bar_style = ProgressStyle::with_template(
+        "[{elapsed_precise}] {bar:60.cyan/blue} {pos:>7}/{len:7} {msg}",
+    )
+    .unwrap()
+    .progress_chars("##-");
+    let multi_progress_bar = MultiProgress::new();
+    let file_progress = multi_progress_bar.add(ProgressBar::new(file_list.len() as _));
+    file_progress.inc(0);
+
+    let batch_size = args.batch_size;
+    for _ in 0..args.thread_num {
+        if let Some(path) = file_list.pop() {
+            let db = db.clone();
+            let mpb = multi_progress_bar.clone();
+            let pb_style = progress_bar_style.clone();
+            let table_name = table_name.to_string();
+            let _ = write_jobs.spawn(async move {
+                write_data(&table_name, batch_size, &db, path, mpb, pb_style).await
+            });
+        }
+    }
+    while write_jobs.join_next().await.is_some() {
+        file_progress.inc(1);
+        if let Some(path) = file_list.pop() {
+            let db = db.clone();
+            let mpb = multi_progress_bar.clone();
+            let pb_style = progress_bar_style.clone();
+            let table_name = table_name.to_string();
+            let _ = write_jobs.spawn(async move {
+                write_data(&table_name, batch_size, &db, path, mpb, pb_style).await
+            });
+        }
+    }
+}
+
+async fn do_query(num_iter: usize, db: &Database, table_name: &str) {
+    for (query_name, query) in query_set(table_name) {
+        println!("Running query: {query}");
+        for i in 0..num_iter {
+            let now = Instant::now();
+            let res = db.sql(&query).await.unwrap();
+            match res.data {
+                OutputData::AffectedRows(_) | OutputData::RecordBatches(_) => (),
+                OutputData::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;
+            }
+        })
+}

benchmarks/src/bin/wal_bench.rs

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

benchmarks/src/lib.rs

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

benchmarks/src/metrics.rs

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

benchmarks/src/wal_bench.rs

@@ -0,0 +1,361 @@
+// Copyright 2023 Greptime Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use std::mem::size_of;
+use std::sync::atomic::{AtomicI64, AtomicU64, Ordering};
+use std::sync::{Arc, Mutex};
+use std::time::Duration;
+
+use api::v1::value::ValueData;
+use api::v1::{ColumnDataType, ColumnSchema, Mutation, OpType, Row, Rows, Value, WalEntry};
+use clap::{Parser, ValueEnum};
+use common_base::readable_size::ReadableSize;
+use common_wal::options::WalOptions;
+use futures::StreamExt;
+use mito2::wal::{Wal, WalWriter};
+use rand::distributions::{Alphanumeric, DistString, Uniform};
+use rand::rngs::SmallRng;
+use rand::{Rng, SeedableRng};
+use serde::{Deserialize, Serialize};
+use store_api::logstore::LogStore;
+use store_api::storage::RegionId;
+
+use crate::metrics;
+
+/// The wal provider.
+#[derive(Clone, ValueEnum, Default, Debug, PartialEq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum WalProvider {
+    #[default]
+    RaftEngine,
+    Kafka,
+}
+
+#[derive(Parser)]
+pub struct Args {
+    /// The provided configuration file.
+    /// The example configuration file can be found at `greptimedb/benchmarks/config/wal_bench.example.toml`.
+    #[clap(long, short = 'c')]
+    pub cfg_file: String,
+
+    /// The wal provider.
+    #[clap(long, value_enum, default_value_t = WalProvider::default())]
+    pub wal_provider: WalProvider,
+
+    /// The advertised addresses of the kafka brokers.
+    /// If there're multiple bootstrap brokers, their addresses should be separated by comma, for e.g. "localhost:9092,localhost:9093".
+    #[clap(long, short = 'b', default_value = "localhost:9092")]
+    pub bootstrap_brokers: String,
+
+    /// The number of workers each running in a dedicated thread.
+    #[clap(long, default_value_t = num_cpus::get() as u32)]
+    pub num_workers: u32,
+
+    /// The number of kafka topics to be created.
+    #[clap(long, default_value_t = 32)]
+    pub num_topics: u32,
+
+    /// The number of regions.
+    #[clap(long, default_value_t = 1000)]
+    pub num_regions: u32,
+
+    /// The number of times each region is scraped.
+    #[clap(long, default_value_t = 1000)]
+    pub num_scrapes: u32,
+
+    /// The number of rows in each wal entry.
+    /// Each time a region is scraped, a wal entry containing will be produced.
+    #[clap(long, default_value_t = 5)]
+    pub num_rows: u32,
+
+    /// The column types of the schema for each region.
+    /// Currently, three column types are supported:
+    /// - i = ColumnDataType::Int64
+    /// - f = ColumnDataType::Float64
+    /// - s = ColumnDataType::String  
+    /// For e.g., "ifs" will be parsed as three columns: i64, f64, and string.
+    ///
+    /// Additionally, a "x" sign can be provided to repeat the column types for a given number of times.
+    /// For e.g., "iix2" will be parsed as 4 columns: i64, i64, i64, and i64.
+    /// This feature is useful if you want to specify many columns.
+    #[clap(long, default_value = "ifs")]
+    pub col_types: String,
+
+    /// The maximum size of a batch of kafka records.
+    /// The default value is 1mb.
+    #[clap(long, default_value = "512KB")]
+    pub max_batch_size: ReadableSize,
+
+    /// The minimum latency the kafka client issues a batch of kafka records.
+    /// However, a batch of kafka records would be immediately issued if a record cannot be fit into the batch.
+    #[clap(long, default_value = "1ms")]
+    pub linger: String,
+
+    /// The initial backoff delay of the kafka consumer.
+    #[clap(long, default_value = "10ms")]
+    pub backoff_init: String,
+
+    /// The maximum backoff delay of the kafka consumer.
+    #[clap(long, default_value = "1s")]
+    pub backoff_max: String,
+
+    /// The exponential backoff rate of the kafka consumer. The next back off = base * the current backoff.
+    #[clap(long, default_value_t = 2)]
+    pub backoff_base: u32,
+
+    /// The deadline of backoff. The backoff ends if the total backoff delay reaches the deadline.
+    #[clap(long, default_value = "3s")]
+    pub backoff_deadline: String,
+
+    /// The client-side compression algorithm for kafka records.
+    #[clap(long, default_value = "zstd")]
+    pub compression: String,
+
+    /// The seed of random number generators.
+    #[clap(long, default_value_t = 42)]
+    pub rng_seed: u64,
+
+    /// Skips the read phase, aka. region replay, if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_read: bool,
+
+    /// Skips the write phase if set to true.
+    #[clap(long, default_value_t = false)]
+    pub skip_write: bool,
+
+    /// Randomly generates topic names if set to true.
+    /// Useful when you want to run the benchmarker without worrying about the topics created before.
+    #[clap(long, default_value_t = false)]
+    pub random_topics: bool,
+
+    /// Logs out the gathered prometheus metrics when the benchmarker ends.
+    #[clap(long, default_value_t = false)]
+    pub report_metrics: bool,
+}
+
+/// Benchmarker config.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Config {
+    pub wal_provider: WalProvider,
+    pub bootstrap_brokers: Vec<String>,
+    pub num_workers: u32,
+    pub num_topics: u32,
+    pub num_regions: u32,
+    pub num_scrapes: u32,
+    pub num_rows: u32,
+    pub col_types: String,
+    pub max_batch_size: ReadableSize,
+    #[serde(with = "humantime_serde")]
+    pub linger: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_init: Duration,
+    #[serde(with = "humantime_serde")]
+    pub backoff_max: Duration,
+    pub backoff_base: u32,
+    #[serde(with = "humantime_serde")]
+    pub backoff_deadline: Duration,
+    pub compression: String,
+    pub rng_seed: u64,
+    pub skip_read: bool,
+    pub skip_write: bool,
+    pub random_topics: bool,
+    pub report_metrics: bool,
+}
+
+impl From<Args> for Config {
+    fn from(args: Args) -> Self {
+        let cfg = Self {
+            wal_provider: args.wal_provider,
+            bootstrap_brokers: args
+                .bootstrap_brokers
+                .split(',')
+                .map(ToString::to_string)
+                .collect::<Vec<_>>(),
+            num_workers: args.num_workers.min(num_cpus::get() as u32),
+            num_topics: args.num_topics,
+            num_regions: args.num_regions,
+            num_scrapes: args.num_scrapes,
+            num_rows: args.num_rows,
+            col_types: args.col_types,
+            max_batch_size: args.max_batch_size,
+            linger: humantime::parse_duration(&args.linger).unwrap(),
+            backoff_init: humantime::parse_duration(&args.backoff_init).unwrap(),
+            backoff_max: humantime::parse_duration(&args.backoff_max).unwrap(),
+            backoff_base: args.backoff_base,
+            backoff_deadline: humantime::parse_duration(&args.backoff_deadline).unwrap(),
+            compression: args.compression,
+            rng_seed: args.rng_seed,
+            skip_read: args.skip_read,
+            skip_write: args.skip_write,
+            random_topics: args.random_topics,
+            report_metrics: args.report_metrics,
+        };
+
+        cfg
+    }
+}
+
+/// The region used for wal benchmarker.
+pub struct Region {
+    id: RegionId,
+    schema: Vec<ColumnSchema>,
+    wal_options: WalOptions,
+    next_sequence: AtomicU64,
+    next_entry_id: AtomicU64,
+    next_timestamp: AtomicI64,
+    rng: Mutex<Option<SmallRng>>,
+    num_rows: u32,
+}
+
+impl Region {
+    /// Creates a new region.
+    pub fn new(
+        id: RegionId,
+        schema: Vec<ColumnSchema>,
+        wal_options: WalOptions,
+        num_rows: u32,
+        rng_seed: u64,
+    ) -> Self {
+        Self {
+            id,
+            schema,
+            wal_options,
+            next_sequence: AtomicU64::new(1),
+            next_entry_id: AtomicU64::new(1),
+            next_timestamp: AtomicI64::new(1655276557000),
+            rng: Mutex::new(Some(SmallRng::seed_from_u64(rng_seed))),
+            num_rows,
+        }
+    }
+
+    /// Scrapes the region and adds the generated entry to wal.
+    pub fn add_wal_entry<S: LogStore>(&self, wal_writer: &mut WalWriter<S>) {
+        let mutation = Mutation {
+            op_type: OpType::Put as i32,
+            sequence: self
+                .next_sequence
+                .fetch_add(self.num_rows as u64, Ordering::Relaxed),
+            rows: Some(self.build_rows()),
+        };
+        let entry = WalEntry {
+            mutations: vec![mutation],
+        };
+        metrics::METRIC_WAL_WRITE_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+
+        wal_writer
+            .add_entry(
+                self.id,
+                self.next_entry_id.fetch_add(1, Ordering::Relaxed),
+                &entry,
+                &self.wal_options,
+            )
+            .unwrap();
+    }
+
+    /// Replays the region.
+    pub async fn replay<S: LogStore>(&self, wal: &Arc<Wal<S>>) {
+        let mut wal_stream = wal.scan(self.id, 0, &self.wal_options).unwrap();
+        while let Some(res) = wal_stream.next().await {
+            let (_, entry) = res.unwrap();
+            metrics::METRIC_WAL_READ_BYTES_TOTAL.inc_by(Self::entry_estimated_size(&entry) as u64);
+        }
+    }
+
+    /// Computes the estimated size in bytes of the entry.
+    pub fn entry_estimated_size(entry: &WalEntry) -> usize {
+        let wrapper_size = size_of::<WalEntry>()
+            + entry.mutations.capacity() * size_of::<Mutation>()
+            + size_of::<Rows>();
+
+        let rows = entry.mutations[0].rows.as_ref().unwrap();
+
+        let schema_size = rows.schema.capacity() * size_of::<ColumnSchema>()
+            + rows
+                .schema
+                .iter()
+                .map(|s| s.column_name.capacity())
+                .sum::<usize>();
+        let values_size = (rows.rows.capacity() * size_of::<Row>())
+            + rows
+                .rows
+                .iter()
+                .map(|r| r.values.capacity() * size_of::<Value>())
+                .sum::<usize>();
+
+        wrapper_size + schema_size + values_size
+    }
+
+    fn build_rows(&self) -> Rows {
+        let cols = self
+            .schema
+            .iter()
+            .map(|col_schema| {
+                let col_data_type = ColumnDataType::try_from(col_schema.datatype).unwrap();
+                self.build_col(&col_data_type, self.num_rows)
+            })
+            .collect::<Vec<_>>();
+
+        let rows = (0..self.num_rows)
+            .map(|i| {
+                let values = cols.iter().map(|col| col[i as usize].clone()).collect();
+                Row { values }
+            })
+            .collect();
+
+        Rows {
+            schema: self.schema.clone(),
+            rows,
+        }
+    }
+
+    fn build_col(&self, col_data_type: &ColumnDataType, num_rows: u32) -> Vec<Value> {
+        let mut rng_guard = self.rng.lock().unwrap();
+        let rng = rng_guard.as_mut().unwrap();
+        match col_data_type {
+            ColumnDataType::TimestampMillisecond => (0..num_rows)
+                .map(|_| {
+                    let ts = self.next_timestamp.fetch_add(1000, Ordering::Relaxed);
+                    Value {
+                        value_data: Some(ValueData::TimestampMillisecondValue(ts)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Int64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0, 10_000));
+                    Value {
+                        value_data: Some(ValueData::I64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::Float64 => (0..num_rows)
+                .map(|_| {
+                    let v = rng.sample(Uniform::new(0.0, 5000.0));
+                    Value {
+                        value_data: Some(ValueData::F64Value(v)),
+                    }
+                })
+                .collect(),
+            ColumnDataType::String => (0..num_rows)
+                .map(|_| {
+                    let v = Alphanumeric.sample_string(rng, 10);
+                    Value {
+                        value_data: Some(ValueData::StringValue(v)),
+                    }
+                })
+                .collect(),
+            _ => unreachable!(),
+        }
+    }
+}

config/config-docs-template.md

@@ -1,16 +1,10 @@
 # Configurations
 
-- [Standalone Mode](#standalone-mode)
-- [Distributed Mode](#distributed-mode)
-    - [Frontend](#frontend)
-    - [Metasrv](#metasrv)
-    - [Datanode](#datanode)
-
 ## Standalone Mode
 
 {{ toml2docs "./standalone.example.toml" }}
 
-## Distributed Mode
+## Cluster Mode
 
 ### Frontend
 

config/config.md

@@ -1,11 +1,5 @@
 # Configurations
 
-- [Standalone Mode](#standalone-mode)
-- [Distributed Mode](#distributed-mode)
-    - [Frontend](#frontend)
-    - [Metasrv](#metasrv)
-    - [Datanode](#datanode)
-
 ## Standalone Mode
 
 | Key | Type | Default | Descriptions |
@@ -13,22 +7,13 @@
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
 | `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
 | `default_timezone` | String | `None` | The default timezone of the server. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.read_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.write_rt_size` | Integer | `8` | The number of threads to execute the runtime for global write operations. |
-| `runtime.bg_rt_size` | Integer | `4` | The number of threads to execute the runtime for global background operations. |
 | `http` | -- | -- | The HTTP server options. |
 | `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
-| `http.timeout` | String | `30s` | HTTP request timeout. Set to 0 to disable timeout. |
-| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
+| `http.timeout` | String | `30s` | HTTP request timeout. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
 | `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
 | `mysql` | -- | -- | MySQL server options. |
 | `mysql.enable` | Bool | `true` | Whether to enable. |
 | `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
@@ -42,13 +27,15 @@
 | `postgres.enable` | Bool | `true` | Whether to enable |
 | `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
 | `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
-| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql.tls` section. |
+| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql_options.tls` section. |
 | `postgres.tls.mode` | String | `disable` | TLS mode. |
 | `postgres.tls.cert_path` | String | `None` | Certificate file path. |
 | `postgres.tls.key_path` | String | `None` | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
-| `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
+| `opentsdb.enable` | Bool | `true` | Whether to enable |
+| `opentsdb.addr` | String | `127.0.0.1:4242` | OpenTSDB telnet API server address. |
+| `opentsdb.runtime_size` | Integer | `2` | The number of server worker threads. |
 | `influxdb` | -- | -- | InfluxDB protocol options. |
 | `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
 | `prom_store` | -- | -- | Prometheus remote storage options |
@@ -66,7 +53,8 @@
 | `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.max_batch_bytes` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
@@ -110,10 +98,6 @@
 | `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
 | `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
 | `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.enable_experimental_write_cache` | Bool | `false` | Whether to enable the experimental write cache. |
-| `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/write_cache`. |
-| `region_engine.mito.experimental_write_cache_size` | String | `512MB` | Capacity for write cache. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | `1h` | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
 | `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
 | `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
@@ -145,11 +129,9 @@
 | `export_metrics.remote_write` | -- | -- | -- |
 | `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
-| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
-## Distributed Mode
+## Cluster Mode
 
 ### Frontend
 
@@ -157,26 +139,16 @@
 | --- | -----| ------- | ----------- |
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
 | `default_timezone` | String | `None` | The default timezone of the server. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.read_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.write_rt_size` | Integer | `8` | The number of threads to execute the runtime for global write operations. |
-| `runtime.bg_rt_size` | Integer | `4` | The number of threads to execute the runtime for global background operations. |
 | `heartbeat` | -- | -- | The heartbeat options. |
 | `heartbeat.interval` | String | `18s` | Interval for sending heartbeat messages to the metasrv. |
 | `heartbeat.retry_interval` | String | `3s` | Interval for retrying to send heartbeat messages to the metasrv. |
 | `http` | -- | -- | The HTTP server options. |
 | `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
-| `http.timeout` | String | `30s` | HTTP request timeout. Set to 0 to disable timeout. |
-| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
+| `http.timeout` | String | `30s` | HTTP request timeout. |
+| `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
-| `grpc.hostname` | String | `127.0.0.1` | The hostname advertised to the metasrv,<br/>and used for connections from outside the host |
 | `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
 | `mysql` | -- | -- | MySQL server options. |
 | `mysql.enable` | Bool | `true` | Whether to enable. |
 | `mysql.addr` | String | `127.0.0.1:4002` | The addr to bind the MySQL server. |
@@ -190,13 +162,15 @@
 | `postgres.enable` | Bool | `true` | Whether to enable |
 | `postgres.addr` | String | `127.0.0.1:4003` | The addr to bind the PostgresSQL server. |
 | `postgres.runtime_size` | Integer | `2` | The number of server worker threads. |
-| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql.tls` section. |
+| `postgres.tls` | -- | -- | PostgresSQL server TLS options, see `mysql_options.tls` section. |
 | `postgres.tls.mode` | String | `disable` | TLS mode. |
 | `postgres.tls.cert_path` | String | `None` | Certificate file path. |
 | `postgres.tls.key_path` | String | `None` | Private key file path. |
 | `postgres.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload |
 | `opentsdb` | -- | -- | OpenTSDB protocol options. |
-| `opentsdb.enable` | Bool | `true` | Whether to enable OpenTSDB put in HTTP API. |
+| `opentsdb.enable` | Bool | `true` | Whether to enable |
+| `opentsdb.addr` | String | `127.0.0.1:4242` | OpenTSDB telnet API server address. |
+| `opentsdb.runtime_size` | Integer | `2` | The number of server worker threads. |
 | `influxdb` | -- | -- | InfluxDB protocol options. |
 | `influxdb.enable` | Bool | `true` | Whether to enable InfluxDB protocol in HTTP API. |
 | `prom_store` | -- | -- | Prometheus remote storage options |
@@ -214,6 +188,7 @@
 | `meta_client.metadata_cache_tti` | String | `5m` | -- |
 | `datanode` | -- | -- | Datanode options. |
 | `datanode.client` | -- | -- | Datanode client options. |
+| `datanode.client.timeout` | String | `10s` | -- |
 | `datanode.client.connect_timeout` | String | `10s` | -- |
 | `datanode.client.tcp_nodelay` | Bool | `true` | -- |
 | `logging` | -- | -- | The logging options. |
@@ -232,8 +207,6 @@
 | `export_metrics.remote_write` | -- | -- | -- |
 | `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
-| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
 ### Metasrv
@@ -248,10 +221,6 @@
 | `use_memory_store` | Bool | `false` | Store data in memory. |
 | `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. |
 | `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.read_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.write_rt_size` | Integer | `8` | The number of threads to execute the runtime for global write operations. |
-| `runtime.bg_rt_size` | Integer | `4` | The number of threads to execute the runtime for global background operations. |
 | `procedure` | -- | -- | Procedure storage options. |
 | `procedure.max_retry_times` | Integer | `12` | Procedure max retry time. |
 | `procedure.retry_delay` | String | `500ms` | Initial retry delay of procedures, increases exponentially |
@@ -294,8 +263,6 @@
 | `export_metrics.remote_write` | -- | -- | -- |
 | `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
-| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |
 
 
 ### Datanode
@@ -306,28 +273,12 @@
 | `node_id` | Integer | `None` | The datanode identifier and should be unique in the cluster. |
 | `require_lease_before_startup` | Bool | `false` | Start services after regions have obtained leases.<br/>It will block the datanode start if it can't receive leases in the heartbeat from metasrv. |
 | `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
+| `rpc_addr` | String | `127.0.0.1:3001` | The gRPC address of the datanode. |
+| `rpc_hostname` | String | `None` | The hostname of the datanode. |
+| `rpc_runtime_size` | Integer | `8` | The number of gRPC server worker threads. |
+| `rpc_max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
+| `rpc_max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
 | `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
-| `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
-| `rpc_addr` | String | `None` | Deprecated, use `grpc.addr` instead. |
-| `rpc_hostname` | String | `None` | Deprecated, use `grpc.hostname` instead. |
-| `rpc_runtime_size` | Integer | `None` | Deprecated, use `grpc.runtime_size` instead. |
-| `rpc_max_recv_message_size` | String | `None` | Deprecated, use `grpc.rpc_max_recv_message_size` instead. |
-| `rpc_max_send_message_size` | String | `None` | Deprecated, use `grpc.rpc_max_send_message_size` instead. |
-| `grpc` | -- | -- | The gRPC server options. |
-| `grpc.addr` | String | `127.0.0.1:3001` | The address to bind the gRPC server. |
-| `grpc.hostname` | String | `127.0.0.1` | The hostname advertised to the metasrv,<br/>and used for connections from outside the host |
-| `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
-| `grpc.max_recv_message_size` | String | `512MB` | The maximum receive message size for gRPC server. |
-| `grpc.max_send_message_size` | String | `512MB` | The maximum send message size for gRPC server. |
-| `grpc.tls` | -- | -- | gRPC server TLS options, see `mysql.tls` section. |
-| `grpc.tls.mode` | String | `disable` | TLS mode. |
-| `grpc.tls.cert_path` | String | `None` | Certificate file path. |
-| `grpc.tls.key_path` | String | `None` | Private key file path. |
-| `grpc.tls.watch` | Bool | `false` | Watch for Certificate and key file change and auto reload.<br/>For now, gRPC tls config does not support auto reload. |
-| `runtime` | -- | -- | The runtime options. |
-| `runtime.read_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
-| `runtime.write_rt_size` | Integer | `8` | The number of threads to execute the runtime for global write operations. |
-| `runtime.bg_rt_size` | Integer | `4` | The number of threads to execute the runtime for global background operations. |
 | `heartbeat` | -- | -- | The heartbeat options. |
 | `heartbeat.interval` | String | `3s` | Interval for sending heartbeat messages to the metasrv. |
 | `heartbeat.retry_interval` | String | `3s` | Interval for retrying to send heartbeat messages to the metasrv. |
@@ -353,7 +304,8 @@
 | `wal.prefill_log_files` | Bool | `false` | Whether to pre-create log files on start up.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_period` | String | `10s` | Duration for fsyncing log files.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.broker_endpoints` | Array | -- | The Kafka broker endpoints.<br/>**It's only used when the provider is `kafka`**. |
-| `wal.max_batch_bytes` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.max_batch_size` | String | `1MB` | The max size of a single producer batch.<br/>Warning: Kafka has a default limit of 1MB per message in a topic.<br/>**It's only used when the provider is `kafka`**. |
+| `wal.linger` | String | `200ms` | The linger duration of a kafka batch producer.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.consumer_wait_timeout` | String | `100ms` | The consumer wait timeout.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_init` | String | `500ms` | The initial backoff delay.<br/>**It's only used when the provider is `kafka`**. |
 | `wal.backoff_max` | String | `10s` | The maximum backoff delay.<br/>**It's only used when the provider is `kafka`**. |
@@ -391,10 +343,6 @@
 | `region_engine.mito.sst_meta_cache_size` | String | `128MB` | Cache size for SST metadata. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/32 of OS memory with a max limitation of 128MB. |
 | `region_engine.mito.vector_cache_size` | String | `512MB` | Cache size for vectors and arrow arrays. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
 | `region_engine.mito.page_cache_size` | String | `512MB` | Cache size for pages of SST row groups. Setting it to 0 to disable the cache.<br/>If not set, it's default to 1/16 of OS memory with a max limitation of 512MB. |
-| `region_engine.mito.enable_experimental_write_cache` | Bool | `false` | Whether to enable the experimental write cache. |
-| `region_engine.mito.experimental_write_cache_path` | String | `""` | File system path for write cache, defaults to `{data_home}/write_cache`. |
-| `region_engine.mito.experimental_write_cache_size` | String | `512MB` | Capacity for write cache. |
-| `region_engine.mito.experimental_write_cache_ttl` | String | `1h` | TTL for write cache. |
 | `region_engine.mito.sst_write_buffer_size` | String | `8MB` | Buffer size for SST writing. |
 | `region_engine.mito.scan_parallelism` | Integer | `0` | Parallelism to scan a region (default: 1/4 of cpu cores).<br/>- `0`: using the default value (1/4 of cpu cores).<br/>- `1`: scan in current thread.<br/>- `n`: scan in parallelism n. |
 | `region_engine.mito.parallel_scan_channel_size` | Integer | `32` | Capacity of the channel to send data from parallel scan tasks to the main task. |
@@ -426,5 +374,3 @@
 | `export_metrics.remote_write` | -- | -- | -- |
 | `export_metrics.remote_write.url` | String | `""` | The url the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=information_schema`. |
 | `export_metrics.remote_write.headers` | InlineTable | -- | HTTP headers of Prometheus remote-write carry. |
-| `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
-| `tracing.tokio_console_addr` | String | `None` | The tokio console address. |

config/datanode.example.toml

@@ -13,71 +13,24 @@ require_lease_before_startup = false
 ## By default, it provides services after all regions have been initialized.
 init_regions_in_background = false
 
-## Enable telemetry to collect anonymous usage data.
-enable_telemetry = true
-
-## Parallelism of initializing regions.
-init_regions_parallelism = 16
-
-## Deprecated, use `grpc.addr` instead.
-## +toml2docs:none-default
+## The gRPC address of the datanode.
 rpc_addr = "127.0.0.1:3001"
 
-## Deprecated, use `grpc.hostname` instead.
+## The hostname of the datanode.
 ## +toml2docs:none-default
 rpc_hostname = "127.0.0.1"
 
-## Deprecated, use `grpc.runtime_size` instead.
-## +toml2docs:none-default
+## The number of gRPC server worker threads.
 rpc_runtime_size = 8
 
-## Deprecated, use `grpc.rpc_max_recv_message_size` instead.
-## +toml2docs:none-default
+## The maximum receive message size for gRPC server.
 rpc_max_recv_message_size = "512MB"
 
-## Deprecated, use `grpc.rpc_max_send_message_size` instead.
-## +toml2docs:none-default
+## The maximum send message size for gRPC server.
 rpc_max_send_message_size = "512MB"
 
-## The gRPC server options.
-[grpc]
-## The address to bind the gRPC server.
-addr = "127.0.0.1:3001"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
-## The number of server worker threads.
-runtime_size = 8
-## The maximum receive message size for gRPC server.
-max_recv_message_size = "512MB"
-## The maximum send message size for gRPC server.
-max_send_message_size = "512MB"
-
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## +toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## +toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
-## The runtime options.
-[runtime]
-## The number of threads to execute the runtime for global read operations.
-read_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-write_rt_size = 8
-## The number of threads to execute the runtime for global background operations.
-bg_rt_size = 4
+## Enable telemetry to collect anonymous usage data.
+enable_telemetry = true
 
 ## The heartbeat options.
 [heartbeat]
@@ -167,7 +120,11 @@ broker_endpoints = ["127.0.0.1:9092"]
 ## The max size of a single producer batch.
 ## Warning: Kafka has a default limit of 1MB per message in a topic.
 ## **It's only used when the provider is `kafka`**.
-max_batch_bytes = "1MB"
+max_batch_size = "1MB"
+
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
 
 ## The consumer wait timeout.
 ## **It's only used when the provider is `kafka`**.
@@ -367,18 +324,6 @@ vector_cache_size = "512MB"
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 page_cache_size = "512MB"
 
-## Whether to enable the experimental write cache.
-enable_experimental_write_cache = false
-
-## File system path for write cache, defaults to `{data_home}/write_cache`.
-experimental_write_cache_path = ""
-
-## Capacity for write cache.
-experimental_write_cache_size = "512MB"
-
-## TTL for write cache.
-experimental_write_cache_ttl = "1h"
-
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
 
@@ -483,9 +428,3 @@ url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
-
-## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
-## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"

config/frontend.example.toml

@@ -5,15 +5,6 @@ mode = "standalone"
 ## +toml2docs:none-default
 default_timezone = "UTC"
 
-## The runtime options.
-[runtime]
-## The number of threads to execute the runtime for global read operations.
-read_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-write_rt_size = 8
-## The number of threads to execute the runtime for global background operations.
-bg_rt_size = 4
-
 ## The heartbeat options.
 [heartbeat]
 ## Interval for sending heartbeat messages to the metasrv.
@@ -26,40 +17,19 @@ retry_interval = "3s"
 [http]
 ## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
+## HTTP request timeout.
 timeout = "30s"
 ## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
+## Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
 body_limit = "64MB"
 
 ## The gRPC server options.
 [grpc]
 ## The address to bind the gRPC server.
 addr = "127.0.0.1:4001"
-## The hostname advertised to the metasrv,
-## and used for connections from outside the host
-hostname = "127.0.0.1"
 ## The number of server worker threads.
 runtime_size = 8
 
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## +toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## +toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
 ## MySQL server options.
 [mysql]
 ## Whether to enable.
@@ -100,7 +70,7 @@ addr = "127.0.0.1:4003"
 ## The number of server worker threads.
 runtime_size = 2
 
-## PostgresSQL server TLS options, see `mysql.tls` section.
+## PostgresSQL server TLS options, see `mysql_options.tls` section.
 [postgres.tls]
 ## TLS mode.
 mode = "disable"
@@ -118,8 +88,12 @@ watch = false
 
 ## OpenTSDB protocol options.
 [opentsdb]
-## Whether to enable OpenTSDB put in HTTP API.
+## Whether to enable
 enable = true
+## OpenTSDB telnet API server address.
+addr = "127.0.0.1:4242"
+## The number of server worker threads.
+runtime_size = 2
 
 ## InfluxDB protocol options.
 [influxdb]
@@ -166,6 +140,7 @@ metadata_cache_tti = "5m"
 [datanode]
 ## Datanode client options.
 [datanode.client]
+timeout = "10s"
 connect_timeout = "10s"
 tcp_nodelay = true
 
@@ -215,9 +190,3 @@ url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
-
-## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
-## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"

config/metasrv.example.toml

@@ -25,15 +25,6 @@ enable_telemetry = true
 ## If it's not empty, the metasrv will store all data with this key prefix.
 store_key_prefix = ""
 
-## The runtime options.
-[runtime]
-## The number of threads to execute the runtime for global read operations.
-read_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-write_rt_size = 8
-## The number of threads to execute the runtime for global background operations.
-bg_rt_size = 4
-
 ## Procedure storage options.
 [procedure]
 
@@ -150,9 +141,3 @@ url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
-
-## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
-## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"

config/standalone.example.toml

@@ -8,24 +8,14 @@ enable_telemetry = true
 ## +toml2docs:none-default
 default_timezone = "UTC"
 
-## The runtime options.
-[runtime]
-## The number of threads to execute the runtime for global read operations.
-read_rt_size = 8
-## The number of threads to execute the runtime for global write operations.
-write_rt_size = 8
-## The number of threads to execute the runtime for global background operations.
-bg_rt_size = 4
-
 ## The HTTP server options.
 [http]
 ## The address to bind the HTTP server.
 addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
+## HTTP request timeout.
 timeout = "30s"
 ## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
+## Support the following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
 body_limit = "64MB"
 
 ## The gRPC server options.
@@ -35,23 +25,6 @@ addr = "127.0.0.1:4001"
 ## The number of server worker threads.
 runtime_size = 8
 
-## gRPC server TLS options, see `mysql.tls` section.
-[grpc.tls]
-## TLS mode.
-mode = "disable"
-
-## Certificate file path.
-## +toml2docs:none-default
-cert_path = ""
-
-## Private key file path.
-## +toml2docs:none-default
-key_path = ""
-
-## Watch for Certificate and key file change and auto reload.
-## For now, gRPC tls config does not support auto reload.
-watch = false
-
 ## MySQL server options.
 [mysql]
 ## Whether to enable.
@@ -92,7 +65,7 @@ addr = "127.0.0.1:4003"
 ## The number of server worker threads.
 runtime_size = 2
 
-## PostgresSQL server TLS options, see `mysql.tls` section.
+## PostgresSQL server TLS options, see `mysql_options.tls` section.
 [postgres.tls]
 ## TLS mode.
 mode = "disable"
@@ -110,8 +83,12 @@ watch = false
 
 ## OpenTSDB protocol options.
 [opentsdb]
-## Whether to enable OpenTSDB put in HTTP API.
+## Whether to enable
 enable = true
+## OpenTSDB telnet API server address.
+addr = "127.0.0.1:4242"
+## The number of server worker threads.
+runtime_size = 2
 
 ## InfluxDB protocol options.
 [influxdb]
@@ -176,7 +153,11 @@ broker_endpoints = ["127.0.0.1:9092"]
 ## The max size of a single producer batch.
 ## Warning: Kafka has a default limit of 1MB per message in a topic.
 ## **It's only used when the provider is `kafka`**.
-max_batch_bytes = "1MB"
+max_batch_size = "1MB"
+
+## The linger duration of a kafka batch producer.
+## **It's only used when the provider is `kafka`**.
+linger = "200ms"
 
 ## The consumer wait timeout.
 ## **It's only used when the provider is `kafka`**.
@@ -390,18 +371,6 @@ vector_cache_size = "512MB"
 ## If not set, it's default to 1/16 of OS memory with a max limitation of 512MB.
 page_cache_size = "512MB"
 
-## Whether to enable the experimental write cache.
-enable_experimental_write_cache = false
-
-## File system path for write cache, defaults to `{data_home}/write_cache`.
-experimental_write_cache_path = ""
-
-## Capacity for write cache.
-experimental_write_cache_size = "512MB"
-
-## TTL for write cache.
-experimental_write_cache_ttl = "1h"
-
 ## Buffer size for SST writing.
 sst_write_buffer_size = "8MB"
 
@@ -506,9 +475,3 @@ url = ""
 
 ## HTTP headers of Prometheus remote-write carry.
 headers = { }
-
-## The tracing options. Only effect when compiled with `tokio-console` feature.
-[tracing]
-## The tokio console address.
-## +toml2docs:none-default
-tokio_console_addr = "127.0.0.1"

cyborg/.gitignore

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

cyborg/bin/check-pull-request.ts

@@ -1,79 +0,0 @@
-/*
- * Copyright 2023 Greptime Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import * as core from '@actions/core'
-import {handleError, obtainClient} from "@/common";
-import {context} from "@actions/github";
-import {PullRequestEvent} from "@octokit/webhooks-types";
-import {Options, sync as conventionalCommitsParser} from 'conventional-commits-parser';
-import conventionalCommitTypes from 'conventional-commit-types';
-import _ from "lodash";
-
-const defaultTypes = Object.keys(conventionalCommitTypes.types)
-const breakingChangeLabel = "breaking-change"
-
-// These options are copied from [1].
-// [1] https://github.com/conventional-changelog/conventional-changelog/blob/3f60b464/packages/conventional-changelog-conventionalcommits/src/parser.js
-export const parserOpts: Options = {
-    headerPattern: /^(\w*)(?:\((.*)\))?!?: (.*)$/,
-    breakingHeaderPattern: /^(\w*)(?:\((.*)\))?!: (.*)$/,
-    headerCorrespondence: [
-        'type',
-        'scope',
-        'subject'
-    ],
-    noteKeywords: ['BREAKING CHANGE', 'BREAKING-CHANGE'],
-    revertPattern: /^(?:Revert|revert:)\s"?([\s\S]+?)"?\s*This reverts commit (\w*)\./i,
-    revertCorrespondence: ['header', 'hash'],
-    issuePrefixes: ['#']
-}
-
-async function main() {
-    if (!context.payload.pull_request) {
-        throw new Error(`Only pull request event supported. ${context.eventName} is unsupported.`)
-    }
-
-    const client = obtainClient("GITHUB_TOKEN")
-    const payload = context.payload as PullRequestEvent
-    const { owner, repo, number } = {
-        owner: payload.pull_request.base.user.login,
-        repo: payload.pull_request.base.repo.name,
-        number: payload.pull_request.number,
-    }
-    const { data: pull_request } = await client.rest.pulls.get({
-        owner, repo, pull_number: number,
-    })
-
-    const commit = conventionalCommitsParser(pull_request.title, parserOpts)
-    core.info(`Receive commit: ${JSON.stringify(commit)}`)
-
-    if (!commit.type) {
-        throw Error(`Malformed commit: ${JSON.stringify(commit)}`)
-    }
-
-    if (!defaultTypes.includes(commit.type)) {
-        throw Error(`Unexpected type ${JSON.stringify(commit.type)} of commit: ${JSON.stringify(commit)}`)
-    }
-
-    const breakingChanges = _.filter(commit.notes, _.matches({ title: 'BREAKING CHANGE'}))
-    if (breakingChanges.length > 0) {
-        await client.rest.issues.addLabels({
-            owner, repo, issue_number: number, labels: [breakingChangeLabel]
-        })
-    }
-}
-
-main().catch(handleError)

cyborg/bin/follow-up-docs-issue.ts

@@ -1,106 +0,0 @@
-/*
- * Copyright 2023 Greptime Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import * as core from '@actions/core'
-import {handleError, obtainClient} from "@/common";
-import {context} from "@actions/github";
-import {PullRequestEditedEvent, PullRequestEvent, PullRequestOpenedEvent} from "@octokit/webhooks-types";
-// @ts-expect-error moduleResolution:nodenext issue 54523
-import {RequestError} from "@octokit/request-error";
-
-const needFollowUpDocs = "[x] This PR requires documentation updates."
-const labelDocsNotRequired = "docs-not-required"
-const labelDocsRequired = "docs-required"
-
-async function main() {
-    if (!context.payload.pull_request) {
-        throw new Error(`Only pull request event supported. ${context.eventName} is unsupported.`)
-    }
-
-    const client = obtainClient("GITHUB_TOKEN")
-    const docsClient = obtainClient("DOCS_REPO_TOKEN")
-    const payload = context.payload as PullRequestEvent
-    const { owner, repo, number, actor, title, html_url } = {
-        owner: payload.pull_request.base.user.login,
-        repo: payload.pull_request.base.repo.name,
-        number: payload.pull_request.number,
-        title: payload.pull_request.title,
-        html_url: payload.pull_request.html_url,
-        actor: payload.pull_request.user.login,
-    }
-    const followUpDocs = checkPullRequestEvent(payload)
-    if (followUpDocs) {
-        core.info("Follow up docs.")
-        await client.rest.issues.removeLabel({
-            owner, repo, issue_number: number, name: labelDocsNotRequired,
-        }).catch((e: RequestError) => {
-            if (e.status != 404) {
-                throw e;
-            }
-            core.debug(`Label ${labelDocsNotRequired} not exist.`)
-        })
-        await client.rest.issues.addLabels({
-            owner, repo, issue_number: number, labels: [labelDocsRequired],
-        })
-        await docsClient.rest.issues.create({
-            owner: 'GreptimeTeam',
-            repo: 'docs',
-            title: `Update docs for ${title}`,
-            body: `A document change request is generated from ${html_url}`,
-            assignee: actor,
-        }).then((res) => {
-            core.info(`Created issue ${res.data}`)
-        })
-    } else {
-        core.info("No need to follow up docs.")
-        await client.rest.issues.removeLabel({
-            owner, repo, issue_number: number, name: labelDocsRequired
-        }).catch((e: RequestError) => {
-            if (e.status != 404) {
-                throw e;
-            }
-            core.debug(`Label ${labelDocsRequired} not exist.`)
-        })
-        await client.rest.issues.addLabels({
-            owner, repo, issue_number: number, labels: [labelDocsNotRequired],
-        })
-    }
-}
-
-function checkPullRequestEvent(payload: PullRequestEvent) {
-    switch (payload.action) {
-        case "opened":
-            return checkPullRequestOpenedEvent(payload as PullRequestOpenedEvent)
-        case "edited":
-            return checkPullRequestEditedEvent(payload as PullRequestEditedEvent)
-        default:
-            throw new Error(`${payload.action} is unsupported.`)
-    }
-}
-
-function checkPullRequestOpenedEvent(event: PullRequestOpenedEvent): boolean {
-    // @ts-ignore
-    return event.pull_request.body?.includes(needFollowUpDocs)
-}
-
-function checkPullRequestEditedEvent(event: PullRequestEditedEvent): boolean {
-    const previous = event.changes.body?.from.includes(needFollowUpDocs)
-    const current = event.pull_request.body?.includes(needFollowUpDocs)
-    // from docs-not-need to docs-required
-    return (!previous) && current
-}
-
-main().catch(handleError)

cyborg/bin/report-ci-failure.ts

@@ -1,83 +0,0 @@
-/*
- * Copyright 2023 Greptime Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import * as core from '@actions/core'
-import {handleError, obtainClient} from "@/common"
-import {context} from "@actions/github"
-import _ from "lodash"
-
-async function main() {
-    const success = process.env["CI_REPORT_STATUS"] === "true"
-    core.info(`CI_REPORT_STATUS=${process.env["CI_REPORT_STATUS"]}, resolved to ${success}`)
-
-    const client = obtainClient("GITHUB_TOKEN")
-    const title = `Workflow run '${context.workflow}' failed`
-    const url = `${process.env["GITHUB_SERVER_URL"]}/${process.env["GITHUB_REPOSITORY"]}/actions/runs/${process.env["GITHUB_RUN_ID"]}`
-    const failure_comment = `@GreptimeTeam/db-approver\nNew failure: ${url} `
-    const success_comment = `@GreptimeTeam/db-approver\nBack to success: ${url}`
-
-    const {owner, repo} = context.repo
-    const labels = ['O-ci-failure']
-
-    const issues = await client.paginate(client.rest.issues.listForRepo, {
-        owner,
-        repo,
-        labels: labels.join(','),
-        state: "open",
-        sort: "created",
-        direction: "desc",
-    });
-    const issue = _.find(issues, (i) => i.title === title);
-
-    if (issue) { // exist issue
-        core.info(`Found previous issue ${issue.html_url}`)
-        if (!success) {
-            await client.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: issue.number,
-                body: failure_comment,
-            })
-        } else {
-            await client.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: issue.number,
-                body: success_comment,
-            })
-            await client.rest.issues.update({
-                owner,
-                repo,
-                issue_number: issue.number,
-                state: "closed",
-                state_reason: "completed",
-            })
-        }
-        core.setOutput("html_url", issue.html_url)
-    } else if (!success) { // create new issue for failure
-        const issue = await client.rest.issues.create({
-            owner,
-            repo,
-            title,
-            labels,
-            body: failure_comment,
-        })
-        core.info(`Created issue ${issue.data.html_url}`)
-        core.setOutput("html_url", issue.data.html_url)
-    }
-}
-
-main().catch(handleError)

cyborg/bin/schedule.ts

@@ -1,73 +0,0 @@
-/*
- * Copyright 2023 Greptime Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import * as core from '@actions/core'
-import {GitHub} from "@actions/github/lib/utils"
-import _ from "lodash";
-import dayjs from "dayjs";
-import {handleError, obtainClient} from "@/common";
-
-async function main() {
-    const client = obtainClient("GITHUB_TOKEN")
-    await unassign(client)
-}
-
-async function unassign(client: InstanceType<typeof GitHub>) {
-    const owner = "GreptimeTeam"
-    const repo = "greptimedb"
-
-    const dt = dayjs().subtract(14, 'days');
-    core.info(`Open issues updated before ${dt.toISOString()} will be considered stale.`)
-
-    const members = await client.paginate(client.rest.repos.listCollaborators, {
-        owner,
-        repo,
-        permission: "push",
-        per_page: 100
-    }).then((members) => members.map((member) => member.login))
-    core.info(`Members (${members.length}): ${members}`)
-
-    const issues = await client.paginate(client.rest.issues.listForRepo, {
-        owner,
-        repo,
-        state: "open",
-        sort: "created",
-        direction: "asc",
-        per_page: 100
-    })
-    for (const issue of issues) {
-        let assignees = [];
-        if (issue.assignee) {
-            assignees.push(issue.assignee.login)
-        }
-        for (const assignee of issue.assignees) {
-            assignees.push(assignee.login)
-        }
-        assignees = _.uniq(assignees)
-        assignees = _.difference(assignees, members)
-        if (assignees.length > 0 && dayjs(issue.updated_at).isBefore(dt)) {
-            core.info(`Assignees ${assignees} of issue ${issue.number} will be unassigned.`)
-            await client.rest.issues.removeAssignees({
-                owner,
-                repo,
-                issue_number: issue.number,
-                assignees: assignees,
-            })
-        }
-    }
-}
-
-main().catch(handleError)

cyborg/package.json

@@ -1,26 +0,0 @@
-{
-  "name": "cyborg",
-  "version": "1.0.0",
-  "description": "Automator for GreptimeDB Repository Management",
-  "private": true,
-  "packageManager": "pnpm@8.15.5",
-  "dependencies": {
-    "@actions/core": "^1.10.1",
-    "@actions/github": "^6.0.0",
-    "@octokit/request-error": "^6.1.1",
-    "@octokit/webhooks-types": "^7.5.1",
-    "conventional-commit-types": "^3.0.0",
-    "conventional-commits-parser": "^5.0.0",
-    "dayjs": "^1.11.11",
-    "dotenv": "^16.4.5",
-    "lodash": "^4.17.21"
-  },
-  "devDependencies": {
-    "@types/conventional-commits-parser": "^5.0.0",
-    "@types/lodash": "^4.17.0",
-    "@types/node": "^20.12.7",
-    "tsconfig-paths": "^4.2.0",
-    "tsx": "^4.8.2",
-    "typescript": "^5.4.5"
-  }
-}

cyborg/pnpm-lock.yaml

@@ -1,612 +0,0 @@
-lockfileVersion: '6.0'
-
-settings:
-  autoInstallPeers: true
-  excludeLinksFromLockfile: false
-
-dependencies:
-  '@actions/core':
-    specifier: ^1.10.1
-    version: 1.10.1
-  '@actions/github':
-    specifier: ^6.0.0
-    version: 6.0.0
-  '@octokit/request-error':
-    specifier: ^6.1.1
-    version: 6.1.1
-  '@octokit/webhooks-types':
-    specifier: ^7.5.1
-    version: 7.5.1
-  conventional-commit-types:
-    specifier: ^3.0.0
-    version: 3.0.0
-  conventional-commits-parser:
-    specifier: ^5.0.0
-    version: 5.0.0
-  dayjs:
-    specifier: ^1.11.11
-    version: 1.11.11
-  dotenv:
-    specifier: ^16.4.5
-    version: 16.4.5
-  lodash:
-    specifier: ^4.17.21
-    version: 4.17.21
-
-devDependencies:
-  '@types/conventional-commits-parser':
-    specifier: ^5.0.0
-    version: 5.0.0
-  '@types/lodash':
-    specifier: ^4.17.0
-    version: 4.17.0
-  '@types/node':
-    specifier: ^20.12.7
-    version: 20.12.7
-  tsconfig-paths:
-    specifier: ^4.2.0
-    version: 4.2.0
-  tsx:
-    specifier: ^4.8.2
-    version: 4.8.2
-  typescript:
-    specifier: ^5.4.5
-    version: 5.4.5
-
-packages:
-
-  /@actions/core@1.10.1:
-    resolution: {integrity: sha512-3lBR9EDAY+iYIpTnTIXmWcNbX3T2kCkAEQGIQx4NVQ0575nk2k3GRZDTPQG+vVtS2izSLmINlxXf0uLtnrTP+g==}
-    dependencies:
-      '@actions/http-client': 2.2.1
-      uuid: 8.3.2
-    dev: false
-
-  /@actions/github@6.0.0:
-    resolution: {integrity: sha512-alScpSVnYmjNEXboZjarjukQEzgCRmjMv6Xj47fsdnqGS73bjJNDpiiXmp8jr0UZLdUB6d9jW63IcmddUP+l0g==}
-    dependencies:
-      '@actions/http-client': 2.2.1
-      '@octokit/core': 5.2.0
-      '@octokit/plugin-paginate-rest': 9.2.1(@octokit/core@5.2.0)
-      '@octokit/plugin-rest-endpoint-methods': 10.4.1(@octokit/core@5.2.0)
-    dev: false
-
-  /@actions/http-client@2.2.1:
-    resolution: {integrity: sha512-KhC/cZsq7f8I4LfZSJKgCvEwfkE8o1538VoBeoGzokVLLnbFDEAdFD3UhoMklxo2un9NJVBdANOresx7vTHlHw==}
-    dependencies:
-      tunnel: 0.0.6
-      undici: 5.28.4
-    dev: false
-
-  /@esbuild/aix-ppc64@0.20.2:
-    resolution: {integrity: sha512-D+EBOJHXdNZcLJRBkhENNG8Wji2kgc9AZ9KiPr1JuZjsNtyHzrsfLRrY0tk2H2aoFu6RANO1y1iPPUCDYWkb5g==}
-    engines: {node: '>=12'}
-    cpu: [ppc64]
-    os: [aix]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/android-arm64@0.20.2:
-    resolution: {integrity: sha512-mRzjLacRtl/tWU0SvD8lUEwb61yP9cqQo6noDZP/O8VkwafSYwZ4yWy24kan8jE/IMERpYncRt2dw438LP3Xmg==}
-    engines: {node: '>=12'}
-    cpu: [arm64]
-    os: [android]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/android-arm@0.20.2:
-    resolution: {integrity: sha512-t98Ra6pw2VaDhqNWO2Oph2LXbz/EJcnLmKLGBJwEwXX/JAN83Fym1rU8l0JUWK6HkIbWONCSSatf4sf2NBRx/w==}
-    engines: {node: '>=12'}
-    cpu: [arm]
-    os: [android]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/android-x64@0.20.2:
-    resolution: {integrity: sha512-btzExgV+/lMGDDa194CcUQm53ncxzeBrWJcncOBxuC6ndBkKxnHdFJn86mCIgTELsooUmwUm9FkhSp5HYu00Rg==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [android]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/darwin-arm64@0.20.2:
-    resolution: {integrity: sha512-4J6IRT+10J3aJH3l1yzEg9y3wkTDgDk7TSDFX+wKFiWjqWp/iCfLIYzGyasx9l0SAFPT1HwSCR+0w/h1ES/MjA==}
-    engines: {node: '>=12'}
-    cpu: [arm64]
-    os: [darwin]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/darwin-x64@0.20.2:
-    resolution: {integrity: sha512-tBcXp9KNphnNH0dfhv8KYkZhjc+H3XBkF5DKtswJblV7KlT9EI2+jeA8DgBjp908WEuYll6pF+UStUCfEpdysA==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [darwin]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/freebsd-arm64@0.20.2:
-    resolution: {integrity: sha512-d3qI41G4SuLiCGCFGUrKsSeTXyWG6yem1KcGZVS+3FYlYhtNoNgYrWcvkOoaqMhwXSMrZRl69ArHsGJ9mYdbbw==}
-    engines: {node: '>=12'}
-    cpu: [arm64]
-    os: [freebsd]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/freebsd-x64@0.20.2:
-    resolution: {integrity: sha512-d+DipyvHRuqEeM5zDivKV1KuXn9WeRX6vqSqIDgwIfPQtwMP4jaDsQsDncjTDDsExT4lR/91OLjRo8bmC1e+Cw==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [freebsd]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-arm64@0.20.2:
-    resolution: {integrity: sha512-9pb6rBjGvTFNira2FLIWqDk/uaf42sSyLE8j1rnUpuzsODBq7FvpwHYZxQ/It/8b+QOS1RYfqgGFNLRI+qlq2A==}
-    engines: {node: '>=12'}
-    cpu: [arm64]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-arm@0.20.2:
-    resolution: {integrity: sha512-VhLPeR8HTMPccbuWWcEUD1Az68TqaTYyj6nfE4QByZIQEQVWBB8vup8PpR7y1QHL3CpcF6xd5WVBU/+SBEvGTg==}
-    engines: {node: '>=12'}
-    cpu: [arm]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-ia32@0.20.2:
-    resolution: {integrity: sha512-o10utieEkNPFDZFQm9CoP7Tvb33UutoJqg3qKf1PWVeeJhJw0Q347PxMvBgVVFgouYLGIhFYG0UGdBumROyiig==}
-    engines: {node: '>=12'}
-    cpu: [ia32]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-loong64@0.20.2:
-    resolution: {integrity: sha512-PR7sp6R/UC4CFVomVINKJ80pMFlfDfMQMYynX7t1tNTeivQ6XdX5r2XovMmha/VjR1YN/HgHWsVcTRIMkymrgQ==}
-    engines: {node: '>=12'}
-    cpu: [loong64]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-mips64el@0.20.2:
-    resolution: {integrity: sha512-4BlTqeutE/KnOiTG5Y6Sb/Hw6hsBOZapOVF6njAESHInhlQAghVVZL1ZpIctBOoTFbQyGW+LsVYZ8lSSB3wkjA==}
-    engines: {node: '>=12'}
-    cpu: [mips64el]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-ppc64@0.20.2:
-    resolution: {integrity: sha512-rD3KsaDprDcfajSKdn25ooz5J5/fWBylaaXkuotBDGnMnDP1Uv5DLAN/45qfnf3JDYyJv/ytGHQaziHUdyzaAg==}
-    engines: {node: '>=12'}
-    cpu: [ppc64]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-riscv64@0.20.2:
-    resolution: {integrity: sha512-snwmBKacKmwTMmhLlz/3aH1Q9T8v45bKYGE3j26TsaOVtjIag4wLfWSiZykXzXuE1kbCE+zJRmwp+ZbIHinnVg==}
-    engines: {node: '>=12'}
-    cpu: [riscv64]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-s390x@0.20.2:
-    resolution: {integrity: sha512-wcWISOobRWNm3cezm5HOZcYz1sKoHLd8VL1dl309DiixxVFoFe/o8HnwuIwn6sXre88Nwj+VwZUvJf4AFxkyrQ==}
-    engines: {node: '>=12'}
-    cpu: [s390x]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/linux-x64@0.20.2:
-    resolution: {integrity: sha512-1MdwI6OOTsfQfek8sLwgyjOXAu+wKhLEoaOLTjbijk6E2WONYpH9ZU2mNtR+lZ2B4uwr+usqGuVfFT9tMtGvGw==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [linux]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/netbsd-x64@0.20.2:
-    resolution: {integrity: sha512-K8/DhBxcVQkzYc43yJXDSyjlFeHQJBiowJ0uVL6Tor3jGQfSGHNNJcWxNbOI8v5k82prYqzPuwkzHt3J1T1iZQ==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [netbsd]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/openbsd-x64@0.20.2:
-    resolution: {integrity: sha512-eMpKlV0SThJmmJgiVyN9jTPJ2VBPquf6Kt/nAoo6DgHAoN57K15ZghiHaMvqjCye/uU4X5u3YSMgVBI1h3vKrQ==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [openbsd]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/sunos-x64@0.20.2:
-    resolution: {integrity: sha512-2UyFtRC6cXLyejf/YEld4Hajo7UHILetzE1vsRcGL3earZEW77JxrFjH4Ez2qaTiEfMgAXxfAZCm1fvM/G/o8w==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [sunos]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/win32-arm64@0.20.2:
-    resolution: {integrity: sha512-GRibxoawM9ZCnDxnP3usoUDO9vUkpAxIIZ6GQI+IlVmr5kP3zUq+l17xELTHMWTWzjxa2guPNyrpq1GWmPvcGQ==}
-    engines: {node: '>=12'}
-    cpu: [arm64]
-    os: [win32]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/win32-ia32@0.20.2:
-    resolution: {integrity: sha512-HfLOfn9YWmkSKRQqovpnITazdtquEW8/SoHW7pWpuEeguaZI4QnCRW6b+oZTztdBnZOS2hqJ6im/D5cPzBTTlQ==}
-    engines: {node: '>=12'}
-    cpu: [ia32]
-    os: [win32]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@esbuild/win32-x64@0.20.2:
-    resolution: {integrity: sha512-N49X4lJX27+l9jbLKSqZ6bKNjzQvHaT8IIFUy+YIqmXQdjYCToGWwOItDrfby14c78aDd5NHQl29xingXfCdLQ==}
-    engines: {node: '>=12'}
-    cpu: [x64]
-    os: [win32]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /@fastify/busboy@2.1.1:
-    resolution: {integrity: sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA==}
-    engines: {node: '>=14'}
-    dev: false
-
-  /@octokit/auth-token@4.0.0:
-    resolution: {integrity: sha512-tY/msAuJo6ARbK6SPIxZrPBms3xPbfwBrulZe0Wtr/DIY9lje2HeV1uoebShn6mx7SjCHif6EjMvoREj+gZ+SA==}
-    engines: {node: '>= 18'}
-    dev: false
-
-  /@octokit/core@5.2.0:
-    resolution: {integrity: sha512-1LFfa/qnMQvEOAdzlQymH0ulepxbxnCYAKJZfMci/5XJyIHWgEYnDmgnKakbTh7CH2tFQ5O60oYDvns4i9RAIg==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/auth-token': 4.0.0
-      '@octokit/graphql': 7.1.0
-      '@octokit/request': 8.4.0
-      '@octokit/request-error': 5.1.0
-      '@octokit/types': 13.5.0
-      before-after-hook: 2.2.3
-      universal-user-agent: 6.0.1
-    dev: false
-
-  /@octokit/endpoint@9.0.5:
-    resolution: {integrity: sha512-ekqR4/+PCLkEBF6qgj8WqJfvDq65RH85OAgrtnVp1mSxaXF03u2xW/hUdweGS5654IlC0wkNYC18Z50tSYTAFw==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/types': 13.5.0
-      universal-user-agent: 6.0.1
-    dev: false
-
-  /@octokit/graphql@7.1.0:
-    resolution: {integrity: sha512-r+oZUH7aMFui1ypZnAvZmn0KSqAUgE1/tUXIWaqUCa1758ts/Jio84GZuzsvUkme98kv0WFY8//n0J1Z+vsIsQ==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/request': 8.4.0
-      '@octokit/types': 13.5.0
-      universal-user-agent: 6.0.1
-    dev: false
-
-  /@octokit/openapi-types@20.0.0:
-    resolution: {integrity: sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA==}
-    dev: false
-
-  /@octokit/openapi-types@22.2.0:
-    resolution: {integrity: sha512-QBhVjcUa9W7Wwhm6DBFu6ZZ+1/t/oYxqc2tp81Pi41YNuJinbFRx8B133qVOrAaBbF7D/m0Et6f9/pZt9Rc+tg==}
-    dev: false
-
-  /@octokit/plugin-paginate-rest@9.2.1(@octokit/core@5.2.0):
-    resolution: {integrity: sha512-wfGhE/TAkXZRLjksFXuDZdmGnJQHvtU/joFQdweXUgzo1XwvBCD4o4+75NtFfjfLK5IwLf9vHTfSiU3sLRYpRw==}
-    engines: {node: '>= 18'}
-    peerDependencies:
-      '@octokit/core': '5'
-    dependencies:
-      '@octokit/core': 5.2.0
-      '@octokit/types': 12.6.0
-    dev: false
-
-  /@octokit/plugin-rest-endpoint-methods@10.4.1(@octokit/core@5.2.0):
-    resolution: {integrity: sha512-xV1b+ceKV9KytQe3zCVqjg+8GTGfDYwaT1ATU5isiUyVtlVAO3HNdzpS4sr4GBx4hxQ46s7ITtZrAsxG22+rVg==}
-    engines: {node: '>= 18'}
-    peerDependencies:
-      '@octokit/core': '5'
-    dependencies:
-      '@octokit/core': 5.2.0
-      '@octokit/types': 12.6.0
-    dev: false
-
-  /@octokit/request-error@5.1.0:
-    resolution: {integrity: sha512-GETXfE05J0+7H2STzekpKObFe765O5dlAKUTLNGeH+x47z7JjXHfsHKo5z21D/o/IOZTUEI6nyWyR+bZVP/n5Q==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/types': 13.5.0
-      deprecation: 2.3.1
-      once: 1.4.0
-    dev: false
-
-  /@octokit/request-error@6.1.1:
-    resolution: {integrity: sha512-1mw1gqT3fR/WFvnoVpY/zUM2o/XkMs/2AszUUG9I69xn0JFLv6PGkPhNk5lbfvROs79wiS0bqiJNxfCZcRJJdg==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/types': 13.5.0
-    dev: false
-
-  /@octokit/request@8.4.0:
-    resolution: {integrity: sha512-9Bb014e+m2TgBeEJGEbdplMVWwPmL1FPtggHQRkV+WVsMggPtEkLKPlcVYm/o8xKLkpJ7B+6N8WfQMtDLX2Dpw==}
-    engines: {node: '>= 18'}
-    dependencies:
-      '@octokit/endpoint': 9.0.5
-      '@octokit/request-error': 5.1.0
-      '@octokit/types': 13.5.0
-      universal-user-agent: 6.0.1
-    dev: false
-
-  /@octokit/types@12.6.0:
-    resolution: {integrity: sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw==}
-    dependencies:
-      '@octokit/openapi-types': 20.0.0
-    dev: false
-
-  /@octokit/types@13.5.0:
-    resolution: {integrity: sha512-HdqWTf5Z3qwDVlzCrP8UJquMwunpDiMPt5er+QjGzL4hqr/vBVY/MauQgS1xWxCDT1oMx1EULyqxncdCY/NVSQ==}
-    dependencies:
-      '@octokit/openapi-types': 22.2.0
-    dev: false
-
-  /@octokit/webhooks-types@7.5.1:
-    resolution: {integrity: sha512-1dozxWEP8lKGbtEu7HkRbK1F/nIPuJXNfT0gd96y6d3LcHZTtRtlf8xz3nicSJfesADxJyDh+mWBOsdLkqgzYw==}
-    dev: false
-
-  /@types/conventional-commits-parser@5.0.0:
-    resolution: {integrity: sha512-loB369iXNmAZglwWATL+WRe+CRMmmBPtpolYzIebFaX4YA3x+BEfLqhUAV9WanycKI3TG1IMr5bMJDajDKLlUQ==}
-    dependencies:
-      '@types/node': 20.12.7
-    dev: true
-
-  /@types/lodash@4.17.0:
-    resolution: {integrity: sha512-t7dhREVv6dbNj0q17X12j7yDG4bD/DHYX7o5/DbDxobP0HnGPgpRz2Ej77aL7TZT3DSw13fqUTj8J4mMnqa7WA==}
-    dev: true
-
-  /@types/node@20.12.7:
-    resolution: {integrity: sha512-wq0cICSkRLVaf3UGLMGItu/PtdY7oaXaI/RVU+xliKVOtRna3PRY57ZDfztpDL0n11vfymMUnXv8QwYCO7L1wg==}
-    dependencies:
-      undici-types: 5.26.5
-    dev: true
-
-  /JSONStream@1.3.5:
-    resolution: {integrity: sha512-E+iruNOY8VV9s4JEbe1aNEm6MiszPRr/UfcHMz0TQh1BXSxHK+ASV1R6W4HpjBhSeS+54PIsAMCBmwD06LLsqQ==}
-    hasBin: true
-    dependencies:
-      jsonparse: 1.3.1
-      through: 2.3.8
-    dev: false
-
-  /before-after-hook@2.2.3:
-    resolution: {integrity: sha512-NzUnlZexiaH/46WDhANlyR2bXRopNg4F/zuSA3OpZnllCUgRaOF2znDioDWrmbNVsuZk6l9pMquQB38cfBZwkQ==}
-    dev: false
-
-  /conventional-commit-types@3.0.0:
-    resolution: {integrity: sha512-SmmCYnOniSsAa9GqWOeLqc179lfr5TRu5b4QFDkbsrJ5TZjPJx85wtOr3zn+1dbeNiXDKGPbZ72IKbPhLXh/Lg==}
-    dev: false
-
-  /conventional-commits-parser@5.0.0:
-    resolution: {integrity: sha512-ZPMl0ZJbw74iS9LuX9YIAiW8pfM5p3yh2o/NbXHbkFuZzY5jvdi5jFycEOkmBW5H5I7nA+D6f3UcsCLP2vvSEA==}
-    engines: {node: '>=16'}
-    hasBin: true
-    dependencies:
-      JSONStream: 1.3.5
-      is-text-path: 2.0.0
-      meow: 12.1.1
-      split2: 4.2.0
-    dev: false
-
-  /dayjs@1.11.11:
-    resolution: {integrity: sha512-okzr3f11N6WuqYtZSvm+F776mB41wRZMhKP+hc34YdW+KmtYYK9iqvHSwo2k9FEH3fhGXvOPV6yz2IcSrfRUDg==}
-    dev: false
-
-  /deprecation@2.3.1:
-    resolution: {integrity: sha512-xmHIy4F3scKVwMsQ4WnVaS8bHOx0DmVwRywosKhaILI0ywMDWPtBSku2HNxRvF7jtwDRsoEwYQSfbxj8b7RlJQ==}
-    dev: false
-
-  /dotenv@16.4.5:
-    resolution: {integrity: sha512-ZmdL2rui+eB2YwhsWzjInR8LldtZHGDoQ1ugH85ppHKwpUHL7j7rN0Ti9NCnGiQbhaZ11FpR+7ao1dNsmduNUg==}
-    engines: {node: '>=12'}
-    dev: false
-
-  /esbuild@0.20.2:
-    resolution: {integrity: sha512-WdOOppmUNU+IbZ0PaDiTst80zjnrOkyJNHoKupIcVyU8Lvla3Ugx94VzkQ32Ijqd7UhHJy75gNWDMUekcrSJ6g==}
-    engines: {node: '>=12'}
-    hasBin: true
-    requiresBuild: true
-    optionalDependencies:
-      '@esbuild/aix-ppc64': 0.20.2
-      '@esbuild/android-arm': 0.20.2
-      '@esbuild/android-arm64': 0.20.2
-      '@esbuild/android-x64': 0.20.2
-      '@esbuild/darwin-arm64': 0.20.2
-      '@esbuild/darwin-x64': 0.20.2
-      '@esbuild/freebsd-arm64': 0.20.2
-      '@esbuild/freebsd-x64': 0.20.2
-      '@esbuild/linux-arm': 0.20.2
-      '@esbuild/linux-arm64': 0.20.2
-      '@esbuild/linux-ia32': 0.20.2
-      '@esbuild/linux-loong64': 0.20.2
-      '@esbuild/linux-mips64el': 0.20.2
-      '@esbuild/linux-ppc64': 0.20.2
-      '@esbuild/linux-riscv64': 0.20.2
-      '@esbuild/linux-s390x': 0.20.2
-      '@esbuild/linux-x64': 0.20.2
-      '@esbuild/netbsd-x64': 0.20.2
-      '@esbuild/openbsd-x64': 0.20.2
-      '@esbuild/sunos-x64': 0.20.2
-      '@esbuild/win32-arm64': 0.20.2
-      '@esbuild/win32-ia32': 0.20.2
-      '@esbuild/win32-x64': 0.20.2
-    dev: true
-
-  /fsevents@2.3.3:
-    resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==}
-    engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
-    os: [darwin]
-    requiresBuild: true
-    dev: true
-    optional: true
-
-  /get-tsconfig@4.7.3:
-    resolution: {integrity: sha512-ZvkrzoUA0PQZM6fy6+/Hce561s+faD1rsNwhnO5FelNjyy7EMGJ3Rz1AQ8GYDWjhRs/7dBLOEJvhK8MiEJOAFg==}
-    dependencies:
-      resolve-pkg-maps: 1.0.0
-    dev: true
-
-  /is-text-path@2.0.0:
-    resolution: {integrity: sha512-+oDTluR6WEjdXEJMnC2z6A4FRwFoYuvShVVEGsS7ewc0UTi2QtAKMDJuL4BDEVt+5T7MjFo12RP8ghOM75oKJw==}
-    engines: {node: '>=8'}
-    dependencies:
-      text-extensions: 2.4.0
-    dev: false
-
-  /json5@2.2.3:
-    resolution: {integrity: sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg==}
-    engines: {node: '>=6'}
-    hasBin: true
-    dev: true
-
-  /jsonparse@1.3.1:
-    resolution: {integrity: sha512-POQXvpdL69+CluYsillJ7SUhKvytYjW9vG/GKpnf+xP8UWgYEM/RaMzHHofbALDiKbbP1W8UEYmgGl39WkPZsg==}
-    engines: {'0': node >= 0.2.0}
-    dev: false
-
-  /lodash@4.17.21:
-    resolution: {integrity: sha512-v2kDEe57lecTulaDIuNTPy3Ry4gLGJ6Z1O3vE1krgXZNrsQ+LFTGHVxVjcXPs17LhbZVGedAJv8XZ1tvj5FvSg==}
-    dev: false
-
-  /meow@12.1.1:
-    resolution: {integrity: sha512-BhXM0Au22RwUneMPwSCnyhTOizdWoIEPU9sp0Aqa1PnDMR5Wv2FGXYDjuzJEIX+Eo2Rb8xuYe5jrnm5QowQFkw==}
-    engines: {node: '>=16.10'}
-    dev: false
-
-  /minimist@1.2.8:
-    resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==}
-    dev: true
-
-  /once@1.4.0:
-    resolution: {integrity: sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==}
-    dependencies:
-      wrappy: 1.0.2
-    dev: false
-
-  /resolve-pkg-maps@1.0.0:
-    resolution: {integrity: sha512-seS2Tj26TBVOC2NIc2rOe2y2ZO7efxITtLZcGSOnHHNOQ7CkiUBfw0Iw2ck6xkIhPwLhKNLS8BO+hEpngQlqzw==}
-    dev: true
-
-  /split2@4.2.0:
-    resolution: {integrity: sha512-UcjcJOWknrNkF6PLX83qcHM6KHgVKNkV62Y8a5uYDVv9ydGQVwAHMKqHdJje1VTWpljG0WYpCDhrCdAOYH4TWg==}
-    engines: {node: '>= 10.x'}
-    dev: false
-
-  /strip-bom@3.0.0:
-    resolution: {integrity: sha512-vavAMRXOgBVNF6nyEEmL3DBK19iRpDcoIwW+swQ+CbGiu7lju6t+JklA1MHweoWtadgt4ISVUsXLyDq34ddcwA==}
-    engines: {node: '>=4'}
-    dev: true
-
-  /text-extensions@2.4.0:
-    resolution: {integrity: sha512-te/NtwBwfiNRLf9Ijqx3T0nlqZiQ2XrrtBvu+cLL8ZRrGkO0NHTug8MYFKyoSrv/sHTaSKfilUkizV6XhxMJ3g==}
-    engines: {node: '>=8'}
-    dev: false
-
-  /through@2.3.8:
-    resolution: {integrity: sha512-w89qg7PI8wAdvX60bMDP+bFoD5Dvhm9oLheFp5O4a2QF0cSBGsBX4qZmadPMvVqlLJBBci+WqGGOAPvcDeNSVg==}
-    dev: false
-
-  /tsconfig-paths@4.2.0:
-    resolution: {integrity: sha512-NoZ4roiN7LnbKn9QqE1amc9DJfzvZXxF4xDavcOWt1BPkdx+m+0gJuPM+S0vCe7zTJMYUP0R8pO2XMr+Y8oLIg==}
-    engines: {node: '>=6'}
-    dependencies:
-      json5: 2.2.3
-      minimist: 1.2.8
-      strip-bom: 3.0.0
-    dev: true
-
-  /tsx@4.8.2:
-    resolution: {integrity: sha512-hmmzS4U4mdy1Cnzpl/NQiPUC2k34EcNSTZYVJThYKhdqTwuBeF+4cG9KUK/PFQ7KHaAaYwqlb7QfmsE2nuj+WA==}
-    engines: {node: '>=18.0.0'}
-    hasBin: true
-    dependencies:
-      esbuild: 0.20.2
-      get-tsconfig: 4.7.3
-    optionalDependencies:
-      fsevents: 2.3.3
-    dev: true
-
-  /tunnel@0.0.6:
-    resolution: {integrity: sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg==}
-    engines: {node: '>=0.6.11 <=0.7.0 || >=0.7.3'}
-    dev: false
-
-  /typescript@5.4.5:
-    resolution: {integrity: sha512-vcI4UpRgg81oIRUFwR0WSIHKt11nJ7SAVlYNIu+QpqeyXP+gpQJy/Z4+F0aGxSE4MqwjyXvW/TzgkLAx2AGHwQ==}
-    engines: {node: '>=14.17'}
-    hasBin: true
-    dev: true
-
-  /undici-types@5.26.5:
-    resolution: {integrity: sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==}
-    dev: true
-
-  /undici@5.28.4:
-    resolution: {integrity: sha512-72RFADWFqKmUb2hmmvNODKL3p9hcB6Gt2DOQMis1SEBaV6a4MH8soBvzg+95CYhCKPFedut2JY9bMfrDl9D23g==}
-    engines: {node: '>=14.0'}
-    dependencies:
-      '@fastify/busboy': 2.1.1
-    dev: false
-
-  /universal-user-agent@6.0.1:
-    resolution: {integrity: sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ==}
-    dev: false
-
-  /uuid@8.3.2:
-    resolution: {integrity: sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==}
-    hasBin: true
-    dev: false
-
-  /wrappy@1.0.2:
-    resolution: {integrity: sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==}
-    dev: false

cyborg/src/common.ts

@@ -1,30 +0,0 @@
-/*
- * Copyright 2023 Greptime Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import * as core from "@actions/core";
-import {config} from "dotenv";
-import {getOctokit} from "@actions/github";
-import {GitHub} from "@actions/github/lib/utils";
-
-export function handleError(err: any): void {
-    console.error(err)
-    core.setFailed(`Unhandled error: ${err}`)
-}
-
-export function obtainClient(token: string): InstanceType<typeof GitHub> {
-    config()
-    return getOctokit(process.env[token])
-}

cyborg/tsconfig.json

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

docker/ci/ubuntu/Dockerfile.fuzztests

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

docker/dev-builder/android/Dockerfile

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

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

@@ -1,102 +0,0 @@
-x-custom:
-  initial_cluster_token: &initial_cluster_token "--initial-cluster-token=etcd-cluster"
-  common_settings: &common_settings
-    image: quay.io/coreos/etcd:v3.5.10
-    entrypoint: /usr/local/bin/etcd
-
-services:
-  etcd0:
-    <<: *common_settings
-    container_name: etcd0
-    ports:
-      - 2379:2379
-      - 2380:2380
-    command:
-      - --name=etcd0
-      - --data-dir=/var/lib/etcd
-      - --initial-advertise-peer-urls=http://etcd0:2380
-      - --listen-peer-urls=http://0.0.0.0:2380
-      - --listen-client-urls=http://0.0.0.0:2379
-      - --advertise-client-urls=http://etcd0:2379
-      - --heartbeat-interval=250
-      - --election-timeout=1250
-      - --initial-cluster=etcd0=http://etcd0:2380
-      - --initial-cluster-state=new
-      - *initial_cluster_token
-    volumes:
-      - /tmp/greptimedb-cluster-docker-compose/etcd0:/var/lib/etcd
-    healthcheck:
-      test: [ "CMD", "etcdctl", "--endpoints=http://etcd0:2379", "endpoint", "health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    networks:
-      - greptimedb
-
-  metasrv:
-    image: docker.io/greptime/greptimedb:latest
-    container_name: metasrv
-    ports:
-      - 3002:3002
-    command:
-      - metasrv
-      - start
-      - --bind-addr=0.0.0.0:3002
-      - --server-addr=metasrv:3002
-      - --store-addrs=etcd0:2379
-    healthcheck:
-      test: [ "CMD", "curl", "-f", "http://metasrv:3002/health" ]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-    depends_on:
-      etcd0:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-  datanode0:
-    image: docker.io/greptime/greptimedb:latest
-    container_name: datanode0
-    ports:
-      - 3001:3001
-    command:
-      - datanode
-      - start
-      - --node-id=0
-      - --rpc-addr=0.0.0.0:3001
-      - --rpc-hostname=datanode0:3001
-      - --metasrv-addr=metasrv:3002
-    volumes:
-      - /tmp/greptimedb-cluster-docker-compose/datanode0:/tmp/greptimedb
-    depends_on:
-      metasrv:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-  frontend0:
-    image: docker.io/greptime/greptimedb:latest
-    container_name: frontend0
-    ports:
-      - 4000:4000
-      - 4001:4001
-      - 4002:4002
-      - 4003:4003
-    command:
-      - frontend
-      - start
-      - --metasrv-addrs=metasrv:3002
-      - --http-addr=0.0.0.0:4000
-      - --rpc-addr=0.0.0.0:4001
-      - --mysql-addr=0.0.0.0:4002
-      - --postgres-addr=0.0.0.0:4003
-    depends_on:
-      metasrv:
-        condition: service_healthy
-    networks:
-      - greptimedb
-
-networks:
-  greptimedb:
-    name: greptimedb

docs/benchmarks/tsbs/README.md

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

docs/benchmarks/tsbs/v0.7.0.md

@@ -23,28 +23,28 @@
 
 ## Write performance
 
-| Environment     | Ingest rate (rows/s) |
-| --------------- | -------------------- |
-| Local           | 369581.464           |
-| EC2 c5d.2xlarge | 298716.664           |
+| Environment        | Ingest rate (rows/s)  |
+| ------------------ | --------------------- |
+| Local              | 3695814.64            |
+| EC2 c5d.2xlarge    | 2987166.64            |
 
 
 ## Query performance
 
-| Query type            | Local (ms) | EC2 c5d.2xlarge (ms) |
-| --------------------- | ---------- | -------------------- |
-| cpu-max-all-1         | 30.56      | 54.74                |
-| cpu-max-all-8         | 52.69      | 70.50                |
-| double-groupby-1      | 664.30     | 1366.63              |
-| double-groupby-5      | 1391.26    | 2141.71              |
-| double-groupby-all    | 2828.94    | 3389.59              |
-| groupby-orderby-limit | 718.92     | 1213.90              |
-| high-cpu-1            | 29.21      | 52.98                |
-| high-cpu-all          | 5514.12    | 7194.91              |
-| lastpoint             | 7571.40    | 9423.41              |
-| single-groupby-1-1-1  | 19.09      | 7.77                 |
-| single-groupby-1-1-12 | 27.28      | 51.64                |
-| single-groupby-1-8-1  | 31.85      | 11.64                |
-| single-groupby-5-1-1  | 16.14      | 9.67                 |
-| single-groupby-5-1-12 | 27.21      | 53.62                |
-| single-groupby-5-8-1  | 39.62      | 14.96                |
+| Query type            | Local (ms) | EC2 c5d.2xlarge (ms)   |
+| --------------------- | ---------- | ---------------------- |
+| cpu-max-all-1         | 30.56      | 54.74                  |
+| cpu-max-all-8         | 52.69      | 70.50                  |
+| double-groupby-1      | 664.30     | 1366.63                |
+| double-groupby-5      | 1391.26    | 2141.71                |
+| double-groupby-all    | 2828.94    | 3389.59                |
+| groupby-orderby-limit | 718.92     | 1213.90                |
+| high-cpu-1            | 29.21      | 52.98                  |
+| high-cpu-all          | 5514.12    | 7194.91                |
+| lastpoint             | 7571.40    | 9423.41                |
+| single-groupby-1-1-1  | 19.09      | 7.77                   |
+| single-groupby-1-1-12 | 27.28      | 51.64                  |
+| single-groupby-1-8-1  | 31.85      | 11.64                  |
+| single-groupby-5-1-1  | 16.14      | 9.67                   |
+| single-groupby-5-1-12 | 27.21      | 53.62                  |
+| single-groupby-5-8-1  | 39.62      | 14.96                  |

docs/benchmarks/tsbs/v0.8.0.md

@@ -1,58 +0,0 @@
-# TSBS benchmark - v0.8.0
-
-## Environment
-
-### Local
-
-|        |                                    |
-| ------ | ---------------------------------- |
-| CPU    | AMD Ryzen 7 7735HS (8 core 3.2GHz) |
-| Memory | 32GB                               |
-| Disk   | SOLIDIGM SSDPFKNU010TZ             |
-| OS     | Ubuntu 22.04.2 LTS                 |
-
-### Amazon EC2
-
-|         |                |
-| ------- | -------------- |
-| Machine | c5d.2xlarge    |
-| CPU     | 8 core         |
-| Memory  | 16GB           |
-| Disk    | 50GB (GP3)     |
-| OS      | Ubuntu 22.04.1 |
-
-## Write performance
-
-| Environment     | Ingest rate (rows/s) |
-| --------------- | -------------------- |
-| Local           | 315369.66            |
-| EC2 c5d.2xlarge | 222148.56            |
-
-## Query performance
-
-| Query type            | Local (ms) | EC2 c5d.2xlarge (ms) |
-| --------------------- | ---------- | -------------------- |
-| cpu-max-all-1         | 24.63      | 15.29                |
-| cpu-max-all-8         | 51.69      | 33.53                |
-| double-groupby-1      | 673.51     | 1295.38              |
-| double-groupby-5      | 1244.93    | 1993.91              |
-| double-groupby-all    | 2215.44    | 3056.77              |
-| groupby-orderby-limit | 754.50     | 1546.49              |
-| high-cpu-1            | 19.62      | 11.58                |
-| high-cpu-all          | 5402.31    | 8011.43              |
-| lastpoint             | 6756.12    | 9312.67              |
-| single-groupby-1-1-1  | 15.70      | 7.67                 |
-| single-groupby-1-1-12 | 16.72      | 9.29                 |
-| single-groupby-1-8-1  | 26.72      | 17.97                |
-| single-groupby-5-1-1  | 18.17      | 10.09                |
-| single-groupby-5-1-12 | 20.04      | 12.37                |
-| single-groupby-5-8-1  | 35.63      | 23.13                |
-
-`single-groupby-1-1-1` query throughput
-
-| Environment     | Client concurrency | mean time (ms) | qps (queries/sec) |
-| --------------- | ------------------ | -------------- | ----------------- |
-| Local           | 50                 | 42.87          | 1165.73           |
-| Local           | 100                | 89.29          | 1119.38           |
-| EC2 c5d.2xlarge | 50                 | 69.25          | 721.73            |
-| EC2 c5d.2xlarge | 100                | 140.93         | 709.35            |

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

@@ -1,136 +0,0 @@
-# How to write fuzz tests
-
-This document introduces how to write fuzz tests in GreptimeDB.
-
-## What is a fuzz test
-Fuzz test is tool that leverage deterministic random generation to assist in finding bugs. The goal of fuzz tests is to identify inputs generated by the fuzzer that cause system panics, crashes, or unexpected behaviors to occur. And we are using the [cargo-fuzz](https://github.com/rust-fuzz/cargo-fuzz) to run our fuzz test targets. 
-
-## Why we need them
-- Find bugs by leveraging random generation
-- Integrate with other tests (e.g., e2e)
-
-## Resources
-All fuzz test-related resources are located in the `/tests-fuzz` directory.
-There are two types of resources: (1) fundamental components and (2) test targets.
-
-### Fundamental components 
-They are located in the `/tests-fuzz/src` directory. The fundamental components define how to generate SQLs (including dialects for different protocols) and validate execution results (e.g., column attribute validation), etc.
-
-### Test targets
-They are located in the `/tests-fuzz/targets` directory, with each file representing an independent fuzz test case. The target utilizes fundamental components to generate SQLs, sends the generated SQLs via specified protocol, and validates the results of SQL execution.
-
-Figure 1 illustrates the fundamental components of the fuzz test provide the ability to generate random SQLs. It utilizes a Random Number Generator (Rng) to generate the Intermediate Representation (IR), then employs a DialectTranslator to produce specified dialects for different protocols. Finally, the fuzz tests send the generated SQL via the specified protocol and verify that the execution results meet expectations.
-```
-                            Rng                                 
-                             |                                  
-                             |                                  
-                             v                                  
-                       ExprGenerator                            
-                             |                                  
-                             |                                  
-                             v                                  
-               Intermediate representation (IR)                 
-                             |                                  
-                             |                                  
-      +----------------------+----------------------+           
-      |                      |                      |           
-      v                      v                      v           
-MySQLTranslator    PostgreSQLTranslator   OtherDialectTranslator
-      |                      |                      |           
-      |                      |                      |           
-      v                      v                      v           
-SQL(MySQL Dialect)         .....                  .....         
-      |
-      |
-      v
-  Fuzz Test
-
-```
-(Figure1: Overview of fuzz tests)
-
-For more details about fuzz targets and fundamental components, please refer to this [tracking issue](https://github.com/GreptimeTeam/greptimedb/issues/3174).
-
-## How to add a fuzz test target
-
-1. Create an empty rust source file under the `/tests-fuzz/targets/<fuzz-target>.rs` directory.
-
-2. Register the fuzz test target in the `/tests-fuzz/Cargo.toml` file.
-
-```toml
-[[bin]]
-name = "<fuzz-target>"
-path = "targets/<fuzz-target>.rs"
-test = false
-bench = false
-doc = false
-```
-
-3. Define the `FuzzInput` in the `/tests-fuzz/targets/<fuzz-target>.rs`.
-
-```rust
-#![no_main]
-use libfuzzer_sys::arbitrary::{Arbitrary, Unstructured};
-
-#[derive(Clone, Debug)]
-struct FuzzInput {
-    seed: u64,
-}
-
-impl Arbitrary<'_> for FuzzInput {
-    fn arbitrary(u: &mut Unstructured<'_>) -> arbitrary::Result<Self> {
-        let seed = u.int_in_range(u64::MIN..=u64::MAX)?;
-        Ok(FuzzInput { seed })
-    }
-}
-```
-
-4. Write your first fuzz test target in the `/tests-fuzz/targets/<fuzz-target>.rs`.
-
-```rust
-use libfuzzer_sys::fuzz_target;
-use rand::{Rng, SeedableRng};
-use rand_chacha::ChaChaRng;
-use snafu::ResultExt;
-use sqlx::{MySql, Pool};
-use tests_fuzz::fake::{
-    merge_two_word_map_fn, random_capitalize_map, uppercase_and_keyword_backtick_map,
-    MappedGenerator, WordGenerator,
-};
-use tests_fuzz::generator::create_expr::CreateTableExprGeneratorBuilder;
-use tests_fuzz::generator::Generator;
-use tests_fuzz::ir::CreateTableExpr;
-use tests_fuzz::translator::mysql::create_expr::CreateTableExprTranslator;
-use tests_fuzz::translator::DslTranslator;
-use tests_fuzz::utils::{init_greptime_connections, Connections};
-
-fuzz_target!(|input: FuzzInput| {
-    common_telemetry::init_default_ut_logging();
-    common_runtime::block_on_write(async {
-        let Connections { mysql } = init_greptime_connections().await;
-            let mut rng = ChaChaRng::seed_from_u64(input.seed);
-            let columns = rng.gen_range(2..30);
-            let create_table_generator = CreateTableExprGeneratorBuilder::default()
-                .name_generator(Box::new(MappedGenerator::new(
-                    WordGenerator,
-                    merge_two_word_map_fn(random_capitalize_map, uppercase_and_keyword_backtick_map),
-                )))
-                .columns(columns)
-                .engine("mito")
-                .if_not_exists(if_not_exists)
-                .build()
-                .unwrap();
-            let ir = create_table_generator.generate(&mut rng);
-            let translator = CreateTableExprTranslator;
-            let sql = translator.translate(&expr).unwrap();
-            mysql.execute(&sql).await
-    })
-});
-```
-
-5. Run your fuzz test target
-
-```bash
-    cargo fuzz run <fuzz-target> --fuzz-dir tests-fuzz
-```
-
-For more details, please refer to this [document](/tests-fuzz/README.md).

docs/schema-structs.md

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

grafana/README.md

@@ -7,60 +7,4 @@ Status notify: we are still working on this config. It's expected to change freq
 
 # How to use
 
-## `greptimedb.json`
-
 Open Grafana Dashboard page, choose `New` -> `Import`. And upload `greptimedb.json` file.
-
-## `greptimedb-cluster.json`
-
-This cluster dashboard provides a comprehensive view of incoming requests, response statuses, and internal activities such as flush and compaction, with a layered structure from frontend to datanode. Designed with a focus on alert functionality, its primary aim is to highlight any anomalies in metrics, allowing users to quickly pinpoint the cause of errors.
-
-We use Prometheus to scrape off metrics from nodes in GreptimeDB cluster, Grafana to visualize the diagram. Any compatible stack should work too.
-
-__Note__: This dashboard is still in an early stage of development. Any issue or advice on improvement is welcomed.
-
-### Configuration
-
-Please ensure the following configuration before importing the dashboard into Grafana.
-
-__1. Prometheus scrape config__
-
-Assign `greptime_pod` label to each host target. We use this label to identify each node instance.
-
-```yml
-# example config
-# only to indicate how to assign labels to each target
-# modify yours accordingly
-scrape_configs:
-  - job_name: metasrv
-    static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: metasrv
-
-  - job_name: datanode
-    static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode1
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode2
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: datanode3
-
-  - job_name: frontend
-    static_configs:
-    - targets: ['<ip>:<port>']
-      labels:
-        greptime_pod: frontend
-```
-
-__2. Grafana config__
-
-Create a Prometheus data source in Grafana before using this dashboard. We use `datasource` as a variable in Grafana dashboard so that multiple environments are supported.
-
-### Usage
-
-Use `datasource` or `greptime_pod` on the upper-left corner to filter data from certain node.

licenserc.toml

@@ -17,15 +17,12 @@ headerPath = "Apache-2.0.txt"
 includes = [
     "*.rs",
     "*.py",
-    "*.ts",
 ]
 
 excludes = [
     # copied sources
     "src/common/base/src/readable_size.rs",
-    "src/common/base/src/secrets.rs",
     "src/servers/src/repeated_field.rs",
-    "src/servers/src/http/test_helpers.rs",
 ]
 
 [properties]

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "nightly-2024-04-20"
+channel = "nightly-2024-04-18"

src/api/src/error.rs

@@ -30,7 +30,6 @@ pub enum Error {
     #[snafu(display("Unknown proto column datatype: {}", datatype))]
     UnknownColumnDataType {
         datatype: i32,
-        #[snafu(implicit)]
         location: Location,
         #[snafu(source)]
         error: prost::DecodeError,
@@ -39,14 +38,12 @@ pub enum Error {
     #[snafu(display("Failed to create column datatype from {:?}", from))]
     IntoColumnDataType {
         from: ConcreteDataType,
-        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Failed to convert column default constraint, column: {}", column))]
     ConvertColumnDefaultConstraint {
         column: String,
-        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },
@@ -54,7 +51,6 @@ pub enum Error {
     #[snafu(display("Invalid column default constraint, column: {}", column))]
     InvalidColumnDefaultConstraint {
         column: String,
-        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },

src/api/src/helper.rs

@@ -20,20 +20,21 @@ use common_decimal::Decimal128;
 use common_time::interval::IntervalUnit;
 use common_time::time::Time;
 use common_time::timestamp::TimeUnit;
-use common_time::{Date, DateTime, Interval, Timestamp};
+use common_time::{Date, DateTime, Duration, Interval, Timestamp};
 use datatypes::prelude::{ConcreteDataType, ValueRef};
 use datatypes::scalars::ScalarVector;
 use datatypes::types::{
-    Int16Type, Int8Type, IntervalType, TimeType, TimestampType, UInt16Type, UInt8Type,
+    DurationType, Int16Type, Int8Type, IntervalType, TimeType, TimestampType, UInt16Type, UInt8Type,
 };
 use datatypes::value::{OrderedF32, OrderedF64, Value};
 use datatypes::vectors::{
-    BinaryVector, BooleanVector, DateTimeVector, DateVector, Decimal128Vector, Float32Vector,
-    Float64Vector, Int32Vector, Int64Vector, IntervalDayTimeVector, IntervalMonthDayNanoVector,
-    IntervalYearMonthVector, PrimitiveVector, StringVector, TimeMicrosecondVector,
-    TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector, TimestampMicrosecondVector,
-    TimestampMillisecondVector, TimestampNanosecondVector, TimestampSecondVector, UInt32Vector,
-    UInt64Vector, VectorRef,
+    BinaryVector, BooleanVector, DateTimeVector, DateVector, Decimal128Vector,
+    DurationMicrosecondVector, DurationMillisecondVector, DurationNanosecondVector,
+    DurationSecondVector, Float32Vector, Float64Vector, Int32Vector, Int64Vector,
+    IntervalDayTimeVector, IntervalMonthDayNanoVector, IntervalYearMonthVector, PrimitiveVector,
+    StringVector, TimeMicrosecondVector, TimeMillisecondVector, TimeNanosecondVector,
+    TimeSecondVector, TimestampMicrosecondVector, TimestampMillisecondVector,
+    TimestampNanosecondVector, TimestampSecondVector, UInt32Vector, UInt64Vector, VectorRef,
 };
 use greptime_proto::v1;
 use greptime_proto::v1::column_data_type_extension::TypeExt;
@@ -126,6 +127,14 @@ impl From<ColumnDataTypeWrapper> for ConcreteDataType {
             ColumnDataType::IntervalMonthDayNano => {
                 ConcreteDataType::interval_month_day_nano_datatype()
             }
+            ColumnDataType::DurationSecond => ConcreteDataType::duration_second_datatype(),
+            ColumnDataType::DurationMillisecond => {
+                ConcreteDataType::duration_millisecond_datatype()
+            }
+            ColumnDataType::DurationMicrosecond => {
+                ConcreteDataType::duration_microsecond_datatype()
+            }
+            ColumnDataType::DurationNanosecond => ConcreteDataType::duration_nanosecond_datatype(),
             ColumnDataType::Decimal128 => {
                 if let Some(TypeExt::DecimalType(d)) = datatype_wrapper
                     .datatype_ext
@@ -203,7 +212,11 @@ impl_column_type_functions_with_snake!(
     TimeNanosecond,
     IntervalYearMonth,
     IntervalDayTime,
-    IntervalMonthDayNano
+    IntervalMonthDayNano,
+    DurationSecond,
+    DurationMillisecond,
+    DurationMicrosecond,
+    DurationNanosecond
 );
 
 impl ColumnDataTypeWrapper {
@@ -257,11 +270,16 @@ impl TryFrom<ConcreteDataType> for ColumnDataTypeWrapper {
                 IntervalType::DayTime(_) => ColumnDataType::IntervalDayTime,
                 IntervalType::MonthDayNano(_) => ColumnDataType::IntervalMonthDayNano,
             },
+            ConcreteDataType::Duration(d) => match d {
+                DurationType::Second(_) => ColumnDataType::DurationSecond,
+                DurationType::Millisecond(_) => ColumnDataType::DurationMillisecond,
+                DurationType::Microsecond(_) => ColumnDataType::DurationMicrosecond,
+                DurationType::Nanosecond(_) => ColumnDataType::DurationNanosecond,
+            },
             ConcreteDataType::Decimal128(_) => ColumnDataType::Decimal128,
             ConcreteDataType::Null(_)
             | ConcreteDataType::List(_)
-            | ConcreteDataType::Dictionary(_)
-            | ConcreteDataType::Duration(_) => {
+            | ConcreteDataType::Dictionary(_) => {
                 return error::IntoColumnDataTypeSnafu { from: datatype }.fail()
             }
         };
@@ -391,6 +409,22 @@ pub fn values_with_capacity(datatype: ColumnDataType, capacity: usize) -> Values
             interval_month_day_nano_values: Vec::with_capacity(capacity),
             ..Default::default()
         },
+        ColumnDataType::DurationSecond => Values {
+            duration_second_values: Vec::with_capacity(capacity),
+            ..Default::default()
+        },
+        ColumnDataType::DurationMillisecond => Values {
+            duration_millisecond_values: Vec::with_capacity(capacity),
+            ..Default::default()
+        },
+        ColumnDataType::DurationMicrosecond => Values {
+            duration_microsecond_values: Vec::with_capacity(capacity),
+            ..Default::default()
+        },
+        ColumnDataType::DurationNanosecond => Values {
+            duration_nanosecond_values: Vec::with_capacity(capacity),
+            ..Default::default()
+        },
         ColumnDataType::Decimal128 => Values {
             decimal128_values: Vec::with_capacity(capacity),
             ..Default::default()
@@ -442,8 +476,14 @@ pub fn push_vals(column: &mut Column, origin_count: usize, vector: VectorRef) {
                 .interval_month_day_nano_values
                 .push(convert_i128_to_interval(val.to_i128())),
         },
+        Value::Duration(val) => match val.unit() {
+            TimeUnit::Second => values.duration_second_values.push(val.value()),
+            TimeUnit::Millisecond => values.duration_millisecond_values.push(val.value()),
+            TimeUnit::Microsecond => values.duration_microsecond_values.push(val.value()),
+            TimeUnit::Nanosecond => values.duration_nanosecond_values.push(val.value()),
+        },
         Value::Decimal128(val) => values.decimal128_values.push(convert_to_pb_decimal128(val)),
-        Value::List(_) | Value::Duration(_) => unreachable!(),
+        Value::List(_) => unreachable!(),
     });
     column.null_mask = null_mask.into_vec();
 }
@@ -478,10 +518,6 @@ fn ddl_request_type(request: &DdlRequest) -> &'static str {
         Some(Expr::Alter(_)) => "ddl.alter",
         Some(Expr::DropTable(_)) => "ddl.drop_table",
         Some(Expr::TruncateTable(_)) => "ddl.truncate_table",
-        Some(Expr::CreateFlow(_)) => "ddl.create_flow",
-        Some(Expr::DropFlow(_)) => "ddl.drop_flow",
-        Some(Expr::CreateView(_)) => "ddl.create_view",
-        Some(Expr::DropView(_)) => "ddl.drop_view",
         None => "ddl.empty",
     }
 }
@@ -547,6 +583,10 @@ pub fn pb_value_to_value_ref<'a>(
             let interval = Interval::from_month_day_nano(v.months, v.days, v.nanoseconds);
             ValueRef::Interval(interval)
         }
+        ValueData::DurationSecondValue(v) => ValueRef::Duration(Duration::new_second(*v)),
+        ValueData::DurationMillisecondValue(v) => ValueRef::Duration(Duration::new_millisecond(*v)),
+        ValueData::DurationMicrosecondValue(v) => ValueRef::Duration(Duration::new_microsecond(*v)),
+        ValueData::DurationNanosecondValue(v) => ValueRef::Duration(Duration::new_nanosecond(*v)),
         ValueData::Decimal128Value(v) => {
             // get precision and scale from datatype_extension
             if let Some(TypeExt::DecimalType(d)) = datatype_ext
@@ -641,15 +681,26 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
                 ))
             }
         },
+        ConcreteDataType::Duration(unit) => match unit {
+            DurationType::Second(_) => Arc::new(DurationSecondVector::from_vec(
+                values.duration_second_values,
+            )),
+            DurationType::Millisecond(_) => Arc::new(DurationMillisecondVector::from_vec(
+                values.duration_millisecond_values,
+            )),
+            DurationType::Microsecond(_) => Arc::new(DurationMicrosecondVector::from_vec(
+                values.duration_microsecond_values,
+            )),
+            DurationType::Nanosecond(_) => Arc::new(DurationNanosecondVector::from_vec(
+                values.duration_nanosecond_values,
+            )),
+        },
         ConcreteDataType::Decimal128(d) => Arc::new(Decimal128Vector::from_values(
             values.decimal128_values.iter().map(|x| {
                 Decimal128::from_value_precision_scale(x.hi, x.lo, d.precision(), d.scale()).into()
             }),
         )),
-        ConcreteDataType::Null(_)
-        | ConcreteDataType::List(_)
-        | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_) => {
+        ConcreteDataType::Null(_) | ConcreteDataType::List(_) | ConcreteDataType::Dictionary(_) => {
             unreachable!()
         }
     }
@@ -798,6 +849,26 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
                 ))
             })
             .collect(),
+        ConcreteDataType::Duration(DurationType::Second(_)) => values
+            .duration_second_values
+            .into_iter()
+            .map(|v| Value::Duration(Duration::new_second(v)))
+            .collect(),
+        ConcreteDataType::Duration(DurationType::Millisecond(_)) => values
+            .duration_millisecond_values
+            .into_iter()
+            .map(|v| Value::Duration(Duration::new_millisecond(v)))
+            .collect(),
+        ConcreteDataType::Duration(DurationType::Microsecond(_)) => values
+            .duration_microsecond_values
+            .into_iter()
+            .map(|v| Value::Duration(Duration::new_microsecond(v)))
+            .collect(),
+        ConcreteDataType::Duration(DurationType::Nanosecond(_)) => values
+            .duration_nanosecond_values
+            .into_iter()
+            .map(|v| Value::Duration(Duration::new_nanosecond(v)))
+            .collect(),
         ConcreteDataType::Decimal128(d) => values
             .decimal128_values
             .into_iter()
@@ -810,10 +881,7 @@ pub fn pb_values_to_values(data_type: &ConcreteDataType, values: Values) -> Vec<
                 ))
             })
             .collect(),
-        ConcreteDataType::Null(_)
-        | ConcreteDataType::List(_)
-        | ConcreteDataType::Dictionary(_)
-        | ConcreteDataType::Duration(_) => {
+        ConcreteDataType::Null(_) | ConcreteDataType::List(_) | ConcreteDataType::Dictionary(_) => {
             unreachable!()
         }
     }
@@ -925,10 +993,24 @@ pub fn to_proto_value(value: Value) -> Option<v1::Value> {
                 )),
             },
         },
+        Value::Duration(v) => match v.unit() {
+            TimeUnit::Second => v1::Value {
+                value_data: Some(ValueData::DurationSecondValue(v.value())),
+            },
+            TimeUnit::Millisecond => v1::Value {
+                value_data: Some(ValueData::DurationMillisecondValue(v.value())),
+            },
+            TimeUnit::Microsecond => v1::Value {
+                value_data: Some(ValueData::DurationMicrosecondValue(v.value())),
+            },
+            TimeUnit::Nanosecond => v1::Value {
+                value_data: Some(ValueData::DurationNanosecondValue(v.value())),
+            },
+        },
         Value::Decimal128(v) => v1::Value {
             value_data: Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
         },
-        Value::List(_) | Value::Duration(_) => return None,
+        Value::List(_) => return None,
     };
 
     Some(proto_value)
@@ -965,6 +1047,10 @@ pub fn proto_value_type(value: &v1::Value) -> Option<ColumnDataType> {
         ValueData::IntervalYearMonthValue(_) => ColumnDataType::IntervalYearMonth,
         ValueData::IntervalDayTimeValue(_) => ColumnDataType::IntervalDayTime,
         ValueData::IntervalMonthDayNanoValue(_) => ColumnDataType::IntervalMonthDayNano,
+        ValueData::DurationSecondValue(_) => ColumnDataType::DurationSecond,
+        ValueData::DurationMillisecondValue(_) => ColumnDataType::DurationMillisecond,
+        ValueData::DurationMicrosecondValue(_) => ColumnDataType::DurationMicrosecond,
+        ValueData::DurationNanosecondValue(_) => ColumnDataType::DurationNanosecond,
         ValueData::Decimal128Value(_) => ColumnDataType::Decimal128,
     };
     Some(value_type)
@@ -1022,8 +1108,14 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
                     ValueData::IntervalMonthDayNanoValue(convert_i128_to_interval(v.to_i128()))
                 }
             }),
+            Value::Duration(v) => Some(match v.unit() {
+                TimeUnit::Second => ValueData::DurationSecondValue(v.value()),
+                TimeUnit::Millisecond => ValueData::DurationMillisecondValue(v.value()),
+                TimeUnit::Microsecond => ValueData::DurationMicrosecondValue(v.value()),
+                TimeUnit::Nanosecond => ValueData::DurationNanosecondValue(v.value()),
+            }),
             Value::Decimal128(v) => Some(ValueData::Decimal128Value(convert_to_pb_decimal128(v))),
-            Value::List(_) | Value::Duration(_) => unreachable!(),
+            Value::List(_) => unreachable!(),
         },
     }
 }
@@ -1033,15 +1125,16 @@ mod tests {
     use std::sync::Arc;
 
     use datatypes::types::{
-        Int32Type, IntervalDayTimeType, IntervalMonthDayNanoType, IntervalYearMonthType,
-        TimeMillisecondType, TimeSecondType, TimestampMillisecondType, TimestampSecondType,
-        UInt32Type,
+        DurationMillisecondType, DurationSecondType, Int32Type, IntervalDayTimeType,
+        IntervalMonthDayNanoType, IntervalYearMonthType, TimeMillisecondType, TimeSecondType,
+        TimestampMillisecondType, TimestampSecondType, UInt32Type,
     };
     use datatypes::vectors::{
-        BooleanVector, IntervalDayTimeVector, IntervalMonthDayNanoVector, IntervalYearMonthVector,
-        TimeMicrosecondVector, TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector,
-        TimestampMicrosecondVector, TimestampMillisecondVector, TimestampNanosecondVector,
-        TimestampSecondVector, Vector,
+        BooleanVector, DurationMicrosecondVector, DurationMillisecondVector,
+        DurationNanosecondVector, DurationSecondVector, IntervalDayTimeVector,
+        IntervalMonthDayNanoVector, IntervalYearMonthVector, TimeMicrosecondVector,
+        TimeMillisecondVector, TimeNanosecondVector, TimeSecondVector, TimestampMicrosecondVector,
+        TimestampMillisecondVector, TimestampNanosecondVector, TimestampSecondVector, Vector,
     };
     use paste::paste;
 
@@ -1117,6 +1210,10 @@ mod tests {
         let values = values.interval_month_day_nano_values;
         assert_eq!(2, values.capacity());
 
+        let values = values_with_capacity(ColumnDataType::DurationMillisecond, 2);
+        let values = values.duration_millisecond_values;
+        assert_eq!(2, values.capacity());
+
         let values = values_with_capacity(ColumnDataType::Decimal128, 2);
         let values = values.decimal128_values;
         assert_eq!(2, values.capacity());
@@ -1204,6 +1301,10 @@ mod tests {
             ConcreteDataType::interval_datatype(IntervalUnit::MonthDayNano),
             ColumnDataTypeWrapper::interval_month_day_nano_datatype().into()
         );
+        assert_eq!(
+            ConcreteDataType::duration_millisecond_datatype(),
+            ColumnDataTypeWrapper::duration_millisecond_datatype().into()
+        );
         assert_eq!(
             ConcreteDataType::decimal128_datatype(10, 2),
             ColumnDataTypeWrapper::decimal128_datatype(10, 2).into()
@@ -1296,6 +1397,12 @@ mod tests {
                 .try_into()
                 .unwrap()
         );
+        assert_eq!(
+            ColumnDataTypeWrapper::duration_millisecond_datatype(),
+            ConcreteDataType::duration_millisecond_datatype()
+                .try_into()
+                .unwrap()
+        );
 
         assert_eq!(
             ColumnDataTypeWrapper::decimal128_datatype(10, 2),
@@ -1449,6 +1556,48 @@ mod tests {
         });
     }
 
+    #[test]
+    fn test_column_put_duration_values() {
+        let mut column = Column {
+            column_name: "test".to_string(),
+            semantic_type: 0,
+            values: Some(Values {
+                ..Default::default()
+            }),
+            null_mask: vec![],
+            datatype: 0,
+            ..Default::default()
+        };
+
+        let vector = Arc::new(DurationNanosecondVector::from_vec(vec![1, 2, 3]));
+        push_vals(&mut column, 3, vector);
+        assert_eq!(
+            vec![1, 2, 3],
+            column.values.as_ref().unwrap().duration_nanosecond_values
+        );
+
+        let vector = Arc::new(DurationMicrosecondVector::from_vec(vec![7, 8, 9]));
+        push_vals(&mut column, 3, vector);
+        assert_eq!(
+            vec![7, 8, 9],
+            column.values.as_ref().unwrap().duration_microsecond_values
+        );
+
+        let vector = Arc::new(DurationMillisecondVector::from_vec(vec![4, 5, 6]));
+        push_vals(&mut column, 3, vector);
+        assert_eq!(
+            vec![4, 5, 6],
+            column.values.as_ref().unwrap().duration_millisecond_values
+        );
+
+        let vector = Arc::new(DurationSecondVector::from_vec(vec![10, 11, 12]));
+        push_vals(&mut column, 3, vector);
+        assert_eq!(
+            vec![10, 11, 12],
+            column.values.as_ref().unwrap().duration_second_values
+        );
+    }
+
     #[test]
     fn test_column_put_vector() {
         use crate::v1::SemanticType;
@@ -1550,6 +1699,39 @@ mod tests {
         assert_eq!(expect, actual);
     }
 
+    #[test]
+    fn test_convert_duration_values() {
+        // second
+        let actual = pb_values_to_values(
+            &ConcreteDataType::Duration(DurationType::Second(DurationSecondType)),
+            Values {
+                duration_second_values: vec![1_i64, 2_i64, 3_i64],
+                ..Default::default()
+            },
+        );
+        let expect = vec![
+            Value::Duration(Duration::new_second(1_i64)),
+            Value::Duration(Duration::new_second(2_i64)),
+            Value::Duration(Duration::new_second(3_i64)),
+        ];
+        assert_eq!(expect, actual);
+
+        // millisecond
+        let actual = pb_values_to_values(
+            &ConcreteDataType::Duration(DurationType::Millisecond(DurationMillisecondType)),
+            Values {
+                duration_millisecond_values: vec![1_i64, 2_i64, 3_i64],
+                ..Default::default()
+            },
+        );
+        let expect = vec![
+            Value::Duration(Duration::new_millisecond(1_i64)),
+            Value::Duration(Duration::new_millisecond(2_i64)),
+            Value::Duration(Duration::new_millisecond(3_i64)),
+        ];
+        assert_eq!(expect, actual);
+    }
+
     #[test]
     fn test_convert_interval_values() {
         // year_month

src/auth/Cargo.toml

@@ -14,12 +14,12 @@ workspace = true
 [dependencies]
 api.workspace = true
 async-trait.workspace = true
-common-base.workspace = true
 common-error.workspace = true
 common-macro.workspace = true
 common-telemetry.workspace = true
 digest = "0.10"
 notify.workspace = true
+secrecy = { version = "0.8", features = ["serde", "alloc"] }
 sha1 = "0.10"
 snafu.workspace = true
 sql.workspace = true

src/auth/src/common.rs

@@ -14,8 +14,8 @@
 
 use std::sync::Arc;
 
-use common_base::secrets::SecretString;
 use digest::Digest;
+use secrecy::SecretString;
 use sha1::Sha1;
 use snafu::{ensure, OptionExt};
 

src/auth/src/error.rs

@@ -34,13 +34,11 @@ pub enum Error {
     Io {
         #[snafu(source)]
         error: std::io::Error,
-        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Auth failed"))]
     AuthBackend {
-        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
@@ -74,10 +72,7 @@ pub enum Error {
     },
 
     #[snafu(display("User is not authorized to perform this action"))]
-    PermissionDenied {
-        #[snafu(implicit)]
-        location: Location,
-    },
+    PermissionDenied { location: Location },
 }
 
 impl ErrorExt for Error {

src/auth/src/permission.rs

@@ -30,7 +30,6 @@ pub enum PermissionReq<'a> {
     PromStoreWrite,
     PromStoreRead,
     Otlp,
-    LogWrite,
 }
 
 #[derive(Debug)]

src/auth/src/tests.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use common_base::secrets::ExposeSecret;
+use secrecy::ExposeSecret;
 
 use crate::error::{
     AccessDeniedSnafu, Result, UnsupportedPasswordTypeSnafu, UserNotFoundSnafu,

src/auth/src/user_provider.rs

@@ -21,7 +21,7 @@ use std::io;
 use std::io::BufRead;
 use std::path::Path;
 
-use common_base::secrets::ExposeSecret;
+use secrecy::ExposeSecret;
 use snafu::{ensure, OptionExt, ResultExt};
 
 use crate::common::{Identity, Password};

src/auth/tests/mod.rs

@@ -52,10 +52,7 @@ fn test_permission_checker() {
 
     let sql_result = checker.check_permission(
         None,
-        PermissionReq::SqlStatement(&Statement::ShowDatabases(ShowDatabases::new(
-            ShowKind::All,
-            false,
-        ))),
+        PermissionReq::SqlStatement(&Statement::ShowDatabases(ShowDatabases::new(ShowKind::All))),
     );
     assert_matches!(sql_result, Ok(PermissionResp::Reject));
 

src/cache/Cargo.toml

@@ -1,14 +0,0 @@
-[package]
-name = "cache"
-version.workspace = true
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-catalog.workspace = true
-common-error.workspace = true
-common-macro.workspace = true
-common-meta.workspace = true
-moka.workspace = true
-snafu.workspace = true
-substrait.workspace = true

src/cache/src/error.rs

@@ -1,44 +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 common_error::ext::ErrorExt;
-use common_error::status_code::StatusCode;
-use common_macro::stack_trace_debug;
-use snafu::{Location, Snafu};
-
-#[derive(Snafu)]
-#[snafu(visibility(pub))]
-#[stack_trace_debug]
-pub enum Error {
-    #[snafu(display("Failed to get cache from cache registry: {}", name))]
-    CacheRequired {
-        #[snafu(implicit)]
-        location: Location,
-        name: String,
-    },
-}
-
-pub type Result<T> = std::result::Result<T, Error>;
-
-impl ErrorExt for Error {
-    fn status_code(&self) -> StatusCode {
-        match self {
-            Error::CacheRequired { .. } => StatusCode::Internal,
-        }
-    }
-
-    fn as_any(&self) -> &dyn std::any::Any {
-        self
-    }
-}

src/cache/src/lib.rs

@@ -1,135 +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.
-
-pub mod error;
-
-use std::sync::Arc;
-use std::time::Duration;
-
-use catalog::kvbackend::new_table_cache;
-use common_meta::cache::{
-    new_table_flownode_set_cache, new_table_info_cache, new_table_name_cache,
-    new_table_route_cache, new_view_info_cache, CacheRegistry, CacheRegistryBuilder,
-    LayeredCacheRegistryBuilder,
-};
-use common_meta::kv_backend::KvBackendRef;
-use moka::future::CacheBuilder;
-use snafu::OptionExt;
-
-use crate::error::Result;
-
-const DEFAULT_CACHE_MAX_CAPACITY: u64 = 65536;
-const DEFAULT_CACHE_TTL: Duration = Duration::from_secs(10 * 60);
-const DEFAULT_CACHE_TTI: Duration = Duration::from_secs(5 * 60);
-
-pub const TABLE_INFO_CACHE_NAME: &str = "table_info_cache";
-pub const VIEW_INFO_CACHE_NAME: &str = "view_info_cache";
-pub const TABLE_NAME_CACHE_NAME: &str = "table_name_cache";
-pub const TABLE_CACHE_NAME: &str = "table_cache";
-pub const TABLE_FLOWNODE_SET_CACHE_NAME: &str = "table_flownode_set_cache";
-pub const TABLE_ROUTE_CACHE_NAME: &str = "table_route_cache";
-
-pub fn build_fundamental_cache_registry(kv_backend: KvBackendRef) -> CacheRegistry {
-    // Builds table info cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let table_info_cache = Arc::new(new_table_info_cache(
-        TABLE_INFO_CACHE_NAME.to_string(),
-        cache,
-        kv_backend.clone(),
-    ));
-
-    // Builds table name cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let table_name_cache = Arc::new(new_table_name_cache(
-        TABLE_NAME_CACHE_NAME.to_string(),
-        cache,
-        kv_backend.clone(),
-    ));
-
-    // Builds table route cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let table_route_cache = Arc::new(new_table_route_cache(
-        TABLE_ROUTE_CACHE_NAME.to_string(),
-        cache,
-        kv_backend.clone(),
-    ));
-
-    // Builds table flownode set cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let table_flownode_set_cache = Arc::new(new_table_flownode_set_cache(
-        TABLE_FLOWNODE_SET_CACHE_NAME.to_string(),
-        cache,
-        kv_backend.clone(),
-    ));
-    // Builds the view info cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let view_info_cache = Arc::new(new_view_info_cache(
-        VIEW_INFO_CACHE_NAME.to_string(),
-        cache,
-        kv_backend.clone(),
-    ));
-
-    CacheRegistryBuilder::default()
-        .add_cache(table_info_cache)
-        .add_cache(table_name_cache)
-        .add_cache(table_route_cache)
-        .add_cache(view_info_cache)
-        .add_cache(table_flownode_set_cache)
-        .build()
-}
-
-// TODO(weny): Make the cache configurable.
-pub fn with_default_composite_cache_registry(
-    builder: LayeredCacheRegistryBuilder,
-) -> Result<LayeredCacheRegistryBuilder> {
-    let table_info_cache = builder.get().context(error::CacheRequiredSnafu {
-        name: TABLE_INFO_CACHE_NAME,
-    })?;
-    let table_name_cache = builder.get().context(error::CacheRequiredSnafu {
-        name: TABLE_NAME_CACHE_NAME,
-    })?;
-
-    // Builds table cache
-    let cache = CacheBuilder::new(DEFAULT_CACHE_MAX_CAPACITY)
-        .time_to_live(DEFAULT_CACHE_TTL)
-        .time_to_idle(DEFAULT_CACHE_TTI)
-        .build();
-    let table_cache = Arc::new(new_table_cache(
-        TABLE_CACHE_NAME.to_string(),
-        cache,
-        table_info_cache,
-        table_name_cache,
-    ));
-
-    let registry = CacheRegistryBuilder::default()
-        .add_cache(table_cache)
-        .build();
-
-    Ok(builder.add_cache_registry(registry))
-}

src/catalog/Cargo.toml

@@ -16,9 +16,7 @@ arrow.workspace = true
 arrow-schema.workspace = true
 async-stream.workspace = true
 async-trait = "0.1"
-bytes.workspace = true
 common-catalog.workspace = true
-common-config.workspace = true
 common-error.workspace = true
 common-macro.workspace = true
 common-meta.workspace = true
@@ -32,7 +30,6 @@ datafusion.workspace = true
 datatypes.workspace = true
 futures = "0.3"
 futures-util.workspace = true
-humantime.workspace = true
 itertools.workspace = true
 lazy_static.workspace = true
 meta-client.workspace = true
@@ -49,11 +46,8 @@ table.workspace = true
 tokio.workspace = true
 
 [dev-dependencies]
-cache.workspace = true
 catalog = { workspace = true, features = ["testing"] }
 chrono.workspace = true
-common-meta = { workspace = true, features = ["testing"] }
-common-query = { workspace = true, features = ["testing"] }
 common-test-util.workspace = true
 log-store.workspace = true
 object-store.workspace = true

src/catalog/src/error.rs

@@ -19,7 +19,10 @@ use common_error::ext::{BoxedError, ErrorExt};
 use common_error::status_code::StatusCode;
 use common_macro::stack_trace_debug;
 use datafusion::error::DataFusionError;
+use datatypes::prelude::ConcreteDataType;
 use snafu::{Location, Snafu};
+use table::metadata::TableId;
+use tokio::task::JoinError;
 
 #[derive(Snafu)]
 #[snafu(visibility(pub))]
@@ -27,14 +30,12 @@ use snafu::{Location, Snafu};
 pub enum Error {
     #[snafu(display("Failed to list catalogs"))]
     ListCatalogs {
-        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
 
     #[snafu(display("Failed to list {}'s schemas", catalog))]
     ListSchemas {
-        #[snafu(implicit)]
         location: Location,
         catalog: String,
         source: BoxedError,
@@ -42,46 +43,80 @@ pub enum Error {
 
     #[snafu(display("Failed to list {}.{}'s tables", catalog, schema))]
     ListTables {
-        #[snafu(implicit)]
         location: Location,
         catalog: String,
         schema: String,
         source: BoxedError,
     },
 
-    #[snafu(display("Failed to list nodes in cluster: {source}"))]
-    ListNodes {
-        #[snafu(implicit)]
+    #[snafu(display("Failed to re-compile script due to internal error"))]
+    CompileScriptInternal {
         location: Location,
         source: BoxedError,
     },
-
-    #[snafu(display("Failed to re-compile script due to internal error"))]
-    CompileScriptInternal {
-        #[snafu(implicit)]
+    #[snafu(display("Failed to open system catalog table"))]
+    OpenSystemCatalog {
         location: Location,
-        source: BoxedError,
+        source: table::error::Error,
+    },
+
+    #[snafu(display("Failed to create system catalog table"))]
+    CreateSystemCatalog {
+        location: Location,
+        source: table::error::Error,
     },
 
     #[snafu(display("Failed to create table, table info: {}", table_info))]
     CreateTable {
         table_info: String,
-        #[snafu(implicit)]
         location: Location,
         source: table::error::Error,
     },
 
     #[snafu(display("System catalog is not valid: {}", msg))]
-    SystemCatalog {
-        msg: String,
-        #[snafu(implicit)]
+    SystemCatalog { msg: String, location: Location },
+
+    #[snafu(display(
+        "System catalog table type mismatch, expected: binary, found: {:?}",
+        data_type,
+    ))]
+    SystemCatalogTypeMismatch {
+        data_type: ConcreteDataType,
         location: Location,
     },
 
+    #[snafu(display("Invalid system catalog entry type: {:?}", entry_type))]
+    InvalidEntryType {
+        entry_type: Option<u8>,
+        location: Location,
+    },
+
+    #[snafu(display("Invalid system catalog key: {:?}", key))]
+    InvalidKey {
+        key: Option<String>,
+        location: Location,
+    },
+
+    #[snafu(display("Catalog value is not present"))]
+    EmptyValue { location: Location },
+
+    #[snafu(display("Failed to deserialize value"))]
+    ValueDeserialize {
+        #[snafu(source)]
+        error: serde_json::error::Error,
+        location: Location,
+    },
+
+    #[snafu(display("Table engine not found: {}", engine_name))]
+    TableEngineNotFound {
+        engine_name: String,
+        location: Location,
+        source: table::error::Error,
+    },
+
     #[snafu(display("Cannot find catalog by name: {}", catalog_name))]
     CatalogNotFound {
         catalog_name: String,
-        #[snafu(implicit)]
         location: Location,
     },
 
@@ -89,28 +124,43 @@ pub enum Error {
     SchemaNotFound {
         catalog: String,
         schema: String,
-        #[snafu(implicit)]
         location: Location,
     },
 
     #[snafu(display("Table `{}` already exists", table))]
-    TableExists {
-        table: String,
-        #[snafu(implicit)]
-        location: Location,
-    },
+    TableExists { table: String, location: Location },
 
     #[snafu(display("Table not found: {}", table))]
-    TableNotExist {
-        table: String,
-        #[snafu(implicit)]
+    TableNotExist { table: String, location: Location },
+
+    #[snafu(display("Schema {} already exists", schema))]
+    SchemaExists { schema: String, location: Location },
+
+    #[snafu(display("Operation {} not implemented yet", operation))]
+    Unimplemented {
+        operation: String,
         location: Location,
     },
 
-    #[snafu(display("View info not found: {}", name))]
-    ViewInfoNotFound {
-        name: String,
-        #[snafu(implicit)]
+    #[snafu(display("Operation {} not supported", op))]
+    NotSupported { op: String, location: Location },
+
+    #[snafu(display("Failed to open table {table_id}"))]
+    OpenTable {
+        table_id: TableId,
+        location: Location,
+        source: table::error::Error,
+    },
+
+    #[snafu(display("Failed to open table in parallel"))]
+    ParallelOpenTable {
+        #[snafu(source)]
+        error: JoinError,
+    },
+
+    #[snafu(display("Table not found while opening table, table info: {}", table_info))]
+    TableNotFound {
+        table_info: String,
         location: Location,
     },
 
@@ -120,44 +170,59 @@ pub enum Error {
     #[snafu(display("Failed to find region routes"))]
     FindRegionRoutes { source: partition::error::Error },
 
-    #[snafu(display("Failed to create recordbatch"))]
-    CreateRecordBatch {
-        #[snafu(implicit)]
+    #[snafu(display("Failed to read system catalog table records"))]
+    ReadSystemCatalog {
         location: Location,
         source: common_recordbatch::error::Error,
     },
 
+    #[snafu(display("Failed to create recordbatch"))]
+    CreateRecordBatch {
+        location: Location,
+        source: common_recordbatch::error::Error,
+    },
+
+    #[snafu(display("Failed to insert table creation record to system catalog"))]
+    InsertCatalogRecord {
+        location: Location,
+        source: table::error::Error,
+    },
+
+    #[snafu(display("Failed to scan system catalog table"))]
+    SystemCatalogTableScan {
+        location: Location,
+        source: table::error::Error,
+    },
+
     #[snafu(display("Internal error"))]
     Internal {
-        #[snafu(implicit)]
         location: Location,
         source: BoxedError,
     },
 
     #[snafu(display("Failed to upgrade weak catalog manager reference"))]
-    UpgradeWeakCatalogManagerRef {
-        #[snafu(implicit)]
-        location: Location,
-    },
+    UpgradeWeakCatalogManagerRef { location: Location },
 
-    #[snafu(display("Failed to decode logical plan for view: {}", name))]
-    DecodePlan {
-        name: String,
-        #[snafu(implicit)]
+    #[snafu(display("Failed to execute system catalog table scan"))]
+    SystemCatalogTableScanExec {
         location: Location,
         source: common_query::error::Error,
     },
 
+    #[snafu(display("Cannot parse catalog value"))]
+    InvalidCatalogValue {
+        location: Location,
+        source: common_catalog::error::Error,
+    },
+
     #[snafu(display("Failed to perform metasrv operation"))]
     Metasrv {
-        #[snafu(implicit)]
         location: Location,
         source: meta_client::error::Error,
     },
 
     #[snafu(display("Invalid table info in catalog"))]
     InvalidTableInfoInCatalog {
-        #[snafu(implicit)]
         location: Location,
         source: datatypes::error::Error,
     },
@@ -169,43 +234,29 @@ pub enum Error {
     Datafusion {
         #[snafu(source)]
         error: DataFusionError,
-        #[snafu(implicit)]
         location: Location,
     },
 
+    #[snafu(display("Table schema mismatch"))]
+    TableSchemaMismatch {
+        location: Location,
+        source: table::error::Error,
+    },
+
+    #[snafu(display("A generic error has occurred, msg: {}", msg))]
+    Generic { msg: String, location: Location },
+
     #[snafu(display("Table metadata manager error"))]
     TableMetadataManager {
         source: common_meta::error::Error,
-        #[snafu(implicit)]
         location: Location,
     },
 
-    #[snafu(display("Failed to get table cache"))]
-    GetTableCache {
-        source: common_meta::error::Error,
-        #[snafu(implicit)]
-        location: Location,
-    },
+    #[snafu(display("Get null from table cache, key: {}", key))]
+    TableCacheNotGet { key: String, location: Location },
 
-    #[snafu(display("Failed to get view info from cache"))]
-    GetViewCache {
-        source: common_meta::error::Error,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("Cache not found: {name}"))]
-    CacheNotFound {
-        name: String,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
-    #[snafu(display("Failed to cast the catalog manager"))]
-    CastManager {
-        #[snafu(implicit)]
-        location: Location,
-    },
+    #[snafu(display("Failed to get table cache, err: {}", err_msg))]
+    GetTableCache { err_msg: String },
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
@@ -213,43 +264,60 @@ pub type Result<T> = std::result::Result<T, Error>;
 impl ErrorExt for Error {
     fn status_code(&self) -> StatusCode {
         match self {
-            Error::SchemaNotFound { .. }
+            Error::InvalidKey { .. }
+            | Error::SchemaNotFound { .. }
             | Error::CatalogNotFound { .. }
             | Error::FindPartitions { .. }
             | Error::FindRegionRoutes { .. }
-            | Error::CacheNotFound { .. }
-            | Error::CastManager { .. } => StatusCode::Unexpected,
+            | Error::InvalidEntryType { .. }
+            | Error::ParallelOpenTable { .. } => StatusCode::Unexpected,
 
-            Error::ViewInfoNotFound { .. } => StatusCode::TableNotFound,
+            Error::TableNotFound { .. } => StatusCode::TableNotFound,
 
-            Error::SystemCatalog { .. } => StatusCode::StorageUnavailable,
+            Error::SystemCatalog { .. }
+            | Error::EmptyValue { .. }
+            | Error::ValueDeserialize { .. } => StatusCode::StorageUnavailable,
 
-            Error::UpgradeWeakCatalogManagerRef { .. } => StatusCode::Internal,
+            Error::Generic { .. }
+            | Error::SystemCatalogTypeMismatch { .. }
+            | Error::UpgradeWeakCatalogManagerRef { .. } => StatusCode::Internal,
+
+            Error::ReadSystemCatalog { source, .. } | Error::CreateRecordBatch { source, .. } => {
+                source.status_code()
+            }
+            Error::InvalidCatalogValue { source, .. } => source.status_code(),
 
-            Error::CreateRecordBatch { source, .. } => source.status_code(),
             Error::TableExists { .. } => StatusCode::TableAlreadyExists,
             Error::TableNotExist { .. } => StatusCode::TableNotFound,
+            Error::SchemaExists { .. } | Error::TableEngineNotFound { .. } => {
+                StatusCode::InvalidArguments
+            }
+
             Error::ListCatalogs { source, .. }
-            | Error::ListNodes { source, .. }
             | Error::ListSchemas { source, .. }
             | Error::ListTables { source, .. } => source.status_code(),
 
-            Error::CreateTable { source, .. } => source.status_code(),
+            Error::OpenSystemCatalog { source, .. }
+            | Error::CreateSystemCatalog { source, .. }
+            | Error::InsertCatalogRecord { source, .. }
+            | Error::OpenTable { source, .. }
+            | Error::CreateTable { source, .. }
+            | Error::TableSchemaMismatch { source, .. } => source.status_code(),
 
             Error::Metasrv { source, .. } => source.status_code(),
-            Error::DecodePlan { source, .. } => source.status_code(),
+            Error::SystemCatalogTableScan { source, .. } => source.status_code(),
+            Error::SystemCatalogTableScanExec { source, .. } => source.status_code(),
             Error::InvalidTableInfoInCatalog { source, .. } => source.status_code(),
 
             Error::CompileScriptInternal { source, .. } | Error::Internal { source, .. } => {
                 source.status_code()
             }
 
+            Error::Unimplemented { .. } | Error::NotSupported { .. } => StatusCode::Unsupported,
             Error::QueryAccessDenied { .. } => StatusCode::AccessDenied,
             Error::Datafusion { .. } => StatusCode::EngineExecuteQuery,
             Error::TableMetadataManager { source, .. } => source.status_code(),
-            Error::GetViewCache { source, .. } | Error::GetTableCache { source, .. } => {
-                source.status_code()
-            }
+            Error::TableCacheNotGet { .. } | Error::GetTableCache { .. } => StatusCode::Internal,
         }
     }
 
@@ -281,6 +349,11 @@ mod tests {
             .status_code()
         );
 
+        assert_eq!(
+            StatusCode::Unexpected,
+            InvalidKeySnafu { key: None }.build().status_code()
+        );
+
         assert_eq!(
             StatusCode::StorageUnavailable,
             Error::SystemCatalog {
@@ -289,6 +362,19 @@ mod tests {
             }
             .status_code()
         );
+
+        assert_eq!(
+            StatusCode::Internal,
+            Error::SystemCatalogTypeMismatch {
+                data_type: ConcreteDataType::binary_datatype(),
+                location: Location::generate(),
+            }
+            .status_code()
+        );
+        assert_eq!(
+            StatusCode::StorageUnavailable,
+            EmptyValueSnafu {}.build().status_code()
+        );
     }
 
     #[test]

src/catalog/src/information_schema.rs

@@ -12,7 +12,6 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-mod cluster_info;
 pub mod columns;
 pub mod key_column_usage;
 mod memory_table;
@@ -24,7 +23,6 @@ pub mod schemata;
 mod table_constraints;
 mod table_names;
 pub mod tables;
-pub(crate) mod utils;
 
 use std::collections::HashMap;
 use std::sync::{Arc, Weak};
@@ -49,7 +47,6 @@ pub use table_names::*;
 
 use self::columns::InformationSchemaColumns;
 use crate::error::Result;
-use crate::information_schema::cluster_info::InformationSchemaClusterInfo;
 use crate::information_schema::key_column_usage::InformationSchemaKeyColumnUsage;
 use crate::information_schema::memory_table::{get_schema_columns, MemoryTable};
 use crate::information_schema::partitions::InformationSchemaPartitions;
@@ -153,7 +150,6 @@ impl InformationSchemaProvider {
     fn build_tables(&mut self) {
         let mut tables = HashMap::new();
 
-        // SECURITY NOTE:
         // Carefully consider the tables that may expose sensitive cluster configurations,
         // authentication details, and other critical information.
         // Only put these tables under `greptime` catalog to prevent info leak.
@@ -170,10 +166,6 @@ impl InformationSchemaProvider {
                 REGION_PEERS.to_string(),
                 self.build_table(REGION_PEERS).unwrap(),
             );
-            tables.insert(
-                CLUSTER_INFO.to_string(),
-                self.build_table(CLUSTER_INFO).unwrap(),
-            );
         }
 
         tables.insert(TABLES.to_string(), self.build_table(TABLES).unwrap());
@@ -259,9 +251,6 @@ impl InformationSchemaProvider {
                 self.catalog_name.clone(),
                 self.catalog_manager.clone(),
             )) as _),
-            CLUSTER_INFO => Some(Arc::new(InformationSchemaClusterInfo::new(
-                self.catalog_manager.clone(),
-            )) as _),
             _ => None,
         }
     }

src/catalog/src/information_schema/cluster_info.rs

@@ -1,317 +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 std::sync::{Arc, Weak};
-use std::time::Duration;
-
-use arrow_schema::SchemaRef as ArrowSchemaRef;
-use common_catalog::consts::INFORMATION_SCHEMA_CLUSTER_INFO_TABLE_ID;
-use common_config::Mode;
-use common_error::ext::BoxedError;
-use common_meta::cluster::{ClusterInfo, NodeInfo, NodeStatus};
-use common_meta::peer::Peer;
-use common_recordbatch::adapter::RecordBatchStreamAdapter;
-use common_recordbatch::{RecordBatch, SendableRecordBatchStream};
-use common_telemetry::warn;
-use common_time::timestamp::Timestamp;
-use datafusion::execution::TaskContext;
-use datafusion::physical_plan::stream::RecordBatchStreamAdapter as DfRecordBatchStreamAdapter;
-use datafusion::physical_plan::streaming::PartitionStream as DfPartitionStream;
-use datafusion::physical_plan::SendableRecordBatchStream as DfSendableRecordBatchStream;
-use datatypes::prelude::{ConcreteDataType, ScalarVectorBuilder, VectorRef};
-use datatypes::schema::{ColumnSchema, Schema, SchemaRef};
-use datatypes::timestamp::TimestampMillisecond;
-use datatypes::value::Value;
-use datatypes::vectors::{
-    Int64VectorBuilder, StringVectorBuilder, TimestampMillisecondVectorBuilder,
-};
-use snafu::ResultExt;
-use store_api::storage::{ScanRequest, TableId};
-
-use super::CLUSTER_INFO;
-use crate::error::{CreateRecordBatchSnafu, InternalSnafu, ListNodesSnafu, Result};
-use crate::information_schema::{utils, InformationTable, Predicates};
-use crate::CatalogManager;
-
-const PEER_ID: &str = "peer_id";
-const PEER_TYPE: &str = "peer_type";
-const PEER_ADDR: &str = "peer_addr";
-const VERSION: &str = "version";
-const GIT_COMMIT: &str = "git_commit";
-const START_TIME: &str = "start_time";
-const UPTIME: &str = "uptime";
-const ACTIVE_TIME: &str = "active_time";
-
-const INIT_CAPACITY: usize = 42;
-
-/// The `CLUSTER_INFO` table provides information about the current topology information of the cluster.
-///
-/// - `peer_id`: the peer server id.
-/// - `peer_type`: the peer type, such as `datanode`, `frontend`, `metasrv` etc.
-/// - `peer_addr`: the peer gRPC address.
-/// - `version`: the build package version of the peer.
-/// - `git_commit`: the build git commit hash of the peer.
-/// - `start_time`: the starting time of the peer.
-/// - `uptime`: the uptime of the peer.
-/// - `active_time`: the time since the last activity of the peer.
-///
-pub(super) struct InformationSchemaClusterInfo {
-    schema: SchemaRef,
-    catalog_manager: Weak<dyn CatalogManager>,
-    start_time_ms: u64,
-}
-
-impl InformationSchemaClusterInfo {
-    pub(super) fn new(catalog_manager: Weak<dyn CatalogManager>) -> Self {
-        Self {
-            schema: Self::schema(),
-            catalog_manager,
-            start_time_ms: common_time::util::current_time_millis() as u64,
-        }
-    }
-
-    pub(crate) fn schema() -> SchemaRef {
-        Arc::new(Schema::new(vec![
-            ColumnSchema::new(PEER_ID, ConcreteDataType::int64_datatype(), false),
-            ColumnSchema::new(PEER_TYPE, ConcreteDataType::string_datatype(), false),
-            ColumnSchema::new(PEER_ADDR, ConcreteDataType::string_datatype(), true),
-            ColumnSchema::new(VERSION, ConcreteDataType::string_datatype(), false),
-            ColumnSchema::new(GIT_COMMIT, ConcreteDataType::string_datatype(), false),
-            ColumnSchema::new(
-                START_TIME,
-                ConcreteDataType::timestamp_millisecond_datatype(),
-                true,
-            ),
-            ColumnSchema::new(UPTIME, ConcreteDataType::string_datatype(), true),
-            ColumnSchema::new(ACTIVE_TIME, ConcreteDataType::string_datatype(), true),
-        ]))
-    }
-
-    fn builder(&self) -> InformationSchemaClusterInfoBuilder {
-        InformationSchemaClusterInfoBuilder::new(
-            self.schema.clone(),
-            self.catalog_manager.clone(),
-            self.start_time_ms,
-        )
-    }
-}
-
-impl InformationTable for InformationSchemaClusterInfo {
-    fn table_id(&self) -> TableId {
-        INFORMATION_SCHEMA_CLUSTER_INFO_TABLE_ID
-    }
-
-    fn table_name(&self) -> &'static str {
-        CLUSTER_INFO
-    }
-
-    fn schema(&self) -> SchemaRef {
-        self.schema.clone()
-    }
-
-    fn to_stream(&self, request: ScanRequest) -> Result<SendableRecordBatchStream> {
-        let schema = self.schema.arrow_schema().clone();
-        let mut builder = self.builder();
-        let stream = Box::pin(DfRecordBatchStreamAdapter::new(
-            schema,
-            futures::stream::once(async move {
-                builder
-                    .make_cluster_info(Some(request))
-                    .await
-                    .map(|x| x.into_df_record_batch())
-                    .map_err(Into::into)
-            }),
-        ));
-        Ok(Box::pin(
-            RecordBatchStreamAdapter::try_new(stream)
-                .map_err(BoxedError::new)
-                .context(InternalSnafu)?,
-        ))
-    }
-}
-
-struct InformationSchemaClusterInfoBuilder {
-    schema: SchemaRef,
-    start_time_ms: u64,
-    catalog_manager: Weak<dyn CatalogManager>,
-
-    peer_ids: Int64VectorBuilder,
-    peer_types: StringVectorBuilder,
-    peer_addrs: StringVectorBuilder,
-    versions: StringVectorBuilder,
-    git_commits: StringVectorBuilder,
-    start_times: TimestampMillisecondVectorBuilder,
-    uptimes: StringVectorBuilder,
-    active_times: StringVectorBuilder,
-}
-
-impl InformationSchemaClusterInfoBuilder {
-    fn new(
-        schema: SchemaRef,
-        catalog_manager: Weak<dyn CatalogManager>,
-        start_time_ms: u64,
-    ) -> Self {
-        Self {
-            schema,
-            catalog_manager,
-            peer_ids: Int64VectorBuilder::with_capacity(INIT_CAPACITY),
-            peer_types: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            peer_addrs: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            versions: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            git_commits: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            start_times: TimestampMillisecondVectorBuilder::with_capacity(INIT_CAPACITY),
-            uptimes: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            active_times: StringVectorBuilder::with_capacity(INIT_CAPACITY),
-            start_time_ms,
-        }
-    }
-
-    /// Construct the `information_schema.cluster_info` virtual table
-    async fn make_cluster_info(&mut self, request: Option<ScanRequest>) -> Result<RecordBatch> {
-        let predicates = Predicates::from_scan_request(&request);
-        let mode = utils::running_mode(&self.catalog_manager)?.unwrap_or(Mode::Standalone);
-
-        match mode {
-            Mode::Standalone => {
-                let build_info = common_version::build_info();
-
-                self.add_node_info(
-                    &predicates,
-                    NodeInfo {
-                        // For the standalone:
-                        // - id always 0
-                        // - empty string for peer_addr
-                        peer: Peer {
-                            id: 0,
-                            addr: "".to_string(),
-                        },
-                        last_activity_ts: -1,
-                        status: NodeStatus::Standalone,
-                        version: build_info.version.to_string(),
-                        git_commit: build_info.commit_short.to_string(),
-                        // Use `self.start_time_ms` instead.
-                        // It's not precise but enough.
-                        start_time_ms: self.start_time_ms,
-                    },
-                );
-            }
-            Mode::Distributed => {
-                if let Some(meta_client) = utils::meta_client(&self.catalog_manager)? {
-                    let node_infos = meta_client
-                        .list_nodes(None)
-                        .await
-                        .map_err(BoxedError::new)
-                        .context(ListNodesSnafu)?;
-
-                    for node_info in node_infos {
-                        self.add_node_info(&predicates, node_info);
-                    }
-                } else {
-                    warn!("Could not find meta client in distributed mode.");
-                }
-            }
-        }
-
-        self.finish()
-    }
-
-    fn add_node_info(&mut self, predicates: &Predicates, node_info: NodeInfo) {
-        let peer_type = node_info.status.role_name();
-
-        let row = [
-            (PEER_ID, &Value::from(node_info.peer.id)),
-            (PEER_TYPE, &Value::from(peer_type)),
-            (PEER_ADDR, &Value::from(node_info.peer.addr.as_str())),
-            (VERSION, &Value::from(node_info.version.as_str())),
-            (GIT_COMMIT, &Value::from(node_info.git_commit.as_str())),
-        ];
-
-        if !predicates.eval(&row) {
-            return;
-        }
-
-        if peer_type == "FRONTEND" || peer_type == "METASRV" {
-            // Always set peer_id to be -1 for frontends and metasrvs
-            self.peer_ids.push(Some(-1));
-        } else {
-            self.peer_ids.push(Some(node_info.peer.id as i64));
-        }
-
-        self.peer_types.push(Some(peer_type));
-        self.peer_addrs.push(Some(&node_info.peer.addr));
-        self.versions.push(Some(&node_info.version));
-        self.git_commits.push(Some(&node_info.git_commit));
-        if node_info.start_time_ms > 0 {
-            self.start_times
-                .push(Some(TimestampMillisecond(Timestamp::new_millisecond(
-                    node_info.start_time_ms as i64,
-                ))));
-            self.uptimes.push(Some(
-                Self::format_duration_since(node_info.start_time_ms).as_str(),
-            ));
-        } else {
-            self.start_times.push(None);
-            self.uptimes.push(None);
-        }
-
-        if node_info.last_activity_ts > 0 {
-            self.active_times.push(Some(
-                Self::format_duration_since(node_info.last_activity_ts as u64).as_str(),
-            ));
-        } else {
-            self.active_times.push(None);
-        }
-    }
-
-    fn format_duration_since(ts: u64) -> String {
-        let now = common_time::util::current_time_millis() as u64;
-        let duration_since = now - ts;
-        humantime::format_duration(Duration::from_millis(duration_since)).to_string()
-    }
-
-    fn finish(&mut self) -> Result<RecordBatch> {
-        let columns: Vec<VectorRef> = vec![
-            Arc::new(self.peer_ids.finish()),
-            Arc::new(self.peer_types.finish()),
-            Arc::new(self.peer_addrs.finish()),
-            Arc::new(self.versions.finish()),
-            Arc::new(self.git_commits.finish()),
-            Arc::new(self.start_times.finish()),
-            Arc::new(self.uptimes.finish()),
-            Arc::new(self.active_times.finish()),
-        ];
-        RecordBatch::new(self.schema.clone(), columns).context(CreateRecordBatchSnafu)
-    }
-}
-
-impl DfPartitionStream for InformationSchemaClusterInfo {
-    fn schema(&self) -> &ArrowSchemaRef {
-        self.schema.arrow_schema()
-    }
-
-    fn execute(&self, _: Arc<TaskContext>) -> DfSendableRecordBatchStream {
-        let schema = self.schema.arrow_schema().clone();
-        let mut builder = self.builder();
-        Box::pin(DfRecordBatchStreamAdapter::new(
-            schema,
-            futures::stream::once(async move {
-                builder
-                    .make_cluster_info(None)
-                    .await
-                    .map(|x| x.into_df_record_batch())
-                    .map_err(Into::into)
-            }),
-        ))
-    }
-}