feat(standalone): support to dump/restore metadata

.coderabbit.yaml

@@ -0,0 +1,15 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+language: "en-US"
+early_access: false
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: true
+  poem: true
+  review_status: true
+  collapse_walkthrough: false
+  auto_review:
+    enabled: false
+    drafts: false
+chat:
+  auto_reply: true

.github/CODEOWNERS

@@ -4,7 +4,7 @@
 
 * @GreptimeTeam/db-approver
 
-## [Module] Database Engine
+## [Module] Databse Engine
 /src/index @zhongzc
 /src/mito2 @evenyag @v0y4g3r @waynexia
 /src/query @evenyag

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

@@ -52,7 +52,7 @@ runs:
       uses: ./.github/actions/build-greptime-binary
       with:
         base-image: ubuntu
-        features: servers/dashboard
+        features: servers/dashboard,pg_kvbackend,mysql_kvbackend
         cargo-profile: ${{ inputs.cargo-profile }}
         artifacts-dir: greptime-linux-${{ inputs.arch }}-${{ inputs.version }}
         version: ${{ inputs.version }}
@@ -70,7 +70,7 @@ runs:
       if: ${{ inputs.arch == 'amd64' && inputs.dev-mode == 'false' }} # Builds greptime for centos if the host machine is amd64.
       with:
         base-image: centos
-        features: servers/dashboard
+        features: servers/dashboard,pg_kvbackend,mysql_kvbackend
         cargo-profile: ${{ inputs.cargo-profile }}
         artifacts-dir: greptime-linux-${{ inputs.arch }}-centos-${{ inputs.version }}
         version: ${{ inputs.version }}

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

@@ -7,8 +7,7 @@ meta:
     provider = "kafka"
     broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
     num_topics = 3
-    auto_prune_interval = "30s"
-    trigger_flush_threshold = 100
+    auto_prune_topic_records = true
 
     [datanode]
     [datanode.client]
@@ -22,7 +21,7 @@ datanode:
     [wal]
     provider = "kafka"
     broker_endpoints = ["kafka.kafka-cluster.svc.cluster.local:9092"]
-    overwrite_entry_start_id = true
+    linger = "2ms"
 frontend:
   configData: |-
     [runtime]

.github/scripts/create-version.sh

@@ -8,20 +8,19 @@ set -e
 # - If it's a nightly build, the version is 'nightly-YYYYMMDD-$(git rev-parse --short HEAD)', like 'nightly-20230712-e5b243c'.
 # create_version ${GIHUB_EVENT_NAME} ${NEXT_RELEASE_VERSION} ${NIGHTLY_RELEASE_PREFIX}
 function create_version() {
-  # Read from environment variables.
+  # Read from envrionment variables.
   if [ -z "$GITHUB_EVENT_NAME" ]; then
-      echo "GITHUB_EVENT_NAME is empty" >&2
+      echo "GITHUB_EVENT_NAME is empty"
       exit 1
   fi
 
   if [ -z "$NEXT_RELEASE_VERSION" ]; then
-      echo "NEXT_RELEASE_VERSION is empty, use version from Cargo.toml" >&2
-      # NOTE: Need a `v` prefix for the version string.
-      export NEXT_RELEASE_VERSION=v$(grep '^version = ' Cargo.toml | cut -d '"' -f 2 | head -n 1)
+      echo "NEXT_RELEASE_VERSION is empty"
+      exit 1
   fi
 
   if [ -z "$NIGHTLY_RELEASE_PREFIX" ]; then
-      echo "NIGHTLY_RELEASE_PREFIX is empty" >&2
+      echo "NIGHTLY_RELEASE_PREFIX is empty"
       exit 1
   fi
 
@@ -36,7 +35,7 @@ function create_version() {
   # It will be like 'dev-2023080819-f0e7216c'.
   if [ "$NEXT_RELEASE_VERSION" = dev ]; then
     if [ -z "$COMMIT_SHA" ]; then
-      echo "COMMIT_SHA is empty in dev build" >&2
+      echo "COMMIT_SHA is empty in dev build"
       exit 1
     fi
     echo "dev-$(date "+%Y%m%d-%s")-$(echo "$COMMIT_SHA" | cut -c1-8)"
@@ -46,7 +45,7 @@ function create_version() {
   # Note: Only output 'version=xxx' to stdout when everything is ok, so that it can be used in GitHub Actions Outputs.
   if [ "$GITHUB_EVENT_NAME" = push ]; then
     if [ -z "$GITHUB_REF_NAME" ]; then
-      echo "GITHUB_REF_NAME is empty in push event" >&2
+      echo "GITHUB_REF_NAME is empty in push event"
       exit 1
     fi
     echo "$GITHUB_REF_NAME"
@@ -55,7 +54,7 @@ function create_version() {
   elif [ "$GITHUB_EVENT_NAME" = schedule ]; then
     echo "$NEXT_RELEASE_VERSION-$NIGHTLY_RELEASE_PREFIX-$(date "+%Y%m%d")"
   else
-    echo "Unsupported GITHUB_EVENT_NAME: $GITHUB_EVENT_NAME" >&2
+    echo "Unsupported GITHUB_EVENT_NAME: $GITHUB_EVENT_NAME"
     exit 1
   fi
 }

.github/scripts/deploy-greptimedb.sh

@@ -10,7 +10,7 @@ GREPTIMEDB_IMAGE_TAG=${GREPTIMEDB_IMAGE_TAG:-latest}
 ETCD_CHART="oci://registry-1.docker.io/bitnamicharts/etcd"
 GREPTIME_CHART="https://greptimeteam.github.io/helm-charts/"
 
-# Create a cluster with 1 control-plane node and 5 workers.
+# Ceate a cluster with 1 control-plane node and 5 workers.
 function create_kind_cluster() {
   cat <<EOF | kind create cluster --name "${CLUSTER}" --image kindest/node:"$KUBERNETES_VERSION" --config=-
 kind: Cluster

.github/scripts/update-dev-builder-version.sh

@@ -1,37 +0,0 @@
-#!/bin/bash
-
-DEV_BUILDER_IMAGE_TAG=$1
-
-update_dev_builder_version() {
-  if [ -z "$DEV_BUILDER_IMAGE_TAG" ]; then
-    echo "Error: Should specify the dev-builder image tag"
-    exit 1
-  fi
-
-  # Configure Git configs.
-  git config --global user.email greptimedb-ci@greptime.com
-  git config --global user.name greptimedb-ci
-
-  # Checkout a new branch.
-  BRANCH_NAME="ci/update-dev-builder-$(date +%Y%m%d%H%M%S)"
-  git checkout -b $BRANCH_NAME
-
-  # Update the dev-builder image tag in the Makefile.
-  sed -i "s/DEV_BUILDER_IMAGE_TAG ?=.*/DEV_BUILDER_IMAGE_TAG ?= ${DEV_BUILDER_IMAGE_TAG}/g" Makefile
-
-  # Commit the changes.
-  git add Makefile
-  git commit -m "ci: update dev-builder image tag"
-  git push origin $BRANCH_NAME
-
-  # Create a Pull Request.
-  gh pr create \
-      --title "ci: update dev-builder image tag" \
-      --body "This PR updates the dev-builder image tag" \
-      --base main \
-      --head $BRANCH_NAME \
-      --reviewer zyy17 \
-      --reviewer daviderli614
-}
-
-update_dev_builder_version

.github/scripts/update-helm-charts-version.sh

@@ -1,46 +0,0 @@
-#!/bin/bash
-
-set -e
-
-VERSION=${VERSION}
-GITHUB_TOKEN=${GITHUB_TOKEN}
-
-update_helm_charts_version() {
-  # Configure Git configs.
-  git config --global user.email update-helm-charts-version@greptime.com
-  git config --global user.name update-helm-charts-version
-
-  # Clone helm-charts repository.
-  git clone "https://x-access-token:${GITHUB_TOKEN}@github.com/GreptimeTeam/helm-charts.git"
-  cd helm-charts
-
-  # Set default remote for gh CLI
-  gh repo set-default GreptimeTeam/helm-charts
-
-  # Checkout a new branch.
-  BRANCH_NAME="chore/greptimedb-${VERSION}"
-  git checkout -b $BRANCH_NAME
-
-  # Update version.
-  make update-version CHART=greptimedb-cluster VERSION=${VERSION}
-  make update-version CHART=greptimedb-standalone VERSION=${VERSION}
-
-  # Update docs.
-  make docs
-
-  # Commit the changes.
-  git add .
-  git commit -m "chore: Update GreptimeDB version to ${VERSION}"
-  git push origin $BRANCH_NAME
-
-  # Create a Pull Request.
-  gh pr create \
-    --title "chore: Update GreptimeDB version to ${VERSION}" \
-    --body "This PR updates the GreptimeDB version." \
-    --base main \
-    --head $BRANCH_NAME \
-    --reviewer zyy17 \
-    --reviewer daviderli614
-}
-
-update_helm_charts_version

.github/scripts/update-homebrew-greptme-version.sh

@@ -1,42 +0,0 @@
-#!/bin/bash
-
-set -e
-
-VERSION=${VERSION}
-GITHUB_TOKEN=${GITHUB_TOKEN}
-
-update_homebrew_greptime_version() {
-  # Configure Git configs.
-  git config --global user.email update-greptime-version@greptime.com
-  git config --global user.name update-greptime-version
-
-  # Clone helm-charts repository.
-  git clone "https://x-access-token:${GITHUB_TOKEN}@github.com/GreptimeTeam/homebrew-greptime.git"
-  cd homebrew-greptime
-
-  # Set default remote for gh CLI
-  gh repo set-default GreptimeTeam/homebrew-greptime
-
-  # Checkout a new branch.
-  BRANCH_NAME="chore/greptimedb-${VERSION}"
-  git checkout -b $BRANCH_NAME
-
-  # Update version.
-  make update-greptime-version VERSION=${VERSION}
-
-  # Commit the changes.
-  git add .
-  git commit -m "chore: Update GreptimeDB version to ${VERSION}"
-  git push origin $BRANCH_NAME
-
-  # Create a Pull Request.
-  gh pr create \
-    --title "chore: Update GreptimeDB version to ${VERSION}" \
-    --body "This PR updates the GreptimeDB version." \
-    --base main \
-    --head $BRANCH_NAME \
-    --reviewer zyy17 \
-    --reviewer daviderli614
-}
-
-update_homebrew_greptime_version

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

@@ -41,7 +41,7 @@ function upload_artifacts() {
 # Updates the latest version information in AWS S3 if UPDATE_VERSION_INFO is true.
 function update_version_info() {
   if [ "$UPDATE_VERSION_INFO" == "true" ]; then
-    # If it's the official release(like v1.0.0, v1.0.1, v1.0.2, etc.), update latest-version.txt.
+    # If it's the officail release(like v1.0.0, v1.0.1, v1.0.2, etc.), update latest-version.txt.
     if [[ "$VERSION" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
       echo "Updating latest-version.txt"
       echo "$VERSION" > latest-version.txt

.github/workflows/dev-build.yml

@@ -55,11 +55,6 @@ on:
         description: Build and push images to DockerHub and ACR
         required: false
         default: true
-      upload_artifacts_to_s3:
-        type: boolean
-        description: Whether upload artifacts to s3
-        required: false
-        default: false
       cargo_profile:
         type: choice
         description: The cargo profile to use in building GreptimeDB.
@@ -243,7 +238,7 @@ jobs:
           version: ${{ needs.allocate-runners.outputs.version }}
           push-latest-tag: false # Don't push the latest tag to registry.
           dev-mode: true # Only build the standard images.
-
+          
       - name: Echo Docker image tag to step summary
         run: |
           echo "## Docker Image Tag" >> $GITHUB_STEP_SUMMARY
@@ -286,7 +281,7 @@ jobs:
           aws-cn-access-key-id: ${{ secrets.AWS_CN_ACCESS_KEY_ID }}
           aws-cn-secret-access-key: ${{ secrets.AWS_CN_SECRET_ACCESS_KEY }}
           aws-cn-region: ${{ vars.AWS_RELEASE_BUCKET_REGION }}
-          upload-to-s3: ${{ inputs.upload_artifacts_to_s3 }}
+          upload-to-s3: false
           dev-mode: true                     # Only build the standard images(exclude centos images).
           push-latest-tag: false             # Don't push the latest tag to registry.
           update-version-info: false         # Don't update the version info in S3.

.github/workflows/develop.yml

@@ -22,7 +22,6 @@ concurrency:
 
 jobs:
   check-typos-and-docs:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Check typos and docs
     runs-on: ubuntu-latest
     steps:
@@ -37,7 +36,6 @@ jobs:
           || (echo "'config/config.md' is not up-to-date, please run 'make config-docs'." && exit 1)
 
   license-header-check:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     runs-on: ubuntu-latest
     name: Check License Header
     steps:
@@ -47,7 +45,6 @@ jobs:
       - uses: korandoru/hawkeye@v5
 
   check:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Check
     runs-on: ${{ matrix.os }}
     strategy:
@@ -74,7 +71,6 @@ jobs:
         run: cargo check --locked --workspace --all-targets
 
   toml:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Toml Check
     runs-on: ubuntu-latest
     timeout-minutes: 60
@@ -89,7 +85,6 @@ jobs:
         run: taplo format --check
 
   build:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Build GreptimeDB binaries
     runs-on: ${{ matrix.os }}
     strategy:
@@ -132,7 +127,6 @@ jobs:
           version: current
 
   fuzztest:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Fuzz Test
     needs: build
     runs-on: ubuntu-latest
@@ -189,13 +183,11 @@ jobs:
           max-total-time: 120
 
   unstable-fuzztest:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Unstable Fuzz Test
     needs: build-greptime-ci
     runs-on: ubuntu-latest
     timeout-minutes: 60
     strategy:
-      fail-fast: false
       matrix:
         target: [ "unstable_fuzz_create_table_standalone" ]
     steps:
@@ -223,12 +215,12 @@ jobs:
         run: |
           sudo apt update && sudo apt install -y libfuzzer-14-dev
           cargo install cargo-fuzz cargo-gc-bin --force
-      - name: Download pre-built binary
+      - name: Download pre-built binariy
         uses: actions/download-artifact@v4
         with:
           name: bin
           path: .
-      - name: Unzip binary
+      - name: Unzip bianry
         run: |
           tar -xvf ./bin.tar.gz
           rm ./bin.tar.gz
@@ -252,7 +244,6 @@ jobs:
           retention-days: 3
 
   build-greptime-ci:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Build GreptimeDB binary (profile-CI)
     runs-on: ${{ matrix.os }}
     strategy:
@@ -276,7 +267,7 @@ jobs:
       - name: Install cargo-gc-bin
         shell: bash
         run: cargo install cargo-gc-bin --force
-      - name: Build greptime binary
+      - name: Build greptime bianry
         shell: bash
         # `cargo gc` will invoke `cargo build` with specified args
         run: cargo gc --profile ci -- --bin greptime --features "pg_kvbackend,mysql_kvbackend"
@@ -294,13 +285,11 @@ jobs:
           version: current
 
   distributed-fuzztest:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Fuzz Test (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
     runs-on: ubuntu-latest
     needs:  build-greptime-ci
     timeout-minutes: 60
     strategy:
-      fail-fast: false
       matrix:
         target: [ "fuzz_create_table", "fuzz_alter_table", "fuzz_create_database", "fuzz_create_logical_table", "fuzz_alter_logical_table", "fuzz_insert", "fuzz_insert_logical_table" ]
         mode:
@@ -330,9 +319,9 @@ jobs:
         name: Setup Minio
         uses: ./.github/actions/setup-minio
       - if: matrix.mode.kafka
-        name: Setup Kafka cluster
+        name: Setup Kafka cluser
         uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluster
+      - name: Setup Etcd cluser
         uses: ./.github/actions/setup-etcd-cluster
       # Prepares for fuzz tests
       - uses: arduino/setup-protoc@v3
@@ -427,13 +416,11 @@ jobs:
           docker system prune -f
 
   distributed-fuzztest-with-chaos:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Fuzz Test with Chaos (Distributed, ${{ matrix.mode.name }}, ${{ matrix.target }})
     runs-on: ubuntu-latest
     needs:  build-greptime-ci
     timeout-minutes: 60
     strategy:
-      fail-fast: false
       matrix:
         target: ["fuzz_migrate_mito_regions", "fuzz_migrate_metric_regions", "fuzz_failover_mito_regions", "fuzz_failover_metric_regions"]
         mode:
@@ -478,9 +465,9 @@ jobs:
         name: Setup Minio
         uses: ./.github/actions/setup-minio
       - if: matrix.mode.kafka
-        name: Setup Kafka cluster
+        name: Setup Kafka cluser
         uses: ./.github/actions/setup-kafka-cluster
-      - name: Setup Etcd cluster
+      - name: Setup Etcd cluser
         uses: ./.github/actions/setup-etcd-cluster
       # Prepares for fuzz tests
       - uses: arduino/setup-protoc@v3
@@ -576,12 +563,10 @@ jobs:
           docker system prune -f
 
   sqlness:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Sqlness Test (${{ matrix.mode.name }})
     needs: build
     runs-on: ${{ matrix.os }}
     strategy:
-      fail-fast: false
       matrix:
         os: [ ubuntu-latest ]
         mode:
@@ -624,7 +609,6 @@ jobs:
           retention-days: 3
 
   fmt:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Rustfmt
     runs-on: ubuntu-latest
     timeout-minutes: 60
@@ -642,7 +626,6 @@ jobs:
         run: make fmt-check
 
   clippy:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Clippy
     runs-on: ubuntu-latest
     timeout-minutes: 60
@@ -668,7 +651,6 @@ jobs:
         run: make clippy
 
   conflict-check:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
     name: Check for conflict
     runs-on: ubuntu-latest
     steps:
@@ -679,7 +661,7 @@ jobs:
         uses: olivernybroe/action-conflict-finder@v4.0
 
   test:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && github.event_name != 'merge_group' }}
+    if: github.event_name != 'merge_group'
     runs-on: ubuntu-22.04-arm
     timeout-minutes: 60
     needs:  [conflict-check, clippy, fmt]
@@ -731,7 +713,7 @@ jobs:
           UNITTEST_LOG_DIR: "__unittest_logs"
 
   coverage:
-    if: ${{ github.repository == 'GreptimeTeam/greptimedb' && github.event_name == 'merge_group' }}
+    if: github.event_name == 'merge_group'
     runs-on: ubuntu-22.04-8-cores
     timeout-minutes: 60
     steps:
@@ -791,7 +773,6 @@ jobs:
           verbose: true
 
   # compat:
-  #   if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
   #   name: Compatibility Test
   #   needs: build
   #   runs-on: ubuntu-22.04

.github/workflows/grafana.yml

@@ -21,6 +21,32 @@ jobs:
         run: sudo apt-get install -y jq
 
       # Make the check.sh script executable
-      - name: Check grafana dashboards
+      - name: Make check.sh executable
+        run: chmod +x grafana/check.sh
+
+      # Run the check.sh script
+      - name: Run check.sh
+        run: ./grafana/check.sh
+
+      # Only run summary.sh for pull_request events (not for merge queues or final pushes)
+      - name: Check if this is a pull request
+        id: check-pr
         run: |
-          make check-dashboards
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "is_pull_request=true" >> $GITHUB_OUTPUT
+          else
+            echo "is_pull_request=false" >> $GITHUB_OUTPUT
+          fi
+
+      # Make the summary.sh script executable
+      - name: Make summary.sh executable
+        if: steps.check-pr.outputs.is_pull_request == 'true'
+        run: chmod +x grafana/summary.sh
+
+      # Run the summary.sh script and add its output to the GitHub Job Summary
+      - name: Run summary.sh and add to Job Summary
+        if: steps.check-pr.outputs.is_pull_request == 'true'
+        run: |
+          SUMMARY=$(./grafana/summary.sh)
+          echo "### Summary of Grafana Panels" >> $GITHUB_STEP_SUMMARY
+          echo "$SUMMARY" >> $GITHUB_STEP_SUMMARY

.github/workflows/nightly-ci.yml

@@ -117,16 +117,16 @@ jobs:
     name: Run clean build on Linux
     runs-on: ubuntu-latest
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' }}
-    timeout-minutes: 45
+    timeout-minutes: 60
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           persist-credentials: false
-      - uses: cachix/install-nix-action@v31
-      - run: nix develop --command cargo check --bin greptime
-        env:
-          CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=mold"
+      - uses: cachix/install-nix-action@v27
+        with:
+          nix_path: nixpkgs=channel:nixos-24.11
+      - run: nix develop --command cargo build
 
   check-status:
     name: Check status

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

@@ -24,19 +24,11 @@ on:
         description: Release dev-builder-android image
         required: false
         default: false
-      update_dev_builder_image_tag:
-        type: boolean
-        description: Update the DEV_BUILDER_IMAGE_TAG in Makefile and create a PR
-        required: false
-        default: false
 
 jobs:
   release-dev-builder-images:
     name: Release dev builder images
-    # The jobs are triggered by the following events:
-    # 1. Manually triggered workflow_dispatch event
-    # 2. Push event when the PR that modifies the `rust-toolchain.toml` or `docker/dev-builder/**` is merged to main
-    if: ${{ github.event_name == 'push' || inputs.release_dev_builder_ubuntu_image || inputs.release_dev_builder_centos_image || inputs.release_dev_builder_android_image }}
+    if: ${{ inputs.release_dev_builder_ubuntu_image || inputs.release_dev_builder_centos_image || inputs.release_dev_builder_android_image }} # Only manually trigger this job.
     runs-on: ubuntu-latest
     outputs:
       version: ${{ steps.set-version.outputs.version }}
@@ -65,9 +57,9 @@ jobs:
           version: ${{ env.VERSION }}
           dockerhub-image-registry-username: ${{ secrets.DOCKERHUB_USERNAME }}
           dockerhub-image-registry-token: ${{ secrets.DOCKERHUB_TOKEN }}
-          build-dev-builder-ubuntu: ${{ inputs.release_dev_builder_ubuntu_image || github.event_name == 'push' }}
-          build-dev-builder-centos: ${{ inputs.release_dev_builder_centos_image || github.event_name == 'push' }}
-          build-dev-builder-android: ${{ inputs.release_dev_builder_android_image || github.event_name == 'push' }}
+          build-dev-builder-ubuntu: ${{ inputs.release_dev_builder_ubuntu_image }}
+          build-dev-builder-centos: ${{ inputs.release_dev_builder_centos_image }}
+          build-dev-builder-android: ${{ inputs.release_dev_builder_android_image }}
 
   release-dev-builder-images-ecr:
     name: Release dev builder images to AWS ECR
@@ -93,7 +85,7 @@ jobs:
 
       - name: Push dev-builder-ubuntu image
         shell: bash
-        if: ${{ inputs.release_dev_builder_ubuntu_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_ubuntu_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -114,7 +106,7 @@ jobs:
 
       - name: Push dev-builder-centos image
         shell: bash
-        if: ${{ inputs.release_dev_builder_centos_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_centos_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -135,7 +127,7 @@ jobs:
 
       - name: Push dev-builder-android image
         shell: bash
-        if: ${{ inputs.release_dev_builder_android_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_android_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -170,7 +162,7 @@ jobs:
 
       - name: Push dev-builder-ubuntu image
         shell: bash
-        if: ${{ inputs.release_dev_builder_ubuntu_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_ubuntu_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -184,7 +176,7 @@ jobs:
 
       - name: Push dev-builder-centos image
         shell: bash
-        if: ${{ inputs.release_dev_builder_centos_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_centos_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -198,7 +190,7 @@ jobs:
 
       - name: Push dev-builder-android image
         shell: bash
-        if: ${{ inputs.release_dev_builder_android_image || github.event_name == 'push' }}
+        if: ${{ inputs.release_dev_builder_android_image }}
         env:
           IMAGE_VERSION: ${{ needs.release-dev-builder-images.outputs.version }}
           IMAGE_NAMESPACE: ${{ vars.IMAGE_NAMESPACE }}
@@ -209,24 +201,3 @@ jobs:
             quay.io/skopeo/stable:latest \
             copy -a docker://docker.io/$IMAGE_NAMESPACE/dev-builder-android:$IMAGE_VERSION \
             docker://$ACR_IMAGE_REGISTRY/$IMAGE_NAMESPACE/dev-builder-android:$IMAGE_VERSION
-  
-  update-dev-builder-image-tag:
-    name: Update dev-builder image tag
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    if: ${{ github.event_name == 'push' || inputs.update_dev_builder_image_tag }}
-    needs: [
-      release-dev-builder-images
-    ]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Update dev-builder image tag
-        shell: bash
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          ./.github/scripts/update-dev-builder-version.sh ${{ needs.release-dev-builder-images.outputs.version }}

.github/workflows/release.yml

@@ -88,8 +88,10 @@ env:
   # Controls whether to run tests, include unit-test, integration-test and sqlness.
   DISABLE_RUN_TESTS: ${{ inputs.skip_test || vars.DEFAULT_SKIP_TEST }}
 
-  # The scheduled version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-YYYYMMDD', like v0.2.0-nightly-20230313;
+  # The scheduled version is '${{ 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: v0.14.0
 
 jobs:
   allocate-runners:
@@ -124,7 +126,7 @@ jobs:
 
       # The create-version will create a global variable named 'version' in the global workflows.
       # - If it's a tag push release, the version is the tag name(${{ github.ref_name }});
-      # - If it's a scheduled release, the version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-$buildTime', like v0.2.0-nightly-20230313;
+      # - If it's a scheduled release, the version is '${{ env.NEXT_RELEASE_VERSION }}-nightly-$buildTime', like v0.2.0-nigthly-20230313;
       # - If it's a manual release, the version is '${{ env.NEXT_RELEASE_VERSION }}-<short-git-sha>-YYYYMMDDSS', like v0.2.0-e5b243c-2023071245;
       - name: Create version
         id: create-version
@@ -133,6 +135,7 @@ jobs:
         env:
           GITHUB_EVENT_NAME: ${{ github.event_name }}
           GITHUB_REF_NAME: ${{ github.ref_name }}
+          NEXT_RELEASE_VERSION: ${{ env.NEXT_RELEASE_VERSION }}
           NIGHTLY_RELEASE_PREFIX: ${{ env.NIGHTLY_RELEASE_PREFIX }}
 
       - name: Allocate linux-amd64 runner
@@ -388,7 +391,7 @@ jobs:
 
   ### Stop runners ###
   # It's very necessary to split the job of releasing runners into 'stop-linux-amd64-runner' and 'stop-linux-arm64-runner'.
-  # Because we can terminate the specified EC2 instance immediately after the job is finished without unnecessary waiting.
+  # Because we can terminate the specified EC2 instance immediately after the job is finished without uncessary waiting.
   stop-linux-amd64-runner: # It's always run as the last job in the workflow to make sure that the runner is released.
     name: Stop linux-amd64 runner
     # Only run this job when the runner is allocated.
@@ -444,7 +447,7 @@ jobs:
   bump-doc-version:
     name: Bump doc version
     if: ${{ github.event_name == 'push' || github.event_name == 'schedule' }}
-    needs: [allocate-runners, publish-github-release]
+    needs: [allocate-runners]
     runs-on: ubuntu-latest
     # Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
     permissions:
@@ -464,71 +467,6 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           DOCS_REPO_TOKEN: ${{ secrets.DOCS_REPO_TOKEN }}
 
-  bump-website-version:
-    name: Bump website version
-    if: ${{ github.ref_type == 'tag' && !contains(github.ref_name, 'nightly') && github.event_name != 'schedule' }}
-    needs: [allocate-runners, publish-github-release]
-    runs-on: ubuntu-latest
-    # Permission reference: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
-    permissions:
-      issues: write # Allows the action to create issues for cyborg.
-      contents: write # Allows the action to create a release.
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-      - uses: ./.github/actions/setup-cyborg
-      - name: Bump website version
-        working-directory: cyborg
-        run: pnpm tsx bin/bump-website-version.ts
-        env:
-          VERSION: ${{ needs.allocate-runners.outputs.version }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          WEBSITE_REPO_TOKEN: ${{ secrets.WEBSITE_REPO_TOKEN }}
-
-  bump-helm-charts-version:
-    name: Bump helm charts version
-    if: ${{ github.ref_type == 'tag' && !contains(github.ref_name, 'nightly') && github.event_name != 'schedule' }}
-    needs: [allocate-runners, publish-github-release]
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Bump helm charts version
-        env:
-          GITHUB_TOKEN: ${{ secrets.HELM_CHARTS_REPO_TOKEN }}
-          VERSION: ${{ needs.allocate-runners.outputs.version }}
-        run: |
-          ./.github/scripts/update-helm-charts-version.sh
-
-  bump-homebrew-greptime-version:
-    name: Bump homebrew greptime version
-    if: ${{ github.ref_type == 'tag' && !contains(github.ref_name, 'nightly') && github.event_name != 'schedule' }}
-    needs: [allocate-runners, publish-github-release]
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Bump homebrew greptime version
-        env:
-          GITHUB_TOKEN: ${{ secrets.HOMEBREW_GREPTIME_REPO_TOKEN }}
-          VERSION: ${{ needs.allocate-runners.outputs.version }}
-        run: |
-          ./.github/scripts/update-homebrew-greptme-version.sh
-
   notification:
     if: ${{ github.repository == 'GreptimeTeam/greptimedb' && (github.event_name == 'push' || github.event_name == 'schedule') && always() }}
     name: Send notification to Greptime team

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

@@ -14,9 +14,6 @@ concurrency:
 jobs:
   check:
     runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write  # Add permissions to modify PRs
-      issues: write
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4

.gitignore

@@ -28,7 +28,6 @@ debug/
 # Logs
 **/__unittest_logs
 logs/
-!grafana/dashboards/logs/
 
 # cpython's generated python byte code
 **/__pycache__/
@@ -58,6 +57,3 @@ tests-fuzz/corpus/
 
 ## default data home
 greptimedb_data
-
-# github
-!/.github

CONTRIBUTING.md

@@ -108,7 +108,7 @@ of what you were trying to do and what went wrong. You can also reach for help i
 The core team will be thrilled if you would like to participate in any way you like. When you are stuck, try to ask for help by filing an issue, with a detailed description of what you were trying to do and what went wrong. If you have any questions or if you would like to get involved in our community, please check out:
 
 - [GreptimeDB Community Slack](https://greptime.com/slack)
-- [GreptimeDB GitHub Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
+- [GreptimeDB Github Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
 
 Also, see some extra GreptimeDB content:
 

Cargo.toml

@@ -36,7 +36,6 @@ members = [
     "src/common/time",
     "src/common/version",
     "src/common/wal",
-    "src/common/workload",
     "src/datanode",
     "src/datatypes",
     "src/file-engine",
@@ -69,17 +68,15 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "0.15.0"
+version = "0.14.0"
 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.result_large_err = "allow"
-clippy.large_enum_variant = "allow"
-clippy.doc_overindented_list_items = "allow"
-clippy.uninlined_format_args = "allow"
 rust.unknown_lints = "deny"
 rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
 
@@ -115,15 +112,15 @@ clap = { version = "4.4", features = ["derive"] }
 config = "0.13.0"
 crossbeam-utils = "0.8"
 dashmap = "6.1"
-datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
-datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "e104c7cf62b11dd5fe41461b82514978234326b4" }
+datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
+datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "5bbedc6704162afb03478f56ffb629405a4e1220" }
 deadpool = "0.12"
 deadpool-postgres = "0.14"
 derive_builder = "0.20"
@@ -132,7 +129,7 @@ etcd-client = "0.14"
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "2dca1dc67862d7b410838aef81232274c019b3f6" }
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "b6d9cffd43c4e6358805a798f17e03e232994b82" }
 hex = "0.4"
 http = "1"
 humantime = "2.1"
@@ -164,10 +161,8 @@ parquet = { version = "54.2", default-features = false, features = ["arrow", "as
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-promql-parser = { git = "https://github.com/GreptimeTeam/promql-parser.git", rev = "0410e8b459dda7cb222ce9596f8bf3971bd07bd2", features = [
-    "ser",
-] }
-prost = { version = "0.13", features = ["no-recursion-limit"] }
+promql-parser = { version = "0.5.1", features = ["ser"] }
+prost = "0.13"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.9"
 ratelimit = "0.10"
@@ -179,7 +174,7 @@ reqwest = { version = "0.12", default-features = false, features = [
     "stream",
     "multipart",
 ] }
-rskafka = { git = "https://github.com/influxdata/rskafka.git", rev = "8dbd01ed809f5a791833a594e85b144e36e45820", features = [
+rskafka = { git = "https://github.com/influxdata/rskafka.git", rev = "75535b5ad9bae4a5dbb582c82e44dfd81ec10105", features = [
     "transport-tls",
 ] }
 rstest = "0.25"
@@ -196,7 +191,7 @@ simd-json = "0.15"
 similar-asserts = "1.6.0"
 smallvec = { version = "1", features = ["serde"] }
 snafu = "0.8"
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "0cf6c04490d59435ee965edd2078e8855bd8471e", features = [
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "e98e6b322426a9d397a71efef17075966223c089", features = [
     "visitor",
     "serde",
 ] } # branch = "v0.54.x"
@@ -260,7 +255,6 @@ common-test-util = { path = "src/common/test-util" }
 common-time = { path = "src/common/time" }
 common-version = { path = "src/common/version" }
 common-wal = { path = "src/common/wal" }
-common-workload = { path = "src/common/workload" }
 datanode = { path = "src/datanode" }
 datatypes = { path = "src/datatypes" }
 file-engine = { path = "src/file-engine" }
@@ -275,9 +269,6 @@ metric-engine = { path = "src/metric-engine" }
 mito2 = { path = "src/mito2" }
 object-store = { path = "src/object-store" }
 operator = { path = "src/operator" }
-otel-arrow-rust = { git = "https://github.com/open-telemetry/otel-arrow", rev = "5d551412d2a12e689cde4d84c14ef29e36784e51", features = [
-    "server",
-] }
 partition = { path = "src/partition" }
 pipeline = { path = "src/pipeline" }
 plugins = { path = "src/plugins" }

Makefile

@@ -8,7 +8,7 @@ CARGO_BUILD_OPTS := --locked
 IMAGE_REGISTRY ?= docker.io
 IMAGE_NAMESPACE ?= greptime
 IMAGE_TAG ?= latest
-DEV_BUILDER_IMAGE_TAG ?= 2025-05-19-b2377d4b-20250520045554
+DEV_BUILDER_IMAGE_TAG ?= 2024-12-25-a71b93dd-20250305072908
 BUILDX_MULTI_PLATFORM_BUILD ?= false
 BUILDX_BUILDER_NAME ?= gtbuilder
 BASE_IMAGE ?= ubuntu
@@ -222,16 +222,6 @@ start-cluster: ## Start the greptimedb cluster with etcd by using docker compose
 stop-cluster: ## Stop the greptimedb cluster that created by docker compose.
 	docker compose -f ./docker/docker-compose/cluster-with-etcd.yaml stop
 
-##@ Grafana
-
-.PHONY: check-dashboards
-check-dashboards: ## Check the Grafana dashboards.
-	@./grafana/scripts/check.sh
-
-.PHONY: dashboards
-dashboards: ## Generate the Grafana dashboards for standalone mode and intermediate dashboards.
-	@./grafana/scripts/gen-dashboards.sh
-
 ##@ Docs
 config-docs: ## Generate configuration documentation from toml files.
 	docker run --rm \

README.md

@@ -6,9 +6,7 @@
   </picture>
 </p>
 
-<h2 align="center">Real-Time & Cloud-Native Observability  Database<br/>for metrics, logs, and traces</h2>
-
->  Delivers sub-second querying at PB scale and exceptional cost efficiency from edge to cloud.
+<h2 align="center">Unified & Cost-Effective Observability  Database for Metrics, Logs, and Events</h2>
 
 <div align="center">
 <h3 align="center">
@@ -51,77 +49,74 @@
 </div>
 
 - [Introduction](#introduction)
-- [⭐ Key Features](#features)
-- [Quick Comparison](#quick-comparison)
-- [Architecture](#architecture)
-- [Try GreptimeDB](#try-greptimedb)
+- [**Features: Why GreptimeDB**](#why-greptimedb)
+- [Architecture](https://docs.greptime.com/contributor-guide/overview/#architecture)
+- [Try it for free](#try-greptimedb)
 - [Getting Started](#getting-started)
-- [Build From Source](#build-from-source)
-- [Tools & Extensions](#tools--extensions)
 - [Project Status](#project-status)
-- [Community](#community)
+- [Join the community](#community)
+  - [Contributing](#contributing)
+- [Tools & Extensions](#tools--extensions)
 - [License](#license)
-- [Commercial Support](#commercial-support)
-- [Contributing](#contributing)
 - [Acknowledgement](#acknowledgement)
 
 ## Introduction
 
-**GreptimeDB** is an open-source, cloud-native database purpose-built for the unified collection and analysis of observability data (metrics, logs, and traces). Whether you’re operating on the edge, in the cloud, or across hybrid environments, GreptimeDB empowers real-time insights at massive scale — all in one system.
+**GreptimeDB** is an open-source, cloud-native, unified & cost-effective observability database for **Metrics**, **Logs**, and **Traces**. You can gain real-time insights from Edge to Cloud at Any Scale.
 
-## Features
+## News
 
-|   Feature  | Description |
-| --------- | ----------- |
-| [Unified Observability Data](https://docs.greptime.com/user-guide/concepts/why-greptimedb) | Store metrics, logs, and traces as timestamped, contextual wide events. Query via [SQL](https://docs.greptime.com/user-guide/query-data/sql), [PromQL](https://docs.greptime.com/user-guide/query-data/promql), and [streaming](https://docs.greptime.com/user-guide/flow-computation/overview). |
-| [High Performance & Cost Effective](https://docs.greptime.com/user-guide/manage-data/data-index) | Written in Rust, with a distributed query engine, [rich indexing](https://docs.greptime.com/user-guide/manage-data/data-index), and optimized columnar storage, delivering sub-second responses at PB scale. |
-| [Cloud-Native Architecture](https://docs.greptime.com/user-guide/concepts/architecture) | Designed for [Kubernetes](https://docs.greptime.com/user-guide/deployments/deploy-on-kubernetes/greptimedb-operator-management), with compute/storage separation, native object storage (AWS S3, Azure Blob, etc.) and seamless cross-cloud access. |
-| [Developer-Friendly](https://docs.greptime.com/user-guide/protocols/overview) | Access via SQL/PromQL interfaces, REST API, MySQL/PostgreSQL protocols, and popular ingestion [protocols](https://docs.greptime.com/user-guide/protocols/overview). |
-| [Flexible Deployment](https://docs.greptime.com/user-guide/deployments/overview) | Deploy anywhere: edge (including ARM/[Android](https://docs.greptime.com/user-guide/deployments/run-on-android)) or cloud, with unified APIs and efficient data sync. |
+**[GreptimeDB tops JSONBench's billion-record cold run test!](https://greptime.com/blogs/2025-03-18-jsonbench-greptimedb-performance)**
 
-Learn more in [Why GreptimeDB](https://docs.greptime.com/user-guide/concepts/why-greptimedb) and [Observability 2.0 and the Database for It](https://greptime.com/blogs/2025-04-25-greptimedb-observability2-new-database).
+## Why GreptimeDB
 
-## Quick Comparison
+Our core developers have been building observability data platforms for years. Based on our best practices, GreptimeDB was born to give you:
 
-| Feature                         | GreptimeDB            | Traditional TSDB   | Log Stores      |
-|----------------------------------|-----------------------|--------------------|-----------------|
-| Data Types                      | Metrics, Logs, Traces | Metrics only       | Logs only       |
-| Query Language                  | SQL, PromQL, Streaming|  Custom/PromQL     | Custom/DSL      |
-| Deployment                      | Edge + Cloud          | Cloud/On-prem      | Mostly central  |
-| Indexing & Performance          | PB-Scale, Sub-second  | Varies             | Varies          |
-| Integration                     | REST, SQL, Common protocols | Varies     | Varies          |
+* **Unified Processing of Observability Data**
 
-**Performance:**
-* [GreptimeDB tops JSONBench's billion-record cold run test!](https://greptime.com/blogs/2025-03-18-jsonbench-greptimedb-performance)
-* [TSBS Benchmark](https://github.com/GreptimeTeam/greptimedb/tree/main/docs/benchmarks/tsbs)
+  A unified database that treats metrics, logs, and traces as timestamped wide events with context, supporting [SQL](https://docs.greptime.com/user-guide/query-data/sql)/[PromQL](https://docs.greptime.com/user-guide/query-data/promql) queries and [stream processing](https://docs.greptime.com/user-guide/flow-computation/overview) to simplify complex data stacks.
 
-Read [more benchmark reports](https://docs.greptime.com/user-guide/concepts/features-that-you-concern#how-is-greptimedbs-performance-compared-to-other-solutions).
+* **High Performance and Cost-effective**
 
-## Architecture
+   Written in Rust, combines a distributed query engine with [rich indexing](https://docs.greptime.com/user-guide/manage-data/data-index) (inverted, fulltext, skip data, and vector) and optimized columnar storage to deliver sub-second responses on petabyte-scale data and high-cost efficiency.
 
-* Read the [architecture](https://docs.greptime.com/contributor-guide/overview/#architecture) document.
-* [DeepWiki](https://deepwiki.com/GreptimeTeam/greptimedb/1-overview) provides an in-depth look at GreptimeDB:
-  <img alt="GreptimeDB System Overview" src="docs/architecture.png">
+* **Cloud-native Distributed Database**
+
+  Built for [Kubernetes](https://docs.greptime.com/user-guide/deployments/deploy-on-kubernetes/greptimedb-operator-management). GreptimeDB achieves seamless scalability with its [cloud-native architecture](https://docs.greptime.com/user-guide/concepts/architecture) of separated compute and storage, built on object storage (AWS S3, Azure Blob Storage, etc.) while enabling cross-cloud deployment through a unified data access layer.
+
+* **Developer-Friendly**
+
+  Access standardized SQL/PromQL interfaces through built-in web dashboard, REST API, and MySQL/PostgreSQL protocols. Supports widely adopted data ingestion [protocols](https://docs.greptime.com/user-guide/protocols/overview) for seamless migration and integration.
+
+* **Flexible Deployment Options**
+
+  Deploy GreptimeDB anywhere from ARM-based edge devices to cloud environments with unified APIs and bandwidth-efficient data synchronization. Query edge and cloud data seamlessly through identical APIs. [Learn how to run on Android](https://docs.greptime.com/user-guide/deployments/run-on-android/).
+
+For more detailed info please read  [Why GreptimeDB](https://docs.greptime.com/user-guide/concepts/why-greptimedb).
 
 ## Try GreptimeDB
 
 ### 1. [Live Demo](https://greptime.com/playground)
 
-Experience GreptimeDB directly in your browser.
+Try out the features of GreptimeDB right from your browser.
 
 ### 2. [GreptimeCloud](https://console.greptime.cloud/)
 
 Start instantly with a free cluster.
 
-### 3. Docker (Local Quickstart)
+### 3. Docker Image
+
+To install GreptimeDB locally, the recommended way is via Docker:
 
 ```shell
 docker pull greptime/greptimedb
 ```
 
+Start a GreptimeDB container with:
+
 ```shell
 docker run -p 127.0.0.1:4000-4003:4000-4003 \
-  -v "$(pwd)/greptimedb_data:/greptimedb_data" \
+  -v "$(pwd)/greptimedb:./greptimedb_data" \
   --name greptime --rm \
   greptime/greptimedb:latest standalone start \
   --http-addr 0.0.0.0:4000 \
@@ -129,89 +124,114 @@ docker run -p 127.0.0.1:4000-4003:4000-4003 \
   --mysql-addr 0.0.0.0:4002 \
   --postgres-addr 0.0.0.0:4003
 ```
-Dashboard: [http://localhost:4000/dashboard](http://localhost:4000/dashboard)
-[Full Install Guide](https://docs.greptime.com/getting-started/installation/overview)
 
-**Troubleshooting:**
-* Cannot connect to the database? Ensure that ports `4000`, `4001`, `4002`, and `4003` are not blocked by a firewall or used by other services.
-* Failed to start? Check the container logs with `docker logs greptime` for further details.
+Access the dashboard via `http://localhost:4000/dashboard`.
+
+Read more about [Installation](https://docs.greptime.com/getting-started/installation/overview) on docs.
 
 ## Getting Started
 
-- [Quickstart](https://docs.greptime.com/getting-started/quick-start)
-- [User Guide](https://docs.greptime.com/user-guide/overview)
-- [Demo Scenes](https://github.com/GreptimeTeam/demo-scene)
-- [FAQ](https://docs.greptime.com/faq-and-others/faq)
+* [Quickstart](https://docs.greptime.com/getting-started/quick-start)
+* [User Guide](https://docs.greptime.com/user-guide/overview)
+* [Demos](https://github.com/GreptimeTeam/demo-scene)
+* [FAQ](https://docs.greptime.com/faq-and-others/faq)
 
-## Build From Source
+## Build
+
+Check the prerequisite:
 
-**Prerequisites:**
 * [Rust toolchain](https://www.rust-lang.org/tools/install) (nightly)
 * [Protobuf compiler](https://grpc.io/docs/protoc-installation/) (>= 3.15)
 * C/C++ building essentials, including `gcc`/`g++`/`autoconf` and glibc library (eg. `libc6-dev` on Ubuntu and `glibc-devel` on Fedora)
 * Python toolchain (optional): Required only if using some test scripts.
 
-**Build and Run:**
-```bash
+Build GreptimeDB binary:
+
+```shell
 make
+```
+
+Run a standalone server:
+
+```shell
 cargo run -- standalone start
 ```
 
 ## Tools & Extensions
 
-- **Kubernetes:** [GreptimeDB Operator](https://github.com/GrepTimeTeam/greptimedb-operator)
-- **Helm Charts:** [Greptime Helm Charts](https://github.com/GreptimeTeam/helm-charts)
-- **Dashboard:** [Web UI](https://github.com/GreptimeTeam/dashboard)
-- **SDKs/Ingester:** [Go](https://github.com/GreptimeTeam/greptimedb-ingester-go), [Java](https://github.com/GreptimeTeam/greptimedb-ingester-java), [C++](https://github.com/GreptimeTeam/greptimedb-ingester-cpp), [Erlang](https://github.com/GreptimeTeam/greptimedb-ingester-erl), [Rust](https://github.com/GreptimeTeam/greptimedb-ingester-rust), [JS](https://github.com/GreptimeTeam/greptimedb-ingester-js)
-- **Grafana**: [Official Dashboard](https://github.com/GreptimeTeam/greptimedb/blob/main/grafana/README.md)
+### Kubernetes
+
+- [GreptimeDB Operator](https://github.com/GrepTimeTeam/greptimedb-operator)
+
+### Dashboard
+
+- [The dashboard UI for GreptimeDB](https://github.com/GreptimeTeam/dashboard)
+
+### SDK
+
+- [GreptimeDB Go Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-go)
+- [GreptimeDB Java Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-java)
+- [GreptimeDB C++ Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-cpp)
+- [GreptimeDB Erlang Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-erl)
+- [GreptimeDB Rust Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-rust)
+- [GreptimeDB JavaScript Ingester](https://github.com/GreptimeTeam/greptimedb-ingester-js)
+
+### Grafana Dashboard
+
+Our official Grafana dashboard for monitoring GreptimeDB is available at [grafana](grafana/README.md) directory.
 
 ## Project Status
 
-> **Status:** Beta.
-> **GA (v1.0):** Targeted for mid 2025.
+GreptimeDB is currently in Beta. We are targeting GA (General Availability) with v1.0 release by Early 2025.
 
-- Being used in production by early adopters
-- Stable, actively maintained, with regular releases ([version info](https://docs.greptime.com/nightly/reference/about-greptimedb-version))
-- Suitable for evaluation and pilot deployments
+While in Beta, GreptimeDB is already:
+
+* Being used in production by early adopters
+* Actively maintained with regular releases, [about version number](https://docs.greptime.com/nightly/reference/about-greptimedb-version)
+* Suitable for testing and evaluation
 
 For production use, we recommend using the latest stable release.
-[![Star History Chart](https://api.star-history.com/svg?repos=GreptimeTeam/GreptimeDB&type=Date)](https://www.star-history.com/#GreptimeTeam/GreptimeDB&Date)
-
-If you find this project useful, a ⭐ would mean a lot to us!
-<img alt="Known Users" src="https://greptime.com/logo/img/users.png"/>
 
 ## Community
 
-We invite you to engage and contribute!
+Our core team is thrilled to see you participate in any ways you like. When you are stuck, try to
+ask for help by filling an issue with a detailed description of what you were trying to do
+and what went wrong. If you have any questions or if you would like to get involved in our
+community, please check out:
 
-- [Slack](https://greptime.com/slack)
-- [Discussions](https://github.com/GreptimeTeam/greptimedb/discussions)
-- [Official Website](https://greptime.com/)
-- [Blog](https://greptime.com/blogs/)
-- [LinkedIn](https://www.linkedin.com/company/greptime/)
-- [Twitter](https://twitter.com/greptime)
+- GreptimeDB Community on [Slack](https://greptime.com/slack)
+- GreptimeDB [GitHub Discussions forum](https://github.com/GreptimeTeam/greptimedb/discussions)
+- Greptime official [website](https://greptime.com)
 
-## License
+In addition, you may:
 
-GreptimeDB is licensed under the [Apache License 2.0](https://apache.org/licenses/LICENSE-2.0.txt).
+- View our official [Blog](https://greptime.com/blogs/)
+- Connect us with [Linkedin](https://www.linkedin.com/company/greptime/)
+- Follow us on [Twitter](https://twitter.com/greptime)
 
 ## Commercial Support
 
-Running GreptimeDB in your organization?
-We offer enterprise add-ons, services, training, and consulting.
-[Contact us](https://greptime.com/contactus) for details.
+If you are running GreptimeDB OSS in your organization, we offer additional
+enterprise add-ons, installation services, training, and consulting. [Contact
+us](https://greptime.com/contactus) and we will reach out to you with more
+detail of our commercial license.
+
+## License
+
+GreptimeDB uses the [Apache License 2.0](https://apache.org/licenses/LICENSE-2.0.txt) to strike a balance between
+open contributions and allowing you to use the software however you want.
 
 ## Contributing
 
-- Read our [Contribution Guidelines](https://github.com/GreptimeTeam/greptimedb/blob/main/CONTRIBUTING.md).
-- Explore [Internal Concepts](https://docs.greptime.com/contributor-guide/overview.html) and [DeepWiki](https://deepwiki.com/GreptimeTeam/greptimedb).
-- Pick up a [good first issue](https://github.com/GreptimeTeam/greptimedb/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) and join the #contributors [Slack](https://greptime.com/slack) channel.
+Please refer to [contribution guidelines](CONTRIBUTING.md) and [internal concepts docs](https://docs.greptime.com/contributor-guide/overview.html) for more information.
 
 ## Acknowledgement
 
-Special thanks to all contributors! See [AUTHORS.md](https://github.com/GreptimeTeam/greptimedb/blob/main/AUTHOR.md).
+Special thanks to all the contributors who have propelled GreptimeDB forward. For a complete list of contributors, please refer to [AUTHOR.md](AUTHOR.md).
 
-- Uses [Apache Arrow™](https://arrow.apache.org/) (memory model)
-- [Apache Parquet™](https://parquet.apache.org/) (file storage)
-- [Apache Arrow DataFusion™](https://arrow.apache.org/datafusion/) (query engine)
-- [Apache OpenDAL™](https://opendal.apache.org/) (data access abstraction)
+- GreptimeDB uses [Apache Arrow™](https://arrow.apache.org/) as the memory model and [Apache Parquet™](https://parquet.apache.org/) as the persistent file format.
+- GreptimeDB's query engine is powered by [Apache Arrow DataFusion™](https://arrow.apache.org/datafusion/).
+- [Apache OpenDAL™](https://opendal.apache.org) gives GreptimeDB a very general and elegant data access abstraction layer.
+- GreptimeDB's meta service is based on [etcd](https://etcd.io/).
+
+<img alt="Known Users" src="https://greptime.com/logo/img/users.png"/>

config/config.md

@@ -27,7 +27,6 @@
 | `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
 | `http.enable_cors` | Bool | `true` | HTTP CORS support, it's turned on by default<br/>This allows browser to access http APIs without CORS restrictions |
 | `http.cors_allowed_origins` | Array | Unset | Customize allowed origins for HTTP CORS. |
-| `http.prom_validation_mode` | String | `strict` | Whether to enable validation for Prometheus remote write requests.<br/>Available options:<br/>- strict: deny invalid UTF-8 strings (default).<br/>- lossy: allow invalid UTF-8 strings, replace invalid characters with REPLACEMENT_CHARACTER(U+FFFD).<br/>- unchecked: do not valid strings. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.bind_addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
 | `grpc.runtime_size` | Integer | `8` | The number of server worker threads. |
@@ -155,7 +154,6 @@
 | `region_engine.mito.index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
 | `region_engine.mito.index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
 | `region_engine.mito.index.content_cache_page_size` | String | `64KiB` | Page size for inverted index content cache. |
-| `region_engine.mito.index.result_cache_size` | String | `128MiB` | Cache size for index result. |
 | `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
 | `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
@@ -190,11 +188,10 @@
 | `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
-| `slow_query` | -- | -- | The slow query log options. |
-| `slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
-| `slow_query.record_type` | String | Unset | The record type of slow queries. It can be `system_table` or `log`. |
-| `slow_query.threshold` | String | Unset | The threshold of slow query. |
-| `slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
@@ -227,7 +224,6 @@
 | `http.body_limit` | String | `64MB` | HTTP request body limit.<br/>The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.<br/>Set to 0 to disable limit. |
 | `http.enable_cors` | Bool | `true` | HTTP CORS support, it's turned on by default<br/>This allows browser to access http APIs without CORS restrictions |
 | `http.cors_allowed_origins` | Array | Unset | Customize allowed origins for HTTP CORS. |
-| `http.prom_validation_mode` | String | `strict` | Whether to enable validation for Prometheus remote write requests.<br/>Available options:<br/>- strict: deny invalid UTF-8 strings (default).<br/>- lossy: allow invalid UTF-8 strings, replace invalid characters with REPLACEMENT_CHARACTER(U+FFFD).<br/>- unchecked: do not valid strings. |
 | `grpc` | -- | -- | The gRPC server options. |
 | `grpc.bind_addr` | String | `127.0.0.1:4001` | The address to bind the gRPC server. |
 | `grpc.server_addr` | String | `127.0.0.1:4001` | The address advertised to the metasrv, and used for connections from outside the host.<br/>If left empty or unset, the server will automatically use the IP address of the first network interface<br/>on the host, with the same port number as the one specified in `grpc.bind_addr`. |
@@ -292,12 +288,10 @@
 | `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
-| `slow_query` | -- | -- | The slow query log options. |
-| `slow_query.enable` | Bool | `true` | Whether to enable slow query log. |
-| `slow_query.record_type` | String | `system_table` | The record type of slow queries. It can be `system_table` or `log`.<br/>If `system_table` is selected, the slow queries will be recorded in a system table `greptime_private.slow_queries`.<br/>If `log` is selected, the slow queries will be logged in a log file `greptimedb-slow-queries.*`. |
-| `slow_query.threshold` | String | `30s` | The threshold of slow query. It can be human readable time string, for example: `10s`, `100ms`, `1s`. |
-| `slow_query.sample_ratio` | Float | `1.0` | The sampling ratio of slow query log. The value should be in the range of (0, 1]. For example, `0.1` means 10% of the slow queries will be logged and `1.0` means all slow queries will be logged. |
-| `slow_query.ttl` | String | `30d` | The TTL of the `slow_queries` system table. Default is `30d` when `record_type` is `system_table`. |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
@@ -325,16 +319,11 @@
 | `selector` | String | `round_robin` | Datanode selector type.<br/>- `round_robin` (default value)<br/>- `lease_based`<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
 | `use_memory_store` | Bool | `false` | Store data in memory. |
 | `enable_region_failover` | Bool | `false` | Whether to enable region failover.<br/>This feature is only available on GreptimeDB running on cluster mode and<br/>- Using Remote WAL<br/>- Using shared storage (e.g., s3). |
-| `allow_region_failover_on_local_wal` | Bool | `false` | Whether to allow region failover on local WAL.<br/>**This option is not recommended to be set to true, because it may lead to data loss during failover.** |
 | `node_max_idle_time` | String | `24hours` | Max allowed idle time before removing node info from metasrv memory. |
 | `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. Enabled by default. |
 | `runtime` | -- | -- | The runtime options. |
 | `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
 | `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
-| `http` | -- | -- | The HTTP server options. |
-| `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
-| `http.timeout` | String | `0s` | 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. |
 | `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 |
@@ -372,6 +361,10 @@
 | `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
@@ -501,7 +494,6 @@
 | `region_engine.mito.index.metadata_cache_size` | String | `64MiB` | Cache size for inverted index metadata. |
 | `region_engine.mito.index.content_cache_size` | String | `128MiB` | Cache size for inverted index content. |
 | `region_engine.mito.index.content_cache_page_size` | String | `64KiB` | Page size for inverted index content cache. |
-| `region_engine.mito.index.result_cache_size` | String | `128MiB` | Cache size for index result. |
 | `region_engine.mito.inverted_index` | -- | -- | The options for inverted index in Mito engine. |
 | `region_engine.mito.inverted_index.create_on_flush` | String | `auto` | Whether to create the index on flush.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
 | `region_engine.mito.inverted_index.create_on_compaction` | String | `auto` | Whether to create the index on compaction.<br/>- `auto`: automatically (default)<br/>- `disable`: never |
@@ -536,6 +528,10 @@
 | `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `export_metrics` | -- | -- | The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.<br/>This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape. |
 | `export_metrics.enable` | Bool | `false` | whether enable export metrics. |
 | `export_metrics.write_interval` | String | `30s` | The interval of export metrics. |
@@ -588,5 +584,9 @@
 | `logging.max_log_files` | Integer | `720` | The maximum amount of log files. |
 | `logging.tracing_sample_ratio` | -- | -- | The percentage of tracing will be sampled and exported.<br/>Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.<br/>ratio > 1 are treated as 1. Fractions < 0 are treated as 0 |
 | `logging.tracing_sample_ratio.default_ratio` | Float | `1.0` | -- |
+| `logging.slow_query` | -- | -- | The slow query log options. |
+| `logging.slow_query.enable` | Bool | `false` | Whether to enable slow query log. |
+| `logging.slow_query.threshold` | String | Unset | The threshold of slow query. |
+| `logging.slow_query.sample_ratio` | Float | Unset | The sampling ratio of slow query log. The value should be in the range of (0, 1]. |
 | `tracing` | -- | -- | The tracing options. Only effect when compiled with `tokio-console` feature. |
 | `tracing.tokio_console_addr` | String | Unset | The tokio console address. |

config/datanode.example.toml

@@ -499,9 +499,6 @@ content_cache_size = "128MiB"
 ## Page size for inverted index content cache.
 content_cache_page_size = "64KiB"
 
-## Cache size for index result.
-result_cache_size = "128MiB"
-
 ## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
 
@@ -635,6 +632,19 @@ max_log_files = 720
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]

config/flownode.example.toml

@@ -100,6 +100,19 @@ max_log_files = 720
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The tracing options. Only effect when compiled with `tokio-console` feature.
 #+ [tracing]
 ## The tokio console address.

config/frontend.example.toml

@@ -37,12 +37,6 @@ enable_cors = true
 ## Customize allowed origins for HTTP CORS.
 ## @toml2docs:none-default
 cors_allowed_origins = ["https://example.com"]
-## Whether to enable validation for Prometheus remote write requests.
-## Available options:
-## - strict: deny invalid UTF-8 strings (default).
-## - lossy: allow invalid UTF-8 strings, replace invalid characters with REPLACEMENT_CHARACTER(U+FFFD).
-## - unchecked: do not valid strings.
-prom_validation_mode = "strict"
 
 ## The gRPC server options.
 [grpc]
@@ -229,24 +223,18 @@ max_log_files = 720
 default_ratio = 1.0
 
 ## The slow query log options.
-[slow_query]
+[logging.slow_query]
 ## Whether to enable slow query log.
-enable = true
+enable = false
 
-## The record type of slow queries. It can be `system_table` or `log`.
-## If `system_table` is selected, the slow queries will be recorded in a system table `greptime_private.slow_queries`.
-## If `log` is selected, the slow queries will be logged in a log file `greptimedb-slow-queries.*`.
-record_type = "system_table"
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
 
-## The threshold of slow query. It can be human readable time string, for example: `10s`, `100ms`, `1s`.
-threshold = "30s"
-
-## The sampling ratio of slow query log. The value should be in the range of (0, 1]. For example, `0.1` means 10% of the slow queries will be logged and `1.0` means all slow queries will be logged.
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
 sample_ratio = 1.0
 
-## The TTL of the `slow_queries` system table. Default is `30d` when `record_type` is `system_table`.
-ttl = "30d"
-
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]

config/metasrv.example.toml

@@ -50,10 +50,6 @@ use_memory_store = false
 ## - Using shared storage (e.g., s3).
 enable_region_failover = false
 
-## Whether to allow region failover on local WAL.
-## **This option is not recommended to be set to true, because it may lead to data loss during failover.**
-allow_region_failover_on_local_wal = false
-
 ## Max allowed idle time before removing node info from metasrv memory.
 node_max_idle_time = "24hours"
 
@@ -67,17 +63,6 @@ node_max_idle_time = "24hours"
 ## The number of threads to execute the runtime for global write operations.
 #+ compact_rt_size = 4
 
-## The HTTP server options.
-[http]
-## The address to bind the HTTP server.
-addr = "127.0.0.1:4000"
-## HTTP request timeout. Set to 0 to disable timeout.
-timeout = "0s"
-## HTTP request body limit.
-## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
-## Set to 0 to disable limit.
-body_limit = "64MB"
-
 ## Procedure storage options.
 [procedure]
 
@@ -229,6 +214,19 @@ max_log_files = 720
 [logging.tracing_sample_ratio]
 default_ratio = 1.0
 
+## The slow query log options.
+[logging.slow_query]
+## Whether to enable slow query log.
+enable = false
+
+## The threshold of slow query.
+## @toml2docs:none-default
+threshold = "10s"
+
+## The sampling ratio of slow query log. The value should be in the range of (0, 1].
+## @toml2docs:none-default
+sample_ratio = 1.0
+
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
 [export_metrics]

config/standalone.example.toml

@@ -43,13 +43,6 @@ enable_cors = true
 ## @toml2docs:none-default
 cors_allowed_origins = ["https://example.com"]
 
-## Whether to enable validation for Prometheus remote write requests.
-## Available options:
-## - strict: deny invalid UTF-8 strings (default).
-## - lossy: allow invalid UTF-8 strings, replace invalid characters with REPLACEMENT_CHARACTER(U+FFFD).
-## - unchecked: do not valid strings.
-prom_validation_mode = "strict"
-
 ## The gRPC server options.
 [grpc]
 ## The address to bind the gRPC server.
@@ -597,9 +590,6 @@ content_cache_size = "128MiB"
 ## Page size for inverted index content cache.
 content_cache_page_size = "64KiB"
 
-## Cache size for index result.
-result_cache_size = "128MiB"
-
 ## The options for inverted index in Mito engine.
 [region_engine.mito.inverted_index]
 
@@ -734,21 +724,17 @@ max_log_files = 720
 default_ratio = 1.0
 
 ## The slow query log options.
-[slow_query]
+[logging.slow_query]
 ## Whether to enable slow query log.
-#+ enable = false
-
-## The record type of slow queries. It can be `system_table` or `log`.
-## @toml2docs:none-default
-#+ record_type = "system_table"
+enable = false
 
 ## The threshold of slow query.
 ## @toml2docs:none-default
-#+ threshold = "10s"
+threshold = "10s"
 
 ## The sampling ratio of slow query log. The value should be in the range of (0, 1].
 ## @toml2docs:none-default
-#+ sample_ratio = 1.0
+sample_ratio = 1.0
 
 ## The datanode can export its metrics and send to Prometheus compatible service (e.g. send to `greptimedb` itself) from remote-write API.
 ## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.

cyborg/bin/bump-website-version.ts

@@ -1,57 +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 {obtainClient} from "@/common";
-
-async function triggerWorkflow(workflowId: string, version: string) {
-  const websiteClient = obtainClient("WEBSITE_REPO_TOKEN")
-  try {
-    await websiteClient.rest.actions.createWorkflowDispatch({
-      owner: "GreptimeTeam",
-      repo: "website",
-      workflow_id: workflowId,
-      ref: "main",
-      inputs: {
-        version,
-      },
-    });
-    console.log(`Successfully triggered ${workflowId} workflow with version ${version}`);
-  } catch (error) {
-    core.setFailed(`Failed to trigger workflow: ${error.message}`);
-  }
-}
-
-const version = process.env.VERSION;
-if (!version) {
-  core.setFailed("VERSION environment variable is required");
-  process.exit(1);
-}
-
-// Remove 'v' prefix if exists
-const cleanVersion = version.startsWith('v') ? version.slice(1) : version;
-
-if (cleanVersion.includes('nightly')) {
-  console.log('Nightly version detected, skipping workflow trigger.');
-  process.exit(0);
-}
-
-try {
-  triggerWorkflow('bump-patch-version.yml', cleanVersion);
-} catch (error) {
-  core.setFailed(`Error processing version: ${error.message}`);
-  process.exit(1);
-}

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

@@ -11,6 +11,6 @@ And database will reply with something like:
 Log Level changed from Some("info") to "trace,flow=debug"%
 ```
 
-The data is a string in the format of `global_level,module1=level1,module2=level2,...` that follows the same rule of `RUST_LOG`. 
+The data is a string in the format of `global_level,module1=level1,module2=level2,...` that follow the same rule of `RUST_LOG`. 
 
 The module is the module name of the log, and the level is the log level. The log level can be one of the following: `trace`, `debug`, `info`, `warn`, `error`, `off`(case insensitive).

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

@@ -14,7 +14,7 @@ impl SqlQueryHandler for Instance {
 ```
 
 Normally, when a SQL query arrives at GreptimeDB, the `do_query` method will be called. After some parsing work, the SQL
-will be fed into `StatementExecutor`:
+will be feed into `StatementExecutor`:
 
 ```rust
 // in Frontend Instance:
@@ -27,7 +27,7 @@ an example.
 
 Now, what if the statements should be handled differently for GreptimeDB Standalone and Cluster? You can see there's
 a `SqlStatementExecutor` field in `StatementExecutor`. Each GreptimeDB Standalone and Cluster has its own implementation
-of `SqlStatementExecutor`. If you are going to implement the statements differently in the two modes (
+of `SqlStatementExecutor`. If you are going to implement the statements differently in the two mode (
 like `CREATE TABLE`), you have to implement them in their own `SqlStatementExecutor`s.
 
 Summarize as the diagram below:

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

@@ -1,6 +1,6 @@
 # Profile memory usage of GreptimeDB
 
-This crate provides an easy approach to dump memory profiling info. A set of ready to use scripts is provided in [docs/how-to/memory-profile-scripts](./memory-profile-scripts/scripts).
+This crate provides an easy approach to dump memory profiling info. A set of ready to use scripts is provided in [docs/how-to/memory-profile-scripts](docs/how-to/memory-profile-scripts).
 
 ## Prerequisites
 ### jemalloc
@@ -44,10 +44,6 @@ Dump memory profiling data through HTTP API:
 
 ```bash
 curl -X POST localhost:4000/debug/prof/mem > greptime.hprof
-# or output flamegraph directly
-curl -X POST "localhost:4000/debug/prof/mem?output=flamegraph" > greptime.svg
-# or output pprof format
-curl -X POST "localhost:4000/debug/prof/mem?output=proto" > greptime.pprof
 ```
 
 You can periodically dump profiling data and compare them to find the delta memory usage.

docs/how-to/how-to-write-aggregate-function.md

@@ -1,8 +1,8 @@
 Currently, our query engine is based on DataFusion, so all aggregate function is executed by DataFusion, through its UDAF interface. You can find DataFusion's UDAF example [here](https://github.com/apache/arrow-datafusion/blob/arrow2/datafusion-examples/examples/simple_udaf.rs). Basically, we provide the same way as DataFusion to write aggregate functions: both are centered in a struct called "Accumulator" to accumulates states along the way in aggregation.
 
-However, DataFusion's UDAF implementation has a huge restriction, that it requires user to provide a concrete "Accumulator". Take `Median` aggregate function for example, to aggregate a `u32` datatype column, you have to write a `MedianU32`, and use `SELECT MEDIANU32(x)` in SQL. `MedianU32` cannot be used to aggregate a `i32` datatype column. Or, there's another way: you can use a special type that can hold all kinds of data (like our `Value` enum or Arrow's `ScalarValue`), and `match` all the way up to do aggregate calculations. It might work, though rather tedious. (But I think it's DataFusion's preferred way to write UDAF.)
+However, DataFusion's UDAF implementation has a huge restriction, that it requires user to provide a concrete "Accumulator". Take `Median` aggregate function for example, to aggregate a `u32` datatype column, you have to write a `MedianU32`, and use `SELECT MEDIANU32(x)` in SQL. `MedianU32` cannot be used to aggregate a `i32` datatype column. Or, there's another way: you can use a special type that can hold all kinds of data (like our `Value` enum or Arrow's `ScalarValue`), and `match` all the way up to do aggregate calculations. It might work, though rather tedious. (But I think it's DataFusion's prefer way to write UDAF.)
 
-So is there a way we can make an aggregate function that automatically match the input data's type? For example, a `Median` aggregator that can work on both `u32` column and `i32`? The answer is yes until we find a way to bypass DataFusion's restriction, a restriction that DataFusion simply doesn't pass the input data's type when creating an Accumulator.
+So is there a way we can make an aggregate function that automatically match the input data's type? For example, a `Median` aggregator that can work on both `u32` column and `i32`? The answer is yes until we found a way to bypassing DataFusion's restriction, a restriction that DataFusion simply don't pass the input data's type when creating an Accumulator.
 
 > There's an example in `my_sum_udaf_example.rs`, take that as quick start.
 
@@ -16,7 +16,7 @@ You must first define a struct that will be used to create your accumulator. For
 struct MySumAccumulatorCreator {}
 ```
 
-Attribute macro `#[as_aggr_func_creator]` and derive macro `#[derive(Debug, AggrFuncTypeStore)]` must both be annotated on the struct. They work together to provide a storage of aggregate function's input data types, which are needed for creating generic accumulator later.  
+Attribute macro `#[as_aggr_func_creator]` and derive macro `#[derive(Debug, AggrFuncTypeStore)]` must both annotated on the struct. They work together to provide a storage of aggregate function's input data types, which are needed for creating generic accumulator later.  
 
 > Note that the `as_aggr_func_creator` macro will add fields to the struct, so the struct cannot be defined as an empty struct without field like `struct Foo;`, neither as a new type like `struct Foo(bar)`.
 
@@ -32,11 +32,11 @@ pub trait AggregateFunctionCreator: Send + Sync + Debug {
 
 You can use input data's type in methods that return output type and state types (just invoke `input_types()`).
 
-The output type is aggregate function's output data's type. For example, `SUM` aggregate function's output type is `u64` for a `u32` datatype column. The state types are accumulator's internal states' types. Take `AVG` aggregate function on a `i32` column as example, its state types are `i64` (for sum) and `u64` (for count).
+The output type is aggregate function's output data's type. For example, `SUM` aggregate function's output type is `u64` for a `u32` datatype column. The state types are accumulator's internal states' types. Take `AVG` aggregate function on a `i32` column as example, it's state types are `i64` (for sum) and `u64` (for count).
 
 The `creator` function is where you define how an accumulator (that will be used in DataFusion) is created. You define "how" to create the accumulator (instead of "what" to create), using the input data's type as arguments. With input datatype known, you can create accumulator generically.
 
-# 2. Impl `Accumulator` trait for your accumulator.
+# 2. Impl `Accumulator` trait for you accumulator.
 
 The accumulator is where you store the aggregate calculation states and evaluate a result. You must impl `Accumulator` trait for it. The trait's definition is:
 
@@ -49,7 +49,7 @@ pub trait Accumulator: Send + Sync + Debug {
 }
 ```
 
-The DataFusion basically executes aggregate like this:
+The DataFusion basically execute aggregate like this:
 
 1. Partitioning all input data for aggregate. Create an accumulator for each part.
 2. Call `update_batch` on each accumulator with partitioned data, to let you update your aggregate calculation.
@@ -57,16 +57,16 @@ The DataFusion basically executes aggregate like this:
 4. Call `merge_batch` to merge all accumulator's internal state to one.
 5. Execute `evaluate` on the chosen one to get the final calculation result.
 
-Once you know the meaning of each method, you can easily write your accumulator. You can refer to `Median` accumulator or `SUM` accumulator defined in file `my_sum_udaf_example.rs` for more details.
+Once you know the meaning of each method, you can easily write your accumulator. You can refer to `Median` accumulator or `SUM` accumulator defined in  file `my_sum_udaf_example.rs` for more details.
 
 # 3. Register your aggregate function to our query engine.
 
 You can call `register_aggregate_function` method in query engine to register your aggregate function. To do that, you have to new an instance of struct `AggregateFunctionMeta`. The struct has three fields, first is the name of your aggregate function's name. The function name is case-sensitive due to DataFusion's restriction. We strongly recommend using lowercase for your name. If you have to use uppercase name, wrap your aggregate function with quotation marks. For example, if you define an aggregate function named "my_aggr", you can use "`SELECT MY_AGGR(x)`"; if you define "my_AGGR", you have to use "`SELECT "my_AGGR"(x)`".
 
-The second field is arg_counts ,the count of the arguments. Like accumulator `percentile`, calculating the p_number of the column. We need to input the value of column and the value of p to calculate, and so the count of the arguments is two.
+The second field is arg_counts ,the count of the arguments. Like accumulator `percentile`, calculating the p_number of the column. We need to input the value of column and the value of p to cacalate, and so the count of the arguments is two.
 
 The third field is a function about how to create your accumulator creator that you defined in step 1 above. Create creator, that's a bit intertwined, but it is how we make DataFusion use a newly created aggregate function each time it executes a SQL, preventing the stored input types from affecting each other. The key detail can be starting looking at our `DfContextProviderAdapter` struct's `get_aggregate_meta` method.
 
 # (Optional) 4. Make your aggregate function automatically registered.
 
-If you've written a great aggregate function that wants to let everyone use it, you can make it automatically register to our query engine at start time. It's quick and simple, just refer to the `AggregateFunctions::register` function in `common/function/src/scalars/aggregate/mod.rs`.
+If you've written a great aggregate function that want to let everyone use it, you can make it automatically registered to our query engine at start time. It's quick simple, just refer to the `AggregateFunctions::register` function in `common/function/src/scalars/aggregate/mod.rs`.

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

@@ -3,7 +3,7 @@
 This document introduces how to write fuzz tests in GreptimeDB.
 
 ## What is a fuzz test
-Fuzz test is tool that leverages 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.
+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

flake.lock

@@ -8,11 +8,11 @@
         "rust-analyzer-src": "rust-analyzer-src"
       },
       "locked": {
-        "lastModified": 1745735608,
-        "narHash": "sha256-L0jzm815XBFfF2wCFmR+M1CF+beIEFj6SxlqVKF59Ec=",
+        "lastModified": 1737613896,
+        "narHash": "sha256-ldqXIglq74C7yKMFUzrS9xMT/EVs26vZpOD68Sh7OcU=",
         "owner": "nix-community",
         "repo": "fenix",
-        "rev": "c39a78eba6ed2a022cc3218db90d485077101496",
+        "rev": "303a062fdd8e89f233db05868468975d17855d80",
         "type": "github"
       },
       "original": {
@@ -41,16 +41,16 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1748162331,
-        "narHash": "sha256-rqc2RKYTxP3tbjA+PB3VMRQNnjesrT0pEofXQTrMsS8=",
+        "lastModified": 1737569578,
+        "narHash": "sha256-6qY0pk2QmUtBT9Mywdvif0i/CLVgpCjMUn6g9vB+f3M=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "7c43f080a7f28b2774f3b3f43234ca11661bf334",
+        "rev": "47addd76727f42d351590c905d9d1905ca895b82",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-25.05",
+        "ref": "nixos-24.11",
         "repo": "nixpkgs",
         "type": "github"
       }
@@ -65,11 +65,11 @@
     "rust-analyzer-src": {
       "flake": false,
       "locked": {
-        "lastModified": 1745694049,
-        "narHash": "sha256-fxvRYH/tS7hGQeg9zCVh5RBcSWT+JGJet7RA8Ss+rC0=",
+        "lastModified": 1737581772,
+        "narHash": "sha256-t1P2Pe3FAX9TlJsCZbmJ3wn+C4qr6aSMypAOu8WNsN0=",
         "owner": "rust-lang",
         "repo": "rust-analyzer",
-        "rev": "d8887c0758bbd2d5f752d5bd405d4491e90e7ed6",
+        "rev": "582af7ee9c8d84f5d534272fc7de9f292bd849be",
         "type": "github"
       },
       "original": {

flake.nix

@@ -2,7 +2,7 @@
   description = "Development environment flake";
 
   inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.05";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
     fenix = {
       url = "github:nix-community/fenix";
       inputs.nixpkgs.follows = "nixpkgs";
@@ -21,7 +21,7 @@
         lib = nixpkgs.lib;
         rustToolchain = fenix.packages.${system}.fromToolchainName {
           name = (lib.importTOML ./rust-toolchain.toml).toolchain.channel;
-          sha256 = "sha256-tJJr8oqX3YD+ohhPK7jlt/7kvKBnBqJVjYtoFr520d4=";
+          sha256 = "sha256-f/CVA1EC61EWbh0SjaRNhLL0Ypx2ObupbzigZp8NmL4=";
         };
       in
       {
@@ -51,7 +51,6 @@
           ];
 
           LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath buildInputs;
-          NIX_HARDENING_ENABLE = "";
         };
       });
 }

grafana/README.md

@@ -1,122 +1,61 @@
-# Grafana dashboards for GreptimeDB
+Grafana dashboard for GreptimeDB
+--------------------------------
 
-## Overview
+GreptimeDB's official Grafana dashboard.
 
-This repository contains Grafana dashboards for visualizing metrics and logs of GreptimeDB instances running in either cluster or standalone mode. **The Grafana version should be greater than 9.0**.
+Status notify: we are still working on this config. It's expected to change frequently in the recent days. Please feel free to submit your feedback and/or contribution to this dashboard 🤗
 
-We highly recommend using the self-monitoring feature provided by [GreptimeDB Operator](https://github.com/GrepTimeTeam/greptimedb-operator) to automatically collect metrics and logs from your GreptimeDB instances and store them in a dedicated GreptimeDB instance.
-
-- **Metrics Dashboards**
-
-  - `dashboards/metrics/cluster/dashboard.json`: The Grafana dashboard for the GreptimeDB cluster. Read the [dashboard.md](./dashboards/metrics/cluster/dashboard.md) for more details.
-  
-  - `dashboards/metrics/standalone/dashboard.json`: The Grafana dashboard for the standalone GreptimeDB instance. **It's generated from the `cluster/dashboard.json` by removing the instance filter through the `make dashboards` command**. Read the [dashboard.md](./dashboards/metrics/standalone/dashboard.md) for more details.
-
-- **Logs Dashboard**
-
-  The `dashboards/logs/dashboard.json` provides a comprehensive Grafana dashboard for visualizing GreptimeDB logs. To utilize this dashboard effectively, you need to collect logs in JSON format from your GreptimeDB instances and store them in a dedicated GreptimeDB instance.
-
-  For proper integration, the logs table must adhere to the following schema design with the table name `_gt_logs`:
-
-  ```sql
-  CREATE TABLE IF NOT EXISTS `_gt_logs` (
-    `pod_ip` STRING NULL,
-    `namespace` STRING NULL,
-    `cluster` STRING NULL,
-    `file` STRING NULL,
-    `module_path` STRING NULL,
-    `level` STRING NULL,
-    `target` STRING NULL,
-    `role` STRING NULL,
-    `pod` STRING NULL SKIPPING INDEX WITH(granularity = '10240', type = 'BLOOM'),
-    `message` STRING NULL FULLTEXT INDEX WITH(analyzer = 'English', backend = 'bloom', case_sensitive = 'false'),
-    `err` STRING NULL FULLTEXT INDEX WITH(analyzer = 'English', backend = 'bloom', case_sensitive = 'false'),
-    `timestamp` TIMESTAMP(9) NOT NULL,
-    TIME INDEX (`timestamp`),
-    PRIMARY KEY (`level`, `target`, `role`)
-  )
-    ENGINE=mito
-  WITH (
-    append_mode = 'true'
-  )
-  ```
-
-## Development
-
-As GreptimeDB evolves rapidly, metrics may change over time. We welcome your feedback and contributions to improve these dashboards 🤗
-
-To modify the metrics dashboards, simply edit the `dashboards/metrics/cluster/dashboard.json` file and run the `make dashboards` command. This will automatically generate the updated `dashboards/metrics/standalone/dashboard.json` and other related files.
-
-For easier dashboard maintenance, we utilize the [`dac`](https://github.com/zyy17/dac) tool to generate human-readable intermediate dashboards and documentation:
-
-- `dashboards/metrics/cluster/dashboard.yaml`: The intermediate dashboard file for the GreptimeDB cluster.
-- `dashboards/metrics/standalone/dashboard.yaml`: The intermediate dashboard file for standalone GreptimeDB instances.
-
-## Data Sources
-
-The following data sources are used to fetch metrics and logs:
-
-- **`${metrics}`**: Prometheus data source for providing the GreptimeDB metrics.
-- **`${logs}`**: MySQL data source for providing the GreptimeDB logs.
-- **`${information_schema}`**: MySQL data source for providing the information schema of the current instance and used for the `overview` panel. It is the MySQL port of the current monitored instance.
-
-## Instance Filters
-
-To deploy the dashboards for multiple scenarios (K8s, bare metal, etc.), we prefer to use the `instance` label when filtering instances.
-
-Additionally, we recommend including the `pod` label in the legend to make it easier to identify each instance, even though this field will be empty in bare metal scenarios.
-
-For example, the following query is recommended:
-
-```promql
-sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)
-```
-
-And the legend will be like: `[{{instance}}]-[{{ pod }}]`.
-
-## Deployment
-
-### (Recommended) Helm Chart
-
-If you use the [Helm Chart](https://github.com/GreptimeTeam/helm-charts) to deploy a GreptimeDB cluster, you can enable self-monitoring by setting the following values in your Helm chart:
+If you use Helm [chart](https://github.com/GreptimeTeam/helm-charts) to deploy GreptimeDB cluster, you can enable self-monitoring by setting the following values in your Helm chart:
 
 - `monitoring.enabled=true`: Deploys a standalone GreptimeDB instance dedicated to monitoring the cluster;
 - `grafana.enabled=true`: Deploys Grafana and automatically imports the monitoring dashboard;
 
-The standalone GreptimeDB instance will collect metrics from your cluster, and the dashboard will be available in the Grafana UI. For detailed deployment instructions, please refer to our [Kubernetes deployment guide](https://docs.greptime.com/nightly/user-guide/deployments/deploy-on-kubernetes/getting-started).
+The standalone GreptimeDB instance will collect metrics from your cluster and the dashboard will be available in the Grafana UI. For detailed deployment instructions, please refer to our [Kubernetes deployment guide](https://docs.greptime.com/nightly/user-guide/deployments/deploy-on-kubernetes/getting-started).
 
-### Self-host Prometheus and import dashboards manually
+# How to use
 
-1. **Configure Prometheus to scrape the cluster**
+## `greptimedb.json`
 
-   The following is an example configuration(**Please modify it according to your actual situation**):
+Open Grafana Dashboard page, choose `New` -> `Import`. And upload `greptimedb.json` file.
 
-    ```yml
-    # example config
-    # only to indicate how to assign labels to each target
-    # modify yours accordingly
-    scrape_configs:
-      - job_name: metasrv
-        static_configs:
-        - targets: ['<metasrv-ip>:<port>']
+## `greptimedb-cluster.json`
 
-      - job_name: datanode
-        static_configs:
-        - targets: ['<datanode0-ip>:<port>', '<datanode1-ip>:<port>', '<datanode2-ip>:<port>']
+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.
 
-      - job_name: frontend
-        static_configs:
-        - targets: ['<frontend-ip>:<port>']
-    ```
+We use Prometheus to scrape off metrics from nodes in GreptimeDB cluster, Grafana to visualize the diagram. Any compatible stack should work too.
 
-2. **Configure the data sources in Grafana**
+__Note__: This dashboard is still in an early stage of development. Any issue or advice on improvement is welcomed.
 
-   You need to add two data sources in Grafana:
+### Configuration
 
-   - Prometheus: It is the Prometheus instance that scrapes the GreptimeDB metrics.
-   - Information Schema: It is the MySQL port of the current monitored instance. The dashboard will use this datasource to show the information schema of the current instance.
+Please ensure the following configuration before importing the dashboard into Grafana.
 
-3. **Import the dashboards based on your deployment scenario**
+__1. Prometheus scrape config__
 
-   - **Cluster**: Import the `dashboards/metrics/cluster/dashboard.json` dashboard.
-   - **Standalone**: Import the `dashboards/metrics/standalone/dashboard.json` dashboard.
+Configure Prometheus to scrape the cluster.
+
+```yml
+# example config
+# only to indicate how to assign labels to each target
+# modify yours accordingly
+scrape_configs:
+  - job_name: metasrv
+    static_configs:
+    - targets: ['<metasrv-ip>:<port>']
+
+  - job_name: datanode
+    static_configs:
+    - targets: ['<datanode0-ip>:<port>', '<datanode1-ip>:<port>', '<datanode2-ip>:<port>']
+
+  - job_name: frontend
+    static_configs:
+    - targets: ['<frontend-ip>:<port>']
+```
+
+__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 `instance` on the upper-left corner to filter data from certain node.

grafana/check.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+BASEDIR=$(dirname "$0")
+
+# Use jq to check for panels with empty or missing descriptions
+invalid_panels=$(cat $BASEDIR/greptimedb-cluster.json | jq -r '
+  .panels[]
+  | select((.type == "stats" or .type == "timeseries") and (.description == "" or .description == null))
+')
+
+# Check if any invalid panels were found
+if [[ -n "$invalid_panels" ]]; then
+  echo "Error: The following panels have empty or missing descriptions:"
+  echo "$invalid_panels"
+  exit 1
+else
+  echo "All panels with type 'stats' or 'timeseries' have valid descriptions."
+  exit 0
+fi

grafana/dashboards/logs/dashboard.json

@@ -1,292 +0,0 @@
-{
-  "annotations": {
-    "list": [
-      {
-        "builtIn": 1,
-        "datasource": {
-          "type": "grafana",
-          "uid": "-- Grafana --"
-        },
-        "enable": true,
-        "hide": true,
-        "iconColor": "rgba(0, 211, 255, 1)",
-        "name": "Annotations & Alerts",
-        "type": "dashboard"
-      }
-    ]
-  },
-  "editable": true,
-  "fiscalYearStartMonth": 0,
-  "graphTooltip": 0,
-  "id": 12,
-  "links": [],
-  "panels": [
-    {
-      "datasource": {
-        "default": false,
-        "type": "mysql",
-        "uid": "${datasource}"
-      },
-      "fieldConfig": {
-        "defaults": {},
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 20,
-        "w": 24,
-        "x": 0,
-        "y": 0
-      },
-      "id": 1,
-      "options": {
-        "dedupStrategy": "none",
-        "enableInfiniteScrolling": true,
-        "enableLogDetails": true,
-        "prettifyLogMessage": false,
-        "showCommonLabels": false,
-        "showLabels": false,
-        "showTime": true,
-        "sortOrder": "Descending",
-        "wrapLogMessage": false
-      },
-      "pluginVersion": "11.6.0",
-      "targets": [
-        {
-          "dataset": "greptime_private",
-          "datasource": {
-            "type": "mysql",
-            "uid": "${datasource}"
-          },
-          "editorMode": "code",
-          "format": "table",
-          "rawQuery": true,
-          "rawSql": "SELECT `timestamp`, CONCAT('[', `level`, ']', ' ', '<', `target`, '>', ' ', `message`),\n  `role`,\n  `pod`,\n  `pod_ip`,\n  `namespace`,\n  `cluster`,\n  `err`,\n  `file`,\n  `module_path`\nFROM\n  `_gt_logs`\nWHERE\n  (\n    \"$level\" = \"'all'\"\n    OR `level` IN ($level)\n  ) \n  AND (\n    \"$role\" = \"'all'\"\n    OR `role` IN ($role)\n  )\n  AND (\n    \"$pod\" = \"\"\n    OR `pod` = '$pod'\n  )\n  AND (\n    \"$target\" = \"\"\n    OR `target` = '$target'\n  )\n  AND (\n    \"$search\" = \"\"\n    OR matches_term(`message`, '$search')\n  )\n  AND (\n    \"$exclude\" = \"\"\n    OR NOT matches_term(`message`, '$exclude')\n  )\n  AND $__timeFilter(`timestamp`)\nORDER BY `timestamp` DESC\nLIMIT $limit;\n",
-          "refId": "A",
-          "sql": {
-            "columns": [
-              {
-                "parameters": [],
-                "type": "function"
-              }
-            ],
-            "groupBy": [
-              {
-                "property": {
-                  "type": "string"
-                },
-                "type": "groupBy"
-              }
-            ],
-            "limit": 50
-          }
-        }
-      ],
-      "title": "Logs",
-      "type": "logs"
-    }
-  ],
-  "preload": false,
-  "refresh": "",
-  "schemaVersion": 41,
-  "tags": [],
-  "templating": {
-    "list": [
-      {
-        "current": {
-          "text": "logs",
-          "value": "P98F38F12DB221A8C"
-        },
-        "includeAll": false,
-        "name": "datasource",
-        "options": [],
-        "query": "mysql",
-        "refresh": 1,
-        "regex": "",
-        "type": "datasource"
-      },
-      {
-        "allValue": "'all'",
-        "current": {
-          "text": [
-            "$__all"
-          ],
-          "value": [
-            "$__all"
-          ]
-        },
-        "includeAll": true,
-        "label": "level",
-        "multi": true,
-        "name": "level",
-        "options": [
-          {
-            "selected": false,
-            "text": "INFO",
-            "value": "INFO"
-          },
-          {
-            "selected": false,
-            "text": "ERROR",
-            "value": "ERROR"
-          },
-          {
-            "selected": false,
-            "text": "WARN",
-            "value": "WARN"
-          },
-          {
-            "selected": false,
-            "text": "DEBUG",
-            "value": "DEBUG"
-          },
-          {
-            "selected": false,
-            "text": "TRACE",
-            "value": "TRACE"
-          }
-        ],
-        "query": "INFO,ERROR,WARN,DEBUG,TRACE",
-        "type": "custom"
-      },
-      {
-        "allValue": "'all'",
-        "current": {
-          "text": [
-            "$__all"
-          ],
-          "value": [
-            "$__all"
-          ]
-        },
-        "includeAll": true,
-        "label": "role",
-        "multi": true,
-        "name": "role",
-        "options": [
-          {
-            "selected": false,
-            "text": "datanode",
-            "value": "datanode"
-          },
-          {
-            "selected": false,
-            "text": "frontend",
-            "value": "frontend"
-          },
-          {
-            "selected": false,
-            "text": "meta",
-            "value": "meta"
-          }
-        ],
-        "query": "datanode,frontend,meta",
-        "type": "custom"
-      },
-      {
-        "current": {
-          "text": "",
-          "value": ""
-        },
-        "label": "pod",
-        "name": "pod",
-        "options": [
-          {
-            "selected": true,
-            "text": "",
-            "value": ""
-          }
-        ],
-        "query": "",
-        "type": "textbox"
-      },
-      {
-        "current": {
-          "text": "",
-          "value": ""
-        },
-        "label": "target",
-        "name": "target",
-        "options": [
-          {
-            "selected": true,
-            "text": "",
-            "value": ""
-          }
-        ],
-        "query": "",
-        "type": "textbox"
-      },
-      {
-        "current": {
-          "text": "",
-          "value": ""
-        },
-        "label": "search",
-        "name": "search",
-        "options": [
-          {
-            "selected": true,
-            "text": "",
-            "value": ""
-          }
-        ],
-        "query": "",
-        "type": "textbox"
-      },
-      {
-        "current": {
-          "text": "",
-          "value": ""
-        },
-        "label": "exclude",
-        "name": "exclude",
-        "options": [
-          {
-            "selected": true,
-            "text": "",
-            "value": ""
-          }
-        ],
-        "query": "",
-        "type": "textbox"
-      },
-      {
-        "current": {
-          "text": "2000",
-          "value": "2000"
-        },
-        "includeAll": false,
-        "label": "limit",
-        "name": "limit",
-        "options": [
-          {
-            "selected": true,
-            "text": "2000",
-            "value": "2000"
-          },
-          {
-            "selected": false,
-            "text": "5000",
-            "value": "5000"
-          },
-          {
-            "selected": false,
-            "text": "8000",
-            "value": "8000"
-          }
-        ],
-        "query": "2000,5000,8000",
-        "type": "custom"
-      }
-    ]
-  },
-  "time": {
-    "from": "now-6h",
-    "to": "now"
-  },
-  "timepicker": {},
-  "timezone": "browser",
-  "title": "GreptimeDB Logs",
-  "uid": "edx5veo4rd3wge2",
-  "version": 1
-}

grafana/dashboards/metrics/cluster/dashboard.md

@@ -1,101 +0,0 @@
-# Overview
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Uptime | `time() - process_start_time_seconds` | `stat` | The start time of GreptimeDB. | `prometheus` | `s` | `__auto` |
-| Version | `SELECT pkg_version FROM information_schema.build_info` | `stat` | GreptimeDB version. | `mysql` | -- | -- |
-| Total Ingestion Rate | `sum(rate(greptime_table_operator_ingest_rows[$__rate_interval]))` | `stat` | Total ingestion rate. | `prometheus` | `rowsps` | `__auto` |
-| Total Storage Size | `select SUM(disk_size) from information_schema.region_statistics;` | `stat` | Total number of data file size. | `mysql` | `decbytes` | -- |
-| Total Rows | `select SUM(region_rows) from information_schema.region_statistics;` | `stat` | Total number of data rows in the cluster. Calculated by sum of rows from each region. | `mysql` | `sishort` | -- |
-| Deployment | `SELECT count(*) as datanode FROM information_schema.cluster_info WHERE peer_type = 'DATANODE';`<br/>`SELECT count(*) as frontend FROM information_schema.cluster_info WHERE peer_type = 'FRONTEND';`<br/>`SELECT count(*) as metasrv FROM information_schema.cluster_info WHERE peer_type = 'METASRV';`<br/>`SELECT count(*) as flownode FROM information_schema.cluster_info WHERE peer_type = 'FLOWNODE';` | `stat` | The deployment topology of GreptimeDB. | `mysql` | -- | -- |
-| Database Resources | `SELECT COUNT(*) as databases FROM information_schema.schemata WHERE schema_name NOT IN ('greptime_private', 'information_schema')`<br/>`SELECT COUNT(*) as tables FROM information_schema.tables WHERE table_schema != 'information_schema'`<br/>`SELECT COUNT(region_id) as regions FROM information_schema.region_peers`<br/>`SELECT COUNT(*) as flows FROM information_schema.flows` | `stat` | The number of the key resources in GreptimeDB. | `mysql` | -- | -- |
-| Data Size | `SELECT SUM(memtable_size) * 0.42825 as WAL FROM information_schema.region_statistics;`<br/>`SELECT SUM(index_size) as index FROM information_schema.region_statistics;`<br/>`SELECT SUM(manifest_size) as manifest FROM information_schema.region_statistics;` | `stat` | The data size of wal/index/manifest in the GreptimeDB. | `mysql` | `decbytes` | -- |
-# Ingestion
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Total Ingestion Rate | `sum(rate(greptime_table_operator_ingest_rows{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Total ingestion rate.<br/><br/>Here we listed 3 primary protocols:<br/><br/>- Prometheus remote write<br/>- Greptime's gRPC API (when using our ingest SDK)<br/>- Log ingestion http API<br/> | `prometheus` | `rowsps` | `ingestion` |
-| Ingestion Rate by Type | `sum(rate(greptime_servers_http_logs_ingestion_counter[$__rate_interval]))`<br/>`sum(rate(greptime_servers_prometheus_remote_write_samples[$__rate_interval]))` | `timeseries` | Total ingestion rate.<br/><br/>Here we listed 3 primary protocols:<br/><br/>- Prometheus remote write<br/>- Greptime's gRPC API (when using our ingest SDK)<br/>- Log ingestion http API<br/> | `prometheus` | `rowsps` | `http-logs` |
-# Queries
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Total Query Rate | `sum (rate(greptime_servers_mysql_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))`<br/>`sum (rate(greptime_servers_postgres_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))`<br/>`sum (rate(greptime_servers_http_promql_elapsed_counte{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Total rate of query API calls by protocol. This metric is collected from frontends.<br/><br/>Here we listed 3 main protocols:<br/>- MySQL<br/>- Postgres<br/>- Prometheus API<br/><br/>Note that there are some other minor query APIs like /sql are not included | `prometheus` | `reqps` | `mysql` |
-# Resources
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Datanode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{instance}}]-[{{ pod }}]` |
-| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$datanode"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-| Frontend Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$frontend"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
-| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$frontend"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
-| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$metasrv"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
-| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$metasrv"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-| Flownode Memory per Instance | `sum(process_resident_memory_bytes{instance=~"$flownode"}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
-| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{instance=~"$flownode"}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-# Frontend Requests
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| HTTP QPS per Instance | `sum by(instance, pod, path, method, code) (rate(greptime_servers_http_requests_elapsed_count{instance=~"$frontend",path!~"/health\|/metrics"}[$__rate_interval]))` | `timeseries` | HTTP QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]` |
-| HTTP P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, path, method, code) (rate(greptime_servers_http_requests_elapsed_bucket{instance=~"$frontend",path!~"/health\|/metrics"}[$__rate_interval])))` | `timeseries` | HTTP P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99` |
-| gRPC QPS per Instance | `sum by(instance, pod, path, code) (rate(greptime_servers_grpc_requests_elapsed_count{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | gRPC QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{code}}]` |
-| gRPC P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, path, code) (rate(greptime_servers_grpc_requests_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))` | `timeseries` | gRPC P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99` |
-| MySQL QPS per Instance | `sum by(pod, instance)(rate(greptime_servers_mysql_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | MySQL QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]` |
-| MySQL P99 per Instance | `histogram_quantile(0.99, sum by(pod, instance, le) (rate(greptime_servers_mysql_query_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))` | `timeseries` | MySQL P99 per Instance. | `prometheus` | `s` | `[{{ instance }}]-[{{ pod }}]-p99` |
-| PostgreSQL QPS per Instance | `sum by(pod, instance)(rate(greptime_servers_postgres_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | PostgreSQL QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]` |
-| PostgreSQL P99 per Instance | `histogram_quantile(0.99, sum by(pod,instance,le) (rate(greptime_servers_postgres_query_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))` | `timeseries` | PostgreSQL P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
-# Frontend to Datanode
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Ingest Rows per Instance | `sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Ingestion rate by row as in each frontend | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
-| Region Call QPS per Instance | `sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{instance=~"$frontend"}[$__rate_interval]))` | `timeseries` | Region Call QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
-| Region Call P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{instance=~"$frontend"}[$__rate_interval])))` | `timeseries` | Region Call P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
-| Frontend Handle Bulk Insert Elapsed Time  | `sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))`<br/>`histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))` | `timeseries` | Per-stage time for frontend to handle bulk insert requests | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG` |
-# Mito Engine
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Request OPS per Instance | `sum by(instance, pod, type) (rate(greptime_mito_handle_request_elapsed_count{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Request QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Request P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, type) (rate(greptime_mito_handle_request_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))` | `timeseries` | Request P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Write Buffer per Instance | `greptime_mito_write_buffer_bytes{instance=~"$datanode"}` | `timeseries` | Write Buffer per Instance. | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]` |
-| Write Rows per Instance | `sum by (instance, pod) (rate(greptime_mito_write_rows_total{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Ingestion size by row counts. | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
-| Flush OPS per Instance | `sum by(instance, pod, reason) (rate(greptime_mito_flush_requests_total{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Flush QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{reason}}]` |
-| Write Stall per Instance | `sum by(instance, pod) (greptime_mito_write_stall_total{instance=~"$datanode"})` | `timeseries` | Write Stall per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]` |
-| Read Stage OPS per Instance | `sum by(instance, pod) (rate(greptime_mito_read_stage_elapsed_count{instance=~"$datanode", stage="total"}[$__rate_interval]))` | `timeseries` | Read Stage OPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]` |
-| Read Stage P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_read_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))` | `timeseries` | Read Stage P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]` |
-| Write Stage P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_write_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))` | `timeseries` | Write Stage P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]` |
-| Compaction OPS per Instance | `sum by(instance, pod) (rate(greptime_mito_compaction_total_elapsed_count{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Compaction OPS per Instance. | `prometheus` | `ops` | `[{{ instance }}]-[{{pod}}]` |
-| Compaction Elapsed Time per Instance by Stage | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))`<br/>`sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_sum{instance=~"$datanode"}[$__rate_interval]))/sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_count{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Compaction latency by stage | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-p99` |
-| Compaction P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le,stage) (rate(greptime_mito_compaction_total_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))` | `timeseries` | Compaction P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-compaction` |
-| WAL write size | `histogram_quantile(0.95, sum by(le,instance, pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))`<br/>`histogram_quantile(0.99, sum by(le,instance,pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))`<br/>`sum by (instance, pod)(rate(raft_engine_write_size_sum[$__rate_interval]))` | `timeseries` | Write-ahead logs write size as bytes. This chart includes stats of p95 and p99 size by instance, total WAL write rate. | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-req-size-p95` |
-| Cached Bytes per Instance | `greptime_mito_cache_bytes{instance=~"$datanode"}` | `timeseries` | Cached Bytes per Instance. | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Inflight Compaction | `greptime_mito_inflight_compaction_count` | `timeseries` | Ongoing compaction task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
-| WAL sync duration seconds | `histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))` | `timeseries` | Raft engine (local disk) log store sync latency, p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
-| Log Store op duration seconds | `histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))` | `timeseries` | Write-ahead log operations latency at p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99` |
-| Inflight Flush | `greptime_mito_inflight_flush_count` | `timeseries` | Ongoing flush task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
-| Compaction Input/Output Bytes | `sum by(instance, pod) (greptime_mito_compaction_input_bytes)`<br/>`sum by(instance, pod) (greptime_mito_compaction_output_bytes)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-input` |
-| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
-| Region Worker Convert Requests | `histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to decode requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
-# OpenDAL
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| QPS per Instance | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Read QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="read"}[$__rate_interval]))` | `timeseries` | Read QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| Read P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode",operation="read"}[$__rate_interval])))` | `timeseries` | Read P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-{{scheme}}` |
-| Write QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="write"}[$__rate_interval]))` | `timeseries` | Write QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-{{scheme}}` |
-| Write P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation="write"}[$__rate_interval])))` | `timeseries` | Write P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| List QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="list"}[$__rate_interval]))` | `timeseries` | List QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| List P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation="list"}[$__rate_interval])))` | `timeseries` | List P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| Other Requests per Instance | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode",operation!~"read\|write\|list\|stat"}[$__rate_interval]))` | `timeseries` | Other Requests per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Other Request P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme, operation) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation!~"read\|write\|list"}[$__rate_interval])))` | `timeseries` | Other Request P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Opendal traffic | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_bytes_sum{instance=~"$datanode"}[$__rate_interval]))` | `timeseries` | Total traffic as in bytes by instance and operation | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| OpenDAL errors per Instance | `sum by(instance, pod, scheme, operation, error) (rate(opendal_operation_errors_total{instance=~"$datanode", error!="NotFound"}[$__rate_interval]))` | `timeseries` | OpenDAL error counts per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]-[{{error}}]` |
-# Metasrv
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Region migration datanode | `greptime_meta_region_migration_stat{datanode_type="src"}`<br/>`greptime_meta_region_migration_stat{datanode_type="desc"}` | `state-timeline` | Counter of region migration by source and destination | `prometheus` | `none` | `from-datanode-{{datanode_id}}` |
-| Region migration error | `greptime_meta_region_migration_error` | `timeseries` | Counter of region migration error | `prometheus` | `none` | `__auto` |
-| Datanode load | `greptime_datanode_load` | `timeseries` | Gauge of load information of each datanode, collected via heartbeat between datanode and metasrv. This information is for metasrv to schedule workloads. | `prometheus` | `none` | `__auto` |
-# Flownode
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Flow Ingest / Output Rate | `sum by(instance, pod, direction) (rate(greptime_flow_processed_rows[$__rate_interval]))` | `timeseries` | Flow Ingest / Output Rate. | `prometheus` | -- | `[{{pod}}]-[{{instance}}]-[{{direction}}]` |
-| Flow Ingest Latency | `histogram_quantile(0.95, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))`<br/>`histogram_quantile(0.99, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))` | `timeseries` | Flow Ingest Latency. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-p95` |
-| Flow Operation Latency | `histogram_quantile(0.95, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))`<br/>`histogram_quantile(0.99, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))` | `timeseries` | Flow Operation Latency. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{type}}]-p95` |
-| Flow Buffer Size per Instance | `greptime_flow_input_buf_size` | `timeseries` | Flow Buffer Size per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}]` |
-| Flow Processing Error per Instance | `sum by(instance,pod,code) (rate(greptime_flow_errors[$__rate_interval]))` | `timeseries` | Flow Processing Error per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{code}}]` |

grafana/dashboards/metrics/cluster/dashboard.yaml

@@ -1,834 +0,0 @@
-groups:
-    - title: Overview
-      panels:
-        - title: Uptime
-          type: stat
-          description: The start time of GreptimeDB.
-          unit: s
-          queries:
-            - expr: time() - process_start_time_seconds
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Version
-          type: stat
-          description: GreptimeDB version.
-          queries:
-            - expr: SELECT pkg_version FROM information_schema.build_info
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Total Ingestion Rate
-          type: stat
-          description: Total ingestion rate.
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_table_operator_ingest_rows[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Total Storage Size
-          type: stat
-          description: Total number of data file size.
-          unit: decbytes
-          queries:
-            - expr: select SUM(disk_size) from information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Total Rows
-          type: stat
-          description: Total number of data rows in the cluster. Calculated by sum of rows from each region.
-          unit: sishort
-          queries:
-            - expr: select SUM(region_rows) from information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Deployment
-          type: stat
-          description: The deployment topology of GreptimeDB.
-          queries:
-            - expr: SELECT count(*) as datanode FROM information_schema.cluster_info WHERE peer_type = 'DATANODE';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as frontend FROM information_schema.cluster_info WHERE peer_type = 'FRONTEND';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as metasrv FROM information_schema.cluster_info WHERE peer_type = 'METASRV';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as flownode FROM information_schema.cluster_info WHERE peer_type = 'FLOWNODE';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Database Resources
-          type: stat
-          description: The number of the key resources in GreptimeDB.
-          queries:
-            - expr: SELECT COUNT(*) as databases FROM information_schema.schemata WHERE schema_name NOT IN ('greptime_private', 'information_schema')
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(*) as tables FROM information_schema.tables WHERE table_schema != 'information_schema'
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(region_id) as regions FROM information_schema.region_peers
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(*) as flows FROM information_schema.flows
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Data Size
-          type: stat
-          description: The data size of wal/index/manifest in the GreptimeDB.
-          unit: decbytes
-          queries:
-            - expr: SELECT SUM(memtable_size) * 0.42825 as WAL FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT SUM(index_size) as index FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT SUM(manifest_size) as manifest FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-    - title: Ingestion
-      panels:
-        - title: Total Ingestion Rate
-          type: timeseries
-          description: |
-            Total ingestion rate.
-
-            Here we listed 3 primary protocols:
-
-            - Prometheus remote write
-            - Greptime's gRPC API (when using our ingest SDK)
-            - Log ingestion http API
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_table_operator_ingest_rows{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: ingestion
-        - title: Ingestion Rate by Type
-          type: timeseries
-          description: |
-            Total ingestion rate.
-
-            Here we listed 3 primary protocols:
-
-            - Prometheus remote write
-            - Greptime's gRPC API (when using our ingest SDK)
-            - Log ingestion http API
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_servers_http_logs_ingestion_counter[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: http-logs
-            - expr: sum(rate(greptime_servers_prometheus_remote_write_samples[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: prometheus-remote-write
-    - title: Queries
-      panels:
-        - title: Total Query Rate
-          type: timeseries
-          description: |-
-            Total rate of query API calls by protocol. This metric is collected from frontends.
-
-            Here we listed 3 main protocols:
-            - MySQL
-            - Postgres
-            - Prometheus API
-
-            Note that there are some other minor query APIs like /sql are not included
-          unit: reqps
-          queries:
-            - expr: sum (rate(greptime_servers_mysql_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: mysql
-            - expr: sum (rate(greptime_servers_postgres_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: pg
-            - expr: sum (rate(greptime_servers_http_promql_elapsed_counte{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: promql
-    - title: Resources
-      panels:
-        - title: Datanode Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{instance=~"$datanode"}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{ pod }}]'
-        - title: Datanode CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{instance=~"$datanode"}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Frontend Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{instance=~"$frontend"}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Frontend CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{instance=~"$frontend"}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-cpu'
-        - title: Metasrv Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{instance=~"$metasrv"}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-resident'
-        - title: Metasrv CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{instance=~"$metasrv"}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Flownode Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{instance=~"$flownode"}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Flownode CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{instance=~"$flownode"}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-    - title: Frontend Requests
-      panels:
-        - title: HTTP QPS per Instance
-          type: timeseries
-          description: HTTP QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(instance, pod, path, method, code) (rate(greptime_servers_http_requests_elapsed_count{instance=~"$frontend",path!~"/health|/metrics"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]'
-        - title: HTTP P99 per Instance
-          type: timeseries
-          description: HTTP P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, path, method, code) (rate(greptime_servers_http_requests_elapsed_bucket{instance=~"$frontend",path!~"/health|/metrics"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99'
-        - title: gRPC QPS per Instance
-          type: timeseries
-          description: gRPC QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(instance, pod, path, code) (rate(greptime_servers_grpc_requests_elapsed_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{code}}]'
-        - title: gRPC P99 per Instance
-          type: timeseries
-          description: gRPC P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, path, code) (rate(greptime_servers_grpc_requests_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99'
-        - title: MySQL QPS per Instance
-          type: timeseries
-          description: MySQL QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(pod, instance)(rate(greptime_servers_mysql_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: MySQL P99 per Instance
-          type: timeseries
-          description: MySQL P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(pod, instance, le) (rate(greptime_servers_mysql_query_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-p99'
-        - title: PostgreSQL QPS per Instance
-          type: timeseries
-          description: PostgreSQL QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(pod, instance)(rate(greptime_servers_postgres_query_elapsed_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: PostgreSQL P99 per Instance
-          type: timeseries
-          description: PostgreSQL P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(pod,instance,le) (rate(greptime_servers_postgres_query_elapsed_bucket{instance=~"$frontend"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-    - title: Frontend to Datanode
-      panels:
-        - title: Ingest Rows per Instance
-          type: timeseries
-          description: Ingestion rate by row as in each frontend
-          unit: rowsps
-          queries:
-            - expr: sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Region Call QPS per Instance
-          type: timeseries
-          description: Region Call QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{instance=~"$frontend"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
-        - title: Region Call P99 per Instance
-          type: timeseries
-          description: Region Call P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{instance=~"$frontend"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
-        - title: 'Frontend Handle Bulk Insert Elapsed Time '
-          type: timeseries
-          description: Per-stage time for frontend to handle bulk insert requests
-          unit: s
-          queries:
-            - expr: sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-            - expr: histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-    - title: Mito Engine
-      panels:
-        - title: Request OPS per Instance
-          type: timeseries
-          description: Request QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, type) (rate(greptime_mito_handle_request_elapsed_count{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Request P99 per Instance
-          type: timeseries
-          description: Request P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, type) (rate(greptime_mito_handle_request_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Write Buffer per Instance
-          type: timeseries
-          description: Write Buffer per Instance.
-          unit: decbytes
-          queries:
-            - expr: greptime_mito_write_buffer_bytes{instance=~"$datanode"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Write Rows per Instance
-          type: timeseries
-          description: Ingestion size by row counts.
-          unit: rowsps
-          queries:
-            - expr: sum by (instance, pod) (rate(greptime_mito_write_rows_total{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Flush OPS per Instance
-          type: timeseries
-          description: Flush QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, reason) (rate(greptime_mito_flush_requests_total{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{reason}}]'
-        - title: Write Stall per Instance
-          type: timeseries
-          description: Write Stall per Instance.
-          queries:
-            - expr: sum by(instance, pod) (greptime_mito_write_stall_total{instance=~"$datanode"})
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Read Stage OPS per Instance
-          type: timeseries
-          description: Read Stage OPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod) (rate(greptime_mito_read_stage_elapsed_count{instance=~"$datanode", stage="total"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Read Stage P99 per Instance
-          type: timeseries
-          description: Read Stage P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_read_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]'
-        - title: Write Stage P99 per Instance
-          type: timeseries
-          description: Write Stage P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_write_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]'
-        - title: Compaction OPS per Instance
-          type: timeseries
-          description: Compaction OPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod) (rate(greptime_mito_compaction_total_elapsed_count{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{pod}}]'
-        - title: Compaction Elapsed Time per Instance by Stage
-          type: timeseries
-          description: Compaction latency by stage
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-p99'
-            - expr: sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_sum{instance=~"$datanode"}[$__rate_interval]))/sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_count{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-avg'
-        - title: Compaction P99 per Instance
-          type: timeseries
-          description: Compaction P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le,stage) (rate(greptime_mito_compaction_total_elapsed_bucket{instance=~"$datanode"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-compaction'
-        - title: WAL write size
-          type: timeseries
-          description: Write-ahead logs write size as bytes. This chart includes stats of p95 and p99 size by instance, total WAL write rate.
-          unit: bytes
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le,instance, pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-req-size-p95'
-            - expr: histogram_quantile(0.99, sum by(le,instance,pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-req-size-p99'
-            - expr: sum by (instance, pod)(rate(raft_engine_write_size_sum[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-throughput'
-        - title: Cached Bytes per Instance
-          type: timeseries
-          description: Cached Bytes per Instance.
-          unit: decbytes
-          queries:
-            - expr: greptime_mito_cache_bytes{instance=~"$datanode"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Inflight Compaction
-          type: timeseries
-          description: Ongoing compaction task count
-          unit: none
-          queries:
-            - expr: greptime_mito_inflight_compaction_count
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: WAL sync duration seconds
-          type: timeseries
-          description: Raft engine (local disk) log store sync latency, p99
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-        - title: Log Store op duration seconds
-          type: timeseries
-          description: Write-ahead log operations latency at p99
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99'
-        - title: Inflight Flush
-          type: timeseries
-          description: Ongoing flush task count
-          unit: none
-          queries:
-            - expr: greptime_mito_inflight_flush_count
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Compaction Input/Output Bytes
-          type: timeseries
-          description: Compaction oinput output bytes
-          unit: bytes
-          queries:
-            - expr: sum by(instance, pod) (greptime_mito_compaction_input_bytes)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-input'
-            - expr: sum by(instance, pod) (greptime_mito_compaction_output_bytes)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-output'
-        - title: Region Worker Handle Bulk Insert Requests
-          type: timeseries
-          description: Per-stage elapsed time for region worker to handle bulk insert region requests.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-            - expr: sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-        - title: Region Worker Convert Requests
-          type: timeseries
-          description: Per-stage elapsed time for region worker to decode requests.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-            - expr: sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-    - title: OpenDAL
-      panels:
-        - title: QPS per Instance
-          type: timeseries
-          description: QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Read QPS per Instance
-          type: timeseries
-          description: Read QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="read"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: Read P99 per Instance
-          type: timeseries
-          description: Read P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode",operation="read"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-{{scheme}}'
-        - title: Write QPS per Instance
-          type: timeseries
-          description: Write QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="write"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-{{scheme}}'
-        - title: Write P99 per Instance
-          type: timeseries
-          description: Write P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation="write"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: List QPS per Instance
-          type: timeseries
-          description: List QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode", operation="list"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: List P99 per Instance
-          type: timeseries
-          description: List P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation="list"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: Other Requests per Instance
-          type: timeseries
-          description: Other Requests per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{instance=~"$datanode",operation!~"read|write|list|stat"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Other Request P99 per Instance
-          type: timeseries
-          description: Other Request P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme, operation) (rate(opendal_operation_duration_seconds_bucket{instance=~"$datanode", operation!~"read|write|list"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Opendal traffic
-          type: timeseries
-          description: Total traffic as in bytes by instance and operation
-          unit: decbytes
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_bytes_sum{instance=~"$datanode"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: OpenDAL errors per Instance
-          type: timeseries
-          description: OpenDAL error counts per Instance.
-          queries:
-            - expr: sum by(instance, pod, scheme, operation, error) (rate(opendal_operation_errors_total{instance=~"$datanode", error!="NotFound"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]-[{{error}}]'
-    - title: Metasrv
-      panels:
-        - title: Region migration datanode
-          type: state-timeline
-          description: Counter of region migration by source and destination
-          unit: none
-          queries:
-            - expr: greptime_meta_region_migration_stat{datanode_type="src"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: from-datanode-{{datanode_id}}
-            - expr: greptime_meta_region_migration_stat{datanode_type="desc"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: to-datanode-{{datanode_id}}
-        - title: Region migration error
-          type: timeseries
-          description: Counter of region migration error
-          unit: none
-          queries:
-            - expr: greptime_meta_region_migration_error
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Datanode load
-          type: timeseries
-          description: Gauge of load information of each datanode, collected via heartbeat between datanode and metasrv. This information is for metasrv to schedule workloads.
-          unit: none
-          queries:
-            - expr: greptime_datanode_load
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-    - title: Flownode
-      panels:
-        - title: Flow Ingest / Output Rate
-          type: timeseries
-          description: Flow Ingest / Output Rate.
-          queries:
-            - expr: sum by(instance, pod, direction) (rate(greptime_flow_processed_rows[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{pod}}]-[{{instance}}]-[{{direction}}]'
-        - title: Flow Ingest Latency
-          type: timeseries
-          description: Flow Ingest Latency.
-          queries:
-            - expr: histogram_quantile(0.95, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p95'
-            - expr: histogram_quantile(0.99, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-        - title: Flow Operation Latency
-          type: timeseries
-          description: Flow Operation Latency.
-          queries:
-            - expr: histogram_quantile(0.95, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]-p95'
-            - expr: histogram_quantile(0.99, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]-p99'
-        - title: Flow Buffer Size per Instance
-          type: timeseries
-          description: Flow Buffer Size per Instance.
-          queries:
-            - expr: greptime_flow_input_buf_size
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}]'
-        - title: Flow Processing Error per Instance
-          type: timeseries
-          description: Flow Processing Error per Instance.
-          queries:
-            - expr: sum by(instance,pod,code) (rate(greptime_flow_errors[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{code}}]'

grafana/dashboards/metrics/standalone/dashboard.md

@@ -1,101 +0,0 @@
-# Overview
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Uptime | `time() - process_start_time_seconds` | `stat` | The start time of GreptimeDB. | `prometheus` | `s` | `__auto` |
-| Version | `SELECT pkg_version FROM information_schema.build_info` | `stat` | GreptimeDB version. | `mysql` | -- | -- |
-| Total Ingestion Rate | `sum(rate(greptime_table_operator_ingest_rows[$__rate_interval]))` | `stat` | Total ingestion rate. | `prometheus` | `rowsps` | `__auto` |
-| Total Storage Size | `select SUM(disk_size) from information_schema.region_statistics;` | `stat` | Total number of data file size. | `mysql` | `decbytes` | -- |
-| Total Rows | `select SUM(region_rows) from information_schema.region_statistics;` | `stat` | Total number of data rows in the cluster. Calculated by sum of rows from each region. | `mysql` | `sishort` | -- |
-| Deployment | `SELECT count(*) as datanode FROM information_schema.cluster_info WHERE peer_type = 'DATANODE';`<br/>`SELECT count(*) as frontend FROM information_schema.cluster_info WHERE peer_type = 'FRONTEND';`<br/>`SELECT count(*) as metasrv FROM information_schema.cluster_info WHERE peer_type = 'METASRV';`<br/>`SELECT count(*) as flownode FROM information_schema.cluster_info WHERE peer_type = 'FLOWNODE';` | `stat` | The deployment topology of GreptimeDB. | `mysql` | -- | -- |
-| Database Resources | `SELECT COUNT(*) as databases FROM information_schema.schemata WHERE schema_name NOT IN ('greptime_private', 'information_schema')`<br/>`SELECT COUNT(*) as tables FROM information_schema.tables WHERE table_schema != 'information_schema'`<br/>`SELECT COUNT(region_id) as regions FROM information_schema.region_peers`<br/>`SELECT COUNT(*) as flows FROM information_schema.flows` | `stat` | The number of the key resources in GreptimeDB. | `mysql` | -- | -- |
-| Data Size | `SELECT SUM(memtable_size) * 0.42825 as WAL FROM information_schema.region_statistics;`<br/>`SELECT SUM(index_size) as index FROM information_schema.region_statistics;`<br/>`SELECT SUM(manifest_size) as manifest FROM information_schema.region_statistics;` | `stat` | The data size of wal/index/manifest in the GreptimeDB. | `mysql` | `decbytes` | -- |
-# Ingestion
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Total Ingestion Rate | `sum(rate(greptime_table_operator_ingest_rows{}[$__rate_interval]))` | `timeseries` | Total ingestion rate.<br/><br/>Here we listed 3 primary protocols:<br/><br/>- Prometheus remote write<br/>- Greptime's gRPC API (when using our ingest SDK)<br/>- Log ingestion http API<br/> | `prometheus` | `rowsps` | `ingestion` |
-| Ingestion Rate by Type | `sum(rate(greptime_servers_http_logs_ingestion_counter[$__rate_interval]))`<br/>`sum(rate(greptime_servers_prometheus_remote_write_samples[$__rate_interval]))` | `timeseries` | Total ingestion rate.<br/><br/>Here we listed 3 primary protocols:<br/><br/>- Prometheus remote write<br/>- Greptime's gRPC API (when using our ingest SDK)<br/>- Log ingestion http API<br/> | `prometheus` | `rowsps` | `http-logs` |
-# Queries
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Total Query Rate | `sum (rate(greptime_servers_mysql_query_elapsed_count{}[$__rate_interval]))`<br/>`sum (rate(greptime_servers_postgres_query_elapsed_count{}[$__rate_interval]))`<br/>`sum (rate(greptime_servers_http_promql_elapsed_counte{}[$__rate_interval]))` | `timeseries` | Total rate of query API calls by protocol. This metric is collected from frontends.<br/><br/>Here we listed 3 main protocols:<br/>- MySQL<br/>- Postgres<br/>- Prometheus API<br/><br/>Note that there are some other minor query APIs like /sql are not included | `prometheus` | `reqps` | `mysql` |
-# Resources
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Datanode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{instance}}]-[{{ pod }}]` |
-| Datanode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-| Frontend Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
-| Frontend CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]-cpu` |
-| Metasrv Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]-resident` |
-| Metasrv CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-| Flownode Memory per Instance | `sum(process_resident_memory_bytes{}) by (instance, pod)` | `timeseries` | Current memory usage by instance | `prometheus` | `decbytes` | `[{{ instance }}]-[{{ pod }}]` |
-| Flownode CPU Usage per Instance | `sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)` | `timeseries` | Current cpu usage by instance | `prometheus` | `none` | `[{{ instance }}]-[{{ pod }}]` |
-# Frontend Requests
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| HTTP QPS per Instance | `sum by(instance, pod, path, method, code) (rate(greptime_servers_http_requests_elapsed_count{path!~"/health\|/metrics"}[$__rate_interval]))` | `timeseries` | HTTP QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]` |
-| HTTP P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, path, method, code) (rate(greptime_servers_http_requests_elapsed_bucket{path!~"/health\|/metrics"}[$__rate_interval])))` | `timeseries` | HTTP P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99` |
-| gRPC QPS per Instance | `sum by(instance, pod, path, code) (rate(greptime_servers_grpc_requests_elapsed_count{}[$__rate_interval]))` | `timeseries` | gRPC QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{code}}]` |
-| gRPC P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, path, code) (rate(greptime_servers_grpc_requests_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | gRPC P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99` |
-| MySQL QPS per Instance | `sum by(pod, instance)(rate(greptime_servers_mysql_query_elapsed_count{}[$__rate_interval]))` | `timeseries` | MySQL QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]` |
-| MySQL P99 per Instance | `histogram_quantile(0.99, sum by(pod, instance, le) (rate(greptime_servers_mysql_query_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | MySQL P99 per Instance. | `prometheus` | `s` | `[{{ instance }}]-[{{ pod }}]-p99` |
-| PostgreSQL QPS per Instance | `sum by(pod, instance)(rate(greptime_servers_postgres_query_elapsed_count{}[$__rate_interval]))` | `timeseries` | PostgreSQL QPS per Instance. | `prometheus` | `reqps` | `[{{instance}}]-[{{pod}}]` |
-| PostgreSQL P99 per Instance | `histogram_quantile(0.99, sum by(pod,instance,le) (rate(greptime_servers_postgres_query_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | PostgreSQL P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
-# Frontend to Datanode
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Ingest Rows per Instance | `sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{}[$__rate_interval]))` | `timeseries` | Ingestion rate by row as in each frontend | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
-| Region Call QPS per Instance | `sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{}[$__rate_interval]))` | `timeseries` | Region Call QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
-| Region Call P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{}[$__rate_interval])))` | `timeseries` | Region Call P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{request_type}}]` |
-| Frontend Handle Bulk Insert Elapsed Time  | `sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))`<br/>`histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))` | `timeseries` | Per-stage time for frontend to handle bulk insert requests | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG` |
-# Mito Engine
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Request OPS per Instance | `sum by(instance, pod, type) (rate(greptime_mito_handle_request_elapsed_count{}[$__rate_interval]))` | `timeseries` | Request QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Request P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, type) (rate(greptime_mito_handle_request_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | Request P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Write Buffer per Instance | `greptime_mito_write_buffer_bytes{}` | `timeseries` | Write Buffer per Instance. | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]` |
-| Write Rows per Instance | `sum by (instance, pod) (rate(greptime_mito_write_rows_total{}[$__rate_interval]))` | `timeseries` | Ingestion size by row counts. | `prometheus` | `rowsps` | `[{{instance}}]-[{{pod}}]` |
-| Flush OPS per Instance | `sum by(instance, pod, reason) (rate(greptime_mito_flush_requests_total{}[$__rate_interval]))` | `timeseries` | Flush QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{reason}}]` |
-| Write Stall per Instance | `sum by(instance, pod) (greptime_mito_write_stall_total{})` | `timeseries` | Write Stall per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]` |
-| Read Stage OPS per Instance | `sum by(instance, pod) (rate(greptime_mito_read_stage_elapsed_count{ stage="total"}[$__rate_interval]))` | `timeseries` | Read Stage OPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]` |
-| Read Stage P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_read_stage_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | Read Stage P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]` |
-| Write Stage P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_write_stage_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | Write Stage P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]` |
-| Compaction OPS per Instance | `sum by(instance, pod) (rate(greptime_mito_compaction_total_elapsed_count{}[$__rate_interval]))` | `timeseries` | Compaction OPS per Instance. | `prometheus` | `ops` | `[{{ instance }}]-[{{pod}}]` |
-| Compaction Elapsed Time per Instance by Stage | `histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_bucket{}[$__rate_interval])))`<br/>`sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_sum{}[$__rate_interval]))/sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_count{}[$__rate_interval]))` | `timeseries` | Compaction latency by stage | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-p99` |
-| Compaction P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le,stage) (rate(greptime_mito_compaction_total_elapsed_bucket{}[$__rate_interval])))` | `timeseries` | Compaction P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-compaction` |
-| WAL write size | `histogram_quantile(0.95, sum by(le,instance, pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))`<br/>`histogram_quantile(0.99, sum by(le,instance,pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))`<br/>`sum by (instance, pod)(rate(raft_engine_write_size_sum[$__rate_interval]))` | `timeseries` | Write-ahead logs write size as bytes. This chart includes stats of p95 and p99 size by instance, total WAL write rate. | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-req-size-p95` |
-| Cached Bytes per Instance | `greptime_mito_cache_bytes{}` | `timeseries` | Cached Bytes per Instance. | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]-[{{type}}]` |
-| Inflight Compaction | `greptime_mito_inflight_compaction_count` | `timeseries` | Ongoing compaction task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
-| WAL sync duration seconds | `histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))` | `timeseries` | Raft engine (local disk) log store sync latency, p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-p99` |
-| Log Store op duration seconds | `histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))` | `timeseries` | Write-ahead log operations latency at p99 | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99` |
-| Inflight Flush | `greptime_mito_inflight_flush_count` | `timeseries` | Ongoing flush task count | `prometheus` | `none` | `[{{instance}}]-[{{pod}}]` |
-| Compaction Input/Output Bytes | `sum by(instance, pod) (greptime_mito_compaction_input_bytes)`<br/>`sum by(instance, pod) (greptime_mito_compaction_output_bytes)` | `timeseries` | Compaction oinput output bytes | `prometheus` | `bytes` | `[{{instance}}]-[{{pod}}]-input` |
-| Region Worker Handle Bulk Insert Requests | `histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to handle bulk insert region requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
-| Region Worker Convert Requests | `histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))`<br/>`sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))` | `timeseries` | Per-stage elapsed time for region worker to decode requests. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{stage}}]-P95` |
-# OpenDAL
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| QPS per Instance | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{}[$__rate_interval]))` | `timeseries` | QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Read QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="read"}[$__rate_interval]))` | `timeseries` | Read QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| Read P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{operation="read"}[$__rate_interval])))` | `timeseries` | Read P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-{{scheme}}` |
-| Write QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="write"}[$__rate_interval]))` | `timeseries` | Write QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-{{scheme}}` |
-| Write P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{ operation="write"}[$__rate_interval])))` | `timeseries` | Write P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| List QPS per Instance | `sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="list"}[$__rate_interval]))` | `timeseries` | List QPS per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| List P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{ operation="list"}[$__rate_interval])))` | `timeseries` | List P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]` |
-| Other Requests per Instance | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{operation!~"read\|write\|list\|stat"}[$__rate_interval]))` | `timeseries` | Other Requests per Instance. | `prometheus` | `ops` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Other Request P99 per Instance | `histogram_quantile(0.99, sum by(instance, pod, le, scheme, operation) (rate(opendal_operation_duration_seconds_bucket{ operation!~"read\|write\|list"}[$__rate_interval])))` | `timeseries` | Other Request P99 per Instance. | `prometheus` | `s` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| Opendal traffic | `sum by(instance, pod, scheme, operation) (rate(opendal_operation_bytes_sum{}[$__rate_interval]))` | `timeseries` | Total traffic as in bytes by instance and operation | `prometheus` | `decbytes` | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]` |
-| OpenDAL errors per Instance | `sum by(instance, pod, scheme, operation, error) (rate(opendal_operation_errors_total{ error!="NotFound"}[$__rate_interval]))` | `timeseries` | OpenDAL error counts per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]-[{{error}}]` |
-# Metasrv
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Region migration datanode | `greptime_meta_region_migration_stat{datanode_type="src"}`<br/>`greptime_meta_region_migration_stat{datanode_type="desc"}` | `state-timeline` | Counter of region migration by source and destination | `prometheus` | `none` | `from-datanode-{{datanode_id}}` |
-| Region migration error | `greptime_meta_region_migration_error` | `timeseries` | Counter of region migration error | `prometheus` | `none` | `__auto` |
-| Datanode load | `greptime_datanode_load` | `timeseries` | Gauge of load information of each datanode, collected via heartbeat between datanode and metasrv. This information is for metasrv to schedule workloads. | `prometheus` | `none` | `__auto` |
-# Flownode
-| Title | Query | Type | Description | Datasource | Unit | Legend Format |
-| --- | --- | --- | --- | --- | --- | --- |
-| Flow Ingest / Output Rate | `sum by(instance, pod, direction) (rate(greptime_flow_processed_rows[$__rate_interval]))` | `timeseries` | Flow Ingest / Output Rate. | `prometheus` | -- | `[{{pod}}]-[{{instance}}]-[{{direction}}]` |
-| Flow Ingest Latency | `histogram_quantile(0.95, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))`<br/>`histogram_quantile(0.99, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))` | `timeseries` | Flow Ingest Latency. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-p95` |
-| Flow Operation Latency | `histogram_quantile(0.95, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))`<br/>`histogram_quantile(0.99, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))` | `timeseries` | Flow Operation Latency. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{type}}]-p95` |
-| Flow Buffer Size per Instance | `greptime_flow_input_buf_size` | `timeseries` | Flow Buffer Size per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}]` |
-| Flow Processing Error per Instance | `sum by(instance,pod,code) (rate(greptime_flow_errors[$__rate_interval]))` | `timeseries` | Flow Processing Error per Instance. | `prometheus` | -- | `[{{instance}}]-[{{pod}}]-[{{code}}]` |

grafana/dashboards/metrics/standalone/dashboard.yaml

@@ -1,834 +0,0 @@
-groups:
-    - title: Overview
-      panels:
-        - title: Uptime
-          type: stat
-          description: The start time of GreptimeDB.
-          unit: s
-          queries:
-            - expr: time() - process_start_time_seconds
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Version
-          type: stat
-          description: GreptimeDB version.
-          queries:
-            - expr: SELECT pkg_version FROM information_schema.build_info
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Total Ingestion Rate
-          type: stat
-          description: Total ingestion rate.
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_table_operator_ingest_rows[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Total Storage Size
-          type: stat
-          description: Total number of data file size.
-          unit: decbytes
-          queries:
-            - expr: select SUM(disk_size) from information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Total Rows
-          type: stat
-          description: Total number of data rows in the cluster. Calculated by sum of rows from each region.
-          unit: sishort
-          queries:
-            - expr: select SUM(region_rows) from information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Deployment
-          type: stat
-          description: The deployment topology of GreptimeDB.
-          queries:
-            - expr: SELECT count(*) as datanode FROM information_schema.cluster_info WHERE peer_type = 'DATANODE';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as frontend FROM information_schema.cluster_info WHERE peer_type = 'FRONTEND';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as metasrv FROM information_schema.cluster_info WHERE peer_type = 'METASRV';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT count(*) as flownode FROM information_schema.cluster_info WHERE peer_type = 'FLOWNODE';
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Database Resources
-          type: stat
-          description: The number of the key resources in GreptimeDB.
-          queries:
-            - expr: SELECT COUNT(*) as databases FROM information_schema.schemata WHERE schema_name NOT IN ('greptime_private', 'information_schema')
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(*) as tables FROM information_schema.tables WHERE table_schema != 'information_schema'
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(region_id) as regions FROM information_schema.region_peers
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT COUNT(*) as flows FROM information_schema.flows
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-        - title: Data Size
-          type: stat
-          description: The data size of wal/index/manifest in the GreptimeDB.
-          unit: decbytes
-          queries:
-            - expr: SELECT SUM(memtable_size) * 0.42825 as WAL FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT SUM(index_size) as index FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-            - expr: SELECT SUM(manifest_size) as manifest FROM information_schema.region_statistics;
-              datasource:
-                type: mysql
-                uid: ${information_schema}
-    - title: Ingestion
-      panels:
-        - title: Total Ingestion Rate
-          type: timeseries
-          description: |
-            Total ingestion rate.
-
-            Here we listed 3 primary protocols:
-
-            - Prometheus remote write
-            - Greptime's gRPC API (when using our ingest SDK)
-            - Log ingestion http API
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_table_operator_ingest_rows{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: ingestion
-        - title: Ingestion Rate by Type
-          type: timeseries
-          description: |
-            Total ingestion rate.
-
-            Here we listed 3 primary protocols:
-
-            - Prometheus remote write
-            - Greptime's gRPC API (when using our ingest SDK)
-            - Log ingestion http API
-          unit: rowsps
-          queries:
-            - expr: sum(rate(greptime_servers_http_logs_ingestion_counter[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: http-logs
-            - expr: sum(rate(greptime_servers_prometheus_remote_write_samples[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: prometheus-remote-write
-    - title: Queries
-      panels:
-        - title: Total Query Rate
-          type: timeseries
-          description: |-
-            Total rate of query API calls by protocol. This metric is collected from frontends.
-
-            Here we listed 3 main protocols:
-            - MySQL
-            - Postgres
-            - Prometheus API
-
-            Note that there are some other minor query APIs like /sql are not included
-          unit: reqps
-          queries:
-            - expr: sum (rate(greptime_servers_mysql_query_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: mysql
-            - expr: sum (rate(greptime_servers_postgres_query_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: pg
-            - expr: sum (rate(greptime_servers_http_promql_elapsed_counte{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: promql
-    - title: Resources
-      panels:
-        - title: Datanode Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{ pod }}]'
-        - title: Datanode CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Frontend Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Frontend CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-cpu'
-        - title: Metasrv Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-resident'
-        - title: Metasrv CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Flownode Memory per Instance
-          type: timeseries
-          description: Current memory usage by instance
-          unit: decbytes
-          queries:
-            - expr: sum(process_resident_memory_bytes{}) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-        - title: Flownode CPU Usage per Instance
-          type: timeseries
-          description: Current cpu usage by instance
-          unit: none
-          queries:
-            - expr: sum(rate(process_cpu_seconds_total{}[$__rate_interval]) * 1000) by (instance, pod)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]'
-    - title: Frontend Requests
-      panels:
-        - title: HTTP QPS per Instance
-          type: timeseries
-          description: HTTP QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(instance, pod, path, method, code) (rate(greptime_servers_http_requests_elapsed_count{path!~"/health|/metrics"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]'
-        - title: HTTP P99 per Instance
-          type: timeseries
-          description: HTTP P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, path, method, code) (rate(greptime_servers_http_requests_elapsed_bucket{path!~"/health|/metrics"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99'
-        - title: gRPC QPS per Instance
-          type: timeseries
-          description: gRPC QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(instance, pod, path, code) (rate(greptime_servers_grpc_requests_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{code}}]'
-        - title: gRPC P99 per Instance
-          type: timeseries
-          description: gRPC P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, path, code) (rate(greptime_servers_grpc_requests_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{path}}]-[{{method}}]-[{{code}}]-p99'
-        - title: MySQL QPS per Instance
-          type: timeseries
-          description: MySQL QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(pod, instance)(rate(greptime_servers_mysql_query_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: MySQL P99 per Instance
-          type: timeseries
-          description: MySQL P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(pod, instance, le) (rate(greptime_servers_mysql_query_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{ pod }}]-p99'
-        - title: PostgreSQL QPS per Instance
-          type: timeseries
-          description: PostgreSQL QPS per Instance.
-          unit: reqps
-          queries:
-            - expr: sum by(pod, instance)(rate(greptime_servers_postgres_query_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: PostgreSQL P99 per Instance
-          type: timeseries
-          description: PostgreSQL P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(pod,instance,le) (rate(greptime_servers_postgres_query_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-    - title: Frontend to Datanode
-      panels:
-        - title: Ingest Rows per Instance
-          type: timeseries
-          description: Ingestion rate by row as in each frontend
-          unit: rowsps
-          queries:
-            - expr: sum by(instance, pod)(rate(greptime_table_operator_ingest_rows{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Region Call QPS per Instance
-          type: timeseries
-          description: Region Call QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, request_type) (rate(greptime_grpc_region_request_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
-        - title: Region Call P99 per Instance
-          type: timeseries
-          description: Region Call P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, request_type) (rate(greptime_grpc_region_request_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{request_type}}]'
-        - title: 'Frontend Handle Bulk Insert Elapsed Time '
-          type: timeseries
-          description: Per-stage time for frontend to handle bulk insert requests
-          unit: s
-          queries:
-            - expr: sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_sum[$__rate_interval]))/sum by(instance, pod, stage) (rate(greptime_table_operator_handle_bulk_insert_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-            - expr: histogram_quantile(0.99, sum by(instance, pod, stage, le) (rate(greptime_table_operator_handle_bulk_insert_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-    - title: Mito Engine
-      panels:
-        - title: Request OPS per Instance
-          type: timeseries
-          description: Request QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, type) (rate(greptime_mito_handle_request_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Request P99 per Instance
-          type: timeseries
-          description: Request P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, type) (rate(greptime_mito_handle_request_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Write Buffer per Instance
-          type: timeseries
-          description: Write Buffer per Instance.
-          unit: decbytes
-          queries:
-            - expr: greptime_mito_write_buffer_bytes{}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Write Rows per Instance
-          type: timeseries
-          description: Ingestion size by row counts.
-          unit: rowsps
-          queries:
-            - expr: sum by (instance, pod) (rate(greptime_mito_write_rows_total{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Flush OPS per Instance
-          type: timeseries
-          description: Flush QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, reason) (rate(greptime_mito_flush_requests_total{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{reason}}]'
-        - title: Write Stall per Instance
-          type: timeseries
-          description: Write Stall per Instance.
-          queries:
-            - expr: sum by(instance, pod) (greptime_mito_write_stall_total{})
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Read Stage OPS per Instance
-          type: timeseries
-          description: Read Stage OPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod) (rate(greptime_mito_read_stage_elapsed_count{ stage="total"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Read Stage P99 per Instance
-          type: timeseries
-          description: Read Stage P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_read_stage_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]'
-        - title: Write Stage P99 per Instance
-          type: timeseries
-          description: Write Stage P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_write_stage_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]'
-        - title: Compaction OPS per Instance
-          type: timeseries
-          description: Compaction OPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod) (rate(greptime_mito_compaction_total_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{ instance }}]-[{{pod}}]'
-        - title: Compaction Elapsed Time per Instance by Stage
-          type: timeseries
-          description: Compaction latency by stage
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-p99'
-            - expr: sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_sum{}[$__rate_interval]))/sum by(instance, pod, le, stage) (rate(greptime_mito_compaction_stage_elapsed_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-avg'
-        - title: Compaction P99 per Instance
-          type: timeseries
-          description: Compaction P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le,stage) (rate(greptime_mito_compaction_total_elapsed_bucket{}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-compaction'
-        - title: WAL write size
-          type: timeseries
-          description: Write-ahead logs write size as bytes. This chart includes stats of p95 and p99 size by instance, total WAL write rate.
-          unit: bytes
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le,instance, pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-req-size-p95'
-            - expr: histogram_quantile(0.99, sum by(le,instance,pod) (rate(raft_engine_write_size_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-req-size-p99'
-            - expr: sum by (instance, pod)(rate(raft_engine_write_size_sum[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-throughput'
-        - title: Cached Bytes per Instance
-          type: timeseries
-          description: Cached Bytes per Instance.
-          unit: decbytes
-          queries:
-            - expr: greptime_mito_cache_bytes{}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]'
-        - title: Inflight Compaction
-          type: timeseries
-          description: Ongoing compaction task count
-          unit: none
-          queries:
-            - expr: greptime_mito_inflight_compaction_count
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: WAL sync duration seconds
-          type: timeseries
-          description: Raft engine (local disk) log store sync latency, p99
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(le, type, node, instance, pod) (rate(raft_engine_sync_log_duration_seconds_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-        - title: Log Store op duration seconds
-          type: timeseries
-          description: Write-ahead log operations latency at p99
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(le,logstore,optype,instance, pod) (rate(greptime_logstore_op_elapsed_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{logstore}}]-[{{optype}}]-p99'
-        - title: Inflight Flush
-          type: timeseries
-          description: Ongoing flush task count
-          unit: none
-          queries:
-            - expr: greptime_mito_inflight_flush_count
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]'
-        - title: Compaction Input/Output Bytes
-          type: timeseries
-          description: Compaction oinput output bytes
-          unit: bytes
-          queries:
-            - expr: sum by(instance, pod) (greptime_mito_compaction_input_bytes)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-input'
-            - expr: sum by(instance, pod) (greptime_mito_compaction_output_bytes)
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-output'
-        - title: Region Worker Handle Bulk Insert Requests
-          type: timeseries
-          description: Per-stage elapsed time for region worker to handle bulk insert region requests.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-            - expr: sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_region_worker_handle_write_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-        - title: Region Worker Convert Requests
-          type: timeseries
-          description: Per-stage elapsed time for region worker to decode requests.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.95, sum by(le, instance, stage, pod) (rate(greptime_datanode_convert_region_request_bucket[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-P95'
-            - expr: sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_sum[$__rate_interval]))/sum by(le,instance, stage, pod) (rate(greptime_datanode_convert_region_request_count[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{stage}}]-AVG'
-    - title: OpenDAL
-      panels:
-        - title: QPS per Instance
-          type: timeseries
-          description: QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Read QPS per Instance
-          type: timeseries
-          description: Read QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="read"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: Read P99 per Instance
-          type: timeseries
-          description: Read P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{operation="read"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-{{scheme}}'
-        - title: Write QPS per Instance
-          type: timeseries
-          description: Write QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="write"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-{{scheme}}'
-        - title: Write P99 per Instance
-          type: timeseries
-          description: Write P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{ operation="write"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: List QPS per Instance
-          type: timeseries
-          description: List QPS per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme) (rate(opendal_operation_duration_seconds_count{ operation="list"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: List P99 per Instance
-          type: timeseries
-          description: List P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme) (rate(opendal_operation_duration_seconds_bucket{ operation="list"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]'
-        - title: Other Requests per Instance
-          type: timeseries
-          description: Other Requests per Instance.
-          unit: ops
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_duration_seconds_count{operation!~"read|write|list|stat"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Other Request P99 per Instance
-          type: timeseries
-          description: Other Request P99 per Instance.
-          unit: s
-          queries:
-            - expr: histogram_quantile(0.99, sum by(instance, pod, le, scheme, operation) (rate(opendal_operation_duration_seconds_bucket{ operation!~"read|write|list"}[$__rate_interval])))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: Opendal traffic
-          type: timeseries
-          description: Total traffic as in bytes by instance and operation
-          unit: decbytes
-          queries:
-            - expr: sum by(instance, pod, scheme, operation) (rate(opendal_operation_bytes_sum{}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]'
-        - title: OpenDAL errors per Instance
-          type: timeseries
-          description: OpenDAL error counts per Instance.
-          queries:
-            - expr: sum by(instance, pod, scheme, operation, error) (rate(opendal_operation_errors_total{ error!="NotFound"}[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{scheme}}]-[{{operation}}]-[{{error}}]'
-    - title: Metasrv
-      panels:
-        - title: Region migration datanode
-          type: state-timeline
-          description: Counter of region migration by source and destination
-          unit: none
-          queries:
-            - expr: greptime_meta_region_migration_stat{datanode_type="src"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: from-datanode-{{datanode_id}}
-            - expr: greptime_meta_region_migration_stat{datanode_type="desc"}
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: to-datanode-{{datanode_id}}
-        - title: Region migration error
-          type: timeseries
-          description: Counter of region migration error
-          unit: none
-          queries:
-            - expr: greptime_meta_region_migration_error
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-        - title: Datanode load
-          type: timeseries
-          description: Gauge of load information of each datanode, collected via heartbeat between datanode and metasrv. This information is for metasrv to schedule workloads.
-          unit: none
-          queries:
-            - expr: greptime_datanode_load
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: __auto
-    - title: Flownode
-      panels:
-        - title: Flow Ingest / Output Rate
-          type: timeseries
-          description: Flow Ingest / Output Rate.
-          queries:
-            - expr: sum by(instance, pod, direction) (rate(greptime_flow_processed_rows[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{pod}}]-[{{instance}}]-[{{direction}}]'
-        - title: Flow Ingest Latency
-          type: timeseries
-          description: Flow Ingest Latency.
-          queries:
-            - expr: histogram_quantile(0.95, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p95'
-            - expr: histogram_quantile(0.99, sum(rate(greptime_flow_insert_elapsed_bucket[$__rate_interval])) by (le, instance, pod))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-p99'
-        - title: Flow Operation Latency
-          type: timeseries
-          description: Flow Operation Latency.
-          queries:
-            - expr: histogram_quantile(0.95, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]-p95'
-            - expr: histogram_quantile(0.99, sum(rate(greptime_flow_processing_time_bucket[$__rate_interval])) by (le,instance,pod,type))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{type}}]-p99'
-        - title: Flow Buffer Size per Instance
-          type: timeseries
-          description: Flow Buffer Size per Instance.
-          queries:
-            - expr: greptime_flow_input_buf_size
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}]'
-        - title: Flow Processing Error per Instance
-          type: timeseries
-          description: Flow Processing Error per Instance.
-          queries:
-            - expr: sum by(instance,pod,code) (rate(greptime_flow_errors[$__rate_interval]))
-              datasource:
-                type: prometheus
-                uid: ${metrics}
-              legendFormat: '[{{instance}}]-[{{pod}}]-[{{code}}]'

grafana/scripts/check.sh

@@ -1,54 +0,0 @@
-#!/usr/bin/env bash
-
-DASHBOARD_DIR=${1:-grafana/dashboards/metrics}
-
-check_dashboard_description() {
-  for dashboard in $(find $DASHBOARD_DIR -name "*.json"); do
-    echo "Checking $dashboard description"
-
-    # Use jq to check for panels with empty or missing descriptions
-    invalid_panels=$(cat $dashboard | jq -r '
-      .panels[]
-    | select((.type == "stats" or .type == "timeseries") and (.description == "" or .description == null))')
-
-    # Check if any invalid panels were found
-    if [[ -n "$invalid_panels" ]]; then
-      echo "Error: The following panels have empty or missing descriptions:"
-      echo "$invalid_panels"
-      exit 1
-    else
-      echo "All panels with type 'stats' or 'timeseries' have valid descriptions."
-    fi
-  done
-}
-
-check_dashboards_generation() {
-  ./grafana/scripts/gen-dashboards.sh
-
-  if [[ -n "$(git diff --name-only grafana/dashboards/metrics)" ]]; then
-    echo "Error: The dashboards are not generated correctly. You should execute the `make dashboards` command."
-    exit 1
-  fi
-}
-
-check_datasource() {
-  for dashboard in $(find $DASHBOARD_DIR -name "*.json"); do
-    echo "Checking $dashboard datasource"
-    jq -r '.panels[] | select(.type != "row") | .targets[] | [.datasource.type, .datasource.uid] | @tsv' $dashboard | while read -r type uid; do
-    # if the datasource is prometheus, check if the uid is ${metrics}
-    if [[ "$type" == "prometheus" && "$uid" != "\${metrics}" ]]; then
-      echo "Error: The datasource uid of $dashboard is not valid. It should be \${metrics}, got $uid"
-      exit 1
-    fi
-    # if the datasource is mysql, check if the uid is ${information_schema}
-    if [[ "$type" == "mysql" && "$uid" != "\${information_schema}" ]]; then
-      echo "Error: The datasource uid of $dashboard is not valid. It should be \${information_schema}, got $uid"
-      exit 1
-    fi
-    done
-  done
-}
-
-check_dashboards_generation
-check_dashboard_description
-check_datasource

grafana/scripts/gen-dashboards.sh

@@ -1,25 +0,0 @@
-#! /usr/bin/env bash
-
-CLUSTER_DASHBOARD_DIR=${1:-grafana/dashboards/metrics/cluster}
-STANDALONE_DASHBOARD_DIR=${2:-grafana/dashboards/metrics/standalone}
-DAC_IMAGE=ghcr.io/zyy17/dac:20250423-522bd35
-
-remove_instance_filters() {
-  # Remove the instance filters for the standalone dashboards.
-  sed -E 's/instance=~\\"(\$datanode|\$frontend|\$metasrv|\$flownode)\\",?//g' "$CLUSTER_DASHBOARD_DIR/dashboard.json" > "$STANDALONE_DASHBOARD_DIR/dashboard.json"
-}
-
-generate_intermediate_dashboards_and_docs() {
-  docker run -v ${PWD}:/greptimedb --rm ${DAC_IMAGE} \
-    -i /greptimedb/$CLUSTER_DASHBOARD_DIR/dashboard.json \
-    -o /greptimedb/$CLUSTER_DASHBOARD_DIR/dashboard.yaml \
-    -m /greptimedb/$CLUSTER_DASHBOARD_DIR/dashboard.md
-
-  docker run -v ${PWD}:/greptimedb --rm ${DAC_IMAGE} \
-    -i /greptimedb/$STANDALONE_DASHBOARD_DIR/dashboard.json \
-    -o /greptimedb/$STANDALONE_DASHBOARD_DIR/dashboard.yaml \
-    -m /greptimedb/$STANDALONE_DASHBOARD_DIR/dashboard.md
-}
-
-remove_instance_filters
-generate_intermediate_dashboards_and_docs

grafana/summary.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+BASEDIR=$(dirname "$0")
+echo '| Title | Description | Expressions |
+|---|---|---|'
+
+cat $BASEDIR/greptimedb-cluster.json | jq -r '
+  .panels |
+  map(select(.type == "stat" or .type == "timeseries")) |
+  .[] | "| \(.title) | \(.description | gsub("\n"; "<br>")) | \(.targets | map(.expr // .rawSql | "`\(.|gsub("\n"; "<br>"))`")  | join("<br>")) |"
+'

licenserc.toml

@@ -26,13 +26,6 @@ excludes = [
     "src/common/base/src/secrets.rs",
     "src/servers/src/repeated_field.rs",
     "src/servers/src/http/test_helpers.rs",
-    # enterprise
-    "src/common/meta/src/rpc/ddl/trigger.rs",
-    "src/operator/src/expr_helper/trigger.rs",
-    "src/sql/src/statements/create/trigger.rs",
-    "src/sql/src/statements/show/trigger.rs",
-    "src/sql/src/parsers/create_parser/trigger.rs",
-    "src/sql/src/parsers/show_parser/trigger.rs",
 ]
 
 [properties]

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "nightly-2025-05-19"
+channel = "nightly-2024-12-25"

src/api/src/helper.rs

@@ -514,7 +514,6 @@ fn query_request_type(request: &QueryRequest) -> &'static str {
         Some(Query::Sql(_)) => "query.sql",
         Some(Query::LogicalPlan(_)) => "query.logical_plan",
         Some(Query::PromRangeQuery(_)) => "query.prom_range",
-        Some(Query::InsertIntoPlan(_)) => "query.insert_into_plan",
         None => "query.empty",
     }
 }
@@ -1050,7 +1049,7 @@ pub fn value_to_grpc_value(value: Value) -> GrpcValue {
             Value::Int64(v) => Some(ValueData::I64Value(v)),
             Value::Float32(v) => Some(ValueData::F32Value(*v)),
             Value::Float64(v) => Some(ValueData::F64Value(*v)),
-            Value::String(v) => Some(ValueData::StringValue(v.into_string())),
+            Value::String(v) => Some(ValueData::StringValue(v.as_utf8().to_string())),
             Value::Binary(v) => Some(ValueData::BinaryValue(v.to_vec())),
             Value::Date(v) => Some(ValueData::DateValue(v.val())),
             Value::Timestamp(v) => Some(match v.unit() {

src/auth/src/common.rs

@@ -36,7 +36,7 @@ pub fn userinfo_by_name(username: Option<String>) -> UserInfoRef {
 }
 
 pub fn user_provider_from_option(opt: &String) -> Result<UserProviderRef> {
-    let (name, content) = opt.split_once(':').with_context(|| InvalidConfigSnafu {
+    let (name, content) = opt.split_once(':').context(InvalidConfigSnafu {
         value: opt.to_string(),
         msg: "UserProviderOption must be in format `<option>:<value>`",
     })?;
@@ -57,24 +57,6 @@ pub fn user_provider_from_option(opt: &String) -> Result<UserProviderRef> {
     }
 }
 
-pub fn static_user_provider_from_option(opt: &String) -> Result<StaticUserProvider> {
-    let (name, content) = opt.split_once(':').with_context(|| InvalidConfigSnafu {
-        value: opt.to_string(),
-        msg: "UserProviderOption must be in format `<option>:<value>`",
-    })?;
-    match name {
-        STATIC_USER_PROVIDER => {
-            let provider = StaticUserProvider::new(content)?;
-            Ok(provider)
-        }
-        _ => InvalidConfigSnafu {
-            value: name.to_string(),
-            msg: format!("Invalid UserProviderOption, expect only {STATIC_USER_PROVIDER}"),
-        }
-        .fail(),
-    }
-}
-
 type Username<'a> = &'a str;
 type HostOrIp<'a> = &'a str;
 

src/auth/src/error.rs

@@ -38,14 +38,6 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display("Failed to convert to utf8"))]
-    FromUtf8 {
-        #[snafu(source)]
-        error: std::string::FromUtf8Error,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
     #[snafu(display("Authentication source failure"))]
     AuthBackend {
         #[snafu(implicit)]
@@ -93,7 +85,7 @@ impl ErrorExt for Error {
     fn status_code(&self) -> StatusCode {
         match self {
             Error::InvalidConfig { .. } => StatusCode::InvalidArguments,
-            Error::IllegalParam { .. } | Error::FromUtf8 { .. } => StatusCode::InvalidArguments,
+            Error::IllegalParam { .. } => StatusCode::InvalidArguments,
             Error::FileWatch { .. } => StatusCode::InvalidArguments,
             Error::InternalState { .. } => StatusCode::Unexpected,
             Error::Io { .. } => StatusCode::StorageUnavailable,

src/auth/src/lib.rs

@@ -22,12 +22,10 @@ mod user_provider;
 pub mod tests;
 
 pub use common::{
-    auth_mysql, static_user_provider_from_option, user_provider_from_option, userinfo_by_name,
-    HashedPassword, Identity, Password,
+    auth_mysql, user_provider_from_option, userinfo_by_name, HashedPassword, Identity, Password,
 };
 pub use permission::{PermissionChecker, PermissionReq, PermissionResp};
 pub use user_info::UserInfo;
-pub use user_provider::static_user_provider::StaticUserProvider;
 pub use user_provider::UserProvider;
 
 /// pub type alias

src/auth/src/user_provider/static_user_provider.rs

@@ -15,15 +15,15 @@
 use std::collections::HashMap;
 
 use async_trait::async_trait;
-use snafu::{OptionExt, ResultExt};
+use snafu::OptionExt;
 
-use crate::error::{FromUtf8Snafu, InvalidConfigSnafu, Result};
+use crate::error::{InvalidConfigSnafu, Result};
 use crate::user_provider::{authenticate_with_credential, load_credential_from_file};
 use crate::{Identity, Password, UserInfoRef, UserProvider};
 
 pub(crate) const STATIC_USER_PROVIDER: &str = "static_user_provider";
 
-pub struct StaticUserProvider {
+pub(crate) struct StaticUserProvider {
     users: HashMap<String, Vec<u8>>,
 }
 
@@ -60,18 +60,6 @@ impl StaticUserProvider {
                 .fail(),
         }
     }
-
-    /// Return a random username/password pair
-    /// This is useful for invoking from other components in the cluster
-    pub fn get_one_user_pwd(&self) -> Result<(String, String)> {
-        let kv = self.users.iter().next().context(InvalidConfigSnafu {
-            value: "",
-            msg: "Expect at least one pair of username and password",
-        })?;
-        let username = kv.0;
-        let pwd = String::from_utf8(kv.1.clone()).context(FromUtf8Snafu)?;
-        Ok((username.clone(), pwd))
-    }
 }
 
 #[async_trait]

src/catalog/src/system_schema/pg_catalog/pg_namespace/oid_map.rs

@@ -84,6 +84,12 @@ mod tests {
         let key1 = "3178510";
         let key2 = "4215648";
 
+        // have collision
+        assert_eq!(
+            oid_map.hasher.hash_one(key1) as u32,
+            oid_map.hasher.hash_one(key2) as u32
+        );
+
         // insert them into oid_map
         let oid1 = oid_map.get_oid(key1);
         let oid2 = oid_map.get_oid(key2);

src/catalog/src/table_source.rs

@@ -27,7 +27,7 @@ use session::context::QueryContextRef;
 use snafu::{ensure, OptionExt, ResultExt};
 use table::metadata::TableType;
 use table::table::adapter::DfTableProviderAdapter;
-pub mod dummy_catalog;
+mod dummy_catalog;
 use dummy_catalog::DummyCatalogList;
 use table::TableRef;
 

src/cli/Cargo.toml

@@ -5,12 +5,8 @@ edition.workspace = true
 license.workspace = true
 
 [features]
-default = [
-    "pg_kvbackend",
-    "mysql_kvbackend",
-]
-pg_kvbackend = ["common-meta/pg_kvbackend", "meta-srv/pg_kvbackend"]
-mysql_kvbackend = ["common-meta/mysql_kvbackend", "meta-srv/mysql_kvbackend"]
+pg_kvbackend = ["common-meta/pg_kvbackend"]
+mysql_kvbackend = ["common-meta/mysql_kvbackend"]
 
 [lints]
 workspace = true
@@ -47,12 +43,15 @@ etcd-client.workspace = true
 futures.workspace = true
 humantime.workspace = true
 meta-client.workspace = true
-meta-srv.workspace = true
 nu-ansi-term = "0.46"
-object-store.workspace = true
+opendal = { version = "0.51.1", features = [
+    "services-fs",
+    "services-s3",
+] }
 query.workspace = true
 rand.workspace = true
 reqwest.workspace = true
+rustyline = "10.1"
 serde.workspace = true
 serde_json.workspace = true
 servers.workspace = true

src/cli/src/cmd.rs

@@ -0,0 +1,154 @@
+// 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 crate::error::{Error, InvalidReplCommandSnafu, Result};
+
+/// Represents the parsed command from the user (which may be over many lines)
+#[derive(Debug, PartialEq)]
+pub(crate) enum ReplCommand {
+    Help,
+    UseDatabase { db_name: String },
+    Sql { sql: String },
+    Exit,
+}
+
+impl TryFrom<&str> for ReplCommand {
+    type Error = Error;
+
+    fn try_from(input: &str) -> Result<Self> {
+        let input = input.trim();
+        if input.is_empty() {
+            return InvalidReplCommandSnafu {
+                reason: "No command specified".to_string(),
+            }
+            .fail();
+        }
+
+        // If line ends with ';', it must be treated as a complete input.
+        // However, the opposite is not true.
+        let input_is_completed = input.ends_with(';');
+
+        let input = input.strip_suffix(';').map(|x| x.trim()).unwrap_or(input);
+        let lowercase = input.to_lowercase();
+        match lowercase.as_str() {
+            "help" => Ok(Self::Help),
+            "exit" | "quit" => Ok(Self::Exit),
+            _ => match input.split_once(' ') {
+                Some((maybe_use, database)) if maybe_use.to_lowercase() == "use" => {
+                    Ok(Self::UseDatabase {
+                        db_name: database.trim().to_string(),
+                    })
+                }
+                // Any valid SQL must contains at least one whitespace.
+                Some(_) if input_is_completed => Ok(Self::Sql {
+                    sql: input.to_string(),
+                }),
+                _ => InvalidReplCommandSnafu {
+                    reason: format!("unknown command '{input}', maybe input is not completed"),
+                }
+                .fail(),
+            },
+        }
+    }
+}
+
+impl ReplCommand {
+    pub fn help() -> &'static str {
+        r#"
+Available commands (case insensitive):
+- 'help': print this help
+- 'exit' or 'quit': exit the REPL
+- 'use <your database name>': switch to another database/schema context
+- Other typed in text will be treated as SQL.
+  You can enter new line while typing, just remember to end it with ';'.
+"#
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::error::Error::InvalidReplCommand;
+
+    #[test]
+    fn test_from_str() {
+        fn test_ok(s: &str, expected: ReplCommand) {
+            let actual: ReplCommand = s.try_into().unwrap();
+            assert_eq!(expected, actual, "'{}'", s);
+        }
+
+        fn test_err(s: &str) {
+            let result: Result<ReplCommand> = s.try_into();
+            assert!(matches!(result, Err(InvalidReplCommand { .. })))
+        }
+
+        test_err("");
+        test_err("  ");
+        test_err("\t");
+
+        test_ok("help", ReplCommand::Help);
+        test_ok("help", ReplCommand::Help);
+        test_ok("  help", ReplCommand::Help);
+        test_ok("  help  ", ReplCommand::Help);
+        test_ok("  HELP  ", ReplCommand::Help);
+        test_ok("  Help;  ", ReplCommand::Help);
+        test_ok("  help  ; ", ReplCommand::Help);
+
+        test_ok("exit", ReplCommand::Exit);
+        test_ok("exit;", ReplCommand::Exit);
+        test_ok("exit ;", ReplCommand::Exit);
+        test_ok("EXIT", ReplCommand::Exit);
+
+        test_ok("quit", ReplCommand::Exit);
+        test_ok("quit;", ReplCommand::Exit);
+        test_ok("quit ;", ReplCommand::Exit);
+        test_ok("QUIT", ReplCommand::Exit);
+
+        test_ok(
+            "use Foo",
+            ReplCommand::UseDatabase {
+                db_name: "Foo".to_string(),
+            },
+        );
+        test_ok(
+            "  use Foo ;  ",
+            ReplCommand::UseDatabase {
+                db_name: "Foo".to_string(),
+            },
+        );
+        // ensure that database name is case sensitive
+        test_ok(
+            "  use FOO ;  ",
+            ReplCommand::UseDatabase {
+                db_name: "FOO".to_string(),
+            },
+        );
+
+        // ensure that we aren't messing with capitalization
+        test_ok(
+            "SELECT * from foo;",
+            ReplCommand::Sql {
+                sql: "SELECT * from foo".to_string(),
+            },
+        );
+        // Input line (that don't belong to any other cases above) must ends with ';' to make it a valid SQL.
+        test_err("insert blah");
+        test_ok(
+            "insert blah;",
+            ReplCommand::Sql {
+                sql: "insert blah".to_string(),
+            },
+        );
+    }
+}

src/cli/src/error.rs

@@ -17,7 +17,6 @@ use std::any::Any;
 use common_error::ext::{BoxedError, ErrorExt};
 use common_error::status_code::StatusCode;
 use common_macro::stack_trace_debug;
-use object_store::Error as ObjectStoreError;
 use snafu::{Location, Snafu};
 
 #[derive(Snafu)]
@@ -102,6 +101,9 @@ pub enum Error {
         error: reqwest::Error,
     },
 
+    #[snafu(display("Invalid REPL command: {reason}"))]
+    InvalidReplCommand { reason: String },
+
     #[snafu(display("Failed to parse SQL: {}", sql))]
     ParseSql {
         sql: String,
@@ -226,7 +228,7 @@ pub enum Error {
         #[snafu(implicit)]
         location: Location,
         #[snafu(source)]
-        error: ObjectStoreError,
+        error: opendal::Error,
     },
     #[snafu(display("S3 config need be set"))]
     S3ConfigNotSet {
@@ -238,12 +240,6 @@ pub enum Error {
         #[snafu(implicit)]
         location: Location,
     },
-    #[snafu(display("KV backend not set: {}", backend))]
-    KvBackendNotSet {
-        backend: String,
-        #[snafu(implicit)]
-        location: Location,
-    },
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
@@ -258,6 +254,7 @@ impl ErrorExt for Error {
             Error::MissingConfig { .. }
             | Error::LoadLayeredConfig { .. }
             | Error::IllegalConfig { .. }
+            | Error::InvalidReplCommand { .. }
             | Error::InitTimezone { .. }
             | Error::ConnectEtcd { .. }
             | Error::CreateDir { .. }
@@ -280,9 +277,8 @@ impl ErrorExt for Error {
 
             Error::Other { source, .. } => source.status_code(),
             Error::OpenDal { .. } => StatusCode::Internal,
-            Error::S3ConfigNotSet { .. }
-            | Error::OutputDirNotSet { .. }
-            | Error::KvBackendNotSet { .. } => StatusCode::InvalidArguments,
+            Error::S3ConfigNotSet { .. } => StatusCode::InvalidArguments,
+            Error::OutputDirNotSet { .. } => StatusCode::InvalidArguments,
 
             Error::BuildRuntime { source, .. } => source.status_code(),
 

src/cli/src/export.rs

@@ -21,8 +21,8 @@ use async_trait::async_trait;
 use clap::{Parser, ValueEnum};
 use common_error::ext::BoxedError;
 use common_telemetry::{debug, error, info};
-use object_store::layers::LoggingLayer;
-use object_store::{services, ObjectStore};
+use opendal::layers::LoggingLayer;
+use opendal::{services, Operator};
 use serde_json::Value;
 use snafu::{OptionExt, ResultExt};
 use tokio::sync::Semaphore;
@@ -110,26 +110,11 @@ pub struct ExportCommand {
     #[clap(long)]
     s3: bool,
 
-    /// if both `s3_ddl_local_dir` and `s3` are set, `s3_ddl_local_dir` will be only used for
-    /// exported SQL files, and the data will be exported to s3.
-    ///
-    /// Note that `s3_ddl_local_dir` export sql files to **LOCAL** file system, this is useful if export client don't have
-    /// direct access to s3.
-    ///
-    /// if `s3` is set but `s3_ddl_local_dir` is not set, both SQL&data will be exported to s3.
-    #[clap(long)]
-    s3_ddl_local_dir: Option<String>,
-
     /// The s3 bucket name
     /// if s3 is set, this is required
     #[clap(long)]
     s3_bucket: Option<String>,
 
-    // The s3 root path
-    /// if s3 is set, this is required
-    #[clap(long)]
-    s3_root: Option<String>,
-
     /// The s3 endpoint
     /// if s3 is set, this is required
     #[clap(long)]
@@ -187,9 +172,7 @@ impl ExportCommand {
             start_time: self.start_time.clone(),
             end_time: self.end_time.clone(),
             s3: self.s3,
-            s3_ddl_local_dir: self.s3_ddl_local_dir.clone(),
             s3_bucket: self.s3_bucket.clone(),
-            s3_root: self.s3_root.clone(),
             s3_endpoint: self.s3_endpoint.clone(),
             s3_access_key: self.s3_access_key.clone(),
             s3_secret_key: self.s3_secret_key.clone(),
@@ -209,9 +192,7 @@ pub struct Export {
     start_time: Option<String>,
     end_time: Option<String>,
     s3: bool,
-    s3_ddl_local_dir: Option<String>,
     s3_bucket: Option<String>,
-    s3_root: Option<String>,
     s3_endpoint: Option<String>,
     s3_access_key: Option<String>,
     s3_secret_key: Option<String>,
@@ -383,7 +364,7 @@ impl Export {
         let timer = Instant::now();
         let db_names = self.get_db_names().await?;
         let db_count = db_names.len();
-        let operator = self.build_prefer_fs_operator().await?;
+        let operator = self.build_operator().await?;
 
         for schema in db_names {
             let create_database = self
@@ -413,7 +394,7 @@ impl Export {
         let semaphore = Arc::new(Semaphore::new(self.parallelism));
         let db_names = self.get_db_names().await?;
         let db_count = db_names.len();
-        let operator = Arc::new(self.build_prefer_fs_operator().await?);
+        let operator = Arc::new(self.build_operator().await?);
         let mut tasks = Vec::with_capacity(db_names.len());
 
         for schema in db_names {
@@ -470,7 +451,7 @@ impl Export {
         Ok(())
     }
 
-    async fn build_operator(&self) -> Result<ObjectStore> {
+    async fn build_operator(&self) -> Result<Operator> {
         if self.s3 {
             self.build_s3_operator().await
         } else {
@@ -478,34 +459,13 @@ impl Export {
         }
     }
 
-    /// build operator with preference for file system
-    async fn build_prefer_fs_operator(&self) -> Result<ObjectStore> {
-        // is under s3 mode and s3_ddl_dir is set, use it as root
-        if self.s3 && self.s3_ddl_local_dir.is_some() {
-            let root = self.s3_ddl_local_dir.as_ref().unwrap().clone();
-            let op = ObjectStore::new(services::Fs::default().root(&root))
-                .context(OpenDalSnafu)?
-                .layer(LoggingLayer::default())
-                .finish();
-            Ok(op)
-        } else if self.s3 {
-            self.build_s3_operator().await
-        } else {
-            self.build_fs_operator().await
-        }
-    }
-
-    async fn build_s3_operator(&self) -> Result<ObjectStore> {
-        let mut builder = services::S3::default().bucket(
+    async fn build_s3_operator(&self) -> Result<Operator> {
+        let mut builder = services::S3::default().root("").bucket(
             self.s3_bucket
                 .as_ref()
                 .expect("s3_bucket must be provided when s3 is enabled"),
         );
 
-        if let Some(root) = self.s3_root.as_ref() {
-            builder = builder.root(root);
-        }
-
         if let Some(endpoint) = self.s3_endpoint.as_ref() {
             builder = builder.endpoint(endpoint);
         }
@@ -522,20 +482,20 @@ impl Export {
             builder = builder.secret_access_key(secret_key);
         }
 
-        let op = ObjectStore::new(builder)
+        let op = Operator::new(builder)
             .context(OpenDalSnafu)?
             .layer(LoggingLayer::default())
             .finish();
         Ok(op)
     }
 
-    async fn build_fs_operator(&self) -> Result<ObjectStore> {
+    async fn build_fs_operator(&self) -> Result<Operator> {
         let root = self
             .output_dir
             .as_ref()
             .context(OutputDirNotSetSnafu)?
             .clone();
-        let op = ObjectStore::new(services::Fs::default().root(&root))
+        let op = Operator::new(services::Fs::default().root(&root))
             .context(OpenDalSnafu)?
             .layer(LoggingLayer::default())
             .finish();
@@ -549,7 +509,6 @@ impl Export {
         let db_count = db_names.len();
         let mut tasks = Vec::with_capacity(db_count);
         let operator = Arc::new(self.build_operator().await?);
-        let fs_first_operator = Arc::new(self.build_prefer_fs_operator().await?);
         let with_options = build_with_options(&self.start_time, &self.end_time);
 
         for schema in db_names {
@@ -557,7 +516,6 @@ impl Export {
             let export_self = self.clone();
             let with_options_clone = with_options.clone();
             let operator = operator.clone();
-            let fs_first_operator = fs_first_operator.clone();
 
             tasks.push(async move {
                 let _permit = semaphore_moved.acquire().await.unwrap();
@@ -591,7 +549,7 @@ impl Export {
                 let copy_from_path = export_self.get_file_path(&schema, "copy_from.sql");
                 export_self
                     .write_to_storage(
-                        &fs_first_operator,
+                        &operator,
                         &copy_from_path,
                         copy_database_from_sql.into_bytes(),
                     )
@@ -622,13 +580,8 @@ impl Export {
     fn format_output_path(&self, file_path: &str) -> String {
         if self.s3 {
             format!(
-                "s3://{}{}/{}",
+                "s3://{}/{}",
                 self.s3_bucket.as_ref().unwrap_or(&String::new()),
-                if let Some(root) = &self.s3_root {
-                    format!("/{}", root)
-                } else {
-                    String::new()
-                },
                 file_path
             )
         } else {
@@ -642,27 +595,19 @@ impl Export {
 
     async fn write_to_storage(
         &self,
-        op: &ObjectStore,
+        op: &Operator,
         file_path: &str,
         content: Vec<u8>,
     ) -> Result<()> {
-        op.write(file_path, content)
-            .await
-            .context(OpenDalSnafu)
-            .map(|_| ())
+        op.write(file_path, content).await.context(OpenDalSnafu)
     }
 
     fn get_storage_params(&self, schema: &str) -> (String, String) {
         if self.s3 {
             let s3_path = format!(
-                "s3://{}{}/{}/{}/",
+                "s3://{}/{}/{}/",
                 // Safety: s3_bucket is required when s3 is enabled
                 self.s3_bucket.as_ref().unwrap(),
-                if let Some(root) = &self.s3_root {
-                    format!("/{}", root)
-                } else {
-                    String::new()
-                },
                 self.catalog,
                 schema
             );

src/cli/src/helper.rs

@@ -0,0 +1,112 @@
+// 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::borrow::Cow;
+
+use rustyline::completion::Completer;
+use rustyline::highlight::{Highlighter, MatchingBracketHighlighter};
+use rustyline::hint::{Hinter, HistoryHinter};
+use rustyline::validate::{ValidationContext, ValidationResult, Validator};
+
+use crate::cmd::ReplCommand;
+
+pub(crate) struct RustylineHelper {
+    hinter: HistoryHinter,
+    highlighter: MatchingBracketHighlighter,
+}
+
+impl Default for RustylineHelper {
+    fn default() -> Self {
+        Self {
+            hinter: HistoryHinter {},
+            highlighter: MatchingBracketHighlighter::default(),
+        }
+    }
+}
+
+impl rustyline::Helper for RustylineHelper {}
+
+impl Validator for RustylineHelper {
+    fn validate(&self, ctx: &mut ValidationContext<'_>) -> rustyline::Result<ValidationResult> {
+        let input = ctx.input();
+        match ReplCommand::try_from(input) {
+            Ok(_) => Ok(ValidationResult::Valid(None)),
+            Err(e) => {
+                if input.trim_end().ends_with(';') {
+                    // If line ends with ';', it HAS to be a valid command.
+                    Ok(ValidationResult::Invalid(Some(e.to_string())))
+                } else {
+                    Ok(ValidationResult::Incomplete)
+                }
+            }
+        }
+    }
+}
+
+impl Hinter for RustylineHelper {
+    type Hint = String;
+
+    fn hint(&self, line: &str, pos: usize, ctx: &rustyline::Context<'_>) -> Option<Self::Hint> {
+        self.hinter.hint(line, pos, ctx)
+    }
+}
+
+impl Highlighter for RustylineHelper {
+    fn highlight<'l>(&self, line: &'l str, pos: usize) -> Cow<'l, str> {
+        self.highlighter.highlight(line, pos)
+    }
+
+    fn highlight_prompt<'b, 's: 'b, 'p: 'b>(
+        &'s self,
+        prompt: &'p str,
+        default: bool,
+    ) -> Cow<'b, str> {
+        self.highlighter.highlight_prompt(prompt, default)
+    }
+
+    fn highlight_hint<'h>(&self, hint: &'h str) -> Cow<'h, str> {
+        use nu_ansi_term::Style;
+        Cow::Owned(Style::new().dimmed().paint(hint).to_string())
+    }
+
+    fn highlight_candidate<'c>(
+        &self,
+        candidate: &'c str,
+        completion: rustyline::CompletionType,
+    ) -> Cow<'c, str> {
+        self.highlighter.highlight_candidate(candidate, completion)
+    }
+
+    fn highlight_char(&self, line: &str, pos: usize) -> bool {
+        self.highlighter.highlight_char(line, pos)
+    }
+}
+
+impl Completer for RustylineHelper {
+    type Candidate = String;
+
+    fn complete(
+        &self,
+        line: &str,
+        pos: usize,
+        ctx: &rustyline::Context<'_>,
+    ) -> rustyline::Result<(usize, Vec<Self::Candidate>)> {
+        // If there is a hint, use that as the auto-complete when user hits `tab`
+        if let Some(hint) = self.hinter.hint(line, pos, ctx) {
+            Ok((pos, vec![hint]))
+        } else {
+            Ok((0, vec![]))
+        }
+    }
+}

src/cli/src/lib.rs

@@ -13,11 +13,16 @@
 // limitations under the License.
 
 mod bench;
-mod database;
 pub mod error;
+// Wait for https://github.com/GreptimeTeam/greptimedb/issues/2373
+#[allow(unused)]
+mod cmd;
 mod export;
+mod helper;
+
+// Wait for https://github.com/GreptimeTeam/greptimedb/issues/2373
+mod database;
 mod import;
-mod meta_snapshot;
 
 use async_trait::async_trait;
 use clap::Parser;
@@ -28,7 +33,6 @@ use error::Result;
 pub use crate::bench::BenchTableMetadataCommand;
 pub use crate::export::ExportCommand;
 pub use crate::import::ImportCommand;
-pub use crate::meta_snapshot::{MetaRestoreCommand, MetaSnapshotCommand};
 
 #[async_trait]
 pub trait Tool: Send + Sync {

src/cli/src/meta_snapshot.rs

@@ -1,329 +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;
-
-use async_trait::async_trait;
-use clap::Parser;
-use common_base::secrets::{ExposeSecret, SecretString};
-use common_error::ext::BoxedError;
-use common_meta::kv_backend::chroot::ChrootKvBackend;
-use common_meta::kv_backend::etcd::EtcdStore;
-use common_meta::kv_backend::KvBackendRef;
-use common_meta::snapshot::MetadataSnapshotManager;
-use meta_srv::bootstrap::create_etcd_client;
-use meta_srv::metasrv::BackendImpl;
-use object_store::services::{Fs, S3};
-use object_store::ObjectStore;
-use snafu::ResultExt;
-
-use crate::error::{KvBackendNotSetSnafu, OpenDalSnafu, S3ConfigNotSetSnafu};
-use crate::Tool;
-#[derive(Debug, Default, Parser)]
-struct MetaConnection {
-    /// The endpoint of store. one of etcd, pg or mysql.
-    #[clap(long, alias = "store-addr", value_delimiter = ',', num_args = 1..)]
-    store_addrs: Vec<String>,
-    /// The database backend.
-    #[clap(long, value_enum)]
-    backend: Option<BackendImpl>,
-    #[clap(long, default_value = "")]
-    store_key_prefix: String,
-    #[cfg(any(feature = "pg_kvbackend", feature = "mysql_kvbackend"))]
-    #[clap(long,default_value = common_meta::kv_backend::DEFAULT_META_TABLE_NAME)]
-    meta_table_name: String,
-    #[clap(long, default_value = "128")]
-    max_txn_ops: usize,
-}
-
-impl MetaConnection {
-    pub async fn build(&self) -> Result<KvBackendRef, BoxedError> {
-        let max_txn_ops = self.max_txn_ops;
-        let store_addrs = &self.store_addrs;
-        if store_addrs.is_empty() {
-            KvBackendNotSetSnafu { backend: "all" }
-                .fail()
-                .map_err(BoxedError::new)
-        } else {
-            let kvbackend = match self.backend {
-                Some(BackendImpl::EtcdStore) => {
-                    let etcd_client = create_etcd_client(store_addrs)
-                        .await
-                        .map_err(BoxedError::new)?;
-                    Ok(EtcdStore::with_etcd_client(etcd_client, max_txn_ops))
-                }
-                #[cfg(feature = "pg_kvbackend")]
-                Some(BackendImpl::PostgresStore) => {
-                    let table_name = &self.meta_table_name;
-                    let pool = meta_srv::bootstrap::create_postgres_pool(store_addrs)
-                        .await
-                        .map_err(BoxedError::new)?;
-                    Ok(common_meta::kv_backend::rds::PgStore::with_pg_pool(
-                        pool,
-                        table_name,
-                        max_txn_ops,
-                    )
-                    .await
-                    .map_err(BoxedError::new)?)
-                }
-                #[cfg(feature = "mysql_kvbackend")]
-                Some(BackendImpl::MysqlStore) => {
-                    let table_name = &self.meta_table_name;
-                    let pool = meta_srv::bootstrap::create_mysql_pool(store_addrs)
-                        .await
-                        .map_err(BoxedError::new)?;
-                    Ok(common_meta::kv_backend::rds::MySqlStore::with_mysql_pool(
-                        pool,
-                        table_name,
-                        max_txn_ops,
-                    )
-                    .await
-                    .map_err(BoxedError::new)?)
-                }
-                _ => KvBackendNotSetSnafu { backend: "all" }
-                    .fail()
-                    .map_err(BoxedError::new),
-            };
-            if self.store_key_prefix.is_empty() {
-                kvbackend
-            } else {
-                let chroot_kvbackend =
-                    ChrootKvBackend::new(self.store_key_prefix.as_bytes().to_vec(), kvbackend?);
-                Ok(Arc::new(chroot_kvbackend))
-            }
-        }
-    }
-}
-
-// TODO(qtang): Abstract a generic s3 config for export import meta snapshot restore
-#[derive(Debug, Default, Parser)]
-struct S3Config {
-    /// whether to use s3 as the output directory. default is false.
-    #[clap(long, default_value = "false")]
-    s3: bool,
-    /// The s3 bucket name.
-    #[clap(long)]
-    s3_bucket: Option<String>,
-    /// The s3 region.
-    #[clap(long)]
-    s3_region: Option<String>,
-    /// The s3 access key.
-    #[clap(long)]
-    s3_access_key: Option<SecretString>,
-    /// The s3 secret key.
-    #[clap(long)]
-    s3_secret_key: Option<SecretString>,
-    /// The s3 endpoint. we will automatically use the default s3 decided by the region if not set.
-    #[clap(long)]
-    s3_endpoint: Option<String>,
-}
-
-impl S3Config {
-    pub fn build(&self, root: &str) -> Result<Option<ObjectStore>, BoxedError> {
-        if !self.s3 {
-            Ok(None)
-        } else {
-            if self.s3_region.is_none()
-                || self.s3_access_key.is_none()
-                || self.s3_secret_key.is_none()
-                || self.s3_bucket.is_none()
-            {
-                return S3ConfigNotSetSnafu.fail().map_err(BoxedError::new);
-            }
-            // Safety, unwrap is safe because we have checked the options above.
-            let mut config = S3::default()
-                .bucket(self.s3_bucket.as_ref().unwrap())
-                .region(self.s3_region.as_ref().unwrap())
-                .access_key_id(self.s3_access_key.as_ref().unwrap().expose_secret())
-                .secret_access_key(self.s3_secret_key.as_ref().unwrap().expose_secret());
-
-            if !root.is_empty() && root != "." {
-                config = config.root(root);
-            }
-
-            if let Some(endpoint) = &self.s3_endpoint {
-                config = config.endpoint(endpoint);
-            }
-            Ok(Some(
-                ObjectStore::new(config)
-                    .context(OpenDalSnafu)
-                    .map_err(BoxedError::new)?
-                    .finish(),
-            ))
-        }
-    }
-}
-
-/// Export metadata snapshot tool.
-/// This tool is used to export metadata snapshot from etcd, pg or mysql.
-/// It will dump the metadata snapshot to local file or s3 bucket.
-/// The snapshot file will be in binary format.
-#[derive(Debug, Default, Parser)]
-pub struct MetaSnapshotCommand {
-    /// The connection to the metadata store.
-    #[clap(flatten)]
-    connection: MetaConnection,
-    /// The s3 config.
-    #[clap(flatten)]
-    s3_config: S3Config,
-    /// The name of the target snapshot file. we will add the file extension automatically.
-    #[clap(long, default_value = "metadata_snapshot")]
-    file_name: String,
-    /// The directory to store the snapshot file.
-    /// if target output is s3 bucket, this is the root directory in the bucket.
-    /// if target output is local file, this is the local directory.
-    #[clap(long, default_value = "")]
-    output_dir: String,
-}
-
-fn create_local_file_object_store(root: &str) -> Result<ObjectStore, BoxedError> {
-    let root = if root.is_empty() { "." } else { root };
-    let object_store = ObjectStore::new(Fs::default().root(root))
-        .context(OpenDalSnafu)
-        .map_err(BoxedError::new)?
-        .finish();
-    Ok(object_store)
-}
-
-impl MetaSnapshotCommand {
-    pub async fn build(&self) -> Result<Box<dyn Tool>, BoxedError> {
-        let kvbackend = self.connection.build().await?;
-        let output_dir = &self.output_dir;
-        let object_store = self.s3_config.build(output_dir).map_err(BoxedError::new)?;
-        if let Some(store) = object_store {
-            let tool = MetaSnapshotTool {
-                inner: MetadataSnapshotManager::new(kvbackend, store),
-                target_file: self.file_name.clone(),
-            };
-            Ok(Box::new(tool))
-        } else {
-            let object_store = create_local_file_object_store(output_dir)?;
-            let tool = MetaSnapshotTool {
-                inner: MetadataSnapshotManager::new(kvbackend, object_store),
-                target_file: self.file_name.clone(),
-            };
-            Ok(Box::new(tool))
-        }
-    }
-}
-
-pub struct MetaSnapshotTool {
-    inner: MetadataSnapshotManager,
-    target_file: String,
-}
-
-#[async_trait]
-impl Tool for MetaSnapshotTool {
-    async fn do_work(&self) -> std::result::Result<(), BoxedError> {
-        self.inner
-            .dump("", &self.target_file)
-            .await
-            .map_err(BoxedError::new)?;
-        Ok(())
-    }
-}
-
-/// Restore metadata snapshot tool.
-/// This tool is used to restore metadata snapshot from etcd, pg or mysql.
-/// It will restore the metadata snapshot from local file or s3 bucket.
-#[derive(Debug, Default, Parser)]
-pub struct MetaRestoreCommand {
-    /// The connection to the metadata store.
-    #[clap(flatten)]
-    connection: MetaConnection,
-    /// The s3 config.
-    #[clap(flatten)]
-    s3_config: S3Config,
-    /// The name of the target snapshot file.
-    #[clap(long, default_value = "metadata_snapshot.metadata.fb")]
-    file_name: String,
-    /// The directory to store the snapshot file.
-    #[clap(long, default_value = ".")]
-    input_dir: String,
-    #[clap(long, default_value = "false")]
-    force: bool,
-}
-
-impl MetaRestoreCommand {
-    pub async fn build(&self) -> Result<Box<dyn Tool>, BoxedError> {
-        let kvbackend = self.connection.build().await?;
-        let input_dir = &self.input_dir;
-        let object_store = self.s3_config.build(input_dir).map_err(BoxedError::new)?;
-        if let Some(store) = object_store {
-            let tool = MetaRestoreTool::new(
-                MetadataSnapshotManager::new(kvbackend, store),
-                self.file_name.clone(),
-                self.force,
-            );
-            Ok(Box::new(tool))
-        } else {
-            let object_store = create_local_file_object_store(input_dir)?;
-            let tool = MetaRestoreTool::new(
-                MetadataSnapshotManager::new(kvbackend, object_store),
-                self.file_name.clone(),
-                self.force,
-            );
-            Ok(Box::new(tool))
-        }
-    }
-}
-
-pub struct MetaRestoreTool {
-    inner: MetadataSnapshotManager,
-    source_file: String,
-    force: bool,
-}
-
-impl MetaRestoreTool {
-    pub fn new(inner: MetadataSnapshotManager, source_file: String, force: bool) -> Self {
-        Self {
-            inner,
-            source_file,
-            force,
-        }
-    }
-}
-
-#[async_trait]
-impl Tool for MetaRestoreTool {
-    async fn do_work(&self) -> std::result::Result<(), BoxedError> {
-        let clean = self
-            .inner
-            .check_target_source_clean()
-            .await
-            .map_err(BoxedError::new)?;
-        if clean {
-            common_telemetry::info!(
-                "The target source is clean, we will restore the metadata snapshot."
-            );
-            self.inner
-                .restore(&self.source_file)
-                .await
-                .map_err(BoxedError::new)?;
-            Ok(())
-        } else if !self.force {
-            common_telemetry::warn!(
-                 "The target source is not clean, if you want to restore the metadata snapshot forcefully, please use --force option."
-             );
-            Ok(())
-        } else {
-            common_telemetry::info!("The target source is not clean, We will restore the metadata snapshot with --force.");
-            self.inner
-                .restore(&self.source_file)
-                .await
-                .map_err(BoxedError::new)?;
-            Ok(())
-        }
-    }
-}

src/client/Cargo.toml

@@ -25,7 +25,6 @@ common-meta.workspace = true
 common-query.workspace = true
 common-recordbatch.workspace = true
 common-telemetry.workspace = true
-datatypes.workspace = true
 enum_dispatch = "0.3"
 futures.workspace = true
 futures-util.workspace = true

src/client/src/database.rs

@@ -14,7 +14,6 @@
 
 use std::pin::Pin;
 use std::str::FromStr;
-use std::sync::Arc;
 
 use api::v1::auth_header::AuthScheme;
 use api::v1::ddl_request::Expr as DdlExpr;
@@ -36,21 +35,21 @@ use common_grpc::flight::do_put::DoPutResponse;
 use common_grpc::flight::{FlightDecoder, FlightMessage};
 use common_query::Output;
 use common_recordbatch::error::ExternalSnafu;
-use common_recordbatch::{RecordBatch, RecordBatchStreamWrapper};
+use common_recordbatch::RecordBatchStreamWrapper;
+use common_telemetry::error;
 use common_telemetry::tracing_context::W3cTrace;
-use common_telemetry::{error, warn};
 use futures::future;
 use futures_util::{Stream, StreamExt, TryStreamExt};
 use prost::Message;
 use snafu::{ensure, ResultExt};
-use tonic::metadata::{AsciiMetadataKey, AsciiMetadataValue, MetadataMap, MetadataValue};
+use tonic::metadata::{AsciiMetadataKey, MetadataValue};
 use tonic::transport::Channel;
 
 use crate::error::{
-    ConvertFlightDataSnafu, Error, FlightGetSnafu, IllegalFlightMessagesSnafu,
+    ConvertFlightDataSnafu, Error, FlightGetSnafu, IllegalFlightMessagesSnafu, InvalidAsciiSnafu,
     InvalidTonicMetadataValueSnafu, ServerSnafu,
 };
-use crate::{error, from_grpc_response, Client, Result};
+use crate::{from_grpc_response, Client, Result};
 
 type FlightDataStream = Pin<Box<dyn Stream<Item = FlightData> + Send>>;
 
@@ -166,27 +165,26 @@ impl Database {
 
         let mut request = tonic::Request::new(request);
         let metadata = request.metadata_mut();
-        Self::put_hints(metadata, hints)?;
-
+        for (key, value) in hints {
+            let key = AsciiMetadataKey::from_bytes(format!("x-greptime-hint-{}", key).as_bytes())
+                .map_err(|_| {
+                InvalidAsciiSnafu {
+                    value: key.to_string(),
+                }
+                .build()
+            })?;
+            let value = value.parse().map_err(|_| {
+                InvalidAsciiSnafu {
+                    value: value.to_string(),
+                }
+                .build()
+            })?;
+            metadata.insert(key, value);
+        }
         let response = client.handle(request).await?.into_inner();
         from_grpc_response(response)
     }
 
-    fn put_hints(metadata: &mut MetadataMap, hints: &[(&str, &str)]) -> Result<()> {
-        let Some(value) = hints
-            .iter()
-            .map(|(k, v)| format!("{}={}", k, v))
-            .reduce(|a, b| format!("{},{}", a, b))
-        else {
-            return Ok(());
-        };
-
-        let key = AsciiMetadataKey::from_static("x-greptime-hints");
-        let value = AsciiMetadataValue::from_str(&value).context(InvalidTonicMetadataValueSnafu)?;
-        metadata.insert(key, value);
-        Ok(())
-    }
-
     pub async fn handle(&self, request: Request) -> Result<u32> {
         let mut client = make_database_client(&self.client)?.inner;
         let request = self.to_rpc_request(request);
@@ -194,36 +192,6 @@ impl Database {
         from_grpc_response(response)
     }
 
-    /// Retry if connection fails, max_retries is the max number of retries, so the total wait time
-    /// is `max_retries * GRPC_CONN_TIMEOUT`
-    pub async fn handle_with_retry(&self, request: Request, max_retries: u32) -> Result<u32> {
-        let mut client = make_database_client(&self.client)?.inner;
-        let mut retries = 0;
-        let request = self.to_rpc_request(request);
-        loop {
-            let raw_response = client.handle(request.clone()).await;
-            match (raw_response, retries < max_retries) {
-                (Ok(resp), _) => return from_grpc_response(resp.into_inner()),
-                (Err(err), true) => {
-                    // determine if the error is retryable
-                    if is_grpc_retryable(&err) {
-                        // retry
-                        retries += 1;
-                        warn!("Retrying {} times with error = {:?}", retries, err);
-                        continue;
-                    }
-                }
-                (Err(err), false) => {
-                    error!(
-                        "Failed to send request to grpc handle after {} retries, error = {:?}",
-                        retries, err
-                    );
-                    return Err(err.into());
-                }
-            }
-        }
-    }
-
     #[inline]
     fn to_rpc_request(&self, request: Request) -> GreptimeRequest {
         GreptimeRequest {
@@ -244,49 +212,39 @@ impl Database {
     where
         S: AsRef<str>,
     {
-        self.sql_with_hint(sql, &[]).await
-    }
-
-    pub async fn sql_with_hint<S>(&self, sql: S, hints: &[(&str, &str)]) -> Result<Output>
-    where
-        S: AsRef<str>,
-    {
-        let request = Request::Query(QueryRequest {
+        self.do_get(Request::Query(QueryRequest {
             query: Some(Query::Sql(sql.as_ref().to_string())),
-        });
-        self.do_get(request, hints).await
+        }))
+        .await
     }
 
     pub async fn logical_plan(&self, logical_plan: Vec<u8>) -> Result<Output> {
-        let request = Request::Query(QueryRequest {
+        self.do_get(Request::Query(QueryRequest {
             query: Some(Query::LogicalPlan(logical_plan)),
-        });
-        self.do_get(request, &[]).await
+        }))
+        .await
     }
 
     pub async fn create(&self, expr: CreateTableExpr) -> Result<Output> {
-        let request = Request::Ddl(DdlRequest {
+        self.do_get(Request::Ddl(DdlRequest {
             expr: Some(DdlExpr::CreateTable(expr)),
-        });
-        self.do_get(request, &[]).await
+        }))
+        .await
     }
 
     pub async fn alter(&self, expr: AlterTableExpr) -> Result<Output> {
-        let request = Request::Ddl(DdlRequest {
+        self.do_get(Request::Ddl(DdlRequest {
             expr: Some(DdlExpr::AlterTable(expr)),
-        });
-        self.do_get(request, &[]).await
+        }))
+        .await
     }
 
-    async fn do_get(&self, request: Request, hints: &[(&str, &str)]) -> Result<Output> {
+    async fn do_get(&self, request: Request) -> Result<Output> {
         let request = self.to_rpc_request(request);
         let request = Ticket {
             ticket: request.encode_to_vec().into(),
         };
 
-        let mut request = tonic::Request::new(request);
-        Self::put_hints(request.metadata_mut(), hints)?;
-
         let mut client = self.client.make_flight_client()?;
 
         let response = client.mut_inner().do_get(request).await.or_else(|e| {
@@ -316,7 +274,7 @@ impl Database {
         let mut flight_message_stream = flight_data_stream.map(move |flight_data| {
             flight_data
                 .map_err(Error::from)
-                .and_then(|data| decoder.try_decode(&data).context(ConvertFlightDataSnafu))
+                .and_then(|data| decoder.try_decode(data).context(ConvertFlightDataSnafu))
         });
 
         let Some(first_flight_message) = flight_message_stream.next().await else {
@@ -338,30 +296,20 @@ impl Database {
                 );
                 Ok(Output::new_with_affected_rows(rows))
             }
-            FlightMessage::RecordBatch(_) | FlightMessage::Metrics(_) => {
+            FlightMessage::Recordbatch(_) | FlightMessage::Metrics(_) => {
                 IllegalFlightMessagesSnafu {
                     reason: "The first flight message cannot be a RecordBatch or Metrics message",
                 }
                 .fail()
             }
             FlightMessage::Schema(schema) => {
-                let schema = Arc::new(
-                    datatypes::schema::Schema::try_from(schema)
-                        .context(error::ConvertSchemaSnafu)?,
-                );
-                let schema_cloned = schema.clone();
                 let stream = Box::pin(stream!({
                     while let Some(flight_message) = flight_message_stream.next().await {
                         let flight_message = flight_message
                             .map_err(BoxedError::new)
                             .context(ExternalSnafu)?;
                         match flight_message {
-                            FlightMessage::RecordBatch(arrow_batch) => {
-                                yield RecordBatch::try_from_df_record_batch(
-                                    schema_cloned.clone(),
-                                    arrow_batch,
-                                )
-                            }
+                            FlightMessage::Recordbatch(record_batch) => yield Ok(record_batch),
                             FlightMessage::Metrics(_) => {}
                             FlightMessage::AffectedRows(_) | FlightMessage::Schema(_) => {
                                 yield IllegalFlightMessagesSnafu {reason: format!("A Schema message must be succeeded exclusively by a set of RecordBatch messages, flight_message: {:?}", flight_message)}
@@ -420,11 +368,6 @@ impl Database {
     }
 }
 
-/// by grpc standard, only `Unavailable` is retryable, see: https://github.com/grpc/grpc/blob/master/doc/statuscodes.md#status-codes-and-their-use-in-grpc
-pub fn is_grpc_retryable(err: &tonic::Status) -> bool {
-    matches!(err.code(), tonic::Code::Unavailable)
-}
-
 #[derive(Default, Debug, Clone)]
 struct FlightContext {
     auth_header: Option<AuthHeader>,

src/client/src/error.rs

@@ -110,6 +110,13 @@ pub enum Error {
         location: Location,
     },
 
+    #[snafu(display("Failed to parse ascii string: {}", value))]
+    InvalidAscii {
+        value: String,
+        #[snafu(implicit)]
+        location: Location,
+    },
+
     #[snafu(display("Invalid Tonic metadata value"))]
     InvalidTonicMetadataValue {
         #[snafu(source)]
@@ -117,13 +124,6 @@ pub enum Error {
         #[snafu(implicit)]
         location: Location,
     },
-
-    #[snafu(display("Failed to convert Schema"))]
-    ConvertSchema {
-        #[snafu(implicit)]
-        location: Location,
-        source: datatypes::error::Error,
-    },
 }
 
 pub type Result<T> = std::result::Result<T, Error>;
@@ -143,8 +143,10 @@ impl ErrorExt for Error {
             | Error::ConvertFlightData { source, .. }
             | Error::CreateTlsChannel { source, .. } => source.status_code(),
             Error::IllegalGrpcClientState { .. } => StatusCode::Unexpected,
-            Error::InvalidTonicMetadataValue { .. } => StatusCode::InvalidArguments,
-            Error::ConvertSchema { source, .. } => source.status_code(),
+
+            Error::InvalidAscii { .. } | Error::InvalidTonicMetadataValue { .. } => {
+                StatusCode::InvalidArguments
+            }
         }
     }
 

src/client/src/region.rs

@@ -28,7 +28,7 @@ use common_meta::error::{self as meta_error, Result as MetaResult};
 use common_meta::node_manager::Datanode;
 use common_query::request::QueryRequest;
 use common_recordbatch::error::ExternalSnafu;
-use common_recordbatch::{RecordBatch, RecordBatchStreamWrapper, SendableRecordBatchStream};
+use common_recordbatch::{RecordBatchStreamWrapper, SendableRecordBatchStream};
 use common_telemetry::error;
 use common_telemetry::tracing_context::TracingContext;
 use prost::Message;
@@ -55,7 +55,6 @@ impl Datanode for RegionRequester {
             if err.should_retry() {
                 meta_error::Error::RetryLater {
                     source: BoxedError::new(err),
-                    clean_poisons: false,
                 }
             } else {
                 meta_error::Error::External {
@@ -126,7 +125,7 @@ impl RegionRequester {
         let mut flight_message_stream = flight_data_stream.map(move |flight_data| {
             flight_data
                 .map_err(Error::from)
-                .and_then(|data| decoder.try_decode(&data).context(ConvertFlightDataSnafu))
+                .and_then(|data| decoder.try_decode(data).context(ConvertFlightDataSnafu))
         });
 
         let Some(first_flight_message) = flight_message_stream.next().await else {
@@ -147,10 +146,6 @@ impl RegionRequester {
 
         let tracing_context = TracingContext::from_current_span();
 
-        let schema = Arc::new(
-            datatypes::schema::Schema::try_from(schema).context(error::ConvertSchemaSnafu)?,
-        );
-        let schema_cloned = schema.clone();
         let stream = Box::pin(stream!({
             let _span = tracing_context.attach(common_telemetry::tracing::info_span!(
                 "poll_flight_data_stream"
@@ -161,12 +156,7 @@ impl RegionRequester {
                     .context(ExternalSnafu)?;
 
                 match flight_message {
-                    FlightMessage::RecordBatch(record_batch) => {
-                        yield RecordBatch::try_from_df_record_batch(
-                            schema_cloned.clone(),
-                            record_batch,
-                        )
-                    }
+                    FlightMessage::Recordbatch(record_batch) => yield Ok(record_batch),
                     FlightMessage::Metrics(s) => {
                         let m = serde_json::from_str(&s).ok().map(Arc::new);
                         metrics_ref.swap(m);

src/cmd/Cargo.toml

@@ -10,13 +10,7 @@ name = "greptime"
 path = "src/bin/greptime.rs"
 
 [features]
-default = [
-    "servers/pprof",
-    "servers/mem-prof",
-    "meta-srv/pg_kvbackend",
-    "meta-srv/mysql_kvbackend",
-]
-enterprise = ["common-meta/enterprise", "frontend/enterprise", "meta-srv/enterprise"]
+default = ["servers/pprof", "servers/mem-prof"]
 tokio-console = ["common-telemetry/tokio-console"]
 
 [lints]

src/cmd/src/bin/greptime.rs

@@ -15,11 +15,9 @@
 #![doc = include_str!("../../../../README.md")]
 
 use clap::{Parser, Subcommand};
-use cmd::datanode::builder::InstanceBuilder;
 use cmd::error::{InitTlsProviderSnafu, Result};
 use cmd::options::GlobalOptions;
 use cmd::{cli, datanode, flownode, frontend, metasrv, standalone, App};
-use common_base::Plugins;
 use common_version::version;
 use servers::install_ring_crypto_provider;
 
@@ -104,10 +102,10 @@ async fn main_body() -> Result<()> {
 async fn start(cli: Command) -> Result<()> {
     match cli.subcmd {
         SubCommand::Datanode(cmd) => {
-            let opts = cmd.load_options(&cli.global_options)?;
-            let plugins = Plugins::new();
-            let builder = InstanceBuilder::try_new_with_init(opts, plugins).await?;
-            cmd.build_with(builder).await?.run().await
+            cmd.build(cmd.load_options(&cli.global_options)?)
+                .await?
+                .run()
+                .await
         }
         SubCommand::Flownode(cmd) => {
             cmd.build(cmd.load_options(&cli.global_options)?)

src/cmd/src/cli.rs

@@ -58,7 +58,7 @@ impl App for Instance {
         false
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         Ok(())
     }
 }
@@ -76,7 +76,6 @@ impl Command {
             &opts,
             &TracingOptions::default(),
             None,
-            None,
         );
 
         let tool = self.cmd.build().await.context(error::BuildCliSnafu)?;

src/cmd/src/datanode.rs

@@ -12,27 +12,33 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-pub mod builder;
-
+use std::sync::Arc;
 use std::time::Duration;
 
 use async_trait::async_trait;
+use cache::build_datanode_cache_registry;
+use catalog::kvbackend::MetaKvBackend;
 use clap::Parser;
+use common_base::Plugins;
 use common_config::Configurable;
+use common_meta::cache::LayeredCacheRegistryBuilder;
 use common_telemetry::logging::TracingOptions;
 use common_telemetry::{info, warn};
+use common_version::{short_version, version};
 use common_wal::config::DatanodeWalConfig;
-use datanode::datanode::Datanode;
-use meta_client::MetaClientOptions;
-use snafu::{ensure, ResultExt};
+use datanode::datanode::{Datanode, DatanodeBuilder};
+use datanode::service::DatanodeServiceBuilder;
+use meta_client::{MetaClientOptions, MetaClientType};
+use servers::Mode;
+use snafu::{ensure, OptionExt, ResultExt};
 use tracing_appender::non_blocking::WorkerGuard;
 
-use crate::datanode::builder::InstanceBuilder;
 use crate::error::{
-    LoadLayeredConfigSnafu, MissingConfigSnafu, Result, ShutdownDatanodeSnafu, StartDatanodeSnafu,
+    LoadLayeredConfigSnafu, MetaClientInitSnafu, MissingConfigSnafu, Result, ShutdownDatanodeSnafu,
+    StartDatanodeSnafu,
 };
 use crate::options::{GlobalOptions, GreptimeOptions};
-use crate::App;
+use crate::{log_versions, App};
 
 pub const APP_NAME: &str = "greptime-datanode";
 
@@ -77,7 +83,7 @@ impl App for Instance {
         self.datanode.start().await.context(StartDatanodeSnafu)
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         self.datanode
             .shutdown()
             .await
@@ -92,8 +98,8 @@ pub struct Command {
 }
 
 impl Command {
-    pub async fn build_with(&self, builder: InstanceBuilder) -> Result<Instance> {
-        self.subcmd.build_with(builder).await
+    pub async fn build(&self, opts: DatanodeOptions) -> Result<Instance> {
+        self.subcmd.build(opts).await
     }
 
     pub fn load_options(&self, global_options: &GlobalOptions) -> Result<DatanodeOptions> {
@@ -109,12 +115,9 @@ enum SubCommand {
 }
 
 impl SubCommand {
-    async fn build_with(&self, builder: InstanceBuilder) -> Result<Instance> {
+    async fn build(&self, opts: DatanodeOptions) -> Result<Instance> {
         match self {
-            SubCommand::Start(cmd) => {
-                info!("Building datanode with {:#?}", cmd);
-                builder.build().await
-            }
+            SubCommand::Start(cmd) => cmd.build(opts).await,
         }
     }
 }
@@ -156,7 +159,6 @@ impl StartCommand {
         .context(LoadLayeredConfigSnafu)?;
 
         self.merge_with_cli_options(global_options, &mut opts)?;
-        opts.component.sanitize();
 
         Ok(opts)
     }
@@ -261,6 +263,74 @@ impl StartCommand {
 
         Ok(())
     }
+
+    async fn build(&self, opts: DatanodeOptions) -> Result<Instance> {
+        common_runtime::init_global_runtimes(&opts.runtime);
+
+        let guard = common_telemetry::init_global_logging(
+            APP_NAME,
+            &opts.component.logging,
+            &opts.component.tracing,
+            opts.component.node_id.map(|x| x.to_string()),
+        );
+        log_versions(version(), short_version(), APP_NAME);
+
+        info!("Datanode start command: {:#?}", self);
+        info!("Datanode options: {:#?}", opts);
+
+        let plugin_opts = opts.plugins;
+        let mut opts = opts.component;
+        opts.grpc.detect_server_addr();
+        let mut plugins = Plugins::new();
+        plugins::setup_datanode_plugins(&mut plugins, &plugin_opts, &opts)
+            .await
+            .context(StartDatanodeSnafu)?;
+
+        let member_id = opts
+            .node_id
+            .context(MissingConfigSnafu { msg: "'node_id'" })?;
+
+        let meta_config = opts.meta_client.as_ref().context(MissingConfigSnafu {
+            msg: "'meta_client_options'",
+        })?;
+
+        let meta_client = meta_client::create_meta_client(
+            MetaClientType::Datanode { member_id },
+            meta_config,
+            None,
+        )
+        .await
+        .context(MetaClientInitSnafu)?;
+
+        let meta_backend = Arc::new(MetaKvBackend {
+            client: meta_client.clone(),
+        });
+
+        // Builds cache registry for datanode.
+        let layered_cache_registry = Arc::new(
+            LayeredCacheRegistryBuilder::default()
+                .add_cache_registry(build_datanode_cache_registry(meta_backend.clone()))
+                .build(),
+        );
+
+        let mut datanode = DatanodeBuilder::new(opts.clone(), plugins, Mode::Distributed)
+            .with_meta_client(meta_client)
+            .with_kv_backend(meta_backend)
+            .with_cache_registry(layered_cache_registry)
+            .build()
+            .await
+            .context(StartDatanodeSnafu)?;
+
+        let services = DatanodeServiceBuilder::new(&opts)
+            .with_default_grpc_server(&datanode.region_server())
+            .enable_http_service()
+            .build()
+            .await
+            .context(StartDatanodeSnafu)?;
+        datanode.setup_services(services);
+
+        Ok(Instance::new(datanode, guard))
+    }
 }
 
 #[cfg(test)]
@@ -282,6 +352,7 @@ mod tests {
         common_telemetry::init_default_ut_logging();
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
             enable_memory_catalog = false
             node_id = 42
 
@@ -308,6 +379,7 @@ mod tests {
     fn test_read_from_config_file() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
             enable_memory_catalog = false
             node_id = 42
 
@@ -473,6 +545,7 @@ mod tests {
     fn test_config_precedence_order() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
             enable_memory_catalog = false
             node_id = 42
             rpc_addr = "127.0.0.1:3001"

src/cmd/src/datanode/builder.rs

@@ -1,138 +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;
-
-use cache::build_datanode_cache_registry;
-use catalog::kvbackend::MetaKvBackend;
-use common_base::Plugins;
-use common_meta::cache::LayeredCacheRegistryBuilder;
-use common_telemetry::info;
-use common_version::{short_version, version};
-use datanode::datanode::DatanodeBuilder;
-use datanode::service::DatanodeServiceBuilder;
-use meta_client::MetaClientType;
-use snafu::{OptionExt, ResultExt};
-use tracing_appender::non_blocking::WorkerGuard;
-
-use crate::datanode::{DatanodeOptions, Instance, APP_NAME};
-use crate::error::{MetaClientInitSnafu, MissingConfigSnafu, Result, StartDatanodeSnafu};
-use crate::log_versions;
-
-/// Builder for Datanode instance.
-pub struct InstanceBuilder {
-    guard: Vec<WorkerGuard>,
-    opts: DatanodeOptions,
-    datanode_builder: DatanodeBuilder,
-}
-
-impl InstanceBuilder {
-    /// Try to create a new [InstanceBuilder], and do some initialization work like allocating
-    /// runtime resources, setting up global logging and plugins, etc.
-    pub async fn try_new_with_init(
-        mut opts: DatanodeOptions,
-        mut plugins: Plugins,
-    ) -> Result<Self> {
-        let guard = Self::init(&mut opts, &mut plugins).await?;
-
-        let datanode_builder = Self::datanode_builder(&opts, plugins).await?;
-
-        Ok(Self {
-            guard,
-            opts,
-            datanode_builder,
-        })
-    }
-
-    async fn init(opts: &mut DatanodeOptions, plugins: &mut Plugins) -> Result<Vec<WorkerGuard>> {
-        common_runtime::init_global_runtimes(&opts.runtime);
-
-        let dn_opts = &mut opts.component;
-        let guard = common_telemetry::init_global_logging(
-            APP_NAME,
-            &dn_opts.logging,
-            &dn_opts.tracing,
-            dn_opts.node_id.map(|x| x.to_string()),
-            None,
-        );
-
-        log_versions(version(), short_version(), APP_NAME);
-
-        plugins::setup_datanode_plugins(plugins, &opts.plugins, dn_opts)
-            .await
-            .context(StartDatanodeSnafu)?;
-
-        dn_opts.grpc.detect_server_addr();
-
-        info!("Initialized Datanode instance with {:#?}", opts);
-        Ok(guard)
-    }
-
-    async fn datanode_builder(opts: &DatanodeOptions, plugins: Plugins) -> Result<DatanodeBuilder> {
-        let dn_opts = &opts.component;
-
-        let member_id = dn_opts
-            .node_id
-            .context(MissingConfigSnafu { msg: "'node_id'" })?;
-        let meta_client_options = dn_opts.meta_client.as_ref().context(MissingConfigSnafu {
-            msg: "meta client options",
-        })?;
-        let client = meta_client::create_meta_client(
-            MetaClientType::Datanode { member_id },
-            meta_client_options,
-            Some(&plugins),
-        )
-        .await
-        .context(MetaClientInitSnafu)?;
-
-        let backend = Arc::new(MetaKvBackend {
-            client: client.clone(),
-        });
-        let mut builder = DatanodeBuilder::new(dn_opts.clone(), plugins.clone(), backend.clone());
-
-        let registry = Arc::new(
-            LayeredCacheRegistryBuilder::default()
-                .add_cache_registry(build_datanode_cache_registry(backend))
-                .build(),
-        );
-        builder
-            .with_cache_registry(registry)
-            .with_meta_client(client.clone());
-        Ok(builder)
-    }
-
-    /// Get the mutable builder for Datanode, in case you want to change some fields before the
-    /// final construction.
-    pub fn mut_datanode_builder(&mut self) -> &mut DatanodeBuilder {
-        &mut self.datanode_builder
-    }
-
-    /// Try to build the Datanode instance.
-    pub async fn build(self) -> Result<Instance> {
-        let mut datanode = self
-            .datanode_builder
-            .build()
-            .await
-            .context(StartDatanodeSnafu)?;
-
-        let services = DatanodeServiceBuilder::new(&self.opts.component)
-            .with_default_grpc_server(&datanode.region_server())
-            .enable_http_service()
-            .build()
-            .context(StartDatanodeSnafu)?;
-        datanode.setup_services(services);
-
-        Ok(Instance::new(datanode, self.guard))
-    }
-}

src/cmd/src/error.rs

@@ -78,6 +78,13 @@ pub enum Error {
         source: datanode::error::Error,
     },
 
+    #[snafu(display("Failed to build object storage manager"))]
+    BuildObjectStorageManager {
+        #[snafu(implicit)]
+        location: Location,
+        source: datanode::error::Error,
+    },
+
     #[snafu(display("Failed to shutdown datanode"))]
     ShutdownDatanode {
         #[snafu(implicit)]
@@ -177,6 +184,9 @@ pub enum Error {
         source: meta_srv::error::Error,
     },
 
+    #[snafu(display("Invalid REPL command: {reason}"))]
+    InvalidReplCommand { reason: String },
+
     #[snafu(display("Failed to parse SQL: {}", sql))]
     ParseSql {
         sql: String,
@@ -325,9 +335,12 @@ impl ErrorExt for Error {
                 source.status_code()
             }
 
+            Error::BuildObjectStorageManager { source, .. } => source.status_code(),
+
             Error::MissingConfig { .. }
             | Error::LoadLayeredConfig { .. }
             | Error::IllegalConfig { .. }
+            | Error::InvalidReplCommand { .. }
             | Error::InitTimezone { .. }
             | Error::ConnectEtcd { .. }
             | Error::CreateDir { .. }

src/cmd/src/flownode.rs

@@ -33,8 +33,7 @@ use common_telemetry::info;
 use common_telemetry::logging::TracingOptions;
 use common_version::{short_version, version};
 use flow::{
-    get_flow_auth_options, FlownodeBuilder, FlownodeInstance, FlownodeServiceBuilder,
-    FrontendClient, FrontendInvoker,
+    FlownodeBuilder, FlownodeInstance, FlownodeServiceBuilder, FrontendClient, FrontendInvoker,
 };
 use meta_client::{MetaClientOptions, MetaClientType};
 use snafu::{ensure, OptionExt, ResultExt};
@@ -83,14 +82,10 @@ impl App for Instance {
     }
 
     async fn start(&mut self) -> Result<()> {
-        plugins::start_flownode_plugins(self.flownode.flow_engine().plugins().clone())
-            .await
-            .context(StartFlownodeSnafu)?;
-
         self.flownode.start().await.context(StartFlownodeSnafu)
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         self.flownode
             .shutdown()
             .await
@@ -156,9 +151,6 @@ struct StartCommand {
     /// HTTP request timeout in seconds.
     #[clap(long)]
     http_timeout: Option<u64>,
-    /// User Provider cfg, for auth, currently only support static user provider
-    #[clap(long)]
-    user_provider: Option<String>,
 }
 
 impl StartCommand {
@@ -222,10 +214,6 @@ impl StartCommand {
             opts.http.timeout = Duration::from_secs(http_timeout);
         }
 
-        if let Some(user_provider) = &self.user_provider {
-            opts.user_provider = Some(user_provider.clone());
-        }
-
         ensure!(
             opts.node_id.is_some(),
             MissingConfigSnafu {
@@ -244,22 +232,15 @@ impl StartCommand {
             &opts.component.logging,
             &opts.component.tracing,
             opts.component.node_id.map(|x| x.to_string()),
-            None,
         );
         log_versions(version(), short_version(), APP_NAME);
 
         info!("Flownode start command: {:#?}", self);
         info!("Flownode options: {:#?}", opts);
 
-        let plugin_opts = opts.plugins;
         let mut opts = opts.component;
         opts.grpc.detect_server_addr();
 
-        let mut plugins = Plugins::new();
-        plugins::setup_flownode_plugins(&mut plugins, &plugin_opts, &opts)
-            .await
-            .context(StartFlownodeSnafu)?;
-
         let member_id = opts
             .node_id
             .context(MissingConfigSnafu { msg: "'node_id'" })?;
@@ -334,12 +315,10 @@ impl StartCommand {
         );
 
         let flow_metadata_manager = Arc::new(FlowMetadataManager::new(cached_meta_backend.clone()));
-        let flow_auth_header = get_flow_auth_options(&opts).context(StartFlownodeSnafu)?;
-        let frontend_client =
-            FrontendClient::from_meta_client(meta_client.clone(), flow_auth_header);
+        let frontend_client = FrontendClient::from_meta_client(meta_client.clone());
         let flownode_builder = FlownodeBuilder::new(
             opts.clone(),
-            plugins,
+            Plugins::new(),
             table_metadata_manager,
             catalog_manager.clone(),
             flow_metadata_manager,
@@ -352,6 +331,7 @@ impl StartCommand {
             .with_grpc_server(flownode.flownode_server().clone())
             .enable_http_service()
             .build()
+            .await
             .context(StartFlownodeSnafu)?;
         flownode.setup_services(services);
         let flownode = flownode;
@@ -365,7 +345,7 @@ impl StartCommand {
         let client = Arc::new(NodeClients::new(channel_config));
 
         let invoker = FrontendInvoker::build_from(
-            flownode.flow_engine().streaming_engine(),
+            flownode.flow_worker_manager().clone(),
             catalog_manager.clone(),
             cached_meta_backend.clone(),
             layered_cache_registry.clone(),
@@ -375,9 +355,7 @@ impl StartCommand {
         .await
         .context(StartFlownodeSnafu)?;
         flownode
-            .flow_engine()
-            .streaming_engine()
-            // TODO(discord9): refactor and avoid circular reference
+            .flow_worker_manager()
             .set_frontend_invoker(invoker)
             .await;
 

src/cmd/src/frontend.rs

@@ -37,6 +37,7 @@ use frontend::heartbeat::HeartbeatTask;
 use frontend::instance::builder::FrontendBuilder;
 use frontend::server::Services;
 use meta_client::{MetaClientOptions, MetaClientType};
+use query::stats::StatementStatistics;
 use servers::export_metrics::ExportMetricsTask;
 use servers::tls::{TlsMode, TlsOption};
 use snafu::{OptionExt, ResultExt};
@@ -88,7 +89,7 @@ impl App for Instance {
             .context(error::StartFrontendSnafu)
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         self.frontend
             .shutdown()
             .await
@@ -268,7 +269,6 @@ impl StartCommand {
             &opts.component.logging,
             &opts.component.tracing,
             opts.component.node_id.clone(),
-            opts.component.slow_query.as_ref(),
         );
         log_versions(version(), short_version(), APP_NAME);
 
@@ -368,6 +368,7 @@ impl StartCommand {
             catalog_manager,
             Arc::new(client),
             meta_client,
+            StatementStatistics::new(opts.logging.slow_query.clone()),
         )
         .with_plugin(plugins.clone())
         .with_local_cache_invalidator(layered_cache_registry)
@@ -381,6 +382,7 @@ impl StartCommand {
 
         let servers = Services::new(opts, instance.clone(), plugins)
             .build()
+            .await
             .context(error::StartFrontendSnafu)?;
 
         let frontend = Frontend {
@@ -446,6 +448,8 @@ mod tests {
     fn test_read_from_config_file() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
+
             [http]
             addr = "127.0.0.1:4000"
             timeout = "0s"
@@ -534,6 +538,8 @@ mod tests {
     fn test_config_precedence_order() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
+
             [http]
             addr = "127.0.0.1:4000"
 

src/cmd/src/lib.rs

@@ -74,7 +74,7 @@ pub trait App: Send {
         true
     }
 
-    async fn stop(&mut self) -> Result<()>;
+    async fn stop(&self) -> Result<()>;
 
     async fn run(&mut self) -> Result<()> {
         info!("Starting app: {}", self.name());

src/cmd/src/metasrv.rs

@@ -12,7 +12,6 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::fmt;
 use std::time::Duration;
 
 use async_trait::async_trait;
@@ -69,7 +68,7 @@ impl App for Instance {
         self.instance.start().await.context(StartMetaServerSnafu)
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         self.instance
             .shutdown()
             .await
@@ -132,8 +131,8 @@ impl SubCommand {
     }
 }
 
-#[derive(Default, Parser)]
-pub struct StartCommand {
+#[derive(Debug, Default, Parser)]
+struct StartCommand {
     /// The address to bind the gRPC server.
     #[clap(long, alias = "bind-addr")]
     rpc_bind_addr: Option<String>,
@@ -172,29 +171,8 @@ pub struct StartCommand {
     backend: Option<BackendImpl>,
 }
 
-impl fmt::Debug for StartCommand {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        f.debug_struct("StartCommand")
-            .field("rpc_bind_addr", &self.rpc_bind_addr)
-            .field("rpc_server_addr", &self.rpc_server_addr)
-            .field("store_addrs", &self.sanitize_store_addrs())
-            .field("config_file", &self.config_file)
-            .field("selector", &self.selector)
-            .field("use_memory_store", &self.use_memory_store)
-            .field("enable_region_failover", &self.enable_region_failover)
-            .field("http_addr", &self.http_addr)
-            .field("http_timeout", &self.http_timeout)
-            .field("env_prefix", &self.env_prefix)
-            .field("data_home", &self.data_home)
-            .field("store_key_prefix", &self.store_key_prefix)
-            .field("max_txn_ops", &self.max_txn_ops)
-            .field("backend", &self.backend)
-            .finish()
-    }
-}
-
 impl StartCommand {
-    pub fn load_options(&self, global_options: &GlobalOptions) -> Result<MetasrvOptions> {
+    fn load_options(&self, global_options: &GlobalOptions) -> Result<MetasrvOptions> {
         let mut opts = MetasrvOptions::load_layered_options(
             self.config_file.as_deref(),
             self.env_prefix.as_ref(),
@@ -206,15 +184,6 @@ impl StartCommand {
         Ok(opts)
     }
 
-    fn sanitize_store_addrs(&self) -> Option<Vec<String>> {
-        self.store_addrs.as_ref().map(|addrs| {
-            addrs
-                .iter()
-                .map(|addr| common_meta::kv_backend::util::sanitize_connection_string(addr))
-                .collect()
-        })
-    }
-
     // The precedence order is: cli > config file > environment variables > default values.
     fn merge_with_cli_options(
         &self,
@@ -292,7 +261,7 @@ impl StartCommand {
         Ok(())
     }
 
-    pub async fn build(&self, opts: MetasrvOptions) -> Result<Instance> {
+    async fn build(&self, opts: MetasrvOptions) -> Result<Instance> {
         common_runtime::init_global_runtimes(&opts.runtime);
 
         let guard = common_telemetry::init_global_logging(
@@ -300,7 +269,6 @@ impl StartCommand {
             &opts.component.logging,
             &opts.component.tracing,
             None,
-            None,
         );
         log_versions(version(), short_version(), APP_NAME);
 

src/cmd/src/standalone.rs

@@ -35,8 +35,6 @@ use common_meta::ddl::flow_meta::{FlowMetadataAllocator, FlowMetadataAllocatorRe
 use common_meta::ddl::table_meta::{TableMetadataAllocator, TableMetadataAllocatorRef};
 use common_meta::ddl::{DdlContext, NoopRegionFailureDetectorControl, ProcedureExecutorRef};
 use common_meta::ddl_manager::DdlManager;
-#[cfg(feature = "enterprise")]
-use common_meta::ddl_manager::TriggerDdlManagerRef;
 use common_meta::key::flow::flow_state::FlowStat;
 use common_meta::key::flow::{FlowMetadataManager, FlowMetadataManagerRef};
 use common_meta::key::{TableMetadataManager, TableMetadataManagerRef};
@@ -46,10 +44,11 @@ use common_meta::peer::Peer;
 use common_meta::region_keeper::MemoryRegionKeeper;
 use common_meta::region_registry::LeaderRegionRegistry;
 use common_meta::sequence::SequenceBuilder;
+use common_meta::snapshot::MetadataSnapshotManager;
 use common_meta::wal_options_allocator::{build_wal_options_allocator, WalOptionsAllocatorRef};
 use common_procedure::{ProcedureInfo, ProcedureManagerRef};
 use common_telemetry::info;
-use common_telemetry::logging::{LoggingOptions, SlowQueryOptions, TracingOptions};
+use common_telemetry::logging::{LoggingOptions, TracingOptions};
 use common_time::timezone::set_default_timezone;
 use common_version::{short_version, version};
 use common_wal::config::DatanodeWalConfig;
@@ -58,8 +57,8 @@ use datanode::datanode::{Datanode, DatanodeBuilder};
 use datanode::region_server::RegionServer;
 use file_engine::config::EngineConfig as FileEngineConfig;
 use flow::{
-    FlowConfig, FlownodeBuilder, FlownodeInstance, FlownodeOptions, FrontendClient,
-    FrontendInvoker, GrpcQueryHandlerWithBoxedError, StreamingEngine,
+    FlowConfig, FlowWorkerManager, FlownodeBuilder, FlownodeInstance, FlownodeOptions,
+    FrontendClient, FrontendInvoker,
 };
 use frontend::frontend::{Frontend, FrontendOptions};
 use frontend::instance::builder::FrontendBuilder;
@@ -71,12 +70,13 @@ use frontend::service_config::{
 };
 use meta_srv::metasrv::{FLOW_ID_SEQ, TABLE_ID_SEQ};
 use mito2::config::MitoConfig;
-use query::options::QueryOptions;
+use query::stats::StatementStatistics;
 use serde::{Deserialize, Serialize};
 use servers::export_metrics::{ExportMetricsOption, ExportMetricsTask};
 use servers::grpc::GrpcOptions;
 use servers::http::HttpOptions;
 use servers::tls::{TlsMode, TlsOption};
+use servers::Mode;
 use snafu::ResultExt;
 use tokio::sync::RwLock;
 use tracing_appender::non_blocking::WorkerGuard;
@@ -155,8 +155,6 @@ pub struct StandaloneOptions {
     pub init_regions_in_background: bool,
     pub init_regions_parallelism: usize,
     pub max_in_flight_write_bytes: Option<ReadableSize>,
-    pub slow_query: Option<SlowQueryOptions>,
-    pub query: QueryOptions,
 }
 
 impl Default for StandaloneOptions {
@@ -188,8 +186,6 @@ impl Default for StandaloneOptions {
             init_regions_in_background: false,
             init_regions_parallelism: 16,
             max_in_flight_write_bytes: None,
-            slow_query: Some(SlowQueryOptions::default()),
-            query: QueryOptions::default(),
         }
     }
 }
@@ -229,7 +225,6 @@ impl StandaloneOptions {
             // Handle the export metrics task run by standalone to frontend for execution
             export_metrics: cloned_opts.export_metrics,
             max_in_flight_write_bytes: cloned_opts.max_in_flight_write_bytes,
-            slow_query: cloned_opts.slow_query,
             ..Default::default()
         }
     }
@@ -245,7 +240,6 @@ impl StandaloneOptions {
             grpc: cloned_opts.grpc,
             init_regions_in_background: cloned_opts.init_regions_in_background,
             init_regions_parallelism: cloned_opts.init_regions_parallelism,
-            query: cloned_opts.query,
             ..Default::default()
         }
     }
@@ -263,8 +257,8 @@ pub struct Instance {
 
 impl Instance {
     /// Find the socket addr of a server by its `name`.
-    pub fn server_addr(&self, name: &str) -> Option<SocketAddr> {
-        self.frontend.server_handlers().addr(name)
+    pub async fn server_addr(&self, name: &str) -> Option<SocketAddr> {
+        self.frontend.server_handlers().addr(name).await
     }
 }
 
@@ -301,7 +295,7 @@ impl App for Instance {
         Ok(())
     }
 
-    async fn stop(&mut self) -> Result<()> {
+    async fn stop(&self) -> Result<()> {
         self.frontend
             .shutdown()
             .await
@@ -455,7 +449,6 @@ impl StartCommand {
             &opts.component.logging,
             &opts.component.tracing,
             None,
-            opts.component.slow_query.as_ref(),
         );
         log_versions(version(), short_version(), APP_NAME);
 
@@ -505,9 +498,16 @@ impl StartCommand {
             .build(),
         );
 
-        let mut builder = DatanodeBuilder::new(dn_opts, plugins.clone(), kv_backend.clone());
-        builder.with_cache_registry(layered_cache_registry.clone());
-        let datanode = builder.build().await.context(error::StartDatanodeSnafu)?;
+        let object_store_manager = DatanodeBuilder::build_object_store_manager(&dn_opts.storage)
+            .await
+            .context(error::BuildObjectStorageManagerSnafu)?;
+
+        let datanode = DatanodeBuilder::new(dn_opts, plugins.clone(), Mode::Standalone)
+            .with_kv_backend(kv_backend.clone())
+            .with_cache_registry(layered_cache_registry.clone())
+            .build()
+            .await
+            .context(error::StartDatanodeSnafu)?;
 
         let information_extension = Arc::new(StandaloneInformationExtension::new(
             datanode.region_server(),
@@ -529,17 +529,17 @@ impl StartCommand {
             ..Default::default()
         };
 
-        // for standalone not use grpc, but get a handler to frontend grpc client without
+        // TODO(discord9): for standalone not use grpc, but just somehow get a handler to frontend grpc client without
         // actually make a connection
-        let (frontend_client, frontend_instance_handler) =
-            FrontendClient::from_empty_grpc_handler();
+        let fe_server_addr = fe_opts.grpc.bind_addr.clone();
+        let frontend_client = FrontendClient::from_static_grpc_addr(fe_server_addr);
         let flow_builder = FlownodeBuilder::new(
             flownode_options,
             plugins.clone(),
             table_metadata_manager.clone(),
             catalog_manager.clone(),
             flow_metadata_manager.clone(),
-            Arc::new(frontend_client.clone()),
+            Arc::new(frontend_client),
         );
         let flownode = flow_builder
             .build()
@@ -549,15 +549,15 @@ impl StartCommand {
 
         // set the ref to query for the local flow state
         {
-            let flow_streaming_engine = flownode.flow_engine().streaming_engine();
+            let flow_worker_manager = flownode.flow_worker_manager();
             information_extension
-                .set_flow_streaming_engine(flow_streaming_engine)
+                .set_flow_worker_manager(flow_worker_manager.clone())
                 .await;
         }
 
         let node_manager = Arc::new(StandaloneDatanodeManager {
             region_server: datanode.region_server(),
-            flow_server: flownode.flow_engine(),
+            flow_server: flownode.flow_worker_manager(),
         });
 
         let table_id_sequence = Arc::new(
@@ -585,8 +585,6 @@ impl StartCommand {
             flow_id_sequence,
         ));
 
-        #[cfg(feature = "enterprise")]
-        let trigger_ddl_manager: Option<TriggerDdlManagerRef> = plugins.get();
         let ddl_task_executor = Self::create_ddl_task_executor(
             procedure_manager.clone(),
             node_manager.clone(),
@@ -595,11 +593,14 @@ impl StartCommand {
             table_meta_allocator,
             flow_metadata_manager,
             flow_meta_allocator,
-            #[cfg(feature = "enterprise")]
-            trigger_ddl_manager,
         )
         .await?;
 
+        let metadata_snapshot_manager = MetadataSnapshotManager::new(
+            kv_backend.clone(),
+            object_store_manager.default_object_store().clone(),
+        );
+
         let fe_instance = FrontendBuilder::new(
             fe_opts.clone(),
             kv_backend.clone(),
@@ -607,26 +608,19 @@ impl StartCommand {
             catalog_manager.clone(),
             node_manager.clone(),
             ddl_task_executor.clone(),
+            StatementStatistics::new(opts.logging.slow_query.clone()),
         )
         .with_plugin(plugins.clone())
+        .with_metadata_snapshot_manager(metadata_snapshot_manager)
         .try_build()
         .await
         .context(error::StartFrontendSnafu)?;
         let fe_instance = Arc::new(fe_instance);
 
-        // set the frontend client for flownode
-        let grpc_handler = fe_instance.clone() as Arc<dyn GrpcQueryHandlerWithBoxedError>;
-        let weak_grpc_handler = Arc::downgrade(&grpc_handler);
-        frontend_instance_handler
-            .lock()
-            .unwrap()
-            .replace(weak_grpc_handler);
-
-        // set the frontend invoker for flownode
-        let flow_streaming_engine = flownode.flow_engine().streaming_engine();
+        let flow_worker_manager = flownode.flow_worker_manager();
         // flow server need to be able to use frontend to write insert requests back
         let invoker = FrontendInvoker::build_from(
-            flow_streaming_engine.clone(),
+            flow_worker_manager.clone(),
             catalog_manager.clone(),
             kv_backend.clone(),
             layered_cache_registry.clone(),
@@ -635,13 +629,14 @@ impl StartCommand {
         )
         .await
         .context(error::StartFlownodeSnafu)?;
-        flow_streaming_engine.set_frontend_invoker(invoker).await;
+        flow_worker_manager.set_frontend_invoker(invoker).await;
 
         let export_metrics_task = ExportMetricsTask::try_new(&opts.export_metrics, Some(&plugins))
             .context(error::ServersSnafu)?;
 
         let servers = Services::new(opts, fe_instance.clone(), plugins)
             .build()
+            .await
             .context(error::StartFrontendSnafu)?;
 
         let frontend = Frontend {
@@ -661,7 +656,6 @@ impl StartCommand {
         })
     }
 
-    #[allow(clippy::too_many_arguments)]
     pub async fn create_ddl_task_executor(
         procedure_manager: ProcedureManagerRef,
         node_manager: NodeManagerRef,
@@ -670,7 +664,6 @@ impl StartCommand {
         table_metadata_allocator: TableMetadataAllocatorRef,
         flow_metadata_manager: FlowMetadataManagerRef,
         flow_metadata_allocator: FlowMetadataAllocatorRef,
-        #[cfg(feature = "enterprise")] trigger_ddl_manager: Option<TriggerDdlManagerRef>,
     ) -> Result<ProcedureExecutorRef> {
         let procedure_executor: ProcedureExecutorRef = Arc::new(
             DdlManager::try_new(
@@ -687,8 +680,6 @@ impl StartCommand {
                 },
                 procedure_manager,
                 true,
-                #[cfg(feature = "enterprise")]
-                trigger_ddl_manager,
             )
             .context(error::InitDdlManagerSnafu)?,
         );
@@ -714,7 +705,7 @@ pub struct StandaloneInformationExtension {
     region_server: RegionServer,
     procedure_manager: ProcedureManagerRef,
     start_time_ms: u64,
-    flow_streaming_engine: RwLock<Option<Arc<StreamingEngine>>>,
+    flow_worker_manager: RwLock<Option<Arc<FlowWorkerManager>>>,
 }
 
 impl StandaloneInformationExtension {
@@ -723,14 +714,14 @@ impl StandaloneInformationExtension {
             region_server,
             procedure_manager,
             start_time_ms: common_time::util::current_time_millis() as u64,
-            flow_streaming_engine: RwLock::new(None),
+            flow_worker_manager: RwLock::new(None),
         }
     }
 
-    /// Set the flow streaming engine for the standalone instance.
-    pub async fn set_flow_streaming_engine(&self, flow_streaming_engine: Arc<StreamingEngine>) {
-        let mut guard = self.flow_streaming_engine.write().await;
-        *guard = Some(flow_streaming_engine);
+    /// Set the flow worker manager for the standalone instance.
+    pub async fn set_flow_worker_manager(&self, flow_worker_manager: Arc<FlowWorkerManager>) {
+        let mut guard = self.flow_worker_manager.write().await;
+        *guard = Some(flow_worker_manager);
     }
 }
 
@@ -809,7 +800,7 @@ impl InformationExtension for StandaloneInformationExtension {
 
     async fn flow_stats(&self) -> std::result::Result<Option<FlowStat>, Self::Error> {
         Ok(Some(
-            self.flow_streaming_engine
+            self.flow_worker_manager
                 .read()
                 .await
                 .as_ref()
@@ -869,6 +860,8 @@ mod tests {
     fn test_read_from_config_file() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
+
             enable_memory_catalog = true
 
             [wal]
@@ -999,6 +992,8 @@ mod tests {
     fn test_config_precedence_order() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "standalone"
+
             [http]
             addr = "127.0.0.1:4000"
 

src/cmd/tests/load_config_test.rs

@@ -18,7 +18,7 @@ use cmd::options::GreptimeOptions;
 use cmd::standalone::StandaloneOptions;
 use common_config::Configurable;
 use common_options::datanode::{ClientOptions, DatanodeClientOptions};
-use common_telemetry::logging::{LoggingOptions, DEFAULT_OTLP_ENDPOINT};
+use common_telemetry::logging::{LoggingOptions, SlowQueryOptions, DEFAULT_OTLP_ENDPOINT};
 use common_wal::config::raft_engine::RaftEngineConfig;
 use common_wal::config::DatanodeWalConfig;
 use datanode::config::{DatanodeOptions, RegionEngineConfig, StorageConfig};
@@ -74,7 +74,6 @@ fn test_load_datanode_example_config() {
                 RegionEngineConfig::File(FileEngineConfig {}),
                 RegionEngineConfig::Metric(MetricEngineConfig {
                     experimental_sparse_primary_key_encoding: false,
-                    flush_metadata_region_interval: Duration::from_secs(30),
                 }),
             ],
             logging: LoggingOptions {
@@ -167,6 +166,11 @@ fn test_load_metasrv_example_config() {
                 level: Some("info".to_string()),
                 otlp_endpoint: Some(DEFAULT_OTLP_ENDPOINT.to_string()),
                 tracing_sample_ratio: Some(Default::default()),
+                slow_query: SlowQueryOptions {
+                    enable: false,
+                    threshold: None,
+                    sample_ratio: None,
+                },
                 ..Default::default()
             },
             datanode: DatanodeClientOptions {
@@ -212,7 +216,6 @@ fn test_load_standalone_example_config() {
                 RegionEngineConfig::File(FileEngineConfig {}),
                 RegionEngineConfig::Metric(MetricEngineConfig {
                     experimental_sparse_primary_key_encoding: false,
-                    flush_metadata_region_interval: Duration::from_secs(30),
                 }),
             ],
             storage: StorageConfig {

src/common/base/src/plugins.rs

@@ -31,8 +31,7 @@ impl Plugins {
     }
 
     pub fn insert<T: 'static + Send + Sync>(&self, value: T) {
-        let last = self.write().insert(value);
-        assert!(last.is_none(), "each type of plugins must be one and only");
+        let _ = self.write().insert(value);
     }
 
     pub fn get<T: 'static + Send + Sync + Clone>(&self) -> Option<T> {
@@ -138,12 +137,4 @@ mod tests {
         assert_eq!(plugins.len(), 2);
         assert!(!plugins.is_empty());
     }
-
-    #[test]
-    #[should_panic(expected = "each type of plugins must be one and only")]
-    fn test_plugin_uniqueness() {
-        let plugins = Plugins::new();
-        plugins.insert(1i32);
-        plugins.insert(2i32);
-    }
 }

src/common/config/src/config.rs

@@ -111,9 +111,11 @@ mod tests {
     use serde::{Deserialize, Serialize};
 
     use super::*;
+    use crate::Mode;
 
-    #[derive(Debug, Serialize, Deserialize, Default)]
+    #[derive(Debug, Serialize, Deserialize)]
     struct TestDatanodeConfig {
+        mode: Mode,
         node_id: Option<u64>,
         logging: LoggingOptions,
         meta_client: Option<MetaClientOptions>,
@@ -121,6 +123,19 @@ mod tests {
         storage: StorageConfig,
     }
 
+    impl Default for TestDatanodeConfig {
+        fn default() -> Self {
+            Self {
+                mode: Mode::Distributed,
+                node_id: None,
+                logging: LoggingOptions::default(),
+                meta_client: None,
+                wal: DatanodeWalConfig::default(),
+                storage: StorageConfig::default(),
+            }
+        }
+    }
+
     impl Configurable for TestDatanodeConfig {
         fn env_list_keys() -> Option<&'static [&'static str]> {
             Some(&["meta_client.metasrv_addrs"])
@@ -131,6 +146,7 @@ mod tests {
     fn test_load_layered_options() {
         let mut file = create_named_temp_file();
         let toml_str = r#"
+            mode = "distributed"
             enable_memory_catalog = false
             rpc_addr = "127.0.0.1:3001"
             rpc_hostname = "127.0.0.1"

src/common/config/src/lib.rs

@@ -26,6 +26,16 @@ pub fn metadata_store_dir(store_dir: &str) -> String {
     format!("{store_dir}/metadata")
 }
 
+/// The Server running mode
+#[derive(Clone, Debug, Serialize, Deserialize, Eq, PartialEq, Copy)]
+#[serde(rename_all = "lowercase")]
+pub enum Mode {
+    // The single process mode.
+    Standalone,
+    // The distributed cluster mode.
+    Distributed,
+}
+
 #[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
 #[serde(default)]
 pub struct KvBackendConfig {

src/common/function/Cargo.toml

@@ -13,7 +13,7 @@ default = ["geo"]
 geo = ["geohash", "h3o", "s2", "wkt", "geo-types", "dep:geo"]
 
 [dependencies]
-ahash.workspace = true
+ahash = "0.8"
 api.workspace = true
 arc-swap = "1.0"
 async-trait.workspace = true

src/common/function/src/adjust_flow.rs

@@ -1,90 +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_macro::admin_fn;
-use common_query::error::{
-    InvalidFuncArgsSnafu, MissingFlowServiceHandlerSnafu, Result, UnsupportedInputDataTypeSnafu,
-};
-use common_query::prelude::Signature;
-use datafusion::logical_expr::Volatility;
-use datatypes::value::{Value, ValueRef};
-use session::context::QueryContextRef;
-use snafu::ensure;
-use store_api::storage::ConcreteDataType;
-
-use crate::handlers::FlowServiceHandlerRef;
-use crate::helper::parse_catalog_flow;
-
-fn adjust_signature() -> Signature {
-    Signature::exact(
-        vec![
-            ConcreteDataType::string_datatype(), // flow name
-            ConcreteDataType::uint64_datatype(), // min_run_interval in seconds
-            ConcreteDataType::uint64_datatype(), // max filter number per query
-        ],
-        Volatility::Immutable,
-    )
-}
-
-#[admin_fn(
-    name = AdjustFlowFunction,
-    display_name = adjust_flow,
-    sig_fn = adjust_signature,
-    ret = uint64
-)]
-pub(crate) async fn adjust_flow(
-    flow_service_handler: &FlowServiceHandlerRef,
-    query_ctx: &QueryContextRef,
-    params: &[ValueRef<'_>],
-) -> Result<Value> {
-    ensure!(
-        params.len() == 3,
-        InvalidFuncArgsSnafu {
-            err_msg: format!(
-                "The length of the args is not correct, expect 3, have: {}",
-                params.len()
-            ),
-        }
-    );
-
-    let (flow_name, min_run_interval, max_filter_num) = match (params[0], params[1], params[2]) {
-        (
-            ValueRef::String(flow_name),
-            ValueRef::UInt64(min_run_interval),
-            ValueRef::UInt64(max_filter_num),
-        ) => (flow_name, min_run_interval, max_filter_num),
-        _ => {
-            return UnsupportedInputDataTypeSnafu {
-                function: "adjust_flow",
-                datatypes: params.iter().map(|v| v.data_type()).collect::<Vec<_>>(),
-            }
-            .fail();
-        }
-    };
-
-    let (catalog_name, flow_name) = parse_catalog_flow(flow_name, query_ctx)?;
-
-    let res = flow_service_handler
-        .adjust(
-            &catalog_name,
-            &flow_name,
-            min_run_interval,
-            max_filter_num as usize,
-            query_ctx.clone(),
-        )
-        .await?;
-    let affected_rows = res.affected_rows;
-
-    Ok(Value::from(affected_rows))
-}

src/common/function/src/admin.rs

@@ -15,6 +15,7 @@
 mod add_region_follower;
 mod flush_compact_region;
 mod flush_compact_table;
+mod metadata_snaphost;
 mod migrate_region;
 mod remove_region_follower;
 
@@ -23,10 +24,10 @@ use std::sync::Arc;
 use add_region_follower::AddRegionFollowerFunction;
 use flush_compact_region::{CompactRegionFunction, FlushRegionFunction};
 use flush_compact_table::{CompactTableFunction, FlushTableFunction};
+use metadata_snaphost::{DumpMetadataFunction, RestoreMetadataFunction};
 use migrate_region::MigrateRegionFunction;
 use remove_region_follower::RemoveRegionFollowerFunction;
 
-use crate::adjust_flow::AdjustFlowFunction;
 use crate::flush_flow::FlushFlowFunction;
 use crate::function_registry::FunctionRegistry;
 
@@ -44,6 +45,7 @@ impl AdminFunction {
         registry.register_async(Arc::new(FlushTableFunction));
         registry.register_async(Arc::new(CompactTableFunction));
         registry.register_async(Arc::new(FlushFlowFunction));
-        registry.register_async(Arc::new(AdjustFlowFunction));
+        registry.register_async(Arc::new(DumpMetadataFunction));
+        registry.register_async(Arc::new(RestoreMetadataFunction));
     }
 }

src/common/function/src/admin/metadata_snaphost.rs

@@ -0,0 +1,56 @@
+use common_macro::admin_fn;
+use common_query::error::{MissingMetadataSnapshotHandlerSnafu, Result};
+use common_query::prelude::{Signature, Volatility};
+use datatypes::prelude::*;
+use session::context::QueryContextRef;
+
+use crate::handlers::MetadataSnapshotHandlerRef;
+
+const METADATA_DIR: &str = "/snaphost/";
+const METADATA_FILE_NAME: &str = "dump_metadata";
+const METADATA_FILE_EXTENSION: &str = "metadata.fb";
+
+#[admin_fn(
+    name = DumpMetadataFunction,
+    display_name = dump_metadata,
+    sig_fn = dump_signature,
+    ret = string
+)]
+pub(crate) async fn dump_metadata(
+    metadata_snapshot_handler: &MetadataSnapshotHandlerRef,
+    _query_ctx: &QueryContextRef,
+    _params: &[ValueRef<'_>],
+) -> Result<Value> {
+    let filename = metadata_snapshot_handler
+        .dump(METADATA_DIR, METADATA_FILE_NAME)
+        .await?;
+    Ok(Value::from(filename))
+}
+
+fn dump_signature() -> Signature {
+    Signature::uniform(0, vec![], Volatility::Immutable)
+}
+
+#[admin_fn(
+    name = RestoreMetadataFunction,
+    display_name = restore_metadata,
+    sig_fn = restore_signature,
+    ret = uint64,
+)]
+pub(crate) async fn restore_metadata(
+    metadata_snapshot_handler: &MetadataSnapshotHandlerRef,
+    _query_ctx: &QueryContextRef,
+    _params: &[ValueRef<'_>],
+) -> Result<Value> {
+    let num_keyvalues = metadata_snapshot_handler
+        .restore(
+            METADATA_DIR,
+            &format!("{METADATA_FILE_NAME}.{METADATA_FILE_EXTENSION}"),
+        )
+        .await?;
+    Ok(Value::from(num_keyvalues))
+}
+
+fn restore_signature() -> Signature {
+    Signature::uniform(0, vec![], Volatility::Immutable)
+}

src/common/function/src/aggr.rs

@@ -19,4 +19,4 @@ mod uddsketch_state;
 pub use geo_path::{GeoPathAccumulator, GEO_PATH_NAME};
 pub(crate) use hll::HllStateType;
 pub use hll::{HllState, HLL_MERGE_NAME, HLL_NAME};
-pub use uddsketch_state::{UddSketchState, UDDSKETCH_MERGE_NAME, UDDSKETCH_STATE_NAME};
+pub use uddsketch_state::{UddSketchState, UDDSKETCH_STATE_NAME};

src/common/function/src/aggr/uddsketch_state.rs

@@ -31,28 +31,23 @@ use datafusion::physical_plan::expressions::Literal;
 use datafusion::prelude::create_udaf;
 use datatypes::arrow::array::ArrayRef;
 use datatypes::arrow::datatypes::{DataType, Float64Type};
-use serde::{Deserialize, Serialize};
 use uddsketch::{SketchHashKey, UDDSketch};
 
 pub const UDDSKETCH_STATE_NAME: &str = "uddsketch_state";
 
-pub const UDDSKETCH_MERGE_NAME: &str = "uddsketch_merge";
-
-#[derive(Debug, Serialize, Deserialize)]
+#[derive(Debug)]
 pub struct UddSketchState {
     uddsketch: UDDSketch,
-    error_rate: f64,
 }
 
 impl UddSketchState {
     pub fn new(bucket_size: u64, error_rate: f64) -> Self {
         Self {
             uddsketch: UDDSketch::new(bucket_size, error_rate),
-            error_rate,
         }
     }
 
-    pub fn state_udf_impl() -> AggregateUDF {
+    pub fn udf_impl() -> AggregateUDF {
         create_udaf(
             UDDSKETCH_STATE_NAME,
             vec![DataType::Int64, DataType::Float64, DataType::Float64],
@@ -66,55 +61,18 @@ impl UddSketchState {
         )
     }
 
-    /// Create a UDF for the `uddsketch_merge` function.
-    ///
-    /// `uddsketch_merge` accepts bucket size, error rate, and a binary column of states generated by `uddsketch_state`
-    /// and merges them into a single state.
-    ///
-    /// The bucket size and error rate must be the same as the original state.
-    pub fn merge_udf_impl() -> AggregateUDF {
-        create_udaf(
-            UDDSKETCH_MERGE_NAME,
-            vec![DataType::Int64, DataType::Float64, DataType::Binary],
-            Arc::new(DataType::Binary),
-            Volatility::Immutable,
-            Arc::new(|args| {
-                let (bucket_size, error_rate) = downcast_accumulator_args(args)?;
-                Ok(Box::new(UddSketchState::new(bucket_size, error_rate)))
-            }),
-            Arc::new(vec![DataType::Binary]),
-        )
-    }
-
     fn update(&mut self, value: f64) {
         self.uddsketch.add_value(value);
     }
 
-    fn merge(&mut self, raw: &[u8]) -> DfResult<()> {
-        if let Ok(uddsketch) = bincode::deserialize::<Self>(raw) {
-            if uddsketch.uddsketch.count() != 0 {
-                if self.uddsketch.max_allowed_buckets() != uddsketch.uddsketch.max_allowed_buckets()
-                    || (self.error_rate - uddsketch.error_rate).abs() >= 1e-9
-                {
-                    return Err(DataFusionError::Plan(format!(
-                        "Merging UDDSketch with different parameters: arguments={:?} vs actual input={:?}",
-                        (
-                            self.uddsketch.max_allowed_buckets(),
-                            self.error_rate
-                        ),
-                        (uddsketch.uddsketch.max_allowed_buckets(), uddsketch.error_rate)
-                    )));
-                }
-                self.uddsketch.merge_sketch(&uddsketch.uddsketch);
+    fn merge(&mut self, raw: &[u8]) {
+        if let Ok(uddsketch) = bincode::deserialize::<UDDSketch>(raw) {
+            if uddsketch.count() != 0 {
+                self.uddsketch.merge_sketch(&uddsketch);
             }
         } else {
             trace!("Warning: Failed to deserialize UDDSketch from {:?}", raw);
-            return Err(DataFusionError::Plan(
-                "Failed to deserialize UDDSketch from binary".to_string(),
-            ));
         }
-
-        Ok(())
     }
 }
 
@@ -155,21 +113,9 @@ fn downcast_accumulator_args(args: AccumulatorArgs) -> DfResult<(u64, f64)> {
 impl DfAccumulator for UddSketchState {
     fn update_batch(&mut self, values: &[ArrayRef]) -> DfResult<()> {
         let array = &values[2]; // the third column is data value
-        match array.data_type() {
-            DataType::Float64 => {
-                let f64_array = as_primitive_array::<Float64Type>(array)?;
-                for v in f64_array.iter().flatten() {
-                    self.update(v);
-                }
-            }
-            // meaning instantiate as `uddsketch_merge`
-            DataType::Binary => self.merge_batch(std::slice::from_ref(array))?,
-            _ => {
-                return not_impl_err!(
-                    "UDDSketch functions do not support data type: {}",
-                    array.data_type()
-                )
-            }
+        let f64_array = as_primitive_array::<Float64Type>(array)?;
+        for v in f64_array.iter().flatten() {
+            self.update(v);
         }
 
         Ok(())
@@ -177,7 +123,7 @@ impl DfAccumulator for UddSketchState {
 
     fn evaluate(&mut self) -> DfResult<ScalarValue> {
         Ok(ScalarValue::Binary(Some(
-            bincode::serialize(&self).map_err(|e| {
+            bincode::serialize(&self.uddsketch).map_err(|e| {
                 DataFusionError::Internal(format!("Failed to serialize UDDSketch: {}", e))
             })?,
         )))
@@ -204,7 +150,7 @@ impl DfAccumulator for UddSketchState {
 
     fn state(&mut self) -> DfResult<Vec<ScalarValue>> {
         Ok(vec![ScalarValue::Binary(Some(
-            bincode::serialize(&self).map_err(|e| {
+            bincode::serialize(&self.uddsketch).map_err(|e| {
                 DataFusionError::Internal(format!("Failed to serialize UDDSketch: {}", e))
             })?,
         ))])
@@ -214,7 +160,7 @@ impl DfAccumulator for UddSketchState {
         let array = &states[0];
         let binary_array = as_binary_array(array)?;
         for v in binary_array.iter().flatten() {
-            self.merge(v)?;
+            self.merge(v);
         }
 
         Ok(())
@@ -236,8 +182,8 @@ mod tests {
 
         let result = state.evaluate().unwrap();
         if let ScalarValue::Binary(Some(bytes)) = result {
-            let deserialized: UddSketchState = bincode::deserialize(&bytes).unwrap();
-            assert_eq!(deserialized.uddsketch.count(), 3);
+            let deserialized: UDDSketch = bincode::deserialize(&bytes).unwrap();
+            assert_eq!(deserialized.count(), 3);
         } else {
             panic!("Expected binary scalar value");
         }
@@ -255,15 +201,13 @@ mod tests {
         // Create new state and merge the serialized data
         let mut new_state = UddSketchState::new(10, 0.01);
         if let ScalarValue::Binary(Some(bytes)) = &serialized {
-            new_state.merge(bytes).unwrap();
+            new_state.merge(bytes);
 
             // Verify the merged state matches original by comparing deserialized values
-            let original_sketch: UddSketchState = bincode::deserialize(bytes).unwrap();
-            let original_sketch = original_sketch.uddsketch;
+            let original_sketch: UDDSketch = bincode::deserialize(bytes).unwrap();
             let new_result = new_state.evaluate().unwrap();
             if let ScalarValue::Binary(Some(new_bytes)) = new_result {
-                let new_sketch: UddSketchState = bincode::deserialize(&new_bytes).unwrap();
-                let new_sketch = new_sketch.uddsketch;
+                let new_sketch: UDDSketch = bincode::deserialize(&new_bytes).unwrap();
                 assert_eq!(original_sketch.count(), new_sketch.count());
                 assert_eq!(original_sketch.sum(), new_sketch.sum());
                 assert_eq!(original_sketch.mean(), new_sketch.mean());
@@ -300,8 +244,7 @@ mod tests {
 
         let result = state.evaluate().unwrap();
         if let ScalarValue::Binary(Some(bytes)) = result {
-            let deserialized: UddSketchState = bincode::deserialize(&bytes).unwrap();
-            let deserialized = deserialized.uddsketch;
+            let deserialized: UDDSketch = bincode::deserialize(&bytes).unwrap();
             assert_eq!(deserialized.count(), 3);
         } else {
             panic!("Expected binary scalar value");
@@ -330,8 +273,7 @@ mod tests {
 
             let result = merged_state.evaluate().unwrap();
             if let ScalarValue::Binary(Some(bytes)) = result {
-                let deserialized: UddSketchState = bincode::deserialize(&bytes).unwrap();
-                let deserialized = deserialized.uddsketch;
+                let deserialized: UDDSketch = bincode::deserialize(&bytes).unwrap();
                 assert_eq!(deserialized.count(), 2);
             } else {
                 panic!("Expected binary scalar value");

src/common/function/src/flush_flow.rs

@@ -12,19 +12,21 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use common_error::ext::BoxedError;
 use common_macro::admin_fn;
 use common_query::error::{
-    InvalidFuncArgsSnafu, MissingFlowServiceHandlerSnafu, Result, UnsupportedInputDataTypeSnafu,
+    ExecuteSnafu, InvalidFuncArgsSnafu, MissingFlowServiceHandlerSnafu, Result,
+    UnsupportedInputDataTypeSnafu,
 };
 use common_query::prelude::Signature;
 use datafusion::logical_expr::Volatility;
 use datatypes::value::{Value, ValueRef};
 use session::context::QueryContextRef;
-use snafu::ensure;
+use snafu::{ensure, ResultExt};
+use sql::parser::ParserContext;
 use store_api::storage::ConcreteDataType;
 
 use crate::handlers::FlowServiceHandlerRef;
-use crate::helper::parse_catalog_flow;
 
 fn flush_signature() -> Signature {
     Signature::uniform(
@@ -45,6 +47,20 @@ pub(crate) async fn flush_flow(
     query_ctx: &QueryContextRef,
     params: &[ValueRef<'_>],
 ) -> Result<Value> {
+    let (catalog_name, flow_name) = parse_flush_flow(params, query_ctx)?;
+
+    let res = flow_service_handler
+        .flush(&catalog_name, &flow_name, query_ctx.clone())
+        .await?;
+    let affected_rows = res.affected_rows;
+
+    Ok(Value::from(affected_rows))
+}
+
+fn parse_flush_flow(
+    params: &[ValueRef<'_>],
+    query_ctx: &QueryContextRef,
+) -> Result<(String, String)> {
     ensure!(
         params.len() == 1,
         InvalidFuncArgsSnafu {
@@ -54,6 +70,7 @@ pub(crate) async fn flush_flow(
             ),
         }
     );
+
     let ValueRef::String(flow_name) = params[0] else {
         return UnsupportedInputDataTypeSnafu {
             function: "flush_flow",
@@ -61,14 +78,27 @@ pub(crate) async fn flush_flow(
         }
         .fail();
     };
-    let (catalog_name, flow_name) = parse_catalog_flow(flow_name, query_ctx)?;
+    let obj_name = ParserContext::parse_table_name(flow_name, query_ctx.sql_dialect())
+        .map_err(BoxedError::new)
+        .context(ExecuteSnafu)?;
 
-    let res = flow_service_handler
-        .flush(&catalog_name, &flow_name, query_ctx.clone())
-        .await?;
-    let affected_rows = res.affected_rows;
-
-    Ok(Value::from(affected_rows))
+    let (catalog_name, flow_name) = match &obj_name.0[..] {
+        [flow_name] => (
+            query_ctx.current_catalog().to_string(),
+            flow_name.value.clone(),
+        ),
+        [catalog, flow_name] => (catalog.value.clone(), flow_name.value.clone()),
+        _ => {
+            return InvalidFuncArgsSnafu {
+                err_msg: format!(
+                    "expect flow name to be <catalog>.<flow-name> or <flow-name>, actual: {}",
+                    obj_name
+                ),
+            }
+            .fail()
+        }
+    };
+    Ok((catalog_name, flow_name))
 }
 
 #[cfg(test)]
@@ -124,7 +154,10 @@ mod test {
             ("catalog.flow_name", ("catalog", "flow_name")),
         ];
         for (input, expected) in testcases.iter() {
-            let result = parse_catalog_flow(input, &QueryContext::arc()).unwrap();
+            let args = vec![*input];
+            let args = args.into_iter().map(ValueRef::String).collect::<Vec<_>>();
+
+            let result = parse_flush_flow(&args, &QueryContext::arc()).unwrap();
             assert_eq!(*expected, (result.0.as_str(), result.1.as_str()));
         }
     }

src/common/function/src/handlers.rs

@@ -87,15 +87,14 @@ pub trait FlowServiceHandler: Send + Sync {
         flow: &str,
         ctx: QueryContextRef,
     ) -> Result<api::v1::flow::FlowResponse>;
+}
 
-    async fn adjust(
-        &self,
-        catalog: &str,
-        flow: &str,
-        min_run_interval_secs: u64,
-        max_filter_num_per_query: usize,
-        ctx: QueryContextRef,
-    ) -> Result<api::v1::flow::FlowResponse>;
+/// This metadata snapshot handler is only use for dump and restore metadata for now.
+#[async_trait]
+pub trait MetadataSnapshotHandler: Send + Sync {
+    async fn dump(&self, path: &str, filename: &str) -> Result<String>;
+
+    async fn restore(&self, path: &str, filename: &str) -> Result<u64>;
 }
 
 pub type TableMutationHandlerRef = Arc<dyn TableMutationHandler>;
@@ -103,3 +102,5 @@ pub type TableMutationHandlerRef = Arc<dyn TableMutationHandler>;
 pub type ProcedureServiceHandlerRef = Arc<dyn ProcedureServiceHandler>;
 
 pub type FlowServiceHandlerRef = Arc<dyn FlowServiceHandler>;
+
+pub type MetadataSnapshotHandlerRef = Arc<dyn MetadataSnapshotHandler>;

src/common/function/src/helper.rs

@@ -12,15 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use common_error::ext::BoxedError;
-use common_query::error::{ExecuteSnafu, InvalidFuncArgsSnafu, InvalidInputTypeSnafu, Result};
+use common_query::error::{InvalidInputTypeSnafu, Result};
 use common_query::prelude::{Signature, TypeSignature, Volatility};
 use datatypes::prelude::ConcreteDataType;
 use datatypes::types::cast::cast;
 use datatypes::value::ValueRef;
-use session::context::QueryContextRef;
 use snafu::ResultExt;
-use sql::parser::ParserContext;
 
 /// Create a function signature with oneof signatures of interleaving two arguments.
 pub fn one_of_sigs2(args1: Vec<ConcreteDataType>, args2: Vec<ConcreteDataType>) -> Signature {
@@ -46,30 +43,3 @@ pub fn cast_u64(value: &ValueRef) -> Result<Option<u64>> {
         })
         .map(|v| v.as_u64())
 }
-
-pub fn parse_catalog_flow(
-    flow_name: &str,
-    query_ctx: &QueryContextRef,
-) -> Result<(String, String)> {
-    let obj_name = ParserContext::parse_table_name(flow_name, query_ctx.sql_dialect())
-        .map_err(BoxedError::new)
-        .context(ExecuteSnafu)?;
-
-    let (catalog_name, flow_name) = match &obj_name.0[..] {
-        [flow_name] => (
-            query_ctx.current_catalog().to_string(),
-            flow_name.value.clone(),
-        ),
-        [catalog, flow_name] => (catalog.value.clone(), flow_name.value.clone()),
-        _ => {
-            return InvalidFuncArgsSnafu {
-                err_msg: format!(
-                    "expect flow name to be <catalog>.<flow-name> or <flow-name>, actual: {}",
-                    obj_name
-                ),
-            }
-            .fail()
-        }
-    };
-    Ok((catalog_name, flow_name))
-}

src/common/function/src/lib.rs

@@ -15,7 +15,6 @@
 #![feature(let_chains)]
 #![feature(try_blocks)]
 
-mod adjust_flow;
 mod admin;
 mod flush_flow;
 mod macros;

src/common/function/src/scalars/ip/cidr.rs

@@ -468,8 +468,8 @@ mod tests {
         let empty_values = vec![""];
         let empty_input = Arc::new(StringVector::from_slice(&empty_values)) as VectorRef;
 
-        let ipv4_result = ipv4_func.eval(&ctx, std::slice::from_ref(&empty_input));
-        let ipv6_result = ipv6_func.eval(&ctx, std::slice::from_ref(&empty_input));
+        let ipv4_result = ipv4_func.eval(&ctx, &[empty_input.clone()]);
+        let ipv6_result = ipv6_func.eval(&ctx, &[empty_input.clone()]);
 
         assert!(ipv4_result.is_err());
         assert!(ipv6_result.is_err());
@@ -478,7 +478,7 @@ mod tests {
         let invalid_values = vec!["not an ip", "192.168.1.256", "zzzz::ffff"];
         let invalid_input = Arc::new(StringVector::from_slice(&invalid_values)) as VectorRef;
 
-        let ipv4_result = ipv4_func.eval(&ctx, std::slice::from_ref(&invalid_input));
+        let ipv4_result = ipv4_func.eval(&ctx, &[invalid_input.clone()]);
 
         assert!(ipv4_result.is_err());
     }

src/common/function/src/scalars/ip/ipv6.rs

@@ -294,7 +294,7 @@ mod tests {
         let input = Arc::new(StringVector::from_slice(&values)) as VectorRef;
 
         // Convert IPv6 addresses to binary
-        let binary_result = to_num.eval(&ctx, std::slice::from_ref(&input)).unwrap();
+        let binary_result = to_num.eval(&ctx, &[input.clone()]).unwrap();
 
         // Convert binary to hex string representation (for ipv6_num_to_string)
         let mut hex_strings = Vec::new();

src/common/function/src/scalars/matches_term.rs

@@ -12,9 +12,8 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::fmt;
-use std::iter::repeat_n;
 use std::sync::Arc;
+use std::{fmt, iter};
 
 use common_query::error::{InvalidFuncArgsSnafu, Result};
 use common_query::prelude::Volatility;
@@ -127,10 +126,9 @@ impl Function for MatchesTermFunction {
             let term = term_column.get_ref(0).as_string().unwrap();
             match term {
                 None => {
-                    return Ok(Arc::new(BooleanVector::from_iter(repeat_n(
-                        None,
-                        text_column.len(),
-                    ))));
+                    return Ok(Arc::new(BooleanVector::from_iter(
+                        iter::repeat(None).take(text_column.len()),
+                    )));
                 }
                 Some(term) => Some(MatchesTermFinder::new(term)),
             }
@@ -219,7 +217,7 @@ impl MatchesTermFinder {
         }
 
         let mut pos = 0;
-        while let Some(found_pos) = self.finder.find(&text.as_bytes()[pos..]) {
+        while let Some(found_pos) = self.finder.find(text[pos..].as_bytes()) {
             let actual_pos = pos + found_pos;
 
             let prev_ok = self.starts_with_non_alnum