securise the connecions between the leader and followers + forbid joining the cluster without the right master key

3587: Enable cache again in test suite CI r=curquiza a=curquiza

Following the change in this PR introduced in v1.1: https://github.com/meilisearch/meilisearch/pull/3422

The cache was removed due to failures (lack of space). Now the binary is smaller (from 250Mb to 50Mb) we want to try to enable the cache again.
Indeed, without the cache step, the CIs are wayyyy slower (45min instead of 20-30min).

For later: Rust 1.68 introduced a new way to fetch crates. Updating the rust version might also help in the future!

Co-authored-by: curquiza <clementine@meilisearch.com>

.github/dependabot.yml

@@ -2,7 +2,6 @@
 
 version: 2
 updates:
-
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:

.github/scripts/check-release.sh

@@ -3,7 +3,7 @@
 # check_tag $current_tag $file_tag $file_name
 function check_tag {
   if [[ "$1" != "$2" ]]; then
-      echo "Error: the current tag does not match the version in $3: found $2 - expected $1"
+      echo "Error: the current tag does not match the version in Cargo.toml: found $2 - expected $1"
       ret=1
   fi
 }
@@ -11,12 +11,8 @@ function check_tag {
 ret=0
 current_tag=${GITHUB_REF#'refs/tags/v'}
 
-toml_files='*/Cargo.toml'
-for toml_file in $toml_files;
-do
-    file_tag="$(grep '^version = ' $toml_file | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
-    check_tag $current_tag $file_tag $toml_file
-done
+file_tag="$(grep '^version = ' Cargo.toml | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
+check_tag $current_tag $file_tag
 
 lock_file='Cargo.lock'
 lock_tag=$(grep -A 1 'name = "meilisearch-auth"' $lock_file | grep version | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')

.github/uffizzi/Dockerfile

@@ -0,0 +1,19 @@
+# Run
+FROM    uffizzi/ttyd:alpine
+
+ENV     MEILI_HTTP_ADDR 0.0.0.0:7700
+ENV     MEILI_SERVER_PROVIDER docker
+ENV     MEILI_NO_ANALYTICS true
+
+RUN     apk update --quiet \
+        && apk add -q --no-cache libgcc tini curl
+
+COPY    target/x86_64-unknown-linux-musl/release/meilisearch /bin/meilisearch
+RUN     ln -s /bin/meilisearch /meilisearch
+
+WORKDIR /meili_data
+
+EXPOSE  7700/tcp
+
+ENTRYPOINT ["tini", "--"]
+CMD     ["ttyd", "/bin/zsh"]

.github/uffizzi/docker-compose.uffizzi.yml

@@ -0,0 +1,26 @@
+version: "3"
+
+x-uffizzi:
+  ingress:
+    service: nginx
+    port: 8081
+
+services:
+  meilisearch:
+    image: "${MEILISEARCH_IMAGE}"
+    restart: unless-stopped
+    ports:
+    - "7681:7681"
+    - "7700:7700"
+    deploy:
+      resources:
+        limits:
+          memory: 500M
+  
+  nginx:
+    image: nginx:alpine
+    restart: unless-stopped
+    ports:
+    - "8081:8081"
+    volumes:
+    - ./.github/uffizzi/nginx:/etc/nginx

.github/uffizzi/nginx/nginx.conf

@@ -0,0 +1,28 @@
+
+events {
+  worker_connections  4096;  ## Default: 1024
+}
+
+http {
+    map $http_upgrade $connection_upgrade {
+        default upgrade;
+        '' close;
+    }
+
+    server {
+        listen 8081;
+
+        location / {
+            proxy_pass http://localhost:7681;
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection $connection_upgrade;
+        }
+
+        location /meilisearch/ {
+            # rewrite /meilisearch/(.*) /$1  break;
+            proxy_pass http://localhost:7700/;
+        }
+    }
+}
+

.github/workflows/benchmarks-manual.yml

@@ -0,0 +1,77 @@
+name: Benchmarks (manual)
+
+on:
+  workflow_dispatch:
+    inputs:
+      dataset_name:
+        description: 'The name of the dataset used to benchmark (search_songs, search_wiki, search_geo or indexing)'
+        required: false
+        default: 'search_songs'
+
+env:
+  BENCH_NAME: ${{ github.event.inputs.dataset_name }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    timeout-minutes: 4320 # 72h
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | tr '/' '_')" >> $GITHUB_OUTPUT
+        id: normalized_current_branch
+      - name: Set shorter commit SHA
+        shell: bash
+        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
+        id: commit_sha
+      - name: Set file basename with format "dataset_branch_commitSHA"
+        shell: bash
+        run: echo "basename=$(echo ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
+
+      # Generate critcmp files
+      - name: Install critcmp
+        uses: taiki-e/install-action@v2
+        with:
+          tool: critcmp
+      - name: Export cripcmp file
+        run: |
+          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
+
+      # Upload benchmarks
+      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
+        uses: BetaHuhn/do-spaces-action@v2
+        with:
+          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
+          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
+          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
+          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
+          source: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ steps.file.outputs.basename }}.json has just been pushed."
+          echo 'How to compare this benchmark with another one?'
+          echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-push-indexing.yml

@@ -0,0 +1,79 @@
+name: Benchmarks of indexing (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+  BENCH_NAME: "indexing"
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    timeout-minutes: 4320 # 72h
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | tr '/' '_')" >> $GITHUB_OUTPUT
+        id: normalized_current_branch
+      - name: Set shorter commit SHA
+        shell: bash
+        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
+        id: commit_sha
+      - name: Set file basename with format "dataset_branch_commitSHA"
+        shell: bash
+        run: echo "basename=$(echo ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
+
+      # Generate critcmp files
+      - name: Install critcmp
+        uses: taiki-e/install-action@v2
+        with:
+          tool: critcmp
+      - name: Export cripcmp file
+        run: |
+          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
+
+      # Upload benchmarks
+      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
+        uses: BetaHuhn/do-spaces-action@v2
+        with:
+          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
+          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
+          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
+          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
+          source: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ steps.file.outputs.basename }}.json has just been pushed."
+          echo 'How to compare this benchmark with another one?'
+          echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-push-search-geo.yml

@@ -0,0 +1,78 @@
+name: Benchmarks of search for geo (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_geo"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | tr '/' '_')" >> $GITHUB_OUTPUT
+        id: normalized_current_branch
+      - name: Set shorter commit SHA
+        shell: bash
+        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
+        id: commit_sha
+      - name: Set file basename with format "dataset_branch_commitSHA"
+        shell: bash
+        run: echo "basename=$(echo ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
+
+      # Generate critcmp files
+      - name: Install critcmp
+        uses: taiki-e/install-action@v2
+        with:
+          tool: critcmp
+      - name: Export cripcmp file
+        run: |
+          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
+
+      # Upload benchmarks
+      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
+        uses: BetaHuhn/do-spaces-action@v2
+        with:
+          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
+          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
+          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
+          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
+          source: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ steps.file.outputs.basename }}.json has just been pushed."
+          echo 'How to compare this benchmark with another one?'
+          echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-push-search-songs.yml

@@ -0,0 +1,78 @@
+name: Benchmarks of search for songs (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_songs"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | tr '/' '_')" >> $GITHUB_OUTPUT
+        id: normalized_current_branch
+      - name: Set shorter commit SHA
+        shell: bash
+        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
+        id: commit_sha
+      - name: Set file basename with format "dataset_branch_commitSHA"
+        shell: bash
+        run: echo "basename=$(echo ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
+
+      # Generate critcmp files
+      - name: Install critcmp
+        uses: taiki-e/install-action@v2
+        with:
+          tool: critcmp
+      - name: Export cripcmp file
+        run: |
+          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
+
+      # Upload benchmarks
+      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
+        uses: BetaHuhn/do-spaces-action@v2
+        with:
+          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
+          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
+          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
+          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
+          source: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ steps.file.outputs.basename }}.json has just been pushed."
+          echo 'How to compare this benchmark with another one?'
+          echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-push-search-wiki.yml

@@ -0,0 +1,78 @@
+name: Benchmarks of search for Wikipedia articles (push)
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  BENCH_NAME: "search_wiki"
+  INFLUX_TOKEN: ${{ secrets.INFLUX_TOKEN }}
+
+jobs:
+  benchmarks:
+    name: Run and upload benchmarks
+    runs-on: benchmarks
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      # Set variables
+      - name: Set current branch name
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/})" >> $GITHUB_OUTPUT
+        id: current_branch
+      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
+        shell: bash
+        run: echo "name=$(echo ${GITHUB_REF#refs/heads/} | tr '/' '_')" >> $GITHUB_OUTPUT
+        id: normalized_current_branch
+      - name: Set shorter commit SHA
+        shell: bash
+        run: echo "short=$(echo $GITHUB_SHA | cut -c1-8)" >> $GITHUB_OUTPUT
+        id: commit_sha
+      - name: Set file basename with format "dataset_branch_commitSHA"
+        shell: bash
+        run: echo "basename=$(echo ${BENCH_NAME}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
+        id: file
+
+      # Run benchmarks
+      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
+        run: |
+          cd benchmarks
+          cargo bench --bench ${BENCH_NAME} -- --save-baseline ${{ steps.file.outputs.basename }}
+
+      # Generate critcmp files
+      - name: Install critcmp
+        uses: taiki-e/install-action@v2
+        with:
+          tool: critcmp
+      - name: Export cripcmp file
+        run: |
+          critcmp --export ${{ steps.file.outputs.basename }} > ${{ steps.file.outputs.basename }}.json
+
+      # Upload benchmarks
+      - name: Upload ${{ steps.file.outputs.basename }}.json to DO Spaces # DigitalOcean Spaces = S3
+        uses: BetaHuhn/do-spaces-action@v2
+        with:
+          access_key: ${{ secrets.DO_SPACES_ACCESS_KEY }}
+          secret_key: ${{ secrets.DO_SPACES_SECRET_KEY }}
+          space_name: ${{ secrets.DO_SPACES_SPACE_NAME }}
+          space_region: ${{ secrets.DO_SPACES_SPACE_REGION }}
+          source: ${{ steps.file.outputs.basename }}.json
+          out_dir: critcmp_results
+
+      # Upload benchmarks to influxdb
+      - name: Upload ${{ steps.file.outputs.basename }}.json to influxDB
+        run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
+
+      # Helper
+      - name: 'README: compare with another benchmark'
+        run: |
+          echo "${{ steps.file.outputs.basename }}.json has just been pushed."
+          echo 'How to compare this benchmark with another one?'
+          echo '  - Check the available files with: ./benchmarks/scripts/list.sh'
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/create-issue-dependencies.yml

@@ -1,23 +0,0 @@
-name: Create issue to upgrade dependencies
-on:
-  schedule:
-    - cron: '0 0 1 */3 *'
-  workflow_dispatch:
-
-jobs:
-  create-issue:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v3
-    - name: Create an issue
-      uses: actions-ecosystem/action-create-issue@v1
-      with:
-        github_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-        title: Upgrade dependencies
-        body: |
-          We need to update the dependencies of the Meilisearch repository, and, if possible, the dependencies of all the engine-team repositories that Meilisearch depends on (milli, charabia, heed...).
-
-          ⚠️ This issue should only be done at the beginning of the sprint!
-        labels: |
-          dependencies
-          maintenance

.github/workflows/dependency-issue.yml

@@ -0,0 +1,24 @@
+name: Create issue to upgrade dependencies
+
+on:
+  schedule:
+    # Run the first of the month, every 3 month
+    - cron: '0 0 1 */3 *'
+  workflow_dispatch:
+
+jobs:
+  create-issue:
+    runs-on: ubuntu-latest
+    env:
+      ISSUE_TEMPLATE: issue-template.md
+      GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
+    steps:
+    - uses: actions/checkout@v3
+    - name: Download the issue template
+      run: curl -s https://raw.githubusercontent.com/meilisearch/engine-team/main/issue-templates/dependency-issue.md > $ISSUE_TEMPLATE
+    - name: Create issue
+      run: |
+        gh issue create \
+          --title 'Upgrade dependencies' \
+          --label 'dependencies,maintenance' \
+          --body-file $ISSUE_TEMPLATE

.github/workflows/flaky-tests.yml

@@ -22,5 +22,11 @@ jobs:
         override: true
     - name: Install cargo-flaky
       run: cargo install cargo-flaky
-    - name: Run cargo flaky 100 times
-      run: cargo flaky -i 100 --release
+    - name: Run cargo flaky in the dumps
+      run: cd dump; cargo flaky -i 100 --release
+    - name: Run cargo flaky in the index-scheduler
+      run: cd index-scheduler; cargo flaky -i 100 --release
+    - name: Run cargo flaky in the auth
+      run: cd meilisearch-auth; cargo flaky -i 100 --release
+    - name: Run cargo flaky in meilisearch
+      run: cd meilisearch; cargo flaky -i 100 --release

.github/workflows/publish-apt-brew-pkg.yml

@@ -1,4 +1,4 @@
-name: Publish to APT repository & Homebrew
+name: Publish to APT & Homebrew
 
 on:
   release:
@@ -35,7 +35,7 @@ jobs:
     - name: Build deb package
       run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
     - name: Upload debian pkg to release
-      uses: svenstaro/upload-release-action@2.3.0
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/debian/meilisearch.deb

.github/workflows/publish-binaries.yml

@@ -1,3 +1,5 @@
+name: Publish binaries to GitHub release
+
 on:
   workflow_dispatch:
   schedule:
@@ -5,8 +7,6 @@ on:
   release:
     types: [published]
 
-name: Publish binaries to release
-
 jobs:
   check-version:
     name: Check the version validity
@@ -54,7 +54,7 @@ jobs:
     # No need to upload binaries for dry run (cron)
     - name: Upload binaries to release
       if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.3.0
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/release/meilisearch
@@ -87,7 +87,7 @@ jobs:
     # No need to upload binaries for dry run (cron)
     - name: Upload binaries to release
       if: github.event_name == 'release'
-      uses: svenstaro/upload-release-action@2.3.0
+      uses: svenstaro/upload-release-action@2.5.0
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/release/${{ matrix.artifact_name }}
@@ -123,7 +123,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.3.0
+        uses: svenstaro/upload-release-action@2.5.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
@@ -183,7 +183,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.3.0
+        uses: svenstaro/upload-release-action@2.5.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

.github/workflows/publish-docker-images.yml

@@ -1,4 +1,5 @@
----
+name: Publish images to Docker Hub
+
 on:
   push:
     # Will run for every tag pushed except `latest`
@@ -12,8 +13,6 @@ on:
     - cron: '0 23 * * *' # Every day at 11:00pm
   workflow_dispatch:
 
-name: Publish tagged images to Docker Hub
-
 jobs:
   docker:
     runs-on: docker
@@ -52,9 +51,6 @@ jobs:
       - name: Set build-args for Docker buildx
         id: build-metadata
         run: |
-          # Define ownership
-          git config --global --add safe.directory /home/meili/actions-runner/_work/meilisearch/meilisearch
-
           # Extract commit date
           commit_date=$(git show -s --format=%cd --date=iso-strict ${{ github.sha }})
 
@@ -87,7 +83,7 @@ jobs:
             type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
 
       - name: Build and push
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v4
         with:
           push: true
           platforms: linux/amd64,linux/arm64
@@ -95,6 +91,7 @@ jobs:
           build-args: |
             COMMIT_SHA=${{ github.sha }}
             COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
+            GIT_TAG=${{ github.ref_name }}
 
       # /!\ Don't touch this without checking with Cloud team
       - name: Send CI information to Cloud team

.github/workflows/rust.yml

@@ -1,127 +0,0 @@
-name: Rust
-
-on:
-  workflow_dispatch:
-  pull_request:
-  push:
-    # trying and staging branches are for Bors config
-    branches:
-      - trying
-      - staging
-
-env:
-  CARGO_TERM_COLOR: always
-  RUST_BACKTRACE: 1
-  RUSTFLAGS: "-D warnings"
-
-jobs:
-  test-linux:
-    name: Tests on ubuntu-18.04
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
-    steps:
-    - uses: actions/checkout@v3
-    - name: Install needed dependencies
-      run: |
-        apt-get update && apt-get install -y curl
-        apt-get install build-essential -y
-    - uses: actions-rs/toolchain@v1
-      with:
-        toolchain: stable
-        override: true
-    - name: Cache dependencies
-      uses: Swatinem/rust-cache@v2.2.0
-    - name: Run cargo check without any default features
-      uses: actions-rs/cargo@v1
-      with:
-        command: build
-        args: --locked --release --no-default-features
-    - name: Run cargo test
-      uses: actions-rs/cargo@v1
-      with:
-        command: test
-        args: --locked --release
-
-  test-others:
-    name: Tests on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [macos-12, windows-2022]
-    steps:
-    - uses: actions/checkout@v3
-    - name: Cache dependencies
-      uses: Swatinem/rust-cache@v2.2.0
-    - name: Run cargo check without any default features
-      uses: actions-rs/cargo@v1
-      with:
-        command: build
-        args: --locked --release --no-default-features
-    - name: Run cargo test
-      uses: actions-rs/cargo@v1
-      with:
-        command: test
-        args: --locked --release
-
-  # We run tests in debug also, to make sure that the debug_assertions are hit
-  test-debug:
-    name: Run tests in debug
-    runs-on: ubuntu-latest
-    container:
-      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
-      image: ubuntu:18.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install needed dependencies
-        run: |
-          apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.2.0
-      - name: Run tests in debug
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked
-
-  clippy:
-    name: Run Clippy
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-          components: clippy
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.2.0
-      - name: Run cargo clippy
-        uses: actions-rs/cargo@v1
-        with:
-          command: clippy
-          args: --all-targets -- --deny warnings --allow clippy::uninlined_format_args
-
-  fmt:
-    name: Run Rustfmt
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: nightly
-          override: true
-          components: rustfmt
-      - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.2.0
-      - name: Run cargo fmt
-        run: cargo fmt --all -- --check

.github/workflows/test-suite.yml

@@ -0,0 +1,172 @@
+name: Test suite
+
+on:
+  workflow_dispatch:
+  schedule:
+    # Everyday at 5:00am
+    - cron: '0 5 * * *'
+  pull_request:
+  push:
+    # trying and staging branches are for Bors config
+    branches:
+      - trying
+      - staging
+
+env:
+  CARGO_TERM_COLOR: always
+  RUST_BACKTRACE: 1
+  RUSTFLAGS: "-D warnings"
+
+jobs:
+  test-linux:
+    name: Tests on ubuntu-18.04
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update && apt-get install -y curl
+          apt-get install build-essential -y
+      - name: Run test with Rust stable
+        if: github.event_name != 'schedule'
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+      - name: Run test with Rust nightly
+        if: github.event_name == 'schedule'
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo check without any default features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --locked --release --no-default-features --all
+      - name: Run cargo test
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --locked --release --all
+
+  test-others:
+    name: Tests on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-12, windows-2022]
+    steps:
+      - uses: actions/checkout@v3
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo check without any default features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --locked --release --no-default-features --all
+      - name: Run cargo test
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --locked --release --all
+
+  test-all-features:
+    name: Tests all features on cron schedule only
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    if: github.event_name == 'schedule'
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update
+          apt-get install --assume-yes build-essential curl
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+      - name: Run cargo build with all features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --workspace --locked --release --all-features
+      - name: Run cargo test with all features
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --workspace --locked --release --all-features
+
+  # We run tests in debug also, to make sure that the debug_assertions are hit
+  test-debug:
+    name: Run tests in debug
+    runs-on: ubuntu-latest
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27, which are the production expectations
+      image: ubuntu:18.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update && apt-get install -y curl
+          apt-get install build-essential -y
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+      - name: Run tests in debug
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --locked --all
+
+  clippy:
+    name: Run Clippy
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: 1.67.0
+          override: true
+          components: clippy
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo clippy
+        uses: actions-rs/cargo@v1
+        with:
+          command: clippy
+          # allow unlined_format_args https://github.com/rust-lang/rust-clippy/issues/10087
+          args: --all-targets -- --deny warnings --allow clippy::uninlined_format_args
+
+  fmt:
+    name: Run Rustfmt
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: nightly
+          override: true
+          components: rustfmt
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+      - name: Run cargo fmt
+        # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
+        # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate
+        # we are going to create an empty file where rustfmt expects it.
+        run: |
+          echo -ne "\n" > benchmarks/benches/datasets_paths.rs
+          cargo fmt --all -- --check

.github/workflows/uffizzi-build.yml

@@ -0,0 +1,120 @@
+name: Uffizzi - Build PR Image
+on:
+  pull_request:
+    types: [opened,synchronize,reopened,closed]
+
+jobs:
+  build-meilisearch:
+    name: Build and push `meilisearch`
+    runs-on: ubuntu-latest
+    outputs:
+      tags: ${{ steps.meta.outputs.tags }}
+    if: ${{ github.event.action != 'closed' }}
+    steps:
+      - name: checkout
+        uses: actions/checkout@v3
+
+      - run: sudo apt-get install musl-tools
+
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+          target: x86_64-unknown-linux-musl
+
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.1
+
+      - name: Run cargo check without any default features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --target x86_64-unknown-linux-musl --release 
+      
+      - name: Remove dockerignore so we can use the target folder in our docker build
+        run: rm -f .dockerignore
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Generate UUID image name
+        id: uuid
+        run: echo "UUID_TAG=$(uuidgen)" >> $GITHUB_ENV
+
+      - name: Docker metadata
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: registry.uffizzi.com/${{ env.UUID_TAG }}
+          tags: | 
+            type=raw,value=60d
+
+      - name: Build Image
+        uses: docker/build-push-action@v4
+        with:
+          context: ./
+          file: .github/uffizzi/Dockerfile
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          push: true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  render-compose-file:
+    name: Render Docker Compose File
+    # Pass output of this workflow to another triggered by `workflow_run` event.
+    runs-on: ubuntu-latest
+    needs: 
+      - build-meilisearch
+    outputs:
+      compose-file-cache-key:  ${{ env.COMPOSE_FILE_HASH }}
+    steps:
+      - name: Checkout git repo
+        uses: actions/checkout@v3
+      - name: Render Compose File
+        run: |
+          MEILISEARCH_IMAGE=$(echo ${{ needs.build-meilisearch.outputs.tags }})
+          export MEILISEARCH_IMAGE
+          # Render simple template from environment variables.
+          envsubst < .github/uffizzi/docker-compose.uffizzi.yml > docker-compose.rendered.yml
+          cat docker-compose.rendered.yml
+      - name: Upload Rendered Compose File as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec 
+          path: docker-compose.rendered.yml
+          retention-days: 2
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2
+
+  delete-preview:
+    name: Call for Preview Deletion
+    runs-on: ubuntu-latest
+    if: ${{ github.event.action == 'closed' }}
+    steps:
+      # If this PR is closing, we will not render a compose file nor pass it to the next workflow.
+      - name: Serialize PR Event to File
+        run:  |
+          cat << EOF > event.json
+          ${{ toJSON(github.event) }} 
+          
+          EOF
+      - name: Upload PR Event as Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: preview-spec
+          path: event.json
+          retention-days: 2

.github/workflows/uffizzi-preview-deploy.yml

@@ -0,0 +1,103 @@
+name: Uffizzi - Deploy Preview
+
+on:
+  workflow_run:
+    workflows:
+      - "Uffizzi - Build PR Image"
+    types:
+      - completed
+
+jobs:
+  cache-compose-file:
+    name: Cache Compose File
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    outputs:
+      compose-file-cache-key: ${{ env.COMPOSE_FILE_HASH }}
+      pr-number: ${{ env.PR_NUMBER }}
+      expected-url: ${{ env.EXPECTED_URL }}
+    steps:
+      - name: 'Download artifacts'
+        # Fetch output (zip archive) from the workflow run that triggered this workflow.
+        uses: actions/github-script@v6
+        with:
+          script: |
+            let allArtifacts = await github.rest.actions.listWorkflowRunArtifacts({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               run_id: context.payload.workflow_run.id,
+            });
+            let matchArtifact = allArtifacts.data.artifacts.filter((artifact) => {
+              return artifact.name == "preview-spec"
+            })[0];
+            let download = await github.rest.actions.downloadArtifact({
+               owner: context.repo.owner,
+               repo: context.repo.repo,
+               artifact_id: matchArtifact.id,
+               archive_format: 'zip',
+            });
+            let fs = require('fs');
+            fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/preview-spec.zip`, Buffer.from(download.data));
+      
+      - name: 'Unzip artifact'
+        run: unzip preview-spec.zip
+      
+      - name: Read Event into ENV
+        run: |
+          echo 'EVENT_JSON<<EOF' >> $GITHUB_ENV
+          cat event.json >> $GITHUB_ENV
+          echo 'EOF' >> $GITHUB_ENV
+      
+      - name: Hash Rendered Compose File
+        id: hash
+        # If the previous workflow was triggered by a PR close event, we will not have a compose file artifact.
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        run: echo "COMPOSE_FILE_HASH=$(md5sum docker-compose.rendered.yml | awk '{ print $1 }')" >> $GITHUB_ENV
+      
+      - name: Cache Rendered Compose File
+        if: ${{ fromJSON(env.EVENT_JSON).action != 'closed' }}
+        uses: actions/cache@v3
+        with:
+          path: docker-compose.rendered.yml
+          key: ${{ env.COMPOSE_FILE_HASH }}
+
+      - name: Read PR Number From Event Object
+        id: pr
+        run: echo "PR_NUMBER=${{ fromJSON(env.EVENT_JSON).number }}" >> $GITHUB_ENV
+      
+      - name: DEBUG - Print Job Outputs
+        if: ${{ runner.debug }}
+        run: |
+          echo "PR number: ${{ env.PR_NUMBER }}"
+          echo "Compose file hash: ${{ env.COMPOSE_FILE_HASH }}"
+          cat event.json
+
+      - name: Add expected URL env var
+        if: ${{ runner.debug }}
+        run: |
+          REPO=$(echo ${{ github.repository }} | sed 's/\./+/g')
+          echo "EXPECTED_URL=${{ inputs.server }}/github.com/$REPO/pull/${{ env.PR_NUMBER }}" >> $GITHUB_ENV
+
+  deploy-uffizzi-preview:
+    name: Use Remote Workflow to Preview on Uffizzi
+    needs:
+      - cache-compose-file
+    uses: UffizziCloud/preview-action/.github/workflows/reusable.yaml@v2
+    with:
+      # If this workflow was triggered by a PR close event, cache-key will be an empty string
+      # and this reusable workflow will delete the preview deployment.
+      compose-file-cache-key: ${{ needs.cache-compose-file.outputs.compose-file-cache-key }}
+      compose-file-cache-path: docker-compose.rendered.yml
+      server: https://app.uffizzi.com
+      pr-number: ${{ needs.cache-compose-file.outputs.pr-number }}
+      description: |
+        The meilisearch preview environment contains a web terminal from where you can run the
+        `meilisearch` command. You should be able to access this instance of meilisearch running in
+        the preview from the link Meilisearch Endpoint link given below.
+         
+        Web Terminal Endpoint : <uffizzi-url>
+        Meilisearch Endpoint : <uffizzi-url>/meilisearch
+    permissions:
+      contents: read
+      pull-requests: write
+      id-token: write

.github/workflows/update-cargo-toml-version.yml

@@ -1,4 +1,4 @@
-name: Update Meilisearch version in all Cargo.toml files
+name: Update Meilisearch version in Cargo.toml
 
 on:
   workflow_dispatch:
@@ -13,9 +13,8 @@ env:
   GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
 
 jobs:
-
   update-version-cargo-toml:
-    name: Update version in Cargo.toml files
+    name: Update version in Cargo.toml
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
@@ -26,23 +25,23 @@ jobs:
           override: true
       - name: Install sd
         run: cargo install sd
-      - name: Update Cargo.toml files
+      - name: Update Cargo.toml file
         run: |
           raw_new_version=$(echo $NEW_VERSION | cut -d 'v' -f 2)
           new_string="version = \"$raw_new_version\""
-          sd '^version = "\d+.\d+.\w+"$' "$new_string" */Cargo.toml
+          sd '^version = "\d+.\d+.\w+"$' "$new_string" Cargo.toml
       - name: Build Meilisearch to update Cargo.lock
         run: cargo build
       - name: Commit and push the changes to the ${{ env.NEW_BRANCH }} branch
         uses: EndBug/add-and-commit@v9
         with:
-          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml files"
+          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml"
           new_branch: ${{ env.NEW_BRANCH }}
       - name: Create the PR pointing to ${{ github.ref_name }}
         run: |
           gh pr create \
-            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml files" \
-            --body '⚠️ This PR is automatically generated. Check the new version is the expected one before merging.' \
+            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml" \
+            --body '⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.' \
             --label 'skip changelog' \
             --milestone $NEW_VERSION \
             --base $GITHUB_REF_NAME

.gitignore

@@ -1,3 +1,5 @@
+.idea/
+.vscode/
 /target
 **/*.csv
 **/*.json_lines
@@ -8,9 +10,11 @@
 /snapshots
 /dumps
 
-
 # Snapshots
 ## ... large
 *.full.snap
 ##  ... unreviewed
 *.snap.new
+
+# Fuzzcheck data for the facet indexing fuzz test
+milli/fuzz/update::facet::incremental::fuzz::fuzz/

CONTRIBUTING.md

@@ -52,6 +52,23 @@ cargo test
 
 This command will be triggered to each PR as a requirement for merging it.
 
+#### Snapshot-based tests
+
+We are using [insta](https://insta.rs) to perform snapshot-based testing.
+We recommend using the insta tooling (such as `cargo-insta`) to update the snapshots if they change following a PR.
+
+New tests should use insta where possible rather than manual `assert` statements.
+
+Furthermore, we provide some macros on top of insta, notably a way to use snapshot hashes instead of inline snapshots, saving a lot of space in the repository.
+
+To effectively debug snapshot-based hashes, we recommend you export the `MEILI_TEST_FULL_SNAPS` environment variable so that snapshot are fully created locally:
+
+```
+export MEILI_TEST_FULL_SNAPS=true # add this to your .bashrc, .zshrc, ...
+```
+
+#### Test troubleshooting
+
 If you get a "Too many open files" error you might want to increase the open file limit using this command:
 
 ```bash
@@ -99,6 +116,34 @@ _[Read more about this](https://github.com/meilisearch/integration-guides/blob/m
 
 The full Meilisearch release process is described in [this guide](https://github.com/meilisearch/engine-team/blob/main/resources/meilisearch-release.md). Please follow it carefully before doing any release.
 
+### How to publish a prototype
+
+Depending on the developed feature, you might need to provide a prototyped version of Meilisearch to make it easier to test by the users.
+
+The prototype name must follow this convention: `prototype-X-Y` where
+- `X` is the feature name formatted in `kebab-case`. It should not end with a single number.
+- `Y` is the version of the prototype, starting from `0`.
+
+✅ Example: `prototype-auto-resize-0`. </br>
+❌ Bad example: `auto-resize-0`: lacks the `prototype` prefix. </br>
+❌ Bad example: `prototype-auto-resize`: lacks the version suffix. </br>
+❌ Bad example: `prototype-auto-resize-0-0`: feature name ends with a single number.
+
+Steps to create a prototype:
+
+1. In your terminal, go to the last commit of your branch (the one you want to provide as a prototype).
+2. Create a tag following the convention: `git tag prototype-X-Y`
+3. Run Meilisearch and check that its launch summary features a line: `Prototype: prototype-X-Y` (you may need to switch branches and back after tagging for this to work).
+3. Push the tag: `git push origin prototype-X-Y`
+4. Check the [Docker CI](https://github.com/meilisearch/meilisearch/actions/workflows/publish-docker-images.yml) is now running.
+
+🐳 Once the CI has finished to run (~1h30), a Docker image named `prototype-X-Y` will be available on [DockerHub](https://hub.docker.com/repository/docker/getmeili/meilisearch/general). People can use it with the following command: `docker run -p 7700:7700 -v $(pwd)/meili_data:/meili_data getmeili/meilisearch:prototype-X-Y`. <br>
+More information about [how to run Meilisearch with Docker](https://docs.meilisearch.com/learn/cookbooks/docker.html#download-meilisearch-with-docker).
+
+⚙️ However, no binaries will be created. If the users do not use Docker, they can go to the `prototype-X-Y` tag in the Meilisearch repository and compile from the source code.
+
+⚠️ When sharing a prototype with users, remind them to not use it in production. Prototypes are solely for test purposes.
+
 ### Release assets
 
 For each release, the following assets are created:

Cargo.toml

@@ -9,13 +9,51 @@ members = [
     "dump",
     "file-store",
     "permissive-json-pointer",
+    "cluster",
+    "milli",
+    "filter-parser",
+    "flatten-serde-json",
+    "json-depth-checker",
+    "benchmarks"
 ]
 
+[workspace.package]
+version = "1.1.0"
+authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
+description = "Meilisearch HTTP server"
+homepage = "https://meilisearch.com"
+readme = "README.md"
+edition = "2021"
+license = "MIT"
+
 [profile.release]
 codegen-units = 1
 
 [profile.dev.package.flate2]
 opt-level = 3
 
-[profile.dev.package.milli]
+[profile.dev.package.grenad]
+opt-level = 3
+[profile.dev.package.roaring]
+opt-level = 3
+
+[profile.dev.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.dev.package.encoding]
+opt-level = 3
+[profile.dev.package.yada]
+opt-level = 3
+
+[profile.release.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.release.package.encoding]
+opt-level = 3
+[profile.release.package.yada]
+opt-level = 3
+
+[profile.bench.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.bench.package.encoding]
+opt-level = 3
+[profile.bench.package.yada]
 opt-level = 3

Dockerfile

@@ -7,7 +7,8 @@ WORKDIR /meilisearch
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
-ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE}
+ARG     GIT_TAG
+ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .

README.md

@@ -13,7 +13,6 @@
 </h4>
 
 <p align="center">
-  <a href="https://github.com/meilisearch/meilisearch/actions"><img src="https://github.com/meilisearch/meilisearch/workflows/Cargo%20test/badge.svg" alt="Build Status"></a>
   <a href="https://deps.rs/repo/github/meilisearch/meilisearch"><img src="https://deps.rs/repo/github/meilisearch/meilisearch/status.svg" alt="Dependency status"></a>
   <a href="https://github.com/meilisearch/meilisearch/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-informational" alt="License"></a>
   <a href="https://app.bors.tech/repositories/26457"><img src="https://bors.tech/images/badge_small.svg" alt="Bors enabled"></a>
@@ -69,7 +68,7 @@ Install one of our SDKs in your project for seamless integration between Meilise
 
 Take a look at the complete [Meilisearch integration list](https://docs.meilisearch.com/learn/what_is_meilisearch/sdks.html).
 
-![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)
+[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://docs.meilisearch.com/learn/what_is_meilisearch/sdks.html)
 
 ## ⚙️ Advanced usage
 
@@ -101,3 +100,15 @@ Meilisearch is a search engine created by [Meili](https://www.welcometothejungle
 - For everything else, please check [this page listing some of the other places where you can find us](https://docs.meilisearch.com/learn/what_is_meilisearch/contact.html)
 
 Thank you for your support!
+
+## 👩‍💻 Contributing
+
+Meilisearch is, and will always be, open-source! If you want to contribute to the project, please take a look at [our contribution guidelines](CONTRIBUTING.md).
+
+## 📦 Versioning
+
+Meilisearch releases and their associated binaries are available [in this GitHub page](https://github.com/meilisearch/meilisearch/releases).
+
+The binaries are versioned following [SemVer conventions](https://semver.org/). To know more, read our [versioning policy](https://github.com/meilisearch/engine-team/blob/main/resources/versioning-policy.md).
+
+Differently from the binaries, crates in this repository are not currently available on [crates.io](https://crates.io/) and do not follow [SemVer conventions](https://semver.org).

assets/milli-logo.svg

@@ -0,0 +1,6 @@
+<svg width="277" height="236" viewBox="0 0 277 236" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M213.085 190L242.907 86H276.196L246.375 190H213.085Z" fill="#494949"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M0 190L29.8215 86H63.1111L33.2896 190H0Z" fill="#494949"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M124.986 0L57.5772 235.083L60.7752 236H90.6038L158.276 0H124.986Z" fill="#494949"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M195.273 0L127.601 236H160.891L228.563 0H195.273Z" fill="#494949"/>
+</svg>

benchmarks/.gitignore

@@ -0,0 +1 @@
+benches/datasets_paths.rs

benchmarks/Cargo.toml

@@ -0,0 +1,54 @@
+[package]
+name = "benchmarks"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+anyhow = "1.0.65"
+csv = "1.1.6"
+milli = { path = "../milli", default-features = false }
+mimalloc = { version = "0.1.29", default-features = false }
+serde_json = { version = "1.0.85", features = ["preserve_order"] }
+
+[dev-dependencies]
+criterion = { version = "0.4.0", features = ["html_reports"] }
+rand = "0.8.5"
+rand_chacha = "0.3.1"
+roaring = "0.10.1"
+
+[build-dependencies]
+anyhow = "1.0.65"
+bytes = "1.2.1"
+convert_case = "0.6.0"
+flate2 = "1.0.24"
+reqwest = { version = "0.11.12", features = ["blocking", "rustls-tls"], default-features = false }
+
+[features]
+default = ["milli/default"]
+
+[[bench]]
+name = "search_songs"
+harness = false
+
+[[bench]]
+name = "search_wiki"
+harness = false
+
+[[bench]]
+name = "search_geo"
+harness = false
+
+[[bench]]
+name = "indexing"
+harness = false
+
+[[bench]]
+name = "formatting"
+harness = false

benchmarks/README.md

@@ -0,0 +1,138 @@
+Benchmarks
+==========
+
+## TOC
+
+- [Run the benchmarks](#run-the-benchmarks)
+- [Comparison between benchmarks](#comparison-between-benchmarks)
+- [Datasets](#datasets)
+
+## Run the benchmarks
+
+### On our private server
+
+The Meili team has self-hosted his own GitHub runner to run benchmarks on our dedicated bare metal server.
+
+To trigger the benchmark workflow:
+- Go to the `Actions` tab of this repository.
+- Select the `Benchmarks` workflow on the left.
+- Click on `Run workflow` in the blue banner.
+- Select the branch on which you want to run the benchmarks and select the dataset you want (default: `songs`).
+- Finally, click on `Run workflow`.
+
+This GitHub workflow will run the benchmarks and push the `critcmp` report to a DigitalOcean Space (= S3).
+
+The name of the uploaded file is displayed in the workflow.
+
+_[More about critcmp](https://github.com/BurntSushi/critcmp)._
+
+💡 To compare the just-uploaded benchmark with another one, check out the [next section](#comparison-between-benchmarks).
+
+### On your machine
+
+To run all the benchmarks (~5h):
+
+```bash
+cargo bench
+```
+
+To run only the `search_songs` (~1h), `search_wiki` (~3h), `search_geo` (~20m) or `indexing` (~2h) benchmark:
+
+```bash
+cargo bench --bench <dataset name>
+```
+
+By default, the benchmarks will be downloaded and uncompressed automatically in the target directory.<br>
+If you don't want to download the datasets every time you update something on the code, you can specify a custom directory with the environment variable `MILLI_BENCH_DATASETS_PATH`:
+
+```bash
+mkdir ~/datasets
+MILLI_BENCH_DATASETS_PATH=~/datasets cargo bench --bench search_songs # the four datasets are downloaded
+touch build.rs
+MILLI_BENCH_DATASETS_PATH=~/datasets cargo bench --bench songs # the code is compiled again but the datasets are not downloaded
+```
+
+## Comparison between benchmarks
+
+The benchmark reports we push are generated with `critcmp`. Thus, we use `critcmp` to show the result of a benchmark, or compare results between multiple benchmarks.
+
+We provide a script to download and display the comparison report.
+
+Requirements:
+- `grep`
+- `curl`
+- [`critcmp`](https://github.com/BurntSushi/critcmp)
+
+List the available file in the DO Space:
+
+```bash
+./benchmarks/script/list.sh
+```
+```bash
+songs_main_09a4321.json
+songs_geosearch_24ec456.json
+search_songs_main_cb45a10b.json
+```
+
+Run the comparison script:
+
+```bash
+# we get the result of ONE benchmark, this give you an idea of how much time an operation took
+./benchmarks/scripts/compare.sh son songs_geosearch_24ec456.json
+# we compare two benchmarks
+./benchmarks/scripts/compare.sh songs_main_09a4321.json songs_geosearch_24ec456.json
+# we compare three benchmarks
+./benchmarks/scripts/compare.sh songs_main_09a4321.json songs_geosearch_24ec456.json search_songs_main_cb45a10b.json
+```
+
+## Datasets
+
+The benchmarks uses the following datasets:
+- `smol-songs`
+- `smol-wiki`
+- `movies`
+- `smol-all-countries`
+
+### Songs
+
+`smol-songs` is a subset of the [`songs.csv` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/songs.csv.gz).
+
+It was generated with this command:
+
+```bash
+xsv sample --seed 42 1000000 songs.csv -o smol-songs.csv
+```
+
+_[Download the generated `smol-songs` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/smol-songs.csv.gz)._
+
+### Wiki
+
+`smol-wiki` is a subset of the [`wikipedia-articles.csv` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/wiki-articles.csv.gz).
+
+It was generated with the following command:
+
+```bash
+xsv sample --seed 42 500000 wiki-articles.csv -o smol-wiki-articles.csv
+```
+
+_[Download the `smol-wiki` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/smol-wiki-articles.csv.gz)._
+
+### Movies
+
+`movies` is a really small dataset we uses as our example in the [getting started](https://docs.meilisearch.com/learn/getting_started/)
+
+_[Download the `movies` dataset](https://docs.meilisearch.com/movies.json)._
+
+
+### All Countries
+
+`smol-all-countries` is a subset of the [`all-countries.csv` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/all-countries.csv.gz)
+It has been converted to jsonlines and then edited so it matches our format for the `_geo` field.
+
+It was generated with the following command:
+```bash
+bat all-countries.csv.gz | gunzip | xsv sample --seed 42 1000000 | csv2json-lite | sd '"latitude":"(.*?)","longitude":"(.*?)"' '"_geo": { "lat": $1, "lng": $2 }' | sd '\[|\]|,$' '' | gzip > smol-all-countries.jsonl.gz
+```
+
+_[Download the `smol-all-countries` dataset](https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets/smol-all-countries.jsonl.gz)._
+

benchmarks/benches/formatting.rs

@@ -0,0 +1,67 @@
+use std::rc::Rc;
+
+use criterion::{criterion_group, criterion_main};
+use milli::tokenizer::TokenizerBuilder;
+use milli::{FormatOptions, MatcherBuilder, MatchingWord, MatchingWords};
+
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+struct Conf<'a> {
+    name: &'a str,
+    text: &'a str,
+    matching_words: MatcherBuilder<'a, Vec<u8>>,
+}
+
+fn bench_formatting(c: &mut criterion::Criterion) {
+    #[rustfmt::skip]
+    let confs = &[
+    	Conf {
+    		name: "'the door d'",
+			text: r#"He used to do the door sounds in "Star Trek" with his mouth, phssst, phssst. The MD-11 passenger and cargo doors also tend to behave like electromagnetic apertures, because the doors do not have continuous electrical contact with the door frames around the door perimeter. But Theodor said that the doors don't work."#,
+			matching_words: MatcherBuilder::new(MatchingWords::new(vec![
+	            (vec![Rc::new(MatchingWord::new("t".to_string(), 0, false).unwrap()), Rc::new(MatchingWord::new("he".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("the".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("door".to_string(), 1, false).unwrap())], vec![1]),
+	            (vec![Rc::new(MatchingWord::new("do".to_string(), 0, false).unwrap()), Rc::new(MatchingWord::new("or".to_string(), 0, false).unwrap())], vec![0]),
+	            (vec![Rc::new(MatchingWord::new("thedoor".to_string(), 1, false).unwrap())], vec![0, 1]),
+	            (vec![Rc::new(MatchingWord::new("d".to_string(), 0, true).unwrap())], vec![2]),
+	            (vec![Rc::new(MatchingWord::new("thedoord".to_string(), 1, true).unwrap())], vec![0, 1, 2]),
+	            (vec![Rc::new(MatchingWord::new("doord".to_string(), 1, true).unwrap())], vec![1, 2]),
+        	]
+            ).unwrap(), TokenizerBuilder::default().build()),
+		},
+    ];
+
+    let format_options = &[
+        FormatOptions { highlight: false, crop: None },
+        FormatOptions { highlight: true, crop: None },
+        FormatOptions { highlight: false, crop: Some(10) },
+        FormatOptions { highlight: true, crop: Some(10) },
+        FormatOptions { highlight: false, crop: Some(20) },
+        FormatOptions { highlight: true, crop: Some(20) },
+    ];
+
+    for option in format_options {
+        let highlight = if option.highlight { "highlight" } else { "no-highlight" };
+
+        let name = match option.crop {
+            Some(size) => format!("{}-crop({})", highlight, size),
+            None => format!("{}-no-crop", highlight),
+        };
+
+        let mut group = c.benchmark_group(&name);
+        for conf in confs {
+            group.bench_function(conf.name, |b| {
+                b.iter(|| {
+                    let mut matcher = conf.matching_words.build(conf.text);
+                    matcher.format(*option);
+                })
+            });
+        }
+        group.finish();
+    }
+}
+
+criterion_group!(benches, bench_formatting);
+criterion_main!(benches);

benchmarks/benches/search_geo.rs

@@ -0,0 +1,122 @@
+mod datasets_paths;
+mod utils;
+
+use criterion::{criterion_group, criterion_main};
+use milli::update::Settings;
+use utils::Conf;
+
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+fn base_conf(builder: &mut Settings) {
+    let displayed_fields =
+        ["geonameid", "name", "asciiname", "alternatenames", "_geo", "population"]
+            .iter()
+            .map(|s| s.to_string())
+            .collect();
+    builder.set_displayed_fields(displayed_fields);
+
+    let searchable_fields =
+        ["name", "alternatenames", "elevation"].iter().map(|s| s.to_string()).collect();
+    builder.set_searchable_fields(searchable_fields);
+
+    let filterable_fields =
+        ["_geo", "population", "elevation"].iter().map(|s| s.to_string()).collect();
+    builder.set_filterable_fields(filterable_fields);
+
+    let sortable_fields =
+        ["_geo", "population", "elevation"].iter().map(|s| s.to_string()).collect();
+    builder.set_sortable_fields(sortable_fields);
+}
+
+#[rustfmt::skip]
+const BASE_CONF: Conf = Conf {
+    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
+    dataset_format: "jsonl",
+    queries: &[
+        "",
+    ],
+    configure: base_conf,
+    primary_key: Some("geonameid"),
+    ..Conf::BASE
+};
+
+fn bench_geo(c: &mut criterion::Criterion) {
+    #[rustfmt::skip]
+    let confs = &[
+        // A basic placeholder with no geo
+        utils::Conf {
+            group_name: "placeholder with no geo",
+            ..BASE_CONF
+        },
+        // Medium aglomeration: probably the most common usecase
+        utils::Conf {
+            group_name: "asc sort from Lille",
+            sort: Some(vec!["_geoPoint(50.62999333378238, 3.086269263384099):asc"]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "desc sort from Lille",
+            sort: Some(vec!["_geoPoint(50.62999333378238, 3.086269263384099):desc"]),
+            ..BASE_CONF
+        },
+        // Big agglomeration: a lot of documents close to our point
+        utils::Conf {
+            group_name: "asc sort from Tokyo",
+            sort: Some(vec!["_geoPoint(35.749512532692144, 139.61664952543356):asc"]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "desc sort from Tokyo",
+            sort: Some(vec!["_geoPoint(35.749512532692144, 139.61664952543356):desc"]),
+            ..BASE_CONF
+        },
+        // The furthest point from any civilization
+        utils::Conf {
+            group_name: "asc sort from Point Nemo",
+            sort: Some(vec!["_geoPoint(-48.87561645055408, -123.39275749319793):asc"]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "desc sort from Point Nemo",
+            sort: Some(vec!["_geoPoint(-48.87561645055408, -123.39275749319793):desc"]),
+            ..BASE_CONF
+        },
+        // Filters
+        utils::Conf {
+            group_name: "filter of 100km from Lille",
+            filter: Some("_geoRadius(50.62999333378238, 3.086269263384099, 100000)"),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "filter of 1km from Lille",
+            filter: Some("_geoRadius(50.62999333378238, 3.086269263384099, 1000)"),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "filter of 100km from Tokyo",
+            filter: Some("_geoRadius(35.749512532692144, 139.61664952543356, 100000)"),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "filter of 1km from Tokyo",
+            filter: Some("_geoRadius(35.749512532692144, 139.61664952543356, 1000)"),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "filter of 100km from Point Nemo",
+            filter: Some("_geoRadius(-48.87561645055408, -123.39275749319793, 100000)"),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "filter of 1km from Point Nemo",
+            filter: Some("_geoRadius(-48.87561645055408, -123.39275749319793, 1000)"),
+            ..BASE_CONF
+        },
+    ];
+
+    utils::run_benches(c, confs);
+}
+
+criterion_group!(benches, bench_geo);
+criterion_main!(benches);

benchmarks/benches/search_songs.rs

@@ -0,0 +1,196 @@
+mod datasets_paths;
+mod utils;
+
+use criterion::{criterion_group, criterion_main};
+use milli::update::Settings;
+use utils::Conf;
+
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+fn base_conf(builder: &mut Settings) {
+    let displayed_fields =
+        ["id", "title", "album", "artist", "genre", "country", "released", "duration"]
+            .iter()
+            .map(|s| s.to_string())
+            .collect();
+    builder.set_displayed_fields(displayed_fields);
+
+    let searchable_fields = ["title", "album", "artist"].iter().map(|s| s.to_string()).collect();
+    builder.set_searchable_fields(searchable_fields);
+
+    let faceted_fields = ["released-timestamp", "duration-float", "genre", "country", "artist"]
+        .iter()
+        .map(|s| s.to_string())
+        .collect();
+    builder.set_filterable_fields(faceted_fields);
+}
+
+#[rustfmt::skip]
+const BASE_CONF: Conf = Conf {
+    dataset: datasets_paths::SMOL_SONGS,
+    queries: &[
+        "john ",             // 9097
+        "david ",            // 4794
+        "charles ",          // 1957
+        "david bowie ",      // 1200
+        "michael jackson ",  // 600
+        "thelonious monk ",  // 303
+        "charles mingus ",   // 142
+        "marcus miller ",    // 60
+        "tamo ",             // 13
+        "Notstandskomitee ", // 4
+    ],
+    configure: base_conf,
+    primary_key: Some("id"),
+    ..Conf::BASE
+};
+
+fn bench_songs(c: &mut criterion::Criterion) {
+    let default_criterion: Vec<String> =
+        milli::default_criteria().iter().map(|criteria| criteria.to_string()).collect();
+    let default_criterion = default_criterion.iter().map(|s| s.as_str());
+    let asc_default: Vec<&str> =
+        std::iter::once("released-timestamp:asc").chain(default_criterion.clone()).collect();
+    let desc_default: Vec<&str> =
+        std::iter::once("released-timestamp:desc").chain(default_criterion.clone()).collect();
+
+    let basic_with_quote: Vec<String> = BASE_CONF
+        .queries
+        .iter()
+        .map(|s| {
+            s.trim().split(' ').map(|s| format!(r#""{}""#, s)).collect::<Vec<String>>().join(" ")
+        })
+        .collect();
+    let basic_with_quote: &[&str] =
+        &basic_with_quote.iter().map(|s| s.as_str()).collect::<Vec<&str>>();
+
+    #[rustfmt::skip]
+    let confs = &[
+        /* first we bench each criterion alone */
+        utils::Conf {
+            group_name: "proximity",
+            queries: &[
+                "black saint sinner lady ",
+                "les dangeureuses 1960 ",
+                "The Disneyland Sing-Along Chorus ",
+                "Under Great Northern Lights ",
+                "7000 Danses Un Jour Dans Notre Vie ",
+            ],
+            criterion: Some(&["proximity"]),
+            optional_words: false,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "typo",
+            queries: &[
+                "mongus ",
+                "thelonius monk ",
+                "Disnaylande ",
+                "the white striper ",
+                "indochie ",
+                "indochien ",
+                "klub des loopers ",
+                "fear of the duck ",
+                "michel depech ",
+                "stromal ",
+                "dire straights ",
+                "Arethla Franklin ",
+            ],
+            criterion: Some(&["typo"]),
+            optional_words: false,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "words",
+            queries: &[
+                "the black saint and the sinner lady and the good doggo ", // four words to pop
+                "les liaisons dangeureuses 1793 ",                         // one word to pop
+                "The Disneyland Children's Sing-Alone song ",              // two words to pop
+                "seven nation mummy ",                                     // one word to pop
+                "7000 Danses / Le Baiser / je me trompe de mots ",         // four words to pop
+                "Bring Your Daughter To The Slaughter but now this is not part of the title ", // nine words to pop
+                "whathavenotnsuchforth and a good amount of words to pop to match the first one ", // 13
+            ],
+            criterion: Some(&["words"]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "asc",
+            criterion: Some(&["released-timestamp:desc"]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "desc",
+            criterion: Some(&["released-timestamp:desc"]),
+            ..BASE_CONF
+        },
+
+        /* then we bench the asc and desc criterion on top of the default criterion */
+        utils::Conf {
+            group_name: "asc + default",
+            criterion: Some(&asc_default[..]),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "desc + default",
+            criterion: Some(&desc_default[..]),
+            ..BASE_CONF
+        },
+
+        /* we bench the filters with the default request */
+        utils::Conf {
+            group_name: "basic filter: <=",
+            filter: Some("released-timestamp <= 946728000"), // year 2000
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "basic filter: TO",
+            filter: Some("released-timestamp 946728000 TO 1262347200"), // year 2000 to 2010
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "big filter",
+            filter: Some("released-timestamp != 1262347200 AND (NOT (released-timestamp = 946728000)) AND (duration-float = 1 OR (duration-float 1.1 TO 1.5 AND released-timestamp > 315576000))"),
+            ..BASE_CONF
+        },
+
+        /* the we bench some global / normal search with all the default criterion in the default
+         * order */
+        utils::Conf {
+            group_name: "basic placeholder",
+            queries: &[""],
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "basic without quote",
+            queries: &BASE_CONF
+                .queries
+                .iter()
+                .map(|s| s.trim()) // we remove the space at the end of each request
+                .collect::<Vec<&str>>(),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "basic with quote",
+            queries: basic_with_quote,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "prefix search",
+            queries: &[
+                "s", // 500k+ results
+                "a", //
+                "b", //
+                "i", //
+                "x", // only 7k results
+            ],
+            ..BASE_CONF
+        },
+    ];
+
+    utils::run_benches(c, confs);
+}
+
+criterion_group!(benches, bench_songs);
+criterion_main!(benches);

benchmarks/benches/search_wiki.rs

@@ -0,0 +1,129 @@
+mod datasets_paths;
+mod utils;
+
+use criterion::{criterion_group, criterion_main};
+use milli::update::Settings;
+use utils::Conf;
+
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+fn base_conf(builder: &mut Settings) {
+    let displayed_fields = ["title", "body", "url"].iter().map(|s| s.to_string()).collect();
+    builder.set_displayed_fields(displayed_fields);
+
+    let searchable_fields = ["title", "body"].iter().map(|s| s.to_string()).collect();
+    builder.set_searchable_fields(searchable_fields);
+}
+
+#[rustfmt::skip]
+const BASE_CONF: Conf = Conf {
+    dataset: datasets_paths::SMOL_WIKI_ARTICLES,
+    queries: &[
+        "mingus ",        // 46 candidates
+        "miles davis ",   // 159
+        "rock and roll ", // 1007
+        "machine ",       // 3448
+        "spain ",         // 7002
+        "japan ",         // 10.593
+        "france ",        // 17.616
+        "film ",          // 24.959
+    ],
+    configure: base_conf,
+    ..Conf::BASE
+};
+
+fn bench_songs(c: &mut criterion::Criterion) {
+    let basic_with_quote: Vec<String> = BASE_CONF
+        .queries
+        .iter()
+        .map(|s| {
+            s.trim().split(' ').map(|s| format!(r#""{}""#, s)).collect::<Vec<String>>().join(" ")
+        })
+        .collect();
+    let basic_with_quote: &[&str] =
+        &basic_with_quote.iter().map(|s| s.as_str()).collect::<Vec<&str>>();
+
+    #[rustfmt::skip]
+    let confs = &[
+        /* first we bench each criterion alone */
+        utils::Conf {
+            group_name: "proximity",
+            queries: &[
+                "herald sings ",
+                "april paris ",
+                "tea two ",
+                "diesel engine ",
+            ],
+            criterion: Some(&["proximity"]),
+            optional_words: false,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "typo",
+            queries: &[
+                "migrosoft ",
+                "linax ",
+                "Disnaylande ",
+                "phytogropher ",
+                "nympalidea ",
+                "aritmetric ",
+                "the fronce ",
+                "sisan ",
+            ],
+            criterion: Some(&["typo"]),
+            optional_words: false,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "words",
+            queries: &[
+                "the black saint and the sinner lady and the good doggo ", // four words to pop, 27 results
+                "Kameya Tokujirō mingus monk ",                            // two words to pop, 55
+                "Ulrich Hensel meilisearch milli ",                        // two words to pop, 306
+                "Idaho Bellevue pizza ",                                   // one word to pop, 800
+                "Abraham machin ",                                         // one word to pop, 1141
+            ],
+            criterion: Some(&["words"]),
+            ..BASE_CONF
+        },
+        /* the we bench some global / normal search with all the default criterion in the default
+         * order */
+        utils::Conf {
+            group_name: "basic placeholder",
+            queries: &[""],
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "basic without quote",
+            queries: &BASE_CONF
+                .queries
+                .iter()
+                .map(|s| s.trim()) // we remove the space at the end of each request
+                .collect::<Vec<&str>>(),
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "basic with quote",
+            queries: basic_with_quote,
+            ..BASE_CONF
+        },
+        utils::Conf {
+            group_name: "prefix search",
+            queries: &[
+                "t", // 453k results
+                "c", // 405k
+                "g", // 318k
+                "j", // 227k
+                "q", // 71k
+                "x", // 17k
+            ],
+            ..BASE_CONF
+        },
+    ];
+
+    utils::run_benches(c, confs);
+}
+
+criterion_group!(benches, bench_songs);
+criterion_main!(benches);

benchmarks/benches/utils.rs

@@ -0,0 +1,256 @@
+#![allow(dead_code)]
+
+use std::fs::{create_dir_all, remove_dir_all, File};
+use std::io::{self, BufRead, BufReader, Cursor, Read, Seek};
+use std::num::ParseFloatError;
+use std::path::Path;
+use std::str::FromStr;
+
+use criterion::BenchmarkId;
+use milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
+use milli::heed::EnvOpenOptions;
+use milli::update::{
+    IndexDocuments, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings,
+};
+use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
+use serde_json::Value;
+
+pub struct Conf<'a> {
+    /// where we are going to create our database.mmdb directory
+    /// each benchmark will first try to delete it and then recreate it
+    pub database_name: &'a str,
+    /// the dataset to be used, it must be an uncompressed csv
+    pub dataset: &'a str,
+    /// The format of the dataset
+    pub dataset_format: &'a str,
+    pub group_name: &'a str,
+    pub queries: &'a [&'a str],
+    /// here you can change which criterion are used and in which order.
+    /// - if you specify something all the base configuration will be thrown out
+    /// - if you don't specify anything (None) the default configuration will be kept
+    pub criterion: Option<&'a [&'a str]>,
+    /// the last chance to configure your database as you want
+    pub configure: fn(&mut Settings),
+    pub filter: Option<&'a str>,
+    pub sort: Option<Vec<&'a str>>,
+    /// enable or disable the optional words on the query
+    pub optional_words: bool,
+    /// primary key, if there is None we'll auto-generate docids for every documents
+    pub primary_key: Option<&'a str>,
+}
+
+impl Conf<'_> {
+    pub const BASE: Self = Conf {
+        database_name: "benches.mmdb",
+        dataset_format: "csv",
+        dataset: "",
+        group_name: "",
+        queries: &[],
+        criterion: None,
+        configure: |_| (),
+        filter: None,
+        sort: None,
+        optional_words: true,
+        primary_key: None,
+    };
+}
+
+pub fn base_setup(conf: &Conf) -> Index {
+    match remove_dir_all(conf.database_name) {
+        Ok(_) => (),
+        Err(e) if e.kind() == std::io::ErrorKind::NotFound => (),
+        Err(e) => panic!("{}", e),
+    }
+    create_dir_all(conf.database_name).unwrap();
+
+    let mut options = EnvOpenOptions::new();
+    options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
+    options.max_readers(10);
+    let index = Index::new(options, conf.database_name).unwrap();
+
+    let config = IndexerConfig::default();
+    let mut wtxn = index.write_txn().unwrap();
+    let mut builder = Settings::new(&mut wtxn, &index, &config);
+
+    if let Some(primary_key) = conf.primary_key {
+        builder.set_primary_key(primary_key.to_string());
+    }
+
+    if let Some(criterion) = conf.criterion {
+        builder.reset_filterable_fields();
+        builder.reset_criteria();
+        builder.reset_stop_words();
+
+        let criterion = criterion.iter().map(|s| Criterion::from_str(s).unwrap()).collect();
+        builder.set_criteria(criterion);
+    }
+
+    (conf.configure)(&mut builder);
+
+    builder.execute(|_| (), || false).unwrap();
+    wtxn.commit().unwrap();
+
+    let config = IndexerConfig::default();
+    let mut wtxn = index.write_txn().unwrap();
+    let indexing_config = IndexDocumentsConfig {
+        autogenerate_docids: conf.primary_key.is_none(),
+        update_method: IndexDocumentsMethod::ReplaceDocuments,
+        ..Default::default()
+    };
+    let builder =
+        IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
+    let documents = documents_from(conf.dataset, conf.dataset_format);
+    let (builder, user_error) = builder.add_documents(documents).unwrap();
+    user_error.unwrap();
+    builder.execute().unwrap();
+    wtxn.commit().unwrap();
+
+    index
+}
+
+pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
+    for conf in confs {
+        let index = base_setup(conf);
+
+        let file_name = Path::new(conf.dataset).file_name().and_then(|f| f.to_str()).unwrap();
+        let name = format!("{}: {}", file_name, conf.group_name);
+        let mut group = c.benchmark_group(&name);
+
+        for &query in conf.queries {
+            group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
+                b.iter(|| {
+                    let rtxn = index.read_txn().unwrap();
+                    let mut search = index.search(&rtxn);
+                    search.query(query).terms_matching_strategy(TermsMatchingStrategy::default());
+                    if let Some(filter) = conf.filter {
+                        let filter = Filter::from_str(filter).unwrap().unwrap();
+                        search.filter(filter);
+                    }
+                    if let Some(sort) = &conf.sort {
+                        let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
+                        search.sort_criteria(sort);
+                    }
+                    let _ids = search.execute().unwrap();
+                });
+            });
+        }
+        group.finish();
+
+        index.prepare_for_closing().wait();
+    }
+}
+
+pub fn documents_from(filename: &str, filetype: &str) -> DocumentsBatchReader<impl BufRead + Seek> {
+    let reader = File::open(filename)
+        .unwrap_or_else(|_| panic!("could not find the dataset in: {}", filename));
+    let reader = BufReader::new(reader);
+    let documents = match filetype {
+        "csv" => documents_from_csv(reader).unwrap(),
+        "json" => documents_from_json(reader).unwrap(),
+        "jsonl" => documents_from_jsonl(reader).unwrap(),
+        otherwise => panic!("invalid update format {:?}", otherwise),
+    };
+    DocumentsBatchReader::from_reader(Cursor::new(documents)).unwrap()
+}
+
+fn documents_from_jsonl(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+
+    for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
+        let object = result?;
+        documents.append_json_object(&object)?;
+    }
+
+    documents.into_inner().map_err(Into::into)
+}
+
+fn documents_from_json(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+
+    documents.append_json_array(reader)?;
+
+    documents.into_inner().map_err(Into::into)
+}
+
+fn documents_from_csv(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
+    let csv = csv::Reader::from_reader(reader);
+
+    let mut documents = DocumentsBatchBuilder::new(Vec::new());
+    documents.append_csv(csv)?;
+
+    documents.into_inner().map_err(Into::into)
+}
+
+enum AllowedType {
+    String,
+    Number,
+}
+
+fn parse_csv_header(header: &str) -> (String, AllowedType) {
+    // if there are several separators we only split on the last one.
+    match header.rsplit_once(':') {
+        Some((field_name, field_type)) => match field_type {
+            "string" => (field_name.to_string(), AllowedType::String),
+            "number" => (field_name.to_string(), AllowedType::Number),
+            // we may return an error in this case.
+            _otherwise => (header.to_string(), AllowedType::String),
+        },
+        None => (header.to_string(), AllowedType::String),
+    }
+}
+
+struct CSVDocumentDeserializer<R>
+where
+    R: Read,
+{
+    documents: csv::StringRecordsIntoIter<R>,
+    headers: Vec<(String, AllowedType)>,
+}
+
+impl<R: Read> CSVDocumentDeserializer<R> {
+    fn from_reader(reader: R) -> io::Result<Self> {
+        let mut records = csv::Reader::from_reader(reader);
+
+        let headers = records.headers()?.into_iter().map(parse_csv_header).collect();
+
+        Ok(Self { documents: records.into_records(), headers })
+    }
+}
+
+impl<R: Read> Iterator for CSVDocumentDeserializer<R> {
+    type Item = anyhow::Result<Object>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let csv_document = self.documents.next()?;
+
+        match csv_document {
+            Ok(csv_document) => {
+                let mut document = Object::new();
+
+                for ((field_name, field_type), value) in
+                    self.headers.iter().zip(csv_document.into_iter())
+                {
+                    let parsed_value: Result<Value, ParseFloatError> = match field_type {
+                        AllowedType::Number => {
+                            value.parse::<f64>().map(Value::from).map_err(Into::into)
+                        }
+                        AllowedType::String => Ok(Value::String(value.to_string())),
+                    };
+
+                    match parsed_value {
+                        Ok(value) => drop(document.insert(field_name.to_string(), value)),
+                        Err(_e) => {
+                            return Some(Err(anyhow::anyhow!(
+                                "Value '{}' is not a valid number",
+                                value
+                            )))
+                        }
+                    }
+                }
+
+                Some(Ok(document))
+            }
+            Err(e) => Some(Err(anyhow::anyhow!("Error parsing csv document: {}", e))),
+        }
+    }
+}

benchmarks/build.rs

@@ -0,0 +1,115 @@
+use std::fs::File;
+use std::io::{Cursor, Read, Seek, Write};
+use std::path::{Path, PathBuf};
+use std::{env, fs};
+
+use bytes::Bytes;
+use convert_case::{Case, Casing};
+use flate2::read::GzDecoder;
+use reqwest::IntoUrl;
+
+const BASE_URL: &str = "https://milli-benchmarks.fra1.digitaloceanspaces.com/datasets";
+
+const DATASET_SONGS: (&str, &str) = ("smol-songs", "csv");
+const DATASET_SONGS_1_2: (&str, &str) = ("smol-songs-1_2", "csv");
+const DATASET_SONGS_3_4: (&str, &str) = ("smol-songs-3_4", "csv");
+const DATASET_SONGS_4_4: (&str, &str) = ("smol-songs-4_4", "csv");
+const DATASET_WIKI: (&str, &str) = ("smol-wiki-articles", "csv");
+const DATASET_WIKI_1_2: (&str, &str) = ("smol-wiki-articles-1_2", "csv");
+const DATASET_WIKI_3_4: (&str, &str) = ("smol-wiki-articles-3_4", "csv");
+const DATASET_WIKI_4_4: (&str, &str) = ("smol-wiki-articles-4_4", "csv");
+const DATASET_MOVIES: (&str, &str) = ("movies", "json");
+const DATASET_MOVIES_1_2: (&str, &str) = ("movies-1_2", "json");
+const DATASET_MOVIES_3_4: (&str, &str) = ("movies-3_4", "json");
+const DATASET_MOVIES_4_4: (&str, &str) = ("movies-4_4", "json");
+const DATASET_NESTED_MOVIES: (&str, &str) = ("nested_movies", "json");
+const DATASET_GEO: (&str, &str) = ("smol-all-countries", "jsonl");
+
+const ALL_DATASETS: &[(&str, &str)] = &[
+    DATASET_SONGS,
+    DATASET_SONGS_1_2,
+    DATASET_SONGS_3_4,
+    DATASET_SONGS_4_4,
+    DATASET_WIKI,
+    DATASET_WIKI_1_2,
+    DATASET_WIKI_3_4,
+    DATASET_WIKI_4_4,
+    DATASET_MOVIES,
+    DATASET_MOVIES_1_2,
+    DATASET_MOVIES_3_4,
+    DATASET_MOVIES_4_4,
+    DATASET_NESTED_MOVIES,
+    DATASET_GEO,
+];
+
+/// The name of the environment variable used to select the path
+/// of the directory containing the datasets
+const BASE_DATASETS_PATH_KEY: &str = "MILLI_BENCH_DATASETS_PATH";
+
+fn main() -> anyhow::Result<()> {
+    let out_dir = PathBuf::from(env::var(BASE_DATASETS_PATH_KEY).unwrap_or(env::var("OUT_DIR")?));
+
+    let benches_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR")?).join("benches");
+    let mut manifest_paths_file = File::create(benches_dir.join("datasets_paths.rs"))?;
+    write!(
+        manifest_paths_file,
+        r#"//! This file is generated by the build script.
+//! Do not modify by hand, use the build.rs file.
+#![allow(dead_code)]
+"#
+    )?;
+    writeln!(manifest_paths_file)?;
+
+    for (dataset, extension) in ALL_DATASETS {
+        let out_path = out_dir.join(dataset);
+        let out_file = out_path.with_extension(extension);
+
+        writeln!(
+            &mut manifest_paths_file,
+            r#"pub const {}: &str = {:?};"#,
+            dataset.to_case(Case::ScreamingSnake),
+            out_file.display(),
+        )?;
+
+        if out_file.exists() {
+            eprintln!(
+                "The dataset {} already exists on the file system and will not be downloaded again",
+                out_path.display(),
+            );
+            continue;
+        }
+        let url = format!("{}/{}.{}.gz", BASE_URL, dataset, extension);
+        eprintln!("downloading: {}", url);
+        let bytes = retry(|| download_dataset(url.clone()), 10)?;
+        eprintln!("{} downloaded successfully", url);
+        eprintln!("uncompressing in {}", out_file.display());
+        uncompress_in_file(bytes, &out_file)?;
+    }
+
+    Ok(())
+}
+
+fn retry<Ok, Err>(fun: impl Fn() -> Result<Ok, Err>, times: usize) -> Result<Ok, Err> {
+    for _ in 0..times {
+        if let ok @ Ok(_) = fun() {
+            return ok;
+        }
+    }
+    fun()
+}
+
+fn download_dataset<U: IntoUrl>(url: U) -> anyhow::Result<Cursor<Bytes>> {
+    let bytes =
+        reqwest::blocking::Client::builder().timeout(None).build()?.get(url).send()?.bytes()?;
+    Ok(Cursor::new(bytes))
+}
+
+fn uncompress_in_file<R: Read + Seek, P: AsRef<Path>>(bytes: R, path: P) -> anyhow::Result<()> {
+    let path = path.as_ref();
+    let mut gz = GzDecoder::new(bytes);
+    let mut dataset = Vec::new();
+    gz.read_to_end(&mut dataset)?;
+
+    fs::write(path, dataset)?;
+    Ok(())
+}

benchmarks/scripts/compare.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+
+# Requirements:
+# - critcmp. See: https://github.com/BurntSushi/critcmp
+# - curl
+
+# Usage
+# $ bash compare.sh json_file1 json_file1
+# ex: bash compare.sh songs_main_09a4321.json songs_geosearch_24ec456.json
+
+# Checking that critcmp is installed
+command -v critcmp > /dev/null 2>&1
+if [[ "$?" -ne 0 ]]; then
+    echo 'You must install critcmp to make this script work.'
+    echo 'See: https://github.com/BurntSushi/critcmp'
+    echo '  $ cargo install critcmp'
+    exit 1
+fi
+
+s3_url='https://milli-benchmarks.fra1.digitaloceanspaces.com/critcmp_results'
+
+for file in $@
+do
+    file_s3_url="$s3_url/$file"
+    file_local_path="/tmp/$file"
+
+    if [[ ! -f $file_local_path ]]; then
+        curl $file_s3_url --output $file_local_path --silent
+        if [[ "$?" -ne 0 ]]; then
+            echo 'curl command failed.'
+            exit 1
+        fi
+    fi
+done
+
+path_list=$(echo " $@" | sed 's/ / \/tmp\//g')
+
+critcmp $path_list

benchmarks/scripts/list.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+
+# Requirements:
+# - curl
+# - grep
+
+res=$(curl -s https://milli-benchmarks.fra1.digitaloceanspaces.com | grep -o '<Key>[^<]\+' | cut -c 5- | grep critcmp_results/ | cut -c 18-)
+
+for pattern in "$@"
+do
+	res=$(echo "$res" | grep $pattern)
+done
+
+echo "$res"

benchmarks/src/lib.rs

@@ -0,0 +1,5 @@
+//! This library is only used to isolate the benchmarks
+//! from the original milli library.
+//!
+//! It does not include interesting functions for milli library
+//! users only for milli contributors.

cluster/Cargo.toml

@@ -0,0 +1,25 @@
+[package]
+name = "cluster"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+ductile = "0.3.0"
+serde = { version = "1.0.155", features = ["derive"] }
+serde_json = "1.0.94"
+thiserror = "1.0.39"
+meilisearch-types = { path = "../meilisearch-types" }
+roaring = { version = "0.10.1", features = ["serde"] }
+log = "0.4.17"
+crossbeam = "0.8.2"
+bus = "2.3.0"
+time = "0.3.20"
+uuid = { version = "1.3.0", features = ["v4"] }
+synchronoise = "1.0.1"

cluster/src/batch.rs

@@ -0,0 +1,148 @@
+use meilisearch_types::milli::update::IndexDocumentsMethod;
+use meilisearch_types::settings::{Settings, Unchecked};
+use meilisearch_types::tasks::TaskId;
+use roaring::RoaringBitmap;
+use serde::{Deserialize, Serialize};
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+/// Represents a combination of tasks that can all be processed at the same time.
+///
+/// A batch contains the set of tasks that it represents (accessible through
+/// [`self.ids()`](Batch::ids)), as well as additional information on how to
+/// be processed.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum Batch {
+    TaskCancelation {
+        /// The task cancelation itself.
+        task: TaskId,
+        /// The date and time at which the previously processing tasks started.
+        previous_started_at: OffsetDateTime,
+        /// The list of tasks that were processing when this task cancelation appeared.
+        previous_processing_tasks: RoaringBitmap,
+    },
+    TaskDeletion(TaskId),
+    SnapshotCreation(Vec<TaskId>),
+    Dump(TaskId),
+    IndexOperation {
+        op: IndexOperation,
+        must_create_index: bool,
+    },
+    IndexCreation {
+        index_uid: String,
+        primary_key: Option<String>,
+        task: TaskId,
+    },
+    IndexUpdate {
+        index_uid: String,
+        primary_key: Option<String>,
+        task: TaskId,
+    },
+    IndexDeletion {
+        index_uid: String,
+        tasks: Vec<TaskId>,
+        index_has_been_created: bool,
+    },
+    IndexSwap {
+        task: TaskId,
+    },
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum DocumentOperation {
+    Add(Uuid),
+    Delete(Vec<String>),
+}
+
+/// A [batch](Batch) that combines multiple tasks operating on an index.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum IndexOperation {
+    DocumentOperation {
+        index_uid: String,
+        primary_key: Option<String>,
+        method: IndexDocumentsMethod,
+        documents_counts: Vec<u64>,
+        operations: Vec<DocumentOperation>,
+        tasks: Vec<TaskId>,
+    },
+    DocumentDeletion {
+        index_uid: String,
+        // The vec associated with each document deletion tasks.
+        documents: Vec<Vec<String>>,
+        tasks: Vec<TaskId>,
+    },
+    DocumentClear {
+        index_uid: String,
+        tasks: Vec<TaskId>,
+    },
+    Settings {
+        index_uid: String,
+        // The boolean indicates if it's a settings deletion or creation.
+        settings: Vec<(bool, Settings<Unchecked>)>,
+        tasks: Vec<TaskId>,
+    },
+    DocumentClearAndSetting {
+        index_uid: String,
+        cleared_tasks: Vec<TaskId>,
+
+        // The boolean indicates if it's a settings deletion or creation.
+        settings: Vec<(bool, Settings<Unchecked>)>,
+        settings_tasks: Vec<TaskId>,
+    },
+    SettingsAndDocumentOperation {
+        index_uid: String,
+
+        primary_key: Option<String>,
+        method: IndexDocumentsMethod,
+        documents_counts: Vec<u64>,
+        operations: Vec<DocumentOperation>,
+        document_import_tasks: Vec<TaskId>,
+
+        // The boolean indicates if it's a settings deletion or creation.
+        settings: Vec<(bool, Settings<Unchecked>)>,
+        settings_tasks: Vec<TaskId>,
+    },
+}
+
+impl Batch {
+    pub fn ids(&self) -> impl Iterator<Item = TaskId> {
+        type Ret = Box<dyn Iterator<Item = TaskId>>;
+
+        match self {
+            Batch::TaskCancelation { task, .. } => Box::new(std::iter::once(*task)) as Ret,
+            Batch::TaskDeletion(task) => Box::new(std::iter::once(*task)) as Ret,
+            Batch::SnapshotCreation(tasks) => Box::new(tasks.clone().into_iter()) as Ret,
+            Batch::Dump(task) => Box::new(std::iter::once(*task)) as Ret,
+            Batch::IndexOperation { op, .. } => match op {
+                IndexOperation::DocumentOperation { tasks, .. } => {
+                    Box::new(tasks.clone().into_iter()) as Ret
+                }
+                IndexOperation::DocumentDeletion { tasks, .. } => {
+                    Box::new(tasks.clone().into_iter()) as Ret
+                }
+                IndexOperation::DocumentClear { tasks, .. } => {
+                    Box::new(tasks.clone().into_iter()) as Ret
+                }
+                IndexOperation::Settings { tasks, .. } => {
+                    Box::new(tasks.clone().into_iter()) as Ret
+                }
+                IndexOperation::DocumentClearAndSetting {
+                    cleared_tasks, settings_tasks, ..
+                } => {
+                    Box::new(cleared_tasks.clone().into_iter().chain(settings_tasks.clone())) as Ret
+                }
+                IndexOperation::SettingsAndDocumentOperation {
+                    document_import_tasks,
+                    settings_tasks,
+                    ..
+                } => Box::new(
+                    document_import_tasks.clone().into_iter().chain(settings_tasks.clone()),
+                ) as Ret,
+            },
+            Batch::IndexCreation { task, .. } => Box::new(std::iter::once(*task)) as Ret,
+            Batch::IndexUpdate { task, .. } => Box::new(std::iter::once(*task)) as Ret,
+            Batch::IndexDeletion { tasks, .. } => Box::new(tasks.clone().into_iter()) as Ret,
+            Batch::IndexSwap { task } => Box::new(std::iter::once(*task)) as Ret,
+        }
+    }
+}

cluster/src/leader.rs

@@ -0,0 +1,276 @@
+use std::net::ToSocketAddrs;
+use std::sync::atomic::{AtomicUsize, Ordering};
+use std::sync::{atomic, Arc, Mutex, RwLock};
+use std::time::Duration;
+
+use bus::{Bus, BusReader};
+use crossbeam::channel::{unbounded, Receiver, Sender};
+use ductile::{ChannelReceiver, ChannelSender, ChannelServer};
+use log::{info, warn};
+use meilisearch_types::keys::Key;
+use meilisearch_types::tasks::Task;
+use synchronoise::SignalEvent;
+use uuid::Uuid;
+
+use crate::batch::Batch;
+use crate::{ApiKeyOperation, Consistency, FollowerMsg, LeaderMsg};
+
+#[derive(Clone)]
+pub struct Leader {
+    task_ready_to_commit: Receiver<u32>,
+    broadcast_to_follower: Sender<LeaderMsg>,
+    needs_key_sender: Sender<Sender<Vec<Key>>>,
+    needs_key_receiver: Receiver<Sender<Vec<Key>>>,
+
+    pub wake_up: Arc<SignalEvent>,
+
+    new_followers: Arc<AtomicUsize>,
+    active_followers: Arc<AtomicUsize>,
+
+    batch_id: Arc<RwLock<u32>>,
+}
+
+impl Leader {
+    pub fn new(
+        listen_on: impl ToSocketAddrs + Send + 'static,
+        master_key: Option<String>,
+    ) -> Leader {
+        let new_followers = Arc::new(AtomicUsize::new(0));
+        let active_followers = Arc::new(AtomicUsize::new(1));
+        let wake_up = Arc::new(SignalEvent::auto(true));
+        let (broadcast_to_follower, process_batch_receiver) = unbounded();
+        let (task_finished_sender, task_finished_receiver) = unbounded();
+        let (needs_key_sender, needs_key_receiver) = unbounded();
+
+        let nf = new_followers.clone();
+        let af = active_followers.clone();
+        let wu = wake_up.clone();
+        std::thread::spawn(move || {
+            Self::listener(
+                listen_on,
+                master_key,
+                nf,
+                af,
+                wu,
+                process_batch_receiver,
+                task_finished_sender,
+            )
+        });
+
+        Leader {
+            task_ready_to_commit: task_finished_receiver,
+            broadcast_to_follower,
+            needs_key_sender,
+            needs_key_receiver,
+
+            wake_up,
+
+            new_followers,
+            active_followers,
+            batch_id: Arc::default(),
+        }
+    }
+
+    pub fn has_new_followers(&self) -> bool {
+        self.new_followers.load(Ordering::Relaxed) != 0
+    }
+
+    /// Takes all the necessary channels to chat with the scheduler and give them
+    /// to each new followers
+    fn listener(
+        listen_on: impl ToSocketAddrs,
+        master_key: Option<String>,
+        new_followers: Arc<AtomicUsize>,
+        active_followers: Arc<AtomicUsize>,
+        wake_up: Arc<SignalEvent>,
+        broadcast_to_follower: Receiver<LeaderMsg>,
+        task_finished: Sender<u32>,
+    ) {
+        let listener: ChannelServer<LeaderMsg, FollowerMsg> = if let Some(ref master_key) =
+            master_key
+        {
+            let mut enc = [0; 32];
+            let master_key = master_key.as_bytes();
+            if master_key.len() < 32 {
+                warn!("Master key is not secure, use a longer master key (at least 32 bytes long)");
+            }
+            enc.iter_mut().zip(master_key).for_each(|(enc, mk)| *enc = *mk);
+            info!("Listening with encryption enabled");
+            ChannelServer::bind_with_enc(listen_on, enc).unwrap()
+        } else {
+            ChannelServer::bind(listen_on).unwrap()
+        };
+
+        info!("Ready to the receive connections");
+
+        // We're going to broadcast all the batches to all our follower
+        let bus: Bus<LeaderMsg> = Bus::new(10);
+        let bus = Arc::new(Mutex::new(bus));
+        let b = bus.clone();
+
+        std::thread::spawn(move || loop {
+            let msg = broadcast_to_follower.recv().expect("Main thread is dead");
+            b.lock().unwrap().broadcast(msg);
+        });
+
+        for (sender, receiver, _addr) in listener {
+            let task_finished = task_finished.clone();
+            let nf = new_followers.clone();
+            let af = active_followers.clone();
+            let wu = wake_up.clone();
+
+            let process_batch = bus.lock().unwrap().add_rx();
+
+            std::thread::spawn(move || {
+                Self::follower(sender, receiver, nf, af, wu, process_batch, task_finished)
+            });
+        }
+    }
+
+    /// Allow a follower to chat with the scheduler
+    fn follower(
+        sender: ChannelSender<LeaderMsg>,
+        receiver: ChannelReceiver<FollowerMsg>,
+        new_followers: Arc<AtomicUsize>,
+        active_followers: Arc<AtomicUsize>,
+        wake_up: Arc<SignalEvent>,
+        mut broadcast_to_follower: BusReader<LeaderMsg>,
+        task_finished: Sender<u32>,
+    ) {
+        let size = new_followers.fetch_add(1, Ordering::Relaxed) + 1;
+        wake_up.signal();
+        info!("A new follower joined the cluster. {} members.", size);
+
+        loop {
+            if let msg @ LeaderMsg::JoinFromDump(_) =
+                broadcast_to_follower.recv().expect("Main thread died")
+            {
+                // we exit the new_follower state and become an active follower even though
+                // the dump will takes some time to index
+                new_followers.fetch_sub(1, Ordering::Relaxed);
+                let size = active_followers.fetch_add(1, Ordering::Relaxed) + 1;
+                info!("A new follower became active. {} active members.", size);
+
+                sender.send(msg).unwrap();
+                break;
+            }
+        }
+
+        // send messages to the follower
+        std::thread::spawn(move || loop {
+            let msg = broadcast_to_follower.recv().expect("Main thread died");
+            match msg {
+                LeaderMsg::JoinFromDump(_) => (),
+                msg => {
+                    if sender.send(msg).is_err() {
+                        // the follower died, the logging and cluster size update should be done
+                        // in the other thread
+                        break;
+                    }
+                }
+            }
+        });
+
+        // receive messages from the follower
+        loop {
+            match receiver.recv() {
+                Err(_) => break,
+                Ok(msg) => match msg {
+                    FollowerMsg::ReadyToCommit(id) => {
+                        task_finished.send(id).expect("Can't reach the main thread")
+                    }
+                    FollowerMsg::RegisterNewTask(_) => todo!(),
+                },
+            }
+        }
+
+        // if we exited from the previous loop it means the follower is down and should
+        // be removed from the cluster
+        let size = active_followers.fetch_sub(1, atomic::Ordering::Relaxed) - 1;
+        info!("A follower left the cluster. {} members.", size);
+    }
+
+    // ============= Everything related to the setup of the cluster
+    pub fn join_me(&self, dump: Vec<u8>) {
+        self.broadcast_to_follower
+            .send(LeaderMsg::JoinFromDump(dump))
+            .expect("Lost the link with the followers");
+    }
+
+    // ============= Everything related to the scheduler
+
+    pub fn starts_batch(&self, batch: Batch) {
+        let mut batch_id = self.batch_id.write().unwrap();
+
+        info!("Send the batch to process to the followers");
+        *batch_id += 1;
+
+        self.broadcast_to_follower
+            .send(LeaderMsg::StartBatch { id: *batch_id, batch })
+            .expect("Can't reach the cluster");
+    }
+
+    pub fn commit(&self, consistency_level: Consistency) {
+        info!("Wait until enough followers are ready to commit a batch");
+
+        let batch_id = self.batch_id.write().unwrap();
+
+        let mut nodes_ready_to_commit = 1;
+
+        loop {
+            let size = self.active_followers.load(atomic::Ordering::Relaxed);
+
+            info!("{nodes_ready_to_commit} nodes are ready to commit for a cluster size of {size}");
+            let all = nodes_ready_to_commit == size;
+
+            match consistency_level {
+                Consistency::One if nodes_ready_to_commit >= 1 || all => break,
+                Consistency::Two if nodes_ready_to_commit >= 2 || all => break,
+                Consistency::Quorum if nodes_ready_to_commit >= (size / 2) || all => break,
+                Consistency::All if all => break,
+                _ => (),
+            }
+
+            // we can't wait forever here because if a node dies the cluster size might get updated while we're stuck
+            match self.task_ready_to_commit.recv_timeout(Duration::new(1, 0)) {
+                Ok(id) if id == *batch_id => nodes_ready_to_commit += 1,
+                _ => continue,
+            };
+        }
+
+        info!("Tells all the follower to commit");
+
+        self.broadcast_to_follower.send(LeaderMsg::Commit(*batch_id)).unwrap();
+    }
+
+    pub fn register_new_task(&self, task: Task, update_file: Option<Vec<u8>>) {
+        info!("Tells all the follower to register a new task");
+        self.broadcast_to_follower
+            .send(LeaderMsg::RegisterNewTask { task, update_file })
+            .expect("Main thread is dead");
+    }
+
+    // ============= Everything related to the api-keys
+
+    pub fn insert_key(&self, key: Key) {
+        self.broadcast_to_follower
+            .send(LeaderMsg::ApiKeyOperation(ApiKeyOperation::Insert(key)))
+            .unwrap()
+    }
+
+    pub fn delete_key(&self, uuid: Uuid) {
+        self.broadcast_to_follower
+            .send(LeaderMsg::ApiKeyOperation(ApiKeyOperation::Delete(uuid)))
+            .unwrap()
+    }
+
+    pub fn needs_keys(&self) -> Sender<Vec<Key>> {
+        self.needs_key_receiver.recv().expect("The cluster is dead")
+    }
+
+    pub fn get_keys(&self) -> Vec<Key> {
+        let (send, rcv) = crossbeam::channel::bounded(1);
+        self.needs_key_sender.send(send).expect("The cluster is dead");
+        rcv.recv().expect("The auth controller is dead")
+    }
+}

cluster/src/lib.rs

@@ -0,0 +1,231 @@
+use std::net::ToSocketAddrs;
+use std::str::FromStr;
+use std::sync::{Arc, RwLock};
+
+use batch::Batch;
+use crossbeam::channel::{unbounded, Receiver, Sender};
+use ductile::{connect_channel, connect_channel_with_enc, ChannelReceiver, ChannelSender};
+use log::{info, warn};
+use meilisearch_types::keys::Key;
+use meilisearch_types::tasks::{KindWithContent, Task};
+use serde::{Deserialize, Serialize};
+
+pub mod batch;
+mod leader;
+
+pub use leader::Leader;
+use uuid::Uuid;
+
+#[derive(Debug, thiserror::Error)]
+pub enum Error {
+    #[error("Network issue occured")]
+    NetworkIssue,
+    #[error("Internal error: {0}")]
+    SerdeJson(#[from] serde_json::Error),
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum LeaderMsg {
+    /// A dump to join the cluster
+    JoinFromDump(Vec<u8>),
+    /// Starts a new batch
+    StartBatch { id: u32, batch: Batch },
+    /// Tell the follower to commit the update asap
+    Commit(u32),
+    /// Tell the follower to commit the update asap
+    RegisterNewTask { task: Task, update_file: Option<Vec<u8>> },
+
+    /// Tell the follower to commit the update asap
+    ApiKeyOperation(ApiKeyOperation),
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub enum FollowerMsg {
+    // Let the leader knows you're ready to commit
+    ReadyToCommit(u32),
+    RegisterNewTask(KindWithContent),
+}
+
+#[derive(Default, Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
+#[serde(rename_all = "lowercase")]
+pub enum Consistency {
+    One,
+    Two,
+    Quorum,
+    #[default]
+    All,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
+pub enum ApiKeyOperation {
+    Insert(Key),
+    Delete(Uuid),
+}
+
+impl std::fmt::Display for Consistency {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Consistency::One => write!(f, "one"),
+            Consistency::Two => write!(f, "two"),
+            Consistency::Quorum => write!(f, "quorum"),
+            Consistency::All => write!(f, "all"),
+        }
+    }
+}
+
+impl FromStr for Consistency {
+    type Err = String;
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        match s {
+            "one" => Ok(Consistency::One),
+            "two" => Ok(Consistency::Two),
+            "quorum" => Ok(Consistency::Quorum),
+            "all" => Ok(Consistency::All),
+            s => Err(format!(
+                "Unexpected value `{s}`, expected one of `one`, `two`, `quorum`, `all`"
+            )),
+        }
+    }
+}
+
+#[derive(Clone)]
+pub enum Cluster {
+    Leader(Leader),
+    Follower(Follower),
+}
+
+#[derive(Clone)]
+pub struct Follower {
+    sender: ChannelSender<FollowerMsg>,
+
+    get_batch: Receiver<(u32, Batch)>,
+    must_commit: Receiver<u32>,
+    register_new_task: Receiver<(Task, Option<Vec<u8>>)>,
+
+    api_key_op: Receiver<ApiKeyOperation>,
+
+    batch_id: Arc<RwLock<u32>>,
+}
+
+impl Follower {
+    pub fn join(leader: impl ToSocketAddrs, master_key: Option<String>) -> (Follower, Vec<u8>) {
+        let (sender, receiver) = if let Some(master_key) = master_key {
+            let mut enc = [0; 32];
+            let master_key = master_key.as_bytes();
+            if master_key.len() < 32 {
+                warn!("Master key is not secure, use a longer master key (at least 32 bytes long)");
+            }
+            enc.iter_mut().zip(master_key).for_each(|(enc, mk)| *enc = *mk);
+            info!("Connecting with encryption enabled");
+            connect_channel_with_enc(leader, &enc).unwrap()
+        } else {
+            connect_channel(leader).unwrap()
+        };
+
+        info!("Connection to the leader established");
+
+        info!("Waiting for the leader to contact us");
+        let state = receiver.recv().unwrap();
+
+        let dump = match state {
+            LeaderMsg::JoinFromDump(dump) => dump,
+            msg => panic!("Received unexpected message {msg:?}"),
+        };
+
+        let (get_batch_sender, get_batch_receiver) = unbounded();
+        let (must_commit_sender, must_commit_receiver) = unbounded();
+        let (register_task_sender, register_task_receiver) = unbounded();
+        let (create_api_key_sender, create_api_key_receiver) = unbounded();
+
+        std::thread::spawn(move || {
+            Self::router(
+                receiver,
+                get_batch_sender,
+                must_commit_sender,
+                register_task_sender,
+                create_api_key_sender,
+            );
+        });
+
+        (
+            Follower {
+                sender,
+                get_batch: get_batch_receiver,
+                must_commit: must_commit_receiver,
+                register_new_task: register_task_receiver,
+                api_key_op: create_api_key_receiver,
+                batch_id: Arc::default(),
+            },
+            dump,
+        )
+    }
+
+    fn router(
+        receiver: ChannelReceiver<LeaderMsg>,
+        get_batch: Sender<(u32, Batch)>,
+        must_commit: Sender<u32>,
+        register_new_task: Sender<(Task, Option<Vec<u8>>)>,
+        api_key_op: Sender<ApiKeyOperation>,
+    ) {
+        loop {
+            match receiver.recv().expect("Lost connection to the leader") {
+                LeaderMsg::JoinFromDump(_) => {
+                    warn!("Received a join from dump msg but I’m already running : ignoring the message")
+                }
+                LeaderMsg::StartBatch { id, batch } => {
+                    info!("Starting to process a new batch");
+                    get_batch.send((id, batch)).expect("Lost connection to the main thread")
+                }
+                LeaderMsg::Commit(id) => {
+                    info!("Must commit");
+                    must_commit.send(id).expect("Lost connection to the main thread")
+                }
+                LeaderMsg::RegisterNewTask { task, update_file } => {
+                    info!("Registered a new task");
+                    register_new_task
+                        .send((task, update_file))
+                        .expect("Lost connection to the main thread")
+                }
+                LeaderMsg::ApiKeyOperation(key) => {
+                    api_key_op.send(key).expect("Lost connection to the main thread")
+                }
+            }
+        }
+    }
+
+    pub fn get_new_batch(&self) -> Batch {
+        info!("Get new batch called");
+        let (id, batch) = self.get_batch.recv().expect("Lost connection to the leader");
+        info!("Got a new batch");
+        *self.batch_id.write().unwrap() = id;
+        batch
+    }
+
+    pub fn ready_to_commit(&self) {
+        info!("I'm ready to commit");
+        let batch_id = self.batch_id.read().unwrap();
+
+        self.sender.send(FollowerMsg::ReadyToCommit(*batch_id)).unwrap();
+
+        loop {
+            let id = self.must_commit.recv().expect("Lost connection to the leader");
+            #[allow(clippy::comparison_chain)]
+            if id == *batch_id {
+                break;
+            } else if id > *batch_id {
+                panic!("We missed a batch");
+            }
+        }
+        info!("I got the right to commit");
+    }
+
+    pub fn get_new_task(&self) -> (Task, Option<Vec<u8>>) {
+        self.register_new_task.recv().expect("Lost connection to the leader")
+    }
+
+    pub fn api_key_operation(&self) -> ApiKeyOperation {
+        info!("Creating a new api key");
+        self.api_key_op.recv().expect("Lost connection to the leader")
+    }
+}

config.toml

@@ -45,7 +45,7 @@ log_level = "INFO"
 
 dump_dir = "dumps/"
 # Sets the directory where Meilisearch will create dump files.
-# https://docs.meilisearch.com/learn/configuration/instance_options.html#dumps-destination
+# https://docs.meilisearch.com/learn/configuration/instance_options.html#dump-directory
 
 # import_dump = "./path/to/my/file.dump"
 # Imports the dump file located at the specified path. Path must point to a .dump file.
@@ -118,3 +118,13 @@ ssl_resumption = false
 ssl_tickets = false
 # Activates SSL tickets.
 # https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-tickets
+
+#############################
+### Experimental features ###
+#############################
+
+experimental_enable_metrics = false
+# Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
+# Enables the Prometheus metrics on the `GET /metrics` endpoint.
+
+

dump/Cargo.toml

@@ -1,7 +1,14 @@
 [package]
 name = "dump"
-version = "1.0.0"
-edition = "2021"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+edition.workspace = true
+homepage.workspace = true
+readme.workspace = true
+license.workspace = true
 
 [dependencies]
 anyhow = "1.0.65"

dump/src/lib.rs

@@ -203,12 +203,11 @@ pub(crate) mod test {
 
     use big_s::S;
     use maplit::btreeset;
-    use meilisearch_types::index_uid::IndexUid;
+    use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
     use meilisearch_types::milli::update::Setting;
     use meilisearch_types::milli::{self};
     use meilisearch_types::settings::{Checked, Settings};
-    use meilisearch_types::star_or::StarOr;
     use meilisearch_types::tasks::{Details, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
@@ -341,7 +340,7 @@ pub(crate) mod test {
                 name: Some(S("doggos_key")),
                 uid: Uuid::from_str("9f8a34da-b6b2-42f0-939b-dbd4c3448655").unwrap(),
                 actions: vec![Action::DocumentsAll],
-                indexes: vec![StarOr::Other(IndexUid::from_str("doggos").unwrap())],
+                indexes: vec![IndexUidPattern::from_str("doggos").unwrap()],
                 expires_at: Some(datetime!(4130-03-14 12:21 UTC)),
                 created_at: datetime!(1960-11-15 0:00 UTC),
                 updated_at: datetime!(2022-11-10 0:00 UTC),
@@ -351,7 +350,7 @@ pub(crate) mod test {
                 name: Some(S("master_key")),
                 uid: Uuid::from_str("4622f717-1c00-47bb-a494-39d76a49b591").unwrap(),
                 actions: vec![Action::All],
-                indexes: vec![StarOr::Star],
+                indexes: vec![IndexUidPattern::all()],
                 expires_at: None,
                 created_at: datetime!(0000-01-01 00:01 UTC),
                 updated_at: datetime!(1964-05-04 17:25 UTC),

dump/src/reader/compat/v5_to_v6.rs

@@ -181,10 +181,8 @@ impl CompatV5ToV6 {
                     .indexes
                     .into_iter()
                     .map(|index| match index {
-                        v5::StarOr::Star => v6::StarOr::Star,
-                        v5::StarOr::Other(uid) => {
-                            v6::StarOr::Other(v6::IndexUid::new_unchecked(uid.as_str()))
-                        }
+                        v5::StarOr::Star => v6::IndexUidPattern::all(),
+                        v5::StarOr::Other(uid) => v6::IndexUidPattern::new_unchecked(uid.as_str()),
                     })
                     .collect(),
                 expires_at: key.expires_at,

dump/src/reader/v3/mod.rs

@@ -112,8 +112,11 @@ impl V3Reader {
     pub fn indexes(&self) -> Result<impl Iterator<Item = Result<V3IndexReader>> + '_> {
         Ok(self.index_uuid.iter().map(|index| -> Result<_> {
             V3IndexReader::new(
-                index.uid.clone(),
                 &self.dump.path().join("indexes").join(index.uuid.to_string()),
+                index,
+                BufReader::new(
+                    File::open(self.dump.path().join("updates").join("data.jsonl")).unwrap(),
+                ),
             )
         }))
     }
@@ -155,16 +158,42 @@ pub struct V3IndexReader {
 }
 
 impl V3IndexReader {
-    pub fn new(name: String, path: &Path) -> Result<Self> {
+    pub fn new(path: &Path, index_uuid: &IndexUuid, tasks: BufReader<File>) -> Result<Self> {
         let meta = File::open(path.join("meta.json"))?;
         let meta: DumpMeta = serde_json::from_reader(meta)?;
 
+        let mut created_at = None;
+        let mut updated_at = None;
+
+        for line in tasks.lines() {
+            let task: Task = serde_json::from_str(&line?)?;
+
+            if !(task.uuid == index_uuid.uuid && task.is_finished()) {
+                continue;
+            }
+
+            let new_created_at = match task.update.meta() {
+                Kind::DocumentAddition { .. } | Kind::Settings(_) => task.update.finished_at(),
+                _ => None,
+            };
+            let new_updated_at = task.update.finished_at();
+
+            if created_at.is_none() || created_at > new_created_at {
+                created_at = new_created_at;
+            }
+
+            if updated_at.is_none() || updated_at < new_updated_at {
+                updated_at = new_updated_at;
+            }
+        }
+
+        let current_time = OffsetDateTime::now_utc();
+
         let metadata = IndexMetadata {
-            uid: name,
+            uid: index_uuid.uid.clone(),
             primary_key: meta.primary_key,
-            // FIXME: Iterate over the whole task queue to find the creation and last update date.
-            created_at: OffsetDateTime::now_utc(),
-            updated_at: OffsetDateTime::now_utc(),
+            created_at: created_at.unwrap_or(current_time),
+            updated_at: updated_at.unwrap_or(current_time),
         };
 
         let ret = V3IndexReader {
@@ -263,12 +292,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        insta::assert_json_snapshot!(products.metadata(), @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "[now]",
-          "updatedAt": "[now]"
+          "createdAt": "2022-10-07T11:38:54.74389899Z",
+          "updatedAt": "2022-10-07T11:38:55.963185778Z"
         }
         "###);
 
@@ -278,12 +307,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        insta::assert_json_snapshot!(movies.metadata(), @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "[now]",
-          "updatedAt": "[now]"
+          "createdAt": "2022-10-07T11:38:54.026649575Z",
+          "updatedAt": "2022-10-07T11:39:04.188852537Z"
         }
         "###);
 
@@ -308,12 +337,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
+        insta::assert_json_snapshot!(spells.metadata(), @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "[now]",
-          "updatedAt": "[now]"
+          "createdAt": "2022-10-07T11:38:56.265951133Z",
+          "updatedAt": "2022-10-07T11:38:56.521004328Z"
         }
         "###);
 

dump/src/reader/v3/updates.rs

@@ -74,6 +74,26 @@ impl UpdateStatus {
             _ => None,
         }
     }
+
+    pub fn enqueued_at(&self) -> Option<OffsetDateTime> {
+        match self {
+            UpdateStatus::Processing(u) => Some(u.from.enqueued_at),
+            UpdateStatus::Enqueued(u) => Some(u.enqueued_at),
+            UpdateStatus::Processed(u) => Some(u.from.from.enqueued_at),
+            UpdateStatus::Aborted(u) => Some(u.from.enqueued_at),
+            UpdateStatus::Failed(u) => Some(u.from.from.enqueued_at),
+        }
+    }
+
+    pub fn finished_at(&self) -> Option<OffsetDateTime> {
+        match self {
+            UpdateStatus::Processing(_) => None,
+            UpdateStatus::Enqueued(_) => None,
+            UpdateStatus::Processed(u) => Some(u.processed_at),
+            UpdateStatus::Aborted(_) => None,
+            UpdateStatus::Failed(u) => Some(u.failed_at),
+        }
+    }
 }
 
 #[derive(Debug, Deserialize, Clone)]

dump/src/reader/v6/mod.rs

@@ -34,8 +34,7 @@ pub type PaginationSettings = meilisearch_types::settings::PaginationSettings;
 
 // everything related to the api keys
 pub type Action = meilisearch_types::keys::Action;
-pub type StarOr<T> = meilisearch_types::star_or::StarOr<T>;
-pub type IndexUid = meilisearch_types::index_uid::IndexUid;
+pub type IndexUidPattern = meilisearch_types::index_uid_pattern::IndexUidPattern;
 
 // everything related to the errors
 pub type ResponseError = meilisearch_types::error::ResponseError;

file-store/Cargo.toml

@@ -1,7 +1,14 @@
 [package]
 name = "file-store"
-version = "1.0.0"
-edition = "2021"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
 
 [dependencies]
 tempfile = "3.3.0"

file-store/src/lib.rs

@@ -116,10 +116,20 @@ impl FileStore {
 
     /// List the Uuids of the files in the FileStore
     pub fn all_uuids(&self) -> Result<impl Iterator<Item = Result<Uuid>>> {
-        Ok(self.path.read_dir()?.map(|entry| {
-            Ok(Uuid::from_str(
-                entry?.file_name().to_str().ok_or(Error::CouldNotParseFileNameAsUtf8)?,
-            )?)
+        Ok(self.path.read_dir()?.filter_map(|entry| {
+            let file_name = match entry {
+                Ok(entry) => entry.file_name(),
+                Err(e) => return Some(Err(e.into())),
+            };
+            let file_name = match file_name.to_str() {
+                Some(file_name) => file_name,
+                None => return Some(Err(Error::CouldNotParseFileNameAsUtf8)),
+            };
+            if file_name.starts_with('.') {
+                None
+            } else {
+                Some(Uuid::from_str(file_name).map_err(|e| e.into()))
+            }
         }))
     }
 }
@@ -135,3 +145,34 @@ impl File {
         Ok(())
     }
 }
+
+#[cfg(test)]
+mod test {
+    use std::io::Write;
+
+    use tempfile::TempDir;
+
+    use super::*;
+
+    #[test]
+    fn all_uuids() {
+        let dir = TempDir::new().unwrap();
+        let fs = FileStore::new(dir.path()).unwrap();
+        let (uuid, mut file) = fs.new_update().unwrap();
+        file.write_all(b"Hello world").unwrap();
+        file.persist().unwrap();
+        let all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(all_uuids, vec![uuid]);
+
+        let (uuid2, file) = fs.new_update().unwrap();
+        let all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        assert_eq!(all_uuids, vec![uuid]);
+
+        file.persist().unwrap();
+        let mut all_uuids = fs.all_uuids().unwrap().collect::<Result<Vec<_>>>().unwrap();
+        all_uuids.sort();
+        let mut expected = vec![uuid, uuid2];
+        expected.sort();
+        assert_eq!(all_uuids, expected);
+    }
+}

filter-parser/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "filter-parser"
+description = "The parser for the Meilisearch filter syntax"
+publish = false
+
+version.workspace = true
+authors.workspace = true
+# description.workspace = true
+homepage.workspace = true
+readme.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+nom = "7.1.1"
+nom_locate = "4.0.0"
+
+[dev-dependencies]
+insta = "1.21.0"

filter-parser/README.md

@@ -0,0 +1,36 @@
+# Filter parser
+
+This workspace is dedicated to the parsing of the Meilisearch filters.
+
+Most of the code and explanation are in the [`lib.rs`](./src/lib.rs). Especially, the BNF of the filters at the top of this file.
+
+The parser use [nom](https://docs.rs/nom/) to do most of its work and [nom-locate](https://docs.rs/nom_locate/) to keep track of what we were doing when we encountered an error.
+
+## Cli
+A simple main is provided to quick-test if a filter can be parsed or not without bringing milli.
+It takes one argument and try to parse it.
+```
+cargo run -- 'field = value' # success
+cargo run -- 'field = "doggo' # error => missing closing delimiter "
+```
+
+## Fuzz
+The workspace have been fuzzed with [cargo-fuzz](https://rust-fuzz.github.io/book/cargo-fuzz.html).
+
+### Setup
+You'll need rust-nightly to execute the fuzzer.
+
+```
+cargo install cargo-fuzz
+```
+
+### Run
+When the filter parser is executed by the fuzzer it's triggering a stackoverflow really fast. We can avoid this problem by limiting the `max_len` of [libfuzzer](https://llvm.org/docs/LibFuzzer.html) at 500 characters.
+```
+cargo fuzz run parse -- -max_len=500
+```
+
+## What to do if you find a bug in the parser
+
+- Write a test at the end of the [`lib.rs`](./src/lib.rs) to ensure it never happens again.
+- Add a file in [the corpus directory](./fuzz/corpus/parse/) with your filter to help the fuzzer find new bugs. Since this directory is going to be heavily polluted by the execution of the fuzzer it's in the gitignore and you'll need to force push your new test.

filter-parser/fuzz/.gitignore

@@ -0,0 +1,3 @@
+/corpus/
+/artifacts/
+/target/

filter-parser/fuzz/Cargo.toml

@@ -0,0 +1,25 @@
+[package]
+name = "filter-parser-fuzz"
+version = "0.0.0"
+authors = ["Automatically generated"]
+publish = false
+edition = "2018"
+
+[package.metadata]
+cargo-fuzz = true
+
+[dependencies]
+libfuzzer-sys = "0.4"
+
+[dependencies.filter-parser]
+path = ".."
+
+# Prevent this from interfering with workspaces
+[workspace]
+members = ["."]
+
+[[bin]]
+name = "parse"
+path = "fuzz_targets/parse.rs"
+test = false
+doc = false

filter-parser/fuzz/corpus/parse/test_1

@@ -0,0 +1 @@
+channel = Ponce

filter-parser/fuzz/corpus/parse/test_10

@@ -0,0 +1 @@
+channel != ponce

filter-parser/fuzz/corpus/parse/test_11

@@ -0,0 +1 @@
+NOT channel = ponce

filter-parser/fuzz/corpus/parse/test_12

@@ -0,0 +1 @@
+subscribers < 1000

filter-parser/fuzz/corpus/parse/test_13

@@ -0,0 +1 @@
+subscribers > 1000

filter-parser/fuzz/corpus/parse/test_14

@@ -0,0 +1 @@
+subscribers <= 1000

filter-parser/fuzz/corpus/parse/test_15

@@ -0,0 +1 @@
+subscribers >= 1000

filter-parser/fuzz/corpus/parse/test_16

@@ -0,0 +1 @@
+NOT subscribers < 1000

filter-parser/fuzz/corpus/parse/test_17

@@ -0,0 +1 @@
+NOT subscribers > 1000

filter-parser/fuzz/corpus/parse/test_18

@@ -0,0 +1 @@
+NOT subscribers <= 1000

filter-parser/fuzz/corpus/parse/test_19

@@ -0,0 +1 @@
+NOT subscribers >= 1000

filter-parser/fuzz/corpus/parse/test_2

@@ -0,0 +1 @@
+subscribers = 12

filter-parser/fuzz/corpus/parse/test_20

@@ -0,0 +1 @@
+subscribers 100 TO 1000

filter-parser/fuzz/corpus/parse/test_21

@@ -0,0 +1 @@
+NOT subscribers 100 TO 1000

filter-parser/fuzz/corpus/parse/test_22

@@ -0,0 +1 @@
+_geoRadius(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_23

@@ -0,0 +1 @@
+NOT _geoRadius(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_24

@@ -0,0 +1 @@
+channel = ponce AND 'dog race' != 'bernese mountain'

filter-parser/fuzz/corpus/parse/test_25

@@ -0,0 +1 @@
+channel = ponce OR 'dog race' != 'bernese mountain'

filter-parser/fuzz/corpus/parse/test_26

@@ -0,0 +1 @@
+channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000

filter-parser/fuzz/corpus/parse/test_27

@@ -0,0 +1 @@
+channel = ponce AND ( 'dog race' != 'bernese mountain' OR subscribers > 1000 )

filter-parser/fuzz/corpus/parse/test_28

@@ -0,0 +1 @@
+(channel = ponce AND 'dog race' != 'bernese mountain' OR subscribers > 1000) AND _geoRadius(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_29

@@ -0,0 +1 @@
+channel = Ponce = 12

filter-parser/fuzz/corpus/parse/test_3

@@ -0,0 +1 @@
+channel = 'Mister Mv'

filter-parser/fuzz/corpus/parse/test_30

@@ -0,0 +1 @@
+channel =

filter-parser/fuzz/corpus/parse/test_31

@@ -0,0 +1 @@
+channel = 🐻

filter-parser/fuzz/corpus/parse/test_32

@@ -0,0 +1 @@
+OR

filter-parser/fuzz/corpus/parse/test_33

@@ -0,0 +1 @@
+AND

filter-parser/fuzz/corpus/parse/test_34

@@ -0,0 +1 @@
+channel Ponce

filter-parser/fuzz/corpus/parse/test_35

@@ -0,0 +1 @@
+channel = Ponce OR

filter-parser/fuzz/corpus/parse/test_36

@@ -0,0 +1 @@
+_geoRadius

filter-parser/fuzz/corpus/parse/test_37

@@ -0,0 +1 @@
+_geoRadius = 12

filter-parser/fuzz/corpus/parse/test_38

@@ -0,0 +1 @@
+_geoPoint(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_39

@@ -0,0 +1 @@
+position <= _geoPoint(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_4

@@ -0,0 +1 @@
+channel = "Mister Mv"

filter-parser/fuzz/corpus/parse/test_40

@@ -0,0 +1 @@
+position <= _geoRadius(12, 13, 14)

filter-parser/fuzz/corpus/parse/test_41

@@ -0,0 +1 @@
+channel = 'ponce

filter-parser/fuzz/corpus/parse/test_42

@@ -0,0 +1 @@
+channel = "ponce

filter-parser/fuzz/corpus/parse/test_43

@@ -0,0 +1 @@
+channel = mv OR (followers >= 1000

filter-parser/fuzz/corpus/parse/test_5

@@ -0,0 +1 @@
+'dog race' = Borzoi

filter-parser/fuzz/corpus/parse/test_6

@@ -0,0 +1 @@
+"dog race" = Chusky

filter-parser/fuzz/corpus/parse/test_7

@@ -0,0 +1 @@
+"dog race" = "Bernese Mountain"

filter-parser/fuzz/corpus/parse/test_8

@@ -0,0 +1 @@
+'dog race' = 'Bernese Mountain'