bump strois version

add a lot of comments and logs

.github/ISSUE_TEMPLATE/sprint_issue.md

@@ -7,17 +7,19 @@ assignees: ''
 
 ---
 
-Related product team resources: [PRD]() (_internal only_)
+Related product team resources: [roadmap card]() (_internal only_) and [PRD]() (_internal only_)
 Related product discussion:
 Related spec: WIP
 
 ## Motivation
 
-<!---Copy/paste the information in PRD or briefly detail the product motivation. Ask product team if any hesitation.-->
+<!---Copy/paste the information in the roadmap resources or briefly detail the product motivation. Ask product team if any hesitation.-->
 
 ## Usage
 
-<!---Link to the public part of the PRD, or to the related product discussion for experimental features-->
+<!---Write a quick description of the usage if the usage has already been defined-->
+
+Refer to the final spec to know the details and the final decisions about the usage.
 
 ## TODO
 

.github/workflows/benchmarks-manual.yml

@@ -74,4 +74,4 @@ jobs:
           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/scripts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"
+          echo "  - Run the following command: ./benchmaks/scipts/compare.sh <file-to-compare-with> ${{ steps.file.outputs.basename }}.json"

.github/workflows/benchmarks-pr.yml

@@ -1,98 +0,0 @@
-name: Benchmarks (PR)
-on: issue_comment
-permissions:
-  issues: write
-
-env:
-  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-
-jobs:
-  run-benchmarks-on-comment:
-    if: startsWith(github.event.comment.body, '/benchmark')
-    name: Run and upload benchmarks
-    runs-on: benchmarks
-    timeout-minutes: 4320 # 72h
-    steps:
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-
-      - name: Check for Command
-        id: command
-        uses: xt0rted/slash-command-action@v2
-        with:
-          command: benchmark
-          reaction-type: "eyes"
-          repo-token: ${{ env.GH_TOKEN }}
-
-      - uses: xt0rted/pull-request-comment-branch@v2
-        id: comment-branch
-        with:
-          repo_token: ${{ env.GH_TOKEN }}
-
-      - uses: actions/checkout@v3
-        if: success()
-        with:
-          fetch-depth: 0 # fetch full history to be able to get main commit sha
-          ref: ${{ steps.comment-branch.outputs.head_ref }}
-
-      # Set variables
-      - name: Set current branch name
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD)" >> $GITHUB_OUTPUT
-        id: current_branch
-      - name: Set normalized current branch name # Replace `/` by `_` in branch name to avoid issues when pushing to S3
-        shell: bash
-        run: echo "name=$(git rev-parse --abbrev-ref HEAD | 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 ${{ steps.command.outputs.command-arguments }}_${{ steps.normalized_current_branch.outputs.name }}_${{ steps.commit_sha.outputs.short }})" >> $GITHUB_OUTPUT
-        id: file
-
-      # Run benchmarks
-      - name: Run benchmarks - Dataset ${{ steps.command.outputs.command-arguments }} - Branch ${{ steps.current_branch.outputs.name }} - Commit ${{ steps.commit_sha.outputs.short }}
-        run: |
-          cd benchmarks
-          cargo bench --bench ${{ steps.command.outputs.command-arguments }} -- --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
-
-      # Compute the diff of the benchmarks and send a message on the GitHub PR
-      - name: Compute and send a message in the PR
-        env:
-          GITHUB_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-        run: |
-          set -x
-          export base_ref=$(git merge-base origin/main ${{ steps.comment-branch.outputs.head_ref }} | head -c8)
-          export base_filename=$(echo ${{ steps.command.outputs.command-arguments }}_main_${base_ref}.json)
-          export bench_name=$(echo ${{ steps.command.outputs.command-arguments }})
-          echo "Here are your $bench_name benchmarks diff 👊" >> body.txt
-          echo '```' >> body.txt
-          ./benchmarks/scripts/compare.sh $base_filename ${{ steps.file.outputs.basename }}.json >> body.txt
-          echo '```' >> body.txt
-          gh pr comment ${{ steps.current_branch.outputs.name }} --body-file body.txt

.github/workflows/dependency-issue.yml

@@ -2,8 +2,8 @@ name: Create issue to upgrade dependencies
 
 on:
   schedule:
-    # Run the first of the month, every 6 month
-    - cron: '0 0 1 */6 *'
+    # Run the first of the month, every 3 month
+    - cron: '0 0 1 */3 *'
   workflow_dispatch:
 
 jobs:

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

@@ -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@2.7.0
+      uses: svenstaro/upload-release-action@2.6.1
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/debian/meilisearch.deb
@@ -50,9 +50,8 @@ jobs:
     needs: check-version
     steps:
       - name: Create PR to Homebrew
-        uses: mislav/bump-homebrew-formula-action@v3
+        uses: mislav/bump-homebrew-formula-action@v2
         with:
           formula-name: meilisearch
-          formula-path: Formula/m/meilisearch.rb
         env:
           COMMITTER_TOKEN: ${{ secrets.HOMEBREW_COMMITTER_TOKEN }}

.github/workflows/publish-binaries.yml

@@ -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@2.7.0
+      uses: svenstaro/upload-release-action@2.6.1
       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@2.7.0
+      uses: svenstaro/upload-release-action@2.6.1
       with:
         repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
         file: target/release/${{ matrix.artifact_name }}
@@ -121,7 +121,7 @@ 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@2.7.0
+        uses: svenstaro/upload-release-action@2.6.1
         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@2.7.0
+        uses: svenstaro/upload-release-action@2.6.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

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

@@ -57,20 +57,20 @@ jobs:
           echo "date=$commit_date" >> $GITHUB_OUTPUT
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v2
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v2
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v4
         with:
           images: getmeili/meilisearch
           # Prevent `latest` to be updated for each new tag pushed.
@@ -83,7 +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@v5
+        uses: docker/build-push-action@v4
         with:
           push: true
           platforms: linux/amd64,linux/arm64

.github/workflows/sdks-tests.yml

@@ -14,7 +14,6 @@ on:
 env:
   MEILI_MASTER_KEY: 'masterKey'
   MEILI_NO_ANALYTICS: 'true'
-  DISABLE_COVERAGE: 'true'
 
 jobs:
   define-docker-image:
@@ -31,117 +30,6 @@ jobs:
           if [[ $event == 'workflow_dispatch' ]]; then
             echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
           fi
-      - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
-
-##########
-## SDKs ##
-##########
-
-  meilisearch-dotnet-tests:
-    needs: define-docker-image
-    name: .NET SDK tests
-    runs-on: ubuntu-latest
-    env:
-      MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
-
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dotnet
-      - name: Setup .NET Core
-        uses: actions/setup-dotnet@v3
-        with:
-          dotnet-version: "6.0.x"
-      - name: Install dependencies
-        run: dotnet restore
-      - name: Build
-        run: dotnet build --configuration Release --no-restore
-      - name: Meilisearch (latest version) setup with Docker
-        run: docker compose up -d
-      - name: Run tests
-        run: dotnet test --no-restore --verbosity normal
-
-  meilisearch-dart-tests:
-    needs: define-docker-image
-    name: Dart SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-dart
-      - uses: dart-lang/setup-dart@v1
-        with:
-          sdk: 3.1.1
-      - name: Install dependencies
-        run: dart pub get
-      - name: Run integration tests
-        run: dart test --concurrency=4
-
-  meilisearch-go-tests:
-    needs: define-docker-image
-    name: Go SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - name: Set up Go
-        uses: actions/setup-go@v4
-        with:
-          go-version: stable
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-go
-      - name: Get dependencies
-        run: |
-          go get -v -t -d ./...
-          if [ -f Gopkg.toml ]; then
-            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-            dep ensure
-          fi
-      - name: Run integration tests
-        run: go test -v ./...
-
-  meilisearch-java-tests:
-    needs: define-docker-image
-    name: Java SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-java
-      - name: Set up Java
-        uses: actions/setup-java@v3
-        with:
-          java-version: 8
-          distribution: 'zulu'
-          cache: gradle
-      - name: Grant execute permission for gradlew
-        run: chmod +x gradlew
-      - name: Build and run unit and integration tests
-        run: ./gradlew build integrationTest
 
   meilisearch-js-tests:
     needs: define-docker-image
@@ -160,7 +48,7 @@ jobs:
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v3
         with:
           cache: 'yarn'
       - name: Install dependencies
@@ -178,6 +66,33 @@ jobs:
       - name: Run Browser env
         run: yarn test:env:browser
 
+  instant-meilisearch-tests:
+    needs: define-docker-image
+    name: instant-meilisearch tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/instant-meilisearch
+      - name: Setup node
+        uses: actions/setup-node@v3
+        with:
+          cache: yarn
+      - name: Install dependencies
+        run: yarn install
+      - name: Run tests
+        run: yarn test
+      - name: Build all the playgrounds and the packages
+        run: yarn build
+
   meilisearch-php-tests:
     needs: define-docker-image
     name: PHP SDK tests
@@ -196,6 +111,8 @@ jobs:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
         uses: shivammathur/setup-php@v2
+        with:
+          coverage: none
       - name: Validate composer.json and composer.lock
         run: composer validate
       - name: Install dependencies
@@ -232,6 +149,36 @@ jobs:
       - name: Test with pytest
         run: pipenv run pytest
 
+  meilisearch-go-tests:
+    needs: define-docker-image
+    name: Go SDK tests
+    runs-on: ubuntu-latest
+    services:
+      meilisearch:
+        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        env:
+          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
+          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: stable
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/meilisearch-go
+      - name: Get dependencies
+        run: |
+          go get -v -t -d ./...
+          if [ -f Gopkg.toml ]; then
+            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
+            dep ensure
+          fi
+      - name: Run integration tests
+        run: go test -v ./...
+
   meilisearch-ruby-tests:
     needs: define-docker-image
     name: Ruby SDK tests
@@ -277,110 +224,3 @@ jobs:
         run: cargo build --verbose
       - name: Run tests
         run: cargo test --verbose
-
-  meilisearch-swift-tests:
-    needs: define-docker-image
-    name: Swift SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-swift
-      - name: Run tests
-        run: swift test
-
-########################
-## FRONT-END PLUGINS ##
-########################
-
-  meilisearch-js-plugins-tests:
-    needs: define-docker-image
-    name: meilisearch-js-plugins tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-js-plugins
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          cache: yarn
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-      - name: Build all the playgrounds and the packages
-        run: yarn build
-
-########################
-## BACK-END PLUGINS ###
-########################
-
-  meilisearch-rails-tests:
-    needs: define-docker-image
-    name: meilisearch-rails tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-rails
-      - name: Set up Ruby 3
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-          bundler-cache: true
-      - name: Run tests
-        run: bundle exec rspec
-
-  meilisearch-symfony-tests:
-    needs: define-docker-image
-    name: meilisearch-symfony tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          repository: meilisearch/meilisearch-symfony
-      - name: Install PHP
-        uses: shivammathur/setup-php@v2
-        with:
-          tools: composer:v2, flex
-      - name: Validate composer.json and composer.lock
-        run: composer validate
-      - name: Install dependencies
-        run: composer install --prefer-dist --no-progress --quiet
-      - name: Remove doctrine/annotations
-        run: composer remove --dev doctrine/annotations
-      - name: Run test suite
-        run: composer test:unit

.github/workflows/test-suite.yml

@@ -37,13 +37,13 @@ jobs:
           toolchain: stable
           override: true
       - name: Setup test with Rust nightly
-        if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
+        if: github.event_name == 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -65,7 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -78,12 +78,12 @@ jobs:
           args: --locked --release --all
 
   test-all-features:
-    name: Tests 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' || github.event_name == 'workflow_dispatch'
+    if: github.event_name == 'schedule'
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -110,7 +110,7 @@ jobs:
     runs-on: ubuntu-latest
     container:
       image: ubuntu:18.04
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
+    if: github.event_name == 'schedule'
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -123,10 +123,7 @@ jobs:
           override: true
       - name: Run cargo tree without default features and check lindera is not present
         run: |
-          if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -vqz lindera; then
-            echo "lindera has been found in the sources and it shouldn't"
-            exit 1
-          fi
+          cargo tree -f '{p} {f}' -e normal --no-default-features | grep lindera -vqz
       - name: Run cargo tree with default features and check lindera is pressent
         run: |
           cargo tree -f '{p} {f}' -e normal | grep lindera -qz
@@ -149,7 +146,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -164,11 +161,11 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.71.1
+          toolchain: 1.69.0
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -187,7 +184,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - 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

Cargo.toml

@@ -2,7 +2,6 @@
 resolver = "2"
 members = [
     "meilisearch",
-    "meilitool",
     "meilisearch-types",
     "meilisearch-auth",
     "meili-snap",
@@ -19,7 +18,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.5.0"
+version = "1.3.0"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"
@@ -37,24 +36,3 @@ opt-level = 3
 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

@@ -3,7 +3,7 @@ FROM    rust:alpine3.16 AS compiler
 
 RUN     apk add -q --update-cache --no-cache build-base openssl-dev
 
-WORKDIR /
+WORKDIR /meilisearch
 
 ARG     COMMIT_SHA
 ARG     COMMIT_DATE
@@ -17,7 +17,7 @@ RUN     set -eux; \
         if [ "$apkArch" = "aarch64" ]; then \
             export JEMALLOC_SYS_WITH_LG_PAGE=16; \
         fi && \
-        cargo build --release -p meilisearch -p meilitool
+        cargo build --release
 
 # Run
 FROM    alpine:3.16
@@ -28,10 +28,9 @@ ENV     MEILI_SERVER_PROVIDER docker
 RUN     apk update --quiet \
         && apk add -q --no-cache libgcc tini curl
 
-# add meilisearch and meilitool to the `/bin` so you can run it from anywhere
-# and it's easy to find.
-COPY    --from=compiler /target/release/meilisearch /bin/meilisearch
-COPY    --from=compiler /target/release/meilitool /bin/meilitool
+# add meilisearch to the `/bin` so you can run it from anywhere and it's easy
+# to find.
+COPY    --from=compiler /meilisearch/target/release/meilisearch /bin/meilisearch
 # To stay compatible with the older version of the container (pre v0.27.0) we're
 # going to symlink the meilisearch binary in the path to `/meilisearch`
 RUN     ln -s /bin/meilisearch /meilisearch

PROFILING.md

@@ -1,14 +1,14 @@
 # Profiling Meilisearch
 
-Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options [in Puffin Viewer](https://github.com/embarkstudios/puffin#ui).
+Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options.
 
 ![An example profiling with Puffin viewer](assets/profiling-example.png)
 
 ## Profiling the Indexing Process
 
-When you enable [the `exportPuffinReports` experimental feature](https://www.meilisearch.com/docs/learn/experimental/overview) of Meilisearch, Puffin reports with the `.puffin` extension will be automatically exported to disk. When this option is enabled, the engine will automatically create a "frame" whenever it executes the `IndexScheduler::tick` method.
+When you enable the `profile-with-puffin` feature of Meilisearch, a Puffin HTTP server will run on Meilisearch and listen on the default _0.0.0.0:8585_ address. This server will record a "frame" whenever it executes the `IndexScheduler::tick` method.
 
-[Puffin Viewer](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) is used to analyze the reports. Those reports show areas where Meilisearch spent time during indexing.
+Once your Meilisearch is running and awaits new indexation operations, you must [install and run the `puffin_viewer` tool](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) to see the profiling results. I advise you to run the viewer with the `RUST_LOG=puffin_http::client=debug` environment variable to see the client trying to connect to your server.
 
 Another piece of advice on the Puffin viewer UI interface is to consider the _Merge children with same ID_ option. It can hide the exact actual timings at which events were sent. Please turn it off when you see strange gaps on the Flamegraph. It can help.
 

benchmarks/benches/indexing.rs

@@ -6,7 +6,9 @@ use std::path::Path;
 
 use criterion::{criterion_group, criterion_main, Criterion};
 use milli::heed::{EnvOpenOptions, RwTxn};
-use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
+use milli::update::{
+    DeleteDocuments, IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings,
+};
 use milli::Index;
 use rand::seq::SliceRandom;
 use rand_chacha::rand_core::SeedableRng;
@@ -264,7 +266,17 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -601,7 +613,17 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -853,31 +875,22 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
 }
 
-fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBitmap>) {
-    let mut wtxn = index.write_txn().unwrap();
-
-    let indexer_config = IndexerConfig::default();
-    for ids in document_ids_to_delete {
-        let config = IndexDocumentsConfig::default();
-
-        let mut builder =
-            IndexDocuments::new(&mut wtxn, &index, &indexer_config, config, |_| (), || false)
-                .unwrap();
-        (builder, _) = builder.remove_documents_from_db_no_batch(&ids).unwrap();
-        builder.execute().unwrap();
-    }
-
-    wtxn.commit().unwrap();
-
-    index.prepare_for_closing().wait();
-}
-
 fn indexing_movies_in_three_batches(c: &mut Criterion) {
     let mut group = c.benchmark_group("indexing");
     group.sample_size(BENCHMARK_ITERATION);
@@ -1099,7 +1112,17 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });
@@ -1315,7 +1338,17 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                 (index, document_ids_to_delete)
             },
             move |(index, document_ids_to_delete)| {
-                delete_documents_from_ids(index, document_ids_to_delete)
+                let mut wtxn = index.write_txn().unwrap();
+
+                for ids in document_ids_to_delete {
+                    let mut builder = DeleteDocuments::new(&mut wtxn, &index).unwrap();
+                    builder.delete_documents(&ids);
+                    builder.execute().unwrap();
+                }
+
+                wtxn.commit().unwrap();
+
+                index.prepare_for_closing().wait();
             },
         )
     });

docker-compose.yml

@@ -0,0 +1,59 @@
+version: "3.9"
+services:
+  zk1:
+    container_name: zk1
+    hostname: zk1
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21811:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=1
+      - ZOO_SERVERS=0.0.0.0:2888:3888,zk2:2888:3888,zk3:2888:3888
+  zk2:
+    container_name: zk2
+    hostname: zk2
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21812:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=2
+      - ZOO_SERVERS=zk1:2888:3888,0.0.0.0:2888:3888,zk3:2888:3888
+  zk3:
+    container_name: zk3
+    hostname: zk3
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21813:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=3
+      - ZOO_SERVERS=zk1:2888:3888,zk2:2888:3888,0.0.0.0:2888:3888
+  zoonavigator:
+    container_name: zoonavigator
+    image: elkozmon/zoonavigator
+    ports:
+      - 9000:9000
+
+# Meilisearch instances
+  # m1:
+  #   container_name: m1
+  #   hostname: m1
+  #   image: getmeili/meilisearch:prototype-zookeeper-ha-0
+  #   ports:
+  #     - 7700:7700
+  #   environment:
+  #     - MEILI_ZK_URL=zk1:2181
+  #     - MEILI_MASTER_KEY=masterkey
+  #   restart: always
+  # m2:
+  #   container_name: m2
+  #   hostname: m2
+  #   image: getmeili/meilisearch:prototype-zookeeper-ha-0
+  #   ports:
+  #     - 7701:7700
+  #   environment:
+  #     - MEILI_ZK_URL=zk2:2181
+  #     - MEILI_MASTER_KEY=masterkey
+  #   restart: always

dump/src/lib.rs

@@ -262,9 +262,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::Set(btreeset! { S("age") }),
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,

dump/src/reader/compat/v5_to_v6.rs

@@ -340,9 +340,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 }
             },
             stop_words: settings.stop_words.into(),
-            non_separator_tokens: v6::Setting::NotSet,
-            separator_tokens: v6::Setting::NotSet,
-            dictionary: v6::Setting::NotSet,
             synonyms: settings.synonyms.into(),
             distinct_attribute: settings.distinct_attribute.into(),
             typo_tolerance: match settings.typo_tolerance {

dump/src/reader/mod.rs

@@ -526,12 +526,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2022-10-09T20:27:22.688964637Z",
-          "updatedAt": "2022-10-09T20:27:23.951017769Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -541,12 +541,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2022-10-09T20:27:22.197788495Z",
-          "updatedAt": "2022-10-09T20:28:01.93111053Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -571,12 +571,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2022-10-09T20:27:24.242683494Z",
-          "updatedAt": "2022-10-09T20:27:24.312809641Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -617,12 +617,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2023-01-30T16:25:56.595257Z",
-          "updatedAt": "2023-01-30T16:25:58.70348Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -632,12 +632,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2023-01-30T16:25:56.192178Z",
-          "updatedAt": "2023-01-30T16:25:56.455714Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -647,12 +647,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2023-01-30T16:25:58.876405Z",
-          "updatedAt": "2023-01-30T16:25:59.079906Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 

dump/src/reader/v2/mod.rs

@@ -46,7 +46,6 @@ pub type Checked = settings::Checked;
 pub type Unchecked = settings::Unchecked;
 
 pub type Task = updates::UpdateEntry;
-pub type Kind = updates::UpdateMeta;
 
 // everything related to the errors
 pub type ResponseError = errors::ResponseError;
@@ -108,11 +107,8 @@ impl V2Reader {
     pub fn indexes(&self) -> Result<impl Iterator<Item = Result<V2IndexReader>> + '_> {
         Ok(self.index_uuid.iter().map(|index| -> Result<_> {
             V2IndexReader::new(
+                index.uid.clone(),
                 &self.dump.path().join("indexes").join(format!("index-{}", index.uuid)),
-                index,
-                BufReader::new(
-                    File::open(self.dump.path().join("updates").join("data.jsonl")).unwrap(),
-                ),
             )
         }))
     }
@@ -147,41 +143,16 @@ pub struct V2IndexReader {
 }
 
 impl V2IndexReader {
-    pub fn new(path: &Path, index_uuid: &IndexUuid, tasks: BufReader<File>) -> Result<Self> {
+    pub fn new(name: String, path: &Path) -> 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::DocumentsAddition { .. } | 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: index_uuid.uid.clone(),
+            uid: name,
             primary_key: meta.primary_key,
-            created_at: created_at.unwrap_or(current_time),
-            updated_at: updated_at.unwrap_or(current_time),
+            // 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(),
         };
 
         let ret = V2IndexReader {
@@ -277,12 +248,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2022-10-09T20:27:22.688964637Z",
-          "updatedAt": "2022-10-09T20:27:23.951017769Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -292,12 +263,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2022-10-09T20:27:22.197788495Z",
-          "updatedAt": "2022-10-09T20:28:01.93111053Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -322,12 +293,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"d751713988987e9331980363e24189ce");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2022-10-09T20:27:24.242683494Z",
-          "updatedAt": "2022-10-09T20:27:24.312809641Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -369,12 +340,12 @@ pub(crate) mod test {
         assert!(indexes.is_empty());
 
         // products
-        insta::assert_json_snapshot!(products.metadata(), @r###"
+        insta::assert_json_snapshot!(products.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "products",
           "primaryKey": "sku",
-          "createdAt": "2023-01-30T16:25:56.595257Z",
-          "updatedAt": "2023-01-30T16:25:58.70348Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -384,12 +355,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"548284a84de510f71e88e6cdea495cf5");
 
         // movies
-        insta::assert_json_snapshot!(movies.metadata(), @r###"
+        insta::assert_json_snapshot!(movies.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "movies",
           "primaryKey": "id",
-          "createdAt": "2023-01-30T16:25:56.192178Z",
-          "updatedAt": "2023-01-30T16:25:56.455714Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 
@@ -399,12 +370,12 @@ pub(crate) mod test {
         meili_snap::snapshot_hash!(format!("{:#?}", documents), @"0227598af846e574139ee0b80e03a720");
 
         // spells
-        insta::assert_json_snapshot!(spells.metadata(), @r###"
+        insta::assert_json_snapshot!(spells.metadata(), { ".createdAt" => "[now]", ".updatedAt" => "[now]" }, @r###"
         {
           "uid": "dnd_spells",
           "primaryKey": "index",
-          "createdAt": "2023-01-30T16:25:58.876405Z",
-          "updatedAt": "2023-01-30T16:25:59.079906Z"
+          "createdAt": "[now]",
+          "updatedAt": "[now]"
         }
         "###);
 

dump/src/reader/v2/updates.rs

@@ -227,14 +227,4 @@ impl UpdateStatus {
             _ => None,
         }
     }
-
-    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),
-        }
-    }
 }

file-store/src/lib.rs

@@ -22,20 +22,6 @@ pub enum Error {
 
 pub type Result<T> = std::result::Result<T, Error>;
 
-impl Deref for File {
-    type Target = NamedTempFile;
-
-    fn deref(&self) -> &Self::Target {
-        &self.file
-    }
-}
-
-impl DerefMut for File {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.file
-    }
-}
-
 #[derive(Clone, Debug)]
 pub struct FileStore {
     path: PathBuf,
@@ -146,6 +132,20 @@ impl File {
     }
 }
 
+impl Deref for File {
+    type Target = NamedTempFile;
+
+    fn deref(&self) -> &Self::Target {
+        &self.file
+    }
+}
+
+impl DerefMut for File {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.file
+    }
+}
+
 #[cfg(test)]
 mod test {
     use std::io::Write;

filter-parser/Cargo.toml

@@ -14,7 +14,6 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.1.0"
-unescaper = "0.1.2"
 
 [dev-dependencies]
 insta = "1.29.0"

filter-parser/src/error.rs

@@ -62,7 +62,6 @@ pub enum ErrorKind<'a> {
     MisusedGeoRadius,
     MisusedGeoBoundingBox,
     InvalidPrimary,
-    InvalidEscapedNumber,
     ExpectedEof,
     ExpectedValue(ExpectedValueKind),
     MalformedValue,
@@ -148,9 +147,6 @@ impl<'a> Display for Error<'a> {
                 let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
                 writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
             }
-            ErrorKind::InvalidEscapedNumber => {
-                writeln!(f, "Found an invalid escaped sequence number: `{}`.", escaped_input)?
-            }
             ErrorKind::ExpectedEof => {
                 writeln!(f, "Found unexpected characters at the end of the filter: `{}`. You probably forgot an `OR` or an `AND` rule.", escaped_input)?
             }

filter-parser/src/lib.rs

@@ -545,8 +545,6 @@ impl<'a> std::fmt::Display for Token<'a> {
 
 #[cfg(test)]
 pub mod tests {
-    use FilterCondition as Fc;
-
     use super::*;
 
     /// Create a raw [Token]. You must specify the string that appear BEFORE your element followed by your element
@@ -558,22 +556,14 @@ pub mod tests {
         unsafe { Span::new_from_raw_offset(offset, lines as u32, value, "") }.into()
     }
 
-    fn p(s: &str) -> impl std::fmt::Display + '_ {
-        Fc::parse(s).unwrap().unwrap()
-    }
-
-    #[test]
-    fn parse_escaped() {
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\'"#), @r#"{title} = {foo\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\'"#), @r#"{title} = {foo\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\'"#), @r#"{title} = {foo\\\}"#);
-        insta::assert_display_snapshot!(p(r#"title = 'foo\\\\\\\\'"#), @r#"{title} = {foo\\\\}"#);
-        // but it also works with other sequencies
-        insta::assert_display_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
-    }
-
     #[test]
     fn parse() {
+        use FilterCondition as Fc;
+
+        fn p(s: &str) -> impl std::fmt::Display + '_ {
+            Fc::parse(s).unwrap().unwrap()
+        }
+
         // Test equal
         insta::assert_display_snapshot!(p("channel = Ponce"), @"{channel} = {Ponce}");
         insta::assert_display_snapshot!(p("subscribers = 12"), @"{subscribers} = {12}");

filter-parser/src/value.rs

@@ -171,24 +171,7 @@ pub fn parse_value(input: Span) -> IResult<Token> {
         })
     })?;
 
-    match unescaper::unescape(value.value()) {
-        Ok(content) => {
-            if content.len() != value.value().len() {
-                Ok((input, Token::new(value.original_span(), Some(content))))
-            } else {
-                Ok((input, value))
-            }
-        }
-        Err(unescaper::Error::IncompleteStr(_)) => Err(nom::Err::Incomplete(nom::Needed::Unknown)),
-        Err(unescaper::Error::ParseIntError { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::InvalidEscapedNumber,
-        ))),
-        Err(unescaper::Error::InvalidChar { .. }) => Err(nom::Err::Error(Error::new_from_kind(
-            value.original_span(),
-            ErrorKind::MalformedValue,
-        ))),
-    }
+    Ok((input, value))
 }
 
 fn is_value_component(c: char) -> bool {
@@ -335,17 +318,17 @@ pub mod test {
             ("\"cha'nnel\"", "cha'nnel", false),
             ("I'm tamo", "I", false),
             // escaped thing but not quote
-            (r#""\\""#, r#"\"#, true),
-            (r#""\\\\\\""#, r#"\\\"#, true),
-            (r#""aa\\aa""#, r#"aa\aa"#, true),
+            (r#""\\""#, r#"\\"#, false),
+            (r#""\\\\\\""#, r#"\\\\\\"#, false),
+            (r#""aa\\aa""#, r#"aa\\aa"#, false),
             // with double quote
             (r#""Hello \"world\"""#, r#"Hello "world""#, true),
-            (r#""Hello \\\"world\\\"""#, r#"Hello \"world\""#, true),
+            (r#""Hello \\\"world\\\"""#, r#"Hello \\"world\\""#, true),
             (r#""I'm \"super\" tamo""#, r#"I'm "super" tamo"#, true),
             (r#""\"\"""#, r#""""#, true),
             // with simple quote
             (r#"'Hello \'world\''"#, r#"Hello 'world'"#, true),
-            (r#"'Hello \\\'world\\\''"#, r#"Hello \'world\'"#, true),
+            (r#"'Hello \\\'world\\\''"#, r#"Hello \\'world\\'"#, true),
             (r#"'I\'m "super" tamo'"#, r#"I'm "super" tamo"#, true),
             (r#"'\'\''"#, r#"''"#, true),
         ];
@@ -367,14 +350,7 @@ pub mod test {
                 "Filter `{}` was not supposed to be escaped",
                 input
             );
-            assert_eq!(
-                token.value(),
-                expected,
-                "Filter `{}` failed by giving `{}` instead of `{}`.",
-                input,
-                token.value(),
-                expected
-            );
+            assert_eq!(token.value(), expected, "Filter `{}` failed.", input);
         }
     }
 

fuzzers/Cargo.toml

@@ -13,7 +13,7 @@ license.workspace = true
 [dependencies]
 arbitrary = { version = "1.3.0", features = ["derive"] }
 clap = { version = "4.3.0", features = ["derive"] }
-fastrand = "2.0.0"
+fastrand = "1.9.0"
 milli = { path = "../milli" }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }

ha_test/run.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+
+function is_everything_installed {
+  everything_ok=yes
+
+  if hash zkli 2>/dev/null; then
+    echo "✅ zkli installed"
+  else
+    everything_ok=no
+    echo "🥺 zkli is missing, please run \`cargo install zkli\`"
+  fi
+
+  if hash s3cmd 2>/dev/null; then
+    echo "✅ s3cmd installed"
+  else
+    everything_ok=no
+    echo "🥺 s3cmd is missing, see how to install it here https://s3tools.org/s3cmd"
+  fi
+
+  if [ $everything_ok = "no" ]; then
+    echo "Exiting..."
+    exit 1
+  fi
+}
+
+# param: addr of zookeeper
+function connect_to_zookeeper {
+  if ! zkli -a "$1" ls > /dev/null; then
+    echo "zkli can't connect"
+    return 1
+  fi
+}
+
+# param: addr of the s3 bucket
+function connect_to_s3 {
+  # S3_SECRET_KEY
+  # S3_ACCESS_KEY
+  # S3_HOST
+  # S3_BUCKET
+
+  s3cmd --host="$S3_HOST" --host-bucket="$S3_BUCKET" --access_key="$ACCESS_KEY" --secret_key="$S3_SECRET_KEY" ls
+
+  if $?; then
+    echo "s3cmd can't connect"
+    return 1
+  fi
+}
+
+is_everything_installed
+
+ZOOKEEPER_ADDR="localhost:2181"
+if ! connect_to_zookeeper $ZOOKEEPER_ADDR; then
+  ZOOKEEPER_ADDR="localhost:21811"
+  if ! connect_to_zookeeper $ZOOKEEPER_ADDR; then
+    echo "Can't connect to zkli"
+    exit 1
+  fi
+fi
+
+
+connect_to_s3

index-scheduler/Cargo.toml

@@ -18,12 +18,11 @@ derive_builder = "0.12.0"
 dump = { path = "../dump" }
 enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
 log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
-puffin = { version = "0.16.0", features = ["serialization"] }
+puffin = "0.16.0"
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
@@ -31,8 +30,11 @@ synchronoise = "1.0.1"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
 time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-ureq = "2.9.1"
 uuid = { version = "1.3.1", features = ["serde", "v4"] }
+tokio = { version = "1.27.0", features = ["full"] }
+zookeeper = "0.8.0"
+parking_lot = "0.12.1"
+strois = "0.0.4"
 
 [dev-dependencies]
 big_s = "1.0.2"

index-scheduler/src/batch.rs

@@ -19,18 +19,18 @@ one indexing operation.
 
 use std::collections::{BTreeSet, HashSet};
 use std::ffi::OsStr;
-use std::fmt;
 use std::fs::{self, File};
 use std::io::BufWriter;
 
 use dump::IndexMetadata;
-use log::{debug, error, info, trace};
+use log::{debug, error, info};
 use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
 use meilisearch_types::milli::heed::CompactionOption;
 use meilisearch_types::milli::update::{
-    IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig, Settings as MilliSettings,
+    DeleteDocuments, DocumentDeletionResult, IndexDocumentsConfig, IndexDocumentsMethod,
+    Settings as MilliSettings,
 };
 use meilisearch_types::milli::{self, Filter, BEU32};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
@@ -43,7 +43,7 @@ use uuid::Uuid;
 
 use crate::autobatcher::{self, BatchKind};
 use crate::utils::{self, swap_index_uid_in_task};
-use crate::{Error, IndexScheduler, MustStopProcessing, ProcessingTasks, Result, TaskId};
+use crate::{Error, IndexSchedulerInner, ProcessingTasks, Result, TaskId};
 
 /// Represents a combination of tasks that can all be processed at the same time.
 ///
@@ -67,6 +67,10 @@ pub(crate) enum Batch {
         op: IndexOperation,
         must_create_index: bool,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -104,9 +108,11 @@ pub(crate) enum IndexOperation {
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
-    IndexDocumentDeletionByFilter {
+    DocumentDeletion {
         index_uid: String,
-        task: Task,
+        // The vec associated with each document deletion tasks.
+        documents: Vec<Vec<String>>,
+        tasks: Vec<Task>,
     },
     DocumentClear {
         index_uid: String,
@@ -149,17 +155,18 @@ impl Batch {
             | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
+            | Batch::IndexDocumentDeletionByFilter { task, .. }
             | Batch::IndexUpdate { task, .. } => vec![task.uid],
             Batch::SnapshotCreation(tasks) | Batch::IndexDeletion { tasks, .. } => {
                 tasks.iter().map(|task| task.uid).collect()
             }
             Batch::IndexOperation { op, .. } => match op {
                 IndexOperation::DocumentOperation { tasks, .. }
+                | IndexOperation::DocumentDeletion { tasks, .. }
                 | IndexOperation::Settings { tasks, .. }
                 | IndexOperation::DocumentClear { tasks, .. } => {
                     tasks.iter().map(|task| task.uid).collect()
                 }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => vec![task.uid],
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
                     settings_tasks: other,
@@ -187,30 +194,37 @@ impl Batch {
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
             | IndexUpdate { index_uid, .. }
-            | IndexDeletion { index_uid, .. } => Some(index_uid),
+            | IndexDeletion { index_uid, .. }
+            | IndexDocumentDeletionByFilter { index_uid, .. } => Some(index_uid),
         }
     }
-}
 
-impl fmt::Display for Batch {
-    /// A text used when we debug the profiling reports.
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let index_uid = self.index_uid();
-        let tasks = self.ids();
+    /// Return the content fields uuids associated with this batch.
+    pub fn content_uuids(&self) -> Vec<Uuid> {
         match self {
-            Batch::TaskCancelation { .. } => f.write_str("TaskCancelation")?,
-            Batch::TaskDeletion(_) => f.write_str("TaskDeletion")?,
-            Batch::SnapshotCreation(_) => f.write_str("SnapshotCreation")?,
-            Batch::Dump(_) => f.write_str("Dump")?,
-            Batch::IndexOperation { op, .. } => write!(f, "{op}")?,
-            Batch::IndexCreation { .. } => f.write_str("IndexCreation")?,
-            Batch::IndexUpdate { .. } => f.write_str("IndexUpdate")?,
-            Batch::IndexDeletion { .. } => f.write_str("IndexDeletion")?,
-            Batch::IndexSwap { .. } => f.write_str("IndexSwap")?,
-        };
-        match index_uid {
-            Some(name) => f.write_fmt(format_args!(" on {name:?} from tasks: {tasks:?}")),
-            None => f.write_fmt(format_args!(" from tasks: {tasks:?}")),
+            Batch::TaskCancelation { .. }
+            | Batch::TaskDeletion(_)
+            | Batch::Dump(_)
+            | Batch::IndexCreation { .. }
+            | Batch::IndexDocumentDeletionByFilter { .. }
+            | Batch::IndexUpdate { .. }
+            | Batch::SnapshotCreation(_)
+            | Batch::IndexDeletion { .. }
+            | Batch::IndexSwap { .. } => vec![],
+            Batch::IndexOperation { op, .. } => match op {
+                IndexOperation::DocumentOperation { operations, .. } => operations
+                    .iter()
+                    .flat_map(|op| match op {
+                        DocumentOperation::Add(uuid) => Some(*uuid),
+                        DocumentOperation::Delete(_) => None,
+                    })
+                    .collect(),
+                IndexOperation::DocumentDeletion { .. }
+                | IndexOperation::Settings { .. }
+                | IndexOperation::DocumentClear { .. }
+                | IndexOperation::SettingsAndDocumentOperation { .. }
+                | IndexOperation::DocumentClearAndSetting { .. } => vec![],
+            },
         }
     }
 }
@@ -219,7 +233,7 @@ impl IndexOperation {
     pub fn index_uid(&self) -> &str {
         match self {
             IndexOperation::DocumentOperation { index_uid, .. }
-            | IndexOperation::IndexDocumentDeletionByFilter { index_uid, .. }
+            | IndexOperation::DocumentDeletion { index_uid, .. }
             | IndexOperation::DocumentClear { index_uid, .. }
             | IndexOperation::Settings { index_uid, .. }
             | IndexOperation::DocumentClearAndSetting { index_uid, .. }
@@ -228,28 +242,7 @@ impl IndexOperation {
     }
 }
 
-impl fmt::Display for IndexOperation {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self {
-            IndexOperation::DocumentOperation { .. } => {
-                f.write_str("IndexOperation::DocumentOperation")
-            }
-            IndexOperation::IndexDocumentDeletionByFilter { .. } => {
-                f.write_str("IndexOperation::IndexDocumentDeletionByFilter")
-            }
-            IndexOperation::DocumentClear { .. } => f.write_str("IndexOperation::DocumentClear"),
-            IndexOperation::Settings { .. } => f.write_str("IndexOperation::Settings"),
-            IndexOperation::DocumentClearAndSetting { .. } => {
-                f.write_str("IndexOperation::DocumentClearAndSetting")
-            }
-            IndexOperation::SettingsAndDocumentOperation { .. } => {
-                f.write_str("IndexOperation::SettingsAndDocumentOperation")
-            }
-        }
-    }
-}
-
-impl IndexScheduler {
+impl IndexSchedulerInner {
     /// Convert an [`BatchKind`](crate::autobatcher::BatchKind) into a [`Batch`].
     ///
     /// ## Arguments
@@ -275,12 +268,9 @@ impl IndexScheduler {
                 let task = self.get_task(rtxn, id)?.ok_or(Error::CorruptedTaskQueue)?;
                 match &task.kind {
                     KindWithContent::DocumentDeletionByFilter { index_uid, .. } => {
-                        Ok(Some(Batch::IndexOperation {
-                            op: IndexOperation::IndexDocumentDeletionByFilter {
-                                index_uid: index_uid.clone(),
-                                task,
-                            },
-                            must_create_index: false,
+                        Ok(Some(Batch::IndexDocumentDeletionByFilter {
+                            index_uid: index_uid.clone(),
+                            task,
                         }))
                     }
                     _ => unreachable!(),
@@ -336,27 +326,18 @@ impl IndexScheduler {
             BatchKind::DocumentDeletion { deletion_ids } => {
                 let tasks = self.get_existing_tasks(rtxn, deletion_ids)?;
 
-                let mut operations = Vec::with_capacity(tasks.len());
-                let mut documents_counts = Vec::with_capacity(tasks.len());
+                let mut documents = Vec::new();
                 for task in &tasks {
                     match task.kind {
                         KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
-                            operations.push(DocumentOperation::Delete(documents_ids.clone()));
-                            documents_counts.push(documents_ids.len() as u64);
+                            documents.push(documents_ids.clone())
                         }
                         _ => unreachable!(),
                     }
                 }
 
                 Ok(Some(Batch::IndexOperation {
-                    op: IndexOperation::DocumentOperation {
-                        index_uid,
-                        primary_key: None,
-                        method: IndexDocumentsMethod::ReplaceDocuments,
-                        documents_counts,
-                        operations,
-                        tasks,
-                    },
+                    op: IndexOperation::DocumentDeletion { index_uid, documents, tasks },
                     must_create_index,
                 }))
             }
@@ -528,8 +509,7 @@ impl IndexScheduler {
         if let Some(task_id) = to_cancel.max() {
             // We retrieve the tasks that were processing before this tasks cancelation started.
             // We must *not* reset the processing tasks before calling this method.
-            let ProcessingTasks { started_at, processing } =
-                &*self.processing_tasks.read().unwrap();
+            let ProcessingTasks { started_at, processing, .. } = &*self.processing_tasks.read();
             return Ok(Some(Batch::TaskCancelation {
                 task: self.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?,
                 previous_started_at: *started_at,
@@ -626,7 +606,7 @@ impl IndexScheduler {
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
 
-        puffin::profile_function!(batch.to_string());
+        puffin::profile_function!(format!("{:?}", batch));
 
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
@@ -822,10 +802,6 @@ impl IndexScheduler {
                 // 2. dump the tasks
                 let mut dump_tasks = dump.create_tasks_queue()?;
                 for ret in self.all_tasks.iter(&rtxn)? {
-                    if self.must_stop_processing.get() {
-                        return Err(Error::AbortedTask);
-                    }
-
                     let (_, mut t) = ret?;
                     let status = t.status;
                     let content_file = t.content_uuid();
@@ -846,9 +822,6 @@ impl IndexScheduler {
 
                     // 2.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
                     if let Some(content_file) = content_file {
-                        if self.must_stop_processing.get() {
-                            return Err(Error::AbortedTask);
-                        }
                         if status == Status::Enqueued {
                             let content_file = self.file_store.get_update(content_file)?;
 
@@ -888,9 +861,6 @@ impl IndexScheduler {
 
                     // 3.1. Dump the documents
                     for ret in index.all_documents(&rtxn)? {
-                        if self.must_stop_processing.get() {
-                            return Err(Error::AbortedTask);
-                        }
                         let (_id, doc) = ret?;
                         let document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
                         index_dumper.push_document(&document)?;
@@ -903,16 +873,13 @@ impl IndexScheduler {
                 })?;
 
                 // 4. Dump experimental feature settings
-                let features = self.features().runtime_features();
+                let features = self.features()?.runtime_features();
                 dump.create_experimental_features(features)?;
 
                 let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
                 )).unwrap();
 
-                if self.must_stop_processing.get() {
-                    return Err(Error::AbortedTask);
-                }
                 let path = self.dumps_path.join(format!("{}.dump", dump_uid));
                 let file = File::create(path)?;
                 dump.persist_to(BufWriter::new(file))?;
@@ -933,10 +900,6 @@ impl IndexScheduler {
                     self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
-                // the index operation can take a long time, so save this handle to make it available to the search for the duration of the tick
-                *self.currently_updating_index.write().unwrap() =
-                    Some((index_uid.clone(), index.clone()));
-
                 let mut index_wtxn = index.write_txn()?;
                 let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
                 index_wtxn.commit()?;
@@ -961,6 +924,51 @@ impl IndexScheduler {
 
                 Ok(tasks)
             }
+            Batch::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
+                let (index_uid, filter) =
+                    if let KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } =
+                        &task.kind
+                    {
+                        (index_uid, filter_expr)
+                    } else {
+                        unreachable!()
+                    };
+                let index = {
+                    let rtxn = self.env.read_txn()?;
+                    self.index_mapper.index(&rtxn, index_uid)?
+                };
+                let deleted_documents = delete_document_by_filter(filter, index);
+                let original_filter = if let Some(Details::DocumentDeletionByFilter {
+                    original_filter,
+                    deleted_documents: _,
+                }) = task.details
+                {
+                    original_filter
+                } else {
+                    // In the case of a `documentDeleteByFilter` the details MUST be set
+                    unreachable!();
+                };
+
+                match deleted_documents {
+                    Ok(deleted_documents) => {
+                        task.status = Status::Succeeded;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(deleted_documents),
+                        });
+                    }
+                    Err(e) => {
+                        task.status = Status::Failed;
+                        task.details = Some(Details::DocumentDeletionByFilter {
+                            original_filter,
+                            deleted_documents: Some(0),
+                        });
+                        task.error = Some(e.into());
+                    }
+                }
+
+                Ok(vec![task])
+            }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 let wtxn = self.env.write_txn()?;
                 if self.index_mapper.exists(&wtxn, &index_uid)? {
@@ -1205,7 +1213,7 @@ impl IndexScheduler {
                     index,
                     indexer_config,
                     config,
-                    |indexing_step| trace!("update: {:?}", indexing_step),
+                    |indexing_step| debug!("update: {:?}", indexing_step),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1252,8 +1260,7 @@ impl IndexScheduler {
                             let (new_builder, user_result) =
                                 builder.remove_documents(document_ids)?;
                             builder = new_builder;
-                            // Uses Invariant: remove documents actually always returns Ok for the inner result
-                            let count = user_result.unwrap();
+
                             let provided_ids =
                                 if let Some(Details::DocumentDeletion { provided_ids, .. }) =
                                     task.details
@@ -1264,11 +1271,23 @@ impl IndexScheduler {
                                     unreachable!();
                                 };
 
-                            task.status = Status::Succeeded;
-                            task.details = Some(Details::DocumentDeletion {
-                                provided_ids,
-                                deleted_documents: Some(count),
-                            });
+                            match user_result {
+                                Ok(count) => {
+                                    task.status = Status::Succeeded;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(count),
+                                    });
+                                }
+                                Err(e) => {
+                                    task.status = Status::Failed;
+                                    task.details = Some(Details::DocumentDeletion {
+                                        provided_ids,
+                                        deleted_documents: Some(0),
+                                    });
+                                    task.error = Some(milli::Error::from(e).into());
+                                }
+                            }
                         }
                     }
                 }
@@ -1283,59 +1302,30 @@ impl IndexScheduler {
                         milli::update::Settings::new(index_wtxn, index, indexer_config);
                     builder.reset_primary_key();
                     builder.execute(
-                        |indexing_step| trace!("update: {:?}", indexing_step),
+                        |indexing_step| debug!("update: {:?}", indexing_step),
                         || must_stop_processing.clone().get(),
                     )?;
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::IndexDocumentDeletionByFilter { mut task, index_uid: _ } => {
-                let filter =
-                    if let KindWithContent::DocumentDeletionByFilter { filter_expr, .. } =
-                        &task.kind
-                    {
-                        filter_expr
-                    } else {
-                        unreachable!()
-                    };
-                let deleted_documents = delete_document_by_filter(
-                    index_wtxn,
-                    filter,
-                    self.index_mapper.indexer_config(),
-                    self.must_stop_processing.clone(),
-                    index,
-                );
-                let original_filter = if let Some(Details::DocumentDeletionByFilter {
-                    original_filter,
-                    deleted_documents: _,
-                }) = task.details
-                {
-                    original_filter
-                } else {
-                    // In the case of a `documentDeleteByFilter` the details MUST be set
-                    unreachable!();
-                };
+            IndexOperation::DocumentDeletion { index_uid: _, documents, mut tasks } => {
+                let mut builder = milli::update::DeleteDocuments::new(index_wtxn, index)?;
+                documents.iter().flatten().for_each(|id| {
+                    builder.delete_external_id(id);
+                });
 
-                match deleted_documents {
-                    Ok(deleted_documents) => {
-                        task.status = Status::Succeeded;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(deleted_documents),
-                        });
-                    }
-                    Err(e) => {
-                        task.status = Status::Failed;
-                        task.details = Some(Details::DocumentDeletionByFilter {
-                            original_filter,
-                            deleted_documents: Some(0),
-                        });
-                        task.error = Some(e.into());
-                    }
+                let DocumentDeletionResult { deleted_documents, .. } = builder.execute()?;
+
+                for (task, documents) in tasks.iter_mut().zip(documents) {
+                    task.status = Status::Succeeded;
+                    task.details = Some(Details::DocumentDeletion {
+                        provided_ids: documents.len(),
+                        deleted_documents: Some(deleted_documents.min(documents.len() as u64)),
+                    });
                 }
 
-                Ok(vec![task])
+                Ok(tasks)
             }
             IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
@@ -1430,7 +1420,7 @@ impl IndexScheduler {
     fn delete_matched_tasks(&self, wtxn: &mut RwTxn, matched_tasks: &RoaringBitmap) -> Result<u64> {
         // 1. Remove from this list the tasks that we are not allowed to delete
         let enqueued_tasks = self.get_status(wtxn, Status::Enqueued)?;
-        let processing_tasks = &self.processing_tasks.read().unwrap().processing.clone();
+        let processing_tasks = &self.processing_tasks.read().processing.clone();
 
         let all_task_ids = self.all_task_ids(wtxn)?;
         let mut to_delete_tasks = all_task_ids & matched_tasks;
@@ -1536,41 +1526,23 @@ impl IndexScheduler {
     }
 }
 
-fn delete_document_by_filter<'a>(
-    wtxn: &mut RwTxn<'a, '_>,
-    filter: &serde_json::Value,
-    indexer_config: &IndexerConfig,
-    must_stop_processing: MustStopProcessing,
-    index: &'a Index,
-) -> Result<u64> {
+fn delete_document_by_filter(filter: &serde_json::Value, index: Index) -> Result<u64> {
     let filter = Filter::from_json(filter)?;
     Ok(if let Some(filter) = filter {
-        let candidates = filter.evaluate(wtxn, index).map_err(|err| match err {
+        let mut wtxn = index.write_txn()?;
+
+        let candidates = filter.evaluate(&wtxn, &index).map_err(|err| match err {
             milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
                 Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
             }
             e => e.into(),
         })?;
-
-        let config = IndexDocumentsConfig {
-            update_method: IndexDocumentsMethod::ReplaceDocuments,
-            ..Default::default()
-        };
-
-        let mut builder = milli::update::IndexDocuments::new(
-            wtxn,
-            index,
-            indexer_config,
-            config,
-            |indexing_step| debug!("update: {:?}", indexing_step),
-            || must_stop_processing.get(),
-        )?;
-
-        let (new_builder, count) = builder.remove_documents_from_db_no_batch(&candidates)?;
-        builder = new_builder;
-
-        let _ = builder.execute()?;
-        count
+        let mut delete_operation = DeleteDocuments::new(&mut wtxn, &index)?;
+        delete_operation.delete_documents(&candidates);
+        let deleted_documents =
+            delete_operation.execute().map(|result| result.deleted_documents)?;
+        wtxn.commit()?;
+        deleted_documents
     } else {
         0
     })

index-scheduler/src/error.rs

@@ -108,8 +108,6 @@ pub enum Error {
     TaskDeletionWithEmptyQuery,
     #[error("Query parameters to filter the tasks to cancel are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
     TaskCancelationWithEmptyQuery,
-    #[error("Aborted task")]
-    AbortedTask,
 
     #[error(transparent)]
     Dump(#[from] dump::Error),
@@ -177,7 +175,6 @@ impl Error {
             | Error::TaskNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
-            | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli(_)
@@ -239,9 +236,6 @@ impl ErrorCode for Error {
             Error::TaskDatabaseUpdate(_) => Code::Internal,
             Error::CreateBatch(_) => Code::Internal,
 
-            // This one should never be seen by the end user
-            Error::AbortedTask => Code::Internal,
-
             #[cfg(test)]
             Error::PlannedFailure => Code::Internal,
         }

index-scheduler/src/features.rs

@@ -1,8 +1,6 @@
-use std::sync::{Arc, RwLock};
-
 use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RwTxn};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
@@ -11,19 +9,20 @@ const EXPERIMENTAL_FEATURES: &str = "experimental-features";
 
 #[derive(Clone)]
 pub(crate) struct FeatureData {
-    persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
-    runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
+    runtime: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
+    instance: InstanceTogglableFeatures,
 }
 
 #[derive(Debug, Clone, Copy)]
 pub struct RoFeatures {
     runtime: RuntimeTogglableFeatures,
+    instance: InstanceTogglableFeatures,
 }
 
 impl RoFeatures {
-    fn new(data: &FeatureData) -> Self {
-        let runtime = data.runtime_features();
-        Self { runtime }
+    fn new(txn: RoTxn<'_>, data: &FeatureData) -> Result<Self> {
+        let runtime = data.runtime_features(txn)?;
+        Ok(Self { runtime, instance: data.instance })
     }
 
     pub fn runtime_features(&self) -> RuntimeTogglableFeatures {
@@ -44,13 +43,13 @@ impl RoFeatures {
     }
 
     pub fn check_metrics(&self) -> Result<()> {
-        if self.runtime.metrics {
+        if self.instance.metrics {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
                 disabled_action: "Getting metrics",
                 feature: "metrics",
-                issue_link: "https://github.com/meilisearch/product/discussions/625",
+                issue_link: "https://github.com/meilisearch/meilisearch/discussions/3518",
             }
             .into())
         }
@@ -68,36 +67,15 @@ impl RoFeatures {
             .into())
         }
     }
-
-    pub fn check_puffin(&self) -> Result<()> {
-        if self.runtime.export_puffin_reports {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Outputting Puffin reports to disk",
-                feature: "export puffin reports",
-                issue_link: "https://github.com/meilisearch/product/discussions/693",
-            }
-            .into())
-        }
-    }
 }
 
 impl FeatureData {
     pub fn new(env: &Env, instance_features: InstanceTogglableFeatures) -> Result<Self> {
         let mut wtxn = env.write_txn()?;
-        let runtime_features_db = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
+        let runtime_features = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
         wtxn.commit()?;
 
-        let txn = env.read_txn()?;
-        let persisted_features: RuntimeTogglableFeatures =
-            runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
-        let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
-            metrics: instance_features.metrics || persisted_features.metrics,
-            ..persisted_features
-        }));
-
-        Ok(Self { persisted: runtime_features_db, runtime })
+        Ok(Self { runtime: runtime_features, instance: instance_features })
     }
 
     pub fn put_runtime_features(
@@ -105,25 +83,16 @@ impl FeatureData {
         mut wtxn: RwTxn,
         features: RuntimeTogglableFeatures,
     ) -> Result<()> {
-        self.persisted.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
+        self.runtime.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
         wtxn.commit()?;
-
-        // safe to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for an assignment here.
-        let mut toggled_features = self.runtime.write().unwrap();
-        *toggled_features = features;
         Ok(())
     }
 
-    fn runtime_features(&self) -> RuntimeTogglableFeatures {
-        // sound to unwrap, the lock will only fail if:
-        // 1. requested by the same thread concurrently -> it is called and released in methods that don't call each other
-        // 2. there's a panic while the thread is held -> it is only used for copying the data here
-        *self.runtime.read().unwrap()
+    fn runtime_features(&self, txn: RoTxn) -> Result<RuntimeTogglableFeatures> {
+        Ok(self.runtime.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default())
     }
 
-    pub fn features(&self) -> RoFeatures {
-        RoFeatures::new(self)
+    pub fn features(&self, txn: RoTxn) -> Result<RoFeatures> {
+        RoFeatures::new(txn, self)
     }
 }

index-scheduler/src/index_mapper/index_map.rs

@@ -295,6 +295,11 @@ impl IndexMap {
             "Attempt to finish deletion of an index that was being closed"
         );
     }
+
+    /// Returns the indexes that were opened by the `IndexMap`.
+    pub fn clear(&mut self) -> Vec<Index> {
+        self.available.clear().into_iter().map(|(_, (_, index))| index).collect()
+    }
 }
 
 /// Create or open an index in the specified path.
@@ -335,7 +340,8 @@ mod tests {
     impl IndexMapper {
         fn test() -> (Self, Env, IndexSchedulerHandle) {
             let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
-            (index_scheduler.index_mapper, index_scheduler.env, handle)
+            let index_scheduler = index_scheduler.inner();
+            (index_scheduler.index_mapper.clone(), index_scheduler.env.clone(), handle)
         }
     }
 

index-scheduler/src/index_mapper/mod.rs

@@ -61,7 +61,7 @@ pub struct IndexMapper {
     pub(crate) index_stats: Database<UuidCodec, SerdeJson<IndexStats>>,
 
     /// Path to the folder where the LMDB environments of each index are.
-    base_path: PathBuf,
+    pub(crate) base_path: PathBuf,
     /// The map size an index is opened with on the first time.
     index_base_map_size: usize,
     /// The quantity by which the map size of an index is incremented upon reopening, in bytes.
@@ -135,7 +135,7 @@ impl IndexMapper {
         index_growth_amount: usize,
         index_count: usize,
         enable_mdb_writemap: bool,
-        indexer_config: IndexerConfig,
+        indexer_config: Arc<IndexerConfig>,
     ) -> Result<Self> {
         let mut wtxn = env.write_txn()?;
         let index_mapping = env.create_database(&mut wtxn, Some(INDEX_MAPPING))?;
@@ -150,7 +150,7 @@ impl IndexMapper {
             index_base_map_size,
             index_growth_amount,
             enable_mdb_writemap,
-            indexer_config: Arc::new(indexer_config),
+            indexer_config,
         })
     }
 
@@ -428,6 +428,11 @@ impl IndexMapper {
         Ok(())
     }
 
+    /// Returns the indexes that were opened by the `IndexMapper`.
+    pub fn clear(&mut self) -> Vec<Index> {
+        self.index_map.write().unwrap().clear()
+    }
+
     /// The stats of an index.
     ///
     /// If available in the cache, they are directly returned.

index-scheduler/src/insta_snapshot.rs

@@ -1,5 +1,6 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
+use std::ops::Deref;
 
 use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
@@ -8,12 +9,13 @@ use meilisearch_types::tasks::{Details, Task};
 use roaring::RoaringBitmap;
 
 use crate::index_mapper::IndexMapper;
-use crate::{IndexScheduler, Kind, Status, BEI128};
+use crate::{IndexScheduler, IndexSchedulerInner, Kind, Status, BEI128};
 
 pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
     scheduler.assert_internally_consistent();
 
-    let IndexScheduler {
+    let inner = scheduler.inner();
+    let IndexSchedulerInner {
         autobatching_enabled,
         must_stop_processing: _,
         processing_tasks,
@@ -30,24 +32,23 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         index_mapper,
         features: _,
         max_number_of_tasks: _,
-        puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,
         auth_path: _,
         version_file_path: _,
-        webhook_url: _,
         test_breakpoint_sdr: _,
         planned_failures: _,
         run_loop_iteration: _,
-        currently_updating_index: _,
-    } = scheduler;
+        zookeeper: _,
+        options: _,
+    } = inner.deref();
 
     let rtxn = env.read_txn().unwrap();
 
     let mut snap = String::new();
 
-    let processing_tasks = processing_tasks.read().unwrap().processing.clone();
+    let processing_tasks = processing_tasks.read().processing.clone();
     snap.push_str(&format!("### Autobatching Enabled = {autobatching_enabled}\n"));
     snap.push_str("### Processing Tasks:\n");
     snap.push_str(&snapshot_bitmap(&processing_tasks));

index-scheduler/src/lru.rs

@@ -1,5 +1,6 @@
 //! Thread-safe `Vec`-backend LRU cache using [`std::sync::atomic::AtomicU64`] for synchronization.
 
+use std::mem;
 use std::sync::atomic::{AtomicU64, Ordering};
 
 /// Thread-safe `Vec`-backend LRU cache
@@ -190,6 +191,11 @@ where
         }
         None
     }
+
+    /// Returns the generation associated to the key and values of the `LruMap`.
+    pub fn clear(&mut self) -> Vec<(AtomicU64, (K, V))> {
+        mem::take(&mut self.0.data)
+    }
 }
 
 /// The result of an insertion in a LRU map.

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/after_dump_register.snap

@@ -1,35 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,]
-----------------------------------------------------------------------
-### Kind:
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/cancel_processed.snap

@@ -1,45 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: canceled, canceled_by: 1, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-1 {uid: 1, status: succeeded, details: { matched_tasks: 1, canceled_tasks: Some(0), original_filter: "cancel dump" }, kind: TaskCancelation { query: "cancel dump", tasks: RoaringBitmap<[0]> }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [1,]
-canceled [0,]
-----------------------------------------------------------------------
-### Kind:
-"taskCancelation" [1,]
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-1 [0,]
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/cancel_processing_dump/cancel_registered.snap

@@ -1,38 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[0,]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}
-1 {uid: 1, status: enqueued, details: { matched_tasks: 1, canceled_tasks: None, original_filter: "cancel dump" }, kind: TaskCancelation { query: "cancel dump", tasks: RoaringBitmap<[0]> }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"taskCancelation" [1,]
-"dumpCreation" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/utils.rs

@@ -10,9 +10,9 @@ use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status
 use roaring::{MultiOps, RoaringBitmap};
 use time::OffsetDateTime;
 
-use crate::{Error, IndexScheduler, Result, Task, TaskId, BEI128};
+use crate::{Error, IndexSchedulerInner, Result, Task, TaskId, BEI128};
 
-impl IndexScheduler {
+impl IndexSchedulerInner {
     pub(crate) fn all_task_ids(&self, rtxn: &RoTxn) -> Result<RoaringBitmap> {
         enum_iterator::all().map(|s| self.get_status(rtxn, s)).union()
     }
@@ -331,11 +331,12 @@ pub fn clamp_to_page_size(size: usize) -> usize {
 }
 
 #[cfg(test)]
-impl IndexScheduler {
+impl crate::IndexScheduler {
     /// Asserts that the index scheduler's content is internally consistent.
     pub fn assert_internally_consistent(&self) {
-        let rtxn = self.env.read_txn().unwrap();
-        for task in self.all_tasks.iter(&rtxn).unwrap() {
+        let this = self.inner();
+        let rtxn = this.env.read_txn().unwrap();
+        for task in this.all_tasks.iter(&rtxn).unwrap() {
             let (task_id, task) = task.unwrap();
             let task_id = task_id.get();
 
@@ -354,21 +355,21 @@ impl IndexScheduler {
             } = task;
             assert_eq!(uid, task.uid);
             if let Some(task_index_uid) = &task_index_uid {
-                assert!(self
+                assert!(this
                     .index_tasks
                     .get(&rtxn, task_index_uid.as_str())
                     .unwrap()
                     .unwrap()
                     .contains(task.uid));
             }
-            let db_enqueued_at = self
+            let db_enqueued_at = this
                 .enqueued_at
                 .get(&rtxn, &BEI128::new(enqueued_at.unix_timestamp_nanos()))
                 .unwrap()
                 .unwrap();
             assert!(db_enqueued_at.contains(task_id));
             if let Some(started_at) = started_at {
-                let db_started_at = self
+                let db_started_at = this
                     .started_at
                     .get(&rtxn, &BEI128::new(started_at.unix_timestamp_nanos()))
                     .unwrap()
@@ -376,7 +377,7 @@ impl IndexScheduler {
                 assert!(db_started_at.contains(task_id));
             }
             if let Some(finished_at) = finished_at {
-                let db_finished_at = self
+                let db_finished_at = this
                     .finished_at
                     .get(&rtxn, &BEI128::new(finished_at.unix_timestamp_nanos()))
                     .unwrap()
@@ -384,9 +385,9 @@ impl IndexScheduler {
                 assert!(db_finished_at.contains(task_id));
             }
             if let Some(canceled_by) = canceled_by {
-                let db_canceled_tasks = self.get_status(&rtxn, Status::Canceled).unwrap();
+                let db_canceled_tasks = this.get_status(&rtxn, Status::Canceled).unwrap();
                 assert!(db_canceled_tasks.contains(uid));
-                let db_canceling_task = self.get_task(&rtxn, canceled_by).unwrap().unwrap();
+                let db_canceling_task = this.get_task(&rtxn, canceled_by).unwrap().unwrap();
                 assert_eq!(db_canceling_task.status, Status::Succeeded);
                 match db_canceling_task.kind {
                     KindWithContent::TaskCancelation { query: _, tasks } => {
@@ -427,7 +428,7 @@ impl IndexScheduler {
                     Details::IndexInfo { primary_key: pk1 } => match &kind {
                         KindWithContent::IndexCreation { index_uid, primary_key: pk2 }
                         | KindWithContent::IndexUpdate { index_uid, primary_key: pk2 } => {
-                            self.index_tasks
+                            this.index_tasks
                                 .get(&rtxn, index_uid.as_str())
                                 .unwrap()
                                 .unwrap()
@@ -535,23 +536,23 @@ impl IndexScheduler {
                 }
             }
 
-            assert!(self.get_status(&rtxn, status).unwrap().contains(uid));
-            assert!(self.get_kind(&rtxn, kind.as_kind()).unwrap().contains(uid));
+            assert!(this.get_status(&rtxn, status).unwrap().contains(uid));
+            assert!(this.get_kind(&rtxn, kind.as_kind()).unwrap().contains(uid));
 
             if let KindWithContent::DocumentAdditionOrUpdate { content_file, .. } = kind {
                 match status {
                     Status::Enqueued | Status::Processing => {
-                        assert!(self
+                        assert!(this
                             .file_store
                             .all_uuids()
                             .unwrap()
                             .any(|uuid| uuid.as_ref().unwrap() == &content_file),
                             "Could not find uuid `{content_file}` in the file_store. Available uuids are {:?}.",
-                            self.file_store.all_uuids().unwrap().collect::<std::result::Result<Vec<_>, file_store::Error>>().unwrap(),
+                            this.file_store.all_uuids().unwrap().collect::<std::result::Result<Vec<_>, file_store::Error>>().unwrap(),
                         );
                     }
                     Status::Succeeded | Status::Failed | Status::Canceled => {
-                        assert!(self
+                        assert!(this
                             .file_store
                             .all_uuids()
                             .unwrap()

meili-snap/src/lib.rs

@@ -167,9 +167,7 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, Some(&snap_name));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
-            }
+            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
         });
     };
     ($value:expr, @$inline:literal) => {
@@ -178,9 +176,7 @@ macro_rules! snapshot {
         let (settings, _, _) = $crate::default_snapshot_settings_for_test("", Some("_dummy_argument"));
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(snap, @$inline);
-            }
+            meili_snap::insta::assert_snapshot!(snap, @$inline);
         });
     };
     ($value:expr) => {
@@ -198,9 +194,7 @@ macro_rules! snapshot {
         let (settings, snap_name, _) = $crate::default_snapshot_settings_for_test(test_name, None);
         settings.bind(|| {
             let snap = format!("{}", $value);
-            insta::allow_duplicates! {
-                meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
-            }
+            meili_snap::insta::assert_snapshot!(format!("{}", snap_name), snap);
         });
     };
 }

meilisearch-auth/Cargo.toml

@@ -14,6 +14,7 @@ license.workspace = true
 base64 = "0.21.0"
 enum-iterator = "1.4.0"
 hmac = "0.12.1"
+log = "0.4.19"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
@@ -24,3 +25,4 @@ sha2 = "0.10.6"
 thiserror = "1.0.40"
 time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 uuid = { version = "1.3.1", features = ["serde", "v4"] }
+zookeeper = "0.8.0"

meilisearch-auth/src/error.rs

@@ -19,6 +19,7 @@ internal_error!(
     AuthControllerError: meilisearch_types::milli::heed::Error,
     std::io::Error,
     serde_json::Error,
+    zookeeper::ZkError,
     std::str::Utf8Error
 );
 

meilisearch-auth/src/lib.rs

@@ -16,22 +16,113 @@ pub use store::open_auth_store_env;
 use store::{generate_key_as_hexa, HeedAuthStore};
 use time::OffsetDateTime;
 use uuid::Uuid;
+use zookeeper::{
+    Acl, AddWatchMode, CreateMode, WatchedEvent, WatchedEventType, ZkError, ZooKeeper,
+};
 
 #[derive(Clone)]
 pub struct AuthController {
     store: Arc<HeedAuthStore>,
     master_key: Option<String>,
+    zookeeper: Option<Arc<ZooKeeper>>,
 }
 
 impl AuthController {
-    pub fn new(db_path: impl AsRef<Path>, master_key: &Option<String>) -> Result<Self> {
+    pub fn new(
+        db_path: impl AsRef<Path>,
+        master_key: &Option<String>,
+        zookeeper: Option<Arc<ZooKeeper>>,
+    ) -> Result<Self> {
         let store = HeedAuthStore::new(db_path)?;
+        let controller = Self { store: Arc::new(store), master_key: master_key.clone(), zookeeper };
 
-        if store.is_empty()? {
-            generate_default_keys(&store)?;
+        match controller.zookeeper {
+            // setup the auth zk environment, the `auth` node
+            Some(ref zookeeper) => {
+                // Zookeeper Event listener loop
+                let controller_clone = controller.clone();
+                let zkk = zookeeper.clone();
+                zookeeper.add_watch("/auth", AddWatchMode::PersistentRecursive, move |event| {
+                    let WatchedEvent { event_type, path, keeper_state: _ } = dbg!(event);
+
+                    match event_type {
+                        WatchedEventType::NodeDeleted => {
+                            // TODO: ugly unwraps
+                            let path = path.unwrap();
+                            let uuid = path.strip_prefix("/auth/").unwrap();
+                            let uuid = Uuid::parse_str(&uuid).unwrap();
+                            log::info!("The key {} has been deleted", uuid);
+                            controller_clone.store.delete_api_key(uuid).unwrap();
+                        }
+                        WatchedEventType::NodeCreated | WatchedEventType::NodeDataChanged => {
+                            let path = path.unwrap();
+                            if path.strip_prefix("/auth/").map_or(false, |s| !s.is_empty()) {
+                                let (key, _stat) = zkk.get_data(&path, false).unwrap();
+                                let key: Key = serde_json::from_slice(&key).unwrap();
+                                log::info!("The key {} has been deleted", key.uid);
+                                controller_clone.store.put_api_key(key).unwrap();
+                            }
+                        }
+                        otherwise => panic!("Got the unexpected `{otherwise:?}` event!"),
+                    }
+                })?;
+
+                // TODO: we should catch the potential unexpected errors here https://docs.rs/zookeeper-client/latest/zookeeper_client/struct.Client.html#method.create
+                // for the moment we consider that `create` only returns Error::NodeExists.
+                match zookeeper.create(
+                    "/auth",
+                    vec![],
+                    Acl::open_unsafe().clone(),
+                    CreateMode::Persistent,
+                ) {
+                    // If the store is empty, we must generate and push the default api-keys.
+                    Ok(_) => generate_default_keys(&controller)?,
+                    // If the node exist we should clear our DB and download all the existing api-keys
+                    Err(ZkError::NodeExists) => {
+                        log::warn!("Auth directory already exists, we need to clear our keys + import the one in zookeeper");
+
+                        let store = controller.store.clone();
+                        store.delete_all_keys()?;
+                        let children = zookeeper
+                            .get_children("/auth", false)
+                            .expect("Internal, the auth directory was deleted during execution.");
+
+                        log::info!("Importing {} api-keys", children.len());
+                        for path in children {
+                            log::info!("  Importing {}", path);
+                            match zookeeper.get_data(&format!("/auth/{}", &path), false) {
+                                Ok((key, _stat)) => {
+                                    let key = serde_json::from_slice(&key).unwrap();
+                                    let store = controller.store.clone();
+                                    store.put_api_key(key)?;
+                                }
+                                Err(e) => panic!("{e}"),
+                            }
+                            // else the file was deleted while we were inserting the key. We ignore it.
+                            // TODO: What happens if someone updates the files before we have the time
+                            //       to setup the watcher
+                        }
+                    }
+                    e @ Err(
+                        ZkError::NoNode | ZkError::NoChildrenForEphemerals | ZkError::InvalidACL,
+                    ) => unreachable!("{e:?}"),
+                    Err(e) => panic!("{e}"),
+                }
+                // TODO: Race condition above:
+                //       What happens if two node join exactly at the same moment:
+                //       One will create the dir
+                //       The second one will delete its DB, load nothing and install a watcher
+                //       The first one will push its keys and should wake up and update the second one.
+                //     / BUT, if the second one delete its DB and the first one push its files before the second one install the watcher we're fucked
+            }
+            None => {
+                if controller.store.is_empty()? {
+                    generate_default_keys(&controller)?;
+                }
+            }
         }
 
-        Ok(Self { store: Arc::new(store), master_key: master_key.clone() })
+        Ok(controller)
     }
 
     /// Return `Ok(())` if the auth controller is able to access one of its database.
@@ -53,7 +144,24 @@ impl AuthController {
     pub fn create_key(&self, create_key: CreateApiKey) -> Result<Key> {
         match self.store.get_api_key(create_key.uid)? {
             Some(_) => Err(AuthControllerError::ApiKeyAlreadyExists(create_key.uid.to_string())),
-            None => self.store.put_api_key(create_key.to_key()),
+            None => self.put_key(create_key.to_key()),
+        }
+    }
+
+    pub fn put_key(&self, key: Key) -> Result<Key> {
+        let store = self.store.clone();
+        match &self.zookeeper {
+            Some(zookeeper) => {
+                zookeeper.create(
+                    &format!("/auth/{}", key.uid),
+                    serde_json::to_vec_pretty(&key)?,
+                    Acl::open_unsafe().clone(),
+                    CreateMode::Persistent,
+                )?;
+
+                Ok(key)
+            }
+            None => store.put_api_key(key),
         }
     }
 
@@ -68,7 +176,20 @@ impl AuthController {
             name => key.name = name.set(),
         };
         key.updated_at = OffsetDateTime::now_utc();
-        self.store.put_api_key(key)
+        let store = self.store.clone();
+        // TODO: we may commit only after zk persisted the keys
+        match &self.zookeeper {
+            Some(zookeeper) => {
+                zookeeper.set_data(
+                    &format!("/auth/{}", key.uid),
+                    serde_json::to_vec_pretty(&key)?,
+                    None,
+                )?;
+
+                Ok(key)
+            }
+            None => store.put_api_key(key),
+        }
     }
 
     pub fn get_key(&self, uid: Uuid) -> Result<Key> {
@@ -110,7 +231,19 @@ impl AuthController {
     }
 
     pub fn delete_key(&self, uid: Uuid) -> Result<()> {
-        if self.store.delete_api_key(uid)? {
+        let deleted = match &self.zookeeper {
+            Some(zookeeper) => match zookeeper.delete(&format!("/auth/{}", uid), None) {
+                Ok(()) => true,
+                Err(ZkError::NoNode) => false,
+                Err(e) => return Err(e.into()),
+            },
+            None => {
+                let store = self.store.clone();
+                store.delete_api_key(uid)?
+            }
+        };
+
+        if deleted {
             Ok(())
         } else {
             Err(AuthControllerError::ApiKeyNotFound(uid.to_string()))
@@ -159,7 +292,7 @@ impl AuthController {
         self.store.delete_all_keys()
     }
 
-    /// Delete all the keys in the DB.
+    /// Insert a key in the DB without any check on its validity
     pub fn raw_insert_key(&mut self, key: Key) -> Result<()> {
         self.store.put_api_key(key)?;
         Ok(())
@@ -304,10 +437,9 @@ pub struct IndexSearchRules {
     pub filter: Option<serde_json::Value>,
 }
 
-fn generate_default_keys(store: &HeedAuthStore) -> Result<()> {
-    store.put_api_key(Key::default_admin())?;
-    store.put_api_key(Key::default_search())?;
-
+fn generate_default_keys(controller: &AuthController) -> Result<()> {
+    controller.put_key(Key::default_admin())?;
+    controller.put_key(Key::default_search())?;
     Ok(())
 }
 

meilisearch-auth/src/store.rs

@@ -129,9 +129,6 @@ impl HeedAuthStore {
                 Action::DumpsAll => {
                     actions.insert(Action::DumpsCreate);
                 }
-                Action::SnapshotsAll => {
-                    actions.insert(Action::SnapshotsCreate);
-                }
                 Action::TasksAll => {
                     actions.extend([Action::TasksGet, Action::TasksDelete, Action::TasksCancel]);
                 }

meilisearch-types/Cargo.toml

@@ -15,13 +15,13 @@ actix-web = { version = "4.3.1", default-features = false }
 anyhow = "1.0.70"
 convert_case = "0.6.0"
 csv = "1.2.1"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+deserr = "0.5.0"
 either = { version = "1.8.1", features = ["serde"] }
 enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
 flate2 = "1.0.25"
 fst = "0.4.7"
-memmap2 = "0.7.1"
+memmap2 = "0.5.10"
 milli = { path = "../milli" }
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
@@ -50,7 +50,6 @@ hebrew = ["milli/hebrew"]
 japanese = ["milli/japanese"]
 # thai specialized tokenization
 thai = ["milli/thai"]
+
 # allow greek specialized tokenization
 greek = ["milli/greek"]
-# allow khmer specialized tokenization
-khmer = ["milli/khmer"]

meilisearch-types/src/error.rs

@@ -175,6 +175,7 @@ macro_rules! make_error_codes {
 
 // An exhaustive list of all the error codes used by meilisearch.
 make_error_codes! {
+S3Error                               , System               , INTERNAL_SERVER_ERROR;
 ApiKeyAlreadyExists                   , InvalidRequest       , CONFLICT ;
 ApiKeyNotFound                        , InvalidRequest       , NOT_FOUND ;
 BadParameter                          , InvalidRequest       , BAD_REQUEST;
@@ -259,9 +260,6 @@ InvalidSettingsRankingRules           , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSearchableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSortableAttributes     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsStopWords              , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsNonSeparatorTokens     , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsSeparatorTokens        , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsDictionary             , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsSynonyms               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsTypoTolerance          , InvalidRequest       , BAD_REQUEST ;
 InvalidState                          , Internal             , INTERNAL_SERVER_ERROR ;
@@ -324,6 +322,7 @@ impl ErrorCode for milli::Error {
                     UserError::SerdeJson(_)
                     | UserError::InvalidLmdbOpenOptions
                     | UserError::DocumentLimitReached
+                    | UserError::AccessingSoftDeletedDocument { .. }
                     | UserError::UnknownInternalDocumentId { .. } => Code::Internal,
                     UserError::InvalidStoreFile => Code::InvalidStoreFile,
                     UserError::NoSpaceLeftOnDevice => Code::NoSpaceLeftOnDevice,

meilisearch-types/src/features.rs

@@ -5,8 +5,6 @@ use serde::{Deserialize, Serialize};
 pub struct RuntimeTogglableFeatures {
     pub score_details: bool,
     pub vector_store: bool,
-    pub metrics: bool,
-    pub export_puffin_reports: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]

meilisearch-types/src/keys.rs

@@ -257,12 +257,6 @@ pub enum Action {
     #[serde(rename = "dumps.create")]
     #[deserr(rename = "dumps.create")]
     DumpsCreate,
-    #[serde(rename = "snapshots.*")]
-    #[deserr(rename = "snapshots.*")]
-    SnapshotsAll,
-    #[serde(rename = "snapshots.create")]
-    #[deserr(rename = "snapshots.create")]
-    SnapshotsCreate,
     #[serde(rename = "version")]
     #[deserr(rename = "version")]
     Version,
@@ -315,7 +309,6 @@ impl Action {
             METRICS_GET => Some(Self::MetricsGet),
             DUMPS_ALL => Some(Self::DumpsAll),
             DUMPS_CREATE => Some(Self::DumpsCreate),
-            SNAPSHOTS_CREATE => Some(Self::SnapshotsCreate),
             VERSION => Some(Self::Version),
             KEYS_CREATE => Some(Self::KeysAdd),
             KEYS_GET => Some(Self::KeysGet),
@@ -360,7 +353,6 @@ pub mod actions {
     pub const METRICS_GET: u8 = MetricsGet.repr();
     pub const DUMPS_ALL: u8 = DumpsAll.repr();
     pub const DUMPS_CREATE: u8 = DumpsCreate.repr();
-    pub const SNAPSHOTS_CREATE: u8 = SnapshotsCreate.repr();
     pub const VERSION: u8 = Version.repr();
     pub const KEYS_CREATE: u8 = KeysAdd.repr();
     pub const KEYS_GET: u8 = KeysGet.repr();

meilisearch-types/src/lib.rs

@@ -9,7 +9,6 @@ pub mod index_uid_pattern;
 pub mod keys;
 pub mod settings;
 pub mod star_or;
-pub mod task_view;
 pub mod tasks;
 pub mod versioning;
 pub use milli::{heed, Index};

meilisearch-types/src/settings.rs

@@ -171,15 +171,6 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsStopWords>)]
     pub stop_words: Setting<BTreeSet<String>>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsNonSeparatorTokens>)]
-    pub non_separator_tokens: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsSeparatorTokens>)]
-    pub separator_tokens: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsDictionary>)]
-    pub dictionary: Setting<BTreeSet<String>>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsSynonyms>)]
     pub synonyms: Setting<BTreeMap<String, Vec<String>>>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
@@ -210,9 +201,6 @@ impl Settings<Checked> {
             ranking_rules: Setting::Reset,
             stop_words: Setting::Reset,
             synonyms: Setting::Reset,
-            non_separator_tokens: Setting::Reset,
-            separator_tokens: Setting::Reset,
-            dictionary: Setting::Reset,
             distinct_attribute: Setting::Reset,
             typo_tolerance: Setting::Reset,
             faceting: Setting::Reset,
@@ -229,9 +217,6 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
             typo_tolerance,
@@ -247,9 +232,6 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
             typo_tolerance,
@@ -292,9 +274,6 @@ impl Settings<Unchecked> {
             ranking_rules: self.ranking_rules,
             stop_words: self.stop_words,
             synonyms: self.synonyms,
-            non_separator_tokens: self.non_separator_tokens,
-            separator_tokens: self.separator_tokens,
-            dictionary: self.dictionary,
             distinct_attribute: self.distinct_attribute,
             typo_tolerance: self.typo_tolerance,
             faceting: self.faceting,
@@ -356,28 +335,6 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.non_separator_tokens {
-        Setting::Set(ref non_separator_tokens) => {
-            builder.set_non_separator_tokens(non_separator_tokens.clone())
-        }
-        Setting::Reset => builder.reset_non_separator_tokens(),
-        Setting::NotSet => (),
-    }
-
-    match settings.separator_tokens {
-        Setting::Set(ref separator_tokens) => {
-            builder.set_separator_tokens(separator_tokens.clone())
-        }
-        Setting::Reset => builder.reset_separator_tokens(),
-        Setting::NotSet => (),
-    }
-
-    match settings.dictionary {
-        Setting::Set(ref dictionary) => builder.set_dictionary(dictionary.clone()),
-        Setting::Reset => builder.reset_dictionary(),
-        Setting::NotSet => (),
-    }
-
     match settings.synonyms {
         Setting::Set(ref synonyms) => builder.set_synonyms(synonyms.clone().into_iter().collect()),
         Setting::Reset => builder.reset_synonyms(),
@@ -502,14 +459,15 @@ pub fn settings(
         })
         .transpose()?
         .unwrap_or_default();
-
-    let non_separator_tokens = index.non_separator_tokens(rtxn)?.unwrap_or_default();
-    let separator_tokens = index.separator_tokens(rtxn)?.unwrap_or_default();
-    let dictionary = index.dictionary(rtxn)?.unwrap_or_default();
-
     let distinct_field = index.distinct_field(rtxn)?.map(String::from);
 
-    let synonyms = index.user_defined_synonyms(rtxn)?;
+    // in milli each word in the synonyms map were split on their separator. Since we lost
+    // this information we are going to put space between words.
+    let synonyms = index
+        .synonyms(rtxn)?
+        .iter()
+        .map(|(key, values)| (key.join(" "), values.iter().map(|value| value.join(" ")).collect()))
+        .collect();
 
     let min_typo_word_len = MinWordSizeTyposSetting {
         one_typo: Setting::Set(index.min_word_len_one_typo(rtxn)?),
@@ -562,9 +520,6 @@ pub fn settings(
         sortable_attributes: Setting::Set(sortable_attributes),
         ranking_rules: Setting::Set(criteria.iter().map(|c| c.clone().into()).collect()),
         stop_words: Setting::Set(stop_words),
-        non_separator_tokens: Setting::Set(non_separator_tokens),
-        separator_tokens: Setting::Set(separator_tokens),
-        dictionary: Setting::Set(dictionary),
         distinct_attribute: match distinct_field {
             Some(field) => Setting::Set(field),
             None => Setting::Reset,
@@ -687,9 +642,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
@@ -711,9 +663,6 @@ pub(crate) mod test {
             sortable_attributes: Setting::NotSet,
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
-            non_separator_tokens: Setting::NotSet,
-            separator_tokens: Setting::NotSet,
-            dictionary: Setting::NotSet,
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,

meilisearch-types/src/task_view.rs

@@ -1,139 +0,0 @@
-use serde::Serialize;
-use time::{Duration, OffsetDateTime};
-
-use crate::error::ResponseError;
-use crate::settings::{Settings, Unchecked};
-use crate::tasks::{serialize_duration, Details, IndexSwap, Kind, Status, Task, TaskId};
-
-#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub struct TaskView {
-    pub uid: TaskId,
-    #[serde(default)]
-    pub index_uid: Option<String>,
-    pub status: Status,
-    #[serde(rename = "type")]
-    pub kind: Kind,
-    pub canceled_by: Option<TaskId>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub details: Option<DetailsView>,
-    pub error: Option<ResponseError>,
-    #[serde(serialize_with = "serialize_duration", default)]
-    pub duration: Option<Duration>,
-    #[serde(with = "time::serde::rfc3339")]
-    pub enqueued_at: OffsetDateTime,
-    #[serde(with = "time::serde::rfc3339::option", default)]
-    pub started_at: Option<OffsetDateTime>,
-    #[serde(with = "time::serde::rfc3339::option", default)]
-    pub finished_at: Option<OffsetDateTime>,
-}
-
-impl TaskView {
-    pub fn from_task(task: &Task) -> TaskView {
-        TaskView {
-            uid: task.uid,
-            index_uid: task.index_uid().map(ToOwned::to_owned),
-            status: task.status,
-            kind: task.kind.as_kind(),
-            canceled_by: task.canceled_by,
-            details: task.details.clone().map(DetailsView::from),
-            error: task.error.clone(),
-            duration: task.started_at.zip(task.finished_at).map(|(start, end)| end - start),
-            enqueued_at: task.enqueued_at,
-            started_at: task.started_at,
-            finished_at: task.finished_at,
-        }
-    }
-}
-
-#[derive(Default, Debug, PartialEq, Eq, Clone, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub struct DetailsView {
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub received_documents: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub indexed_documents: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub primary_key: Option<Option<String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub provided_ids: Option<usize>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub deleted_documents: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub matched_tasks: Option<u64>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub canceled_tasks: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub deleted_tasks: Option<Option<u64>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub original_filter: Option<Option<String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub dump_uid: Option<Option<String>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    #[serde(flatten)]
-    pub settings: Option<Box<Settings<Unchecked>>>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub swaps: Option<Vec<IndexSwap>>,
-}
-
-impl From<Details> for DetailsView {
-    fn from(details: Details) -> Self {
-        match details {
-            Details::DocumentAdditionOrUpdate { received_documents, indexed_documents } => {
-                DetailsView {
-                    received_documents: Some(received_documents),
-                    indexed_documents: Some(indexed_documents),
-                    ..DetailsView::default()
-                }
-            }
-            Details::SettingsUpdate { settings } => {
-                DetailsView { settings: Some(settings), ..DetailsView::default() }
-            }
-            Details::IndexInfo { primary_key } => {
-                DetailsView { primary_key: Some(primary_key), ..DetailsView::default() }
-            }
-            Details::DocumentDeletion {
-                provided_ids: received_document_ids,
-                deleted_documents,
-            } => DetailsView {
-                provided_ids: Some(received_document_ids),
-                deleted_documents: Some(deleted_documents),
-                original_filter: Some(None),
-                ..DetailsView::default()
-            },
-            Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
-                DetailsView {
-                    provided_ids: Some(0),
-                    original_filter: Some(Some(original_filter)),
-                    deleted_documents: Some(deleted_documents),
-                    ..DetailsView::default()
-                }
-            }
-            Details::ClearAll { deleted_documents } => {
-                DetailsView { deleted_documents: Some(deleted_documents), ..DetailsView::default() }
-            }
-            Details::TaskCancelation { matched_tasks, canceled_tasks, original_filter } => {
-                DetailsView {
-                    matched_tasks: Some(matched_tasks),
-                    canceled_tasks: Some(canceled_tasks),
-                    original_filter: Some(Some(original_filter)),
-                    ..DetailsView::default()
-                }
-            }
-            Details::TaskDeletion { matched_tasks, deleted_tasks, original_filter } => {
-                DetailsView {
-                    matched_tasks: Some(matched_tasks),
-                    deleted_tasks: Some(deleted_tasks),
-                    original_filter: Some(Some(original_filter)),
-                    ..DetailsView::default()
-                }
-            }
-            Details::Dump { dump_uid } => {
-                DetailsView { dump_uid: Some(dump_uid), ..DetailsView::default() }
-            }
-            Details::IndexSwap { swaps } => {
-                DetailsView { swaps: Some(swaps), ..Default::default() }
-            }
-        }
-    }
-}

meilisearch/Cargo.toml

@@ -39,7 +39,7 @@ byte-unit = { version = "4.0.19", default-features = false, features = [
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
-deserr = { version = "0.6.0", features = ["actix-web"]}
+deserr = "0.5.0"
 dump = { path = "../dump" }
 either = "1.8.1"
 env_logger = "0.10.0"
@@ -50,9 +50,9 @@ futures = "0.3.28"
 futures-util = "0.3.28"
 http = "0.2.9"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.0.0", features = ["serde"] }
+indexmap = { version = "1.9.3", features = ["serde-1"] }
 is-terminal = "0.4.8"
-itertools = "0.11.0"
+itertools = "0.10.5"
 jsonwebtoken = "8.3.0"
 lazy_static = "1.4.0"
 log = "0.4.17"
@@ -69,7 +69,8 @@ permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.9"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
-puffin = { version = "0.16.0", features = ["serialization"] }
+puffin = "0.16.0"
+puffin_http = { version = "0.13.0", optional = true }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
@@ -79,6 +80,7 @@ reqwest = { version = "0.11.16", features = [
 ], default-features = false }
 rustls = "0.20.8"
 rustls-pemfile = "1.0.2"
+strois = "0.0.4"
 segment = { version = "0.2.2", optional = true }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
@@ -86,7 +88,7 @@ sha2 = "0.10.6"
 siphasher = "0.3.10"
 slice-group-by = "0.3.0"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.29.7"
+sysinfo = "0.28.4"
 tar = "0.4.38"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
@@ -104,7 +106,7 @@ walkdir = "2.3.3"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
 termcolor = "1.2.0"
-url = { version = "2.5.0", features = ["serde"] }
+zookeeper = "0.8.0"
 
 [dev-dependencies]
 actix-rt = "2.8.0"
@@ -135,6 +137,7 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
+profile-with-puffin = ["dep:puffin_http"]
 mini-dashboard = [
     "actix-web-static-files",
     "static-files",
@@ -151,7 +154,6 @@ hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
-khmer = ["meilisearch-types/khmer"]
 
 [package.metadata.mini-dashboard]
 assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.11/build.zip"

meilisearch/src/analytics/mock_analytics.rs

@@ -20,7 +20,7 @@ pub struct SearchAggregator;
 #[allow(dead_code)]
 impl SearchAggregator {
     pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self, _: &dyn Any) {}
@@ -32,7 +32,7 @@ pub struct MultiSearchAggregator;
 #[allow(dead_code)]
 impl MultiSearchAggregator {
     pub fn from_queries(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self) {}
@@ -44,7 +44,7 @@ pub struct FacetSearchAggregator;
 #[allow(dead_code)]
 impl FacetSearchAggregator {
     pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self
+        Self::default()
     }
 
     pub fn succeed(&mut self, _: &dyn Any) {}

meilisearch/src/analytics/mod.rs

@@ -1,5 +1,6 @@
 mod mock_analytics;
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 mod segment_analytics;
 
 use std::fs;
@@ -16,25 +17,26 @@ use serde_json::Value;
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
 use crate::routes::tasks::TasksFilterQuery;
 
-// if the analytics feature is disabled
+// if we are in debug mode OR the analytics feature is disabled
 // the `SegmentAnalytics` point to the mock instead of the real analytics
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SegmentAnalytics = mock_analytics::MockAnalytics;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type SearchAggregator = mock_analytics::SearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(not(feature = "analytics"))]
+#[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
-// if the feature analytics is enabled we use the real analytics
-#[cfg(feature = "analytics")]
+// if we are in release mode and the feature analytics was enabled
+// we use the real analytics
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type SearchAggregator = segment_analytics::SearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(feature = "analytics")]
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:

meilisearch/src/error.rs

@@ -33,6 +33,8 @@ pub enum MeilisearchHttpError {
         .0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len()
     )]
     SwapIndexPayloadWrongLength(Vec<IndexUid>),
+    #[error("S3 Error: {0}")]
+    S3Error(#[from] strois::Error),
     #[error(transparent)]
     IndexUid(#[from] IndexUidFormatError),
     #[error(transparent)]
@@ -65,6 +67,7 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::InvalidExpression(_, _) => Code::InvalidSearchFilter,
             MeilisearchHttpError::PayloadTooLarge(_) => Code::PayloadTooLarge,
             MeilisearchHttpError::SwapIndexPayloadWrongLength(_) => Code::InvalidSwapIndexes,
+            MeilisearchHttpError::S3Error(_) => Code::S3Error,
             MeilisearchHttpError::IndexUid(e) => e.error_code(),
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,
             MeilisearchHttpError::HeedError(_) => Code::Internal,

meilisearch/src/lib.rs

@@ -39,6 +39,8 @@ use meilisearch_types::versioning::{check_version_file, create_version_file};
 use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
 pub use option::Opt;
 use option::ScheduleSnapshot;
+use strois::Client;
+use zookeeper::ZooKeeper;
 
 use crate::error::MeilisearchHttpError;
 
@@ -114,7 +116,10 @@ pub fn create_app(
         .configure(routes::configure)
         .configure(|s| dashboard(s, enable_dashboard));
 
-    let app = app.wrap(middleware::RouteMetrics);
+    let app = app.wrap(actix_web::middleware::Condition::new(
+        opt.experimental_enable_metrics,
+        middleware::RouteMetrics,
+    ));
     app.wrap(
         Cors::default()
             .send_wildcard()
@@ -133,14 +138,17 @@ enum OnFailure {
     KeepDb,
 }
 
-pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
+pub async fn setup_meilisearch(
+    opt: &Opt,
+    zookeeper: Option<Arc<ZooKeeper>>,
+) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
     let empty_db = is_empty_db(&opt.db_path);
     let (index_scheduler, auth_controller) = if let Some(ref snapshot_path) = opt.import_snapshot {
         let snapshot_path_exists = snapshot_path.exists();
         // the db is empty and the snapshot exists, import it
         if empty_db && snapshot_path_exists {
             match compression::from_tar_gz(snapshot_path, &opt.db_path) {
-                Ok(()) => open_or_create_database_unchecked(opt, OnFailure::RemoveDb)?,
+                Ok(()) => open_or_create_database_unchecked(opt, OnFailure::RemoveDb, zookeeper)?,
                 Err(e) => {
                     std::fs::remove_dir_all(&opt.db_path)?;
                     return Err(e);
@@ -157,14 +165,14 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
             bail!("snapshot doesn't exist at {}", snapshot_path.display())
         // the snapshot and the db exist, and we can ignore the snapshot because of the ignore_snapshot_if_db_exists flag
         } else {
-            open_or_create_database(opt, empty_db)?
+            open_or_create_database(opt, empty_db, zookeeper)?
         }
     } else if let Some(ref path) = opt.import_dump {
         let src_path_exists = path.exists();
         // the db is empty and the dump exists, import it
         if empty_db && src_path_exists {
             let (mut index_scheduler, mut auth_controller) =
-                open_or_create_database_unchecked(opt, OnFailure::RemoveDb)?;
+                open_or_create_database_unchecked(opt, OnFailure::RemoveDb, zookeeper)?;
             match import_dump(&opt.db_path, path, &mut index_scheduler, &mut auth_controller) {
                 Ok(()) => (index_scheduler, auth_controller),
                 Err(e) => {
@@ -184,10 +192,10 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         // the dump and the db exist and we can ignore the dump because of the ignore_dump_if_db_exists flag
         // or, the dump is missing but we can ignore that because of the ignore_missing_dump flag
         } else {
-            open_or_create_database(opt, empty_db)?
+            open_or_create_database(opt, empty_db, zookeeper)?
         }
     } else {
-        open_or_create_database(opt, empty_db)?
+        open_or_create_database(opt, empty_db, zookeeper)?
     };
 
     // We create a loop in a thread that registers snapshotCreation tasks
@@ -196,15 +204,12 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
     if let ScheduleSnapshot::Enabled(snapshot_delay) = opt.schedule_snapshot {
         let snapshot_delay = Duration::from_secs(snapshot_delay);
         let index_scheduler = index_scheduler.clone();
-        thread::Builder::new()
-            .name(String::from("register-snapshot-tasks"))
-            .spawn(move || loop {
-                thread::sleep(snapshot_delay);
-                if let Err(e) = index_scheduler.register(KindWithContent::SnapshotCreation) {
-                    error!("Error while registering snapshot: {}", e);
-                }
-            })
-            .unwrap();
+        thread::spawn(move || loop {
+            thread::sleep(snapshot_delay);
+            if let Err(e) = index_scheduler.register(KindWithContent::SnapshotCreation) {
+                error!("Error while registering snapshot: {}", e);
+            }
+        });
     }
 
     Ok((index_scheduler, auth_controller))
@@ -214,35 +219,49 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
 fn open_or_create_database_unchecked(
     opt: &Opt,
     on_failure: OnFailure,
+    zookeeper: Option<Arc<ZooKeeper>>,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     // we don't want to create anything in the data.ms yet, thus we
     // wrap our two builders in a closure that'll be executed later.
-    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key);
+    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key, zookeeper.clone());
     let instance_features = opt.to_instance_features();
-    let index_scheduler_builder = || -> anyhow::Result<_> {
-        Ok(IndexScheduler::new(IndexSchedulerOptions {
-            version_file_path: opt.db_path.join(VERSION_FILE_NAME),
-            auth_path: opt.db_path.join("auth"),
-            tasks_path: opt.db_path.join("tasks"),
-            update_file_path: opt.db_path.join("update_files"),
-            indexes_path: opt.db_path.join("indexes"),
-            snapshots_path: opt.snapshot_dir.clone(),
-            dumps_path: opt.dump_dir.clone(),
-            webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
-            task_db_size: opt.max_task_db_size.get_bytes() as usize,
-            index_base_map_size: opt.max_index_size.get_bytes() as usize,
-            enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
-            indexer_config: (&opt.indexer_options).try_into()?,
-            autobatching_enabled: true,
-            max_number_of_tasks: 1_000_000,
-            index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
-            index_count: DEFAULT_INDEX_COUNT,
-            instance_features,
-        })?)
-    };
+    let index_scheduler = IndexScheduler::new(Arc::new(IndexSchedulerOptions {
+        version_file_path: opt.db_path.join(VERSION_FILE_NAME),
+        auth_path: opt.db_path.join("auth"),
+        tasks_path: opt.db_path.join("tasks"),
+        update_file_path: opt.db_path.join("update_files"),
+        indexes_path: opt.db_path.join("indexes"),
+        snapshots_path: opt.snapshot_dir.clone(),
+        dumps_path: opt.dump_dir.clone(),
+        task_db_size: opt.max_task_db_size.get_bytes() as usize,
+        index_base_map_size: opt.max_index_size.get_bytes() as usize,
+        enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
+        indexer_config: (&opt.indexer_options).try_into().map(Arc::new)?,
+        autobatching_enabled: true,
+        max_number_of_tasks: 1_000_000,
+        index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
+        index_count: DEFAULT_INDEX_COUNT,
+        instance_features,
+        zookeeper: zookeeper.clone(),
+        s3: opt.s3_url.as_ref().map(|url| {
+            Arc::new(
+                Client::builder(url)
+                    .unwrap()
+                    .key(opt.s3_access_key.as_ref().expect("Need s3 key to work").clone())
+                    .secret(opt.s3_secret_key.as_ref().expect("Need s3 secret to work").clone())
+                    .maybe_token(opt.s3_security_token.clone())
+                    .region(&opt.s3_region)
+                    .bucket(opt.s3_bucket.as_ref().expect("Need an s3 bucket to work"))
+                    .unwrap()
+                    .get_or_create()
+                    .unwrap(),
+            )
+        }),
+    }))
+    .map_err(anyhow::Error::from);
 
     match (
-        index_scheduler_builder(),
+        index_scheduler,
         auth_controller.map_err(anyhow::Error::from),
         create_version_file(&opt.db_path).map_err(anyhow::Error::from),
     ) {
@@ -260,12 +279,13 @@ fn open_or_create_database_unchecked(
 fn open_or_create_database(
     opt: &Opt,
     empty_db: bool,
+    zookeeper: Option<Arc<ZooKeeper>>,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     if !empty_db {
         check_version_file(&opt.db_path)?;
     }
 
-    open_or_create_database_unchecked(opt, OnFailure::KeepDb)
+    open_or_create_database_unchecked(opt, OnFailure::KeepDb, zookeeper)
 }
 
 fn import_dump(
@@ -275,6 +295,7 @@ fn import_dump(
     auth: &mut AuthController,
 ) -> Result<(), anyhow::Error> {
     let reader = File::open(dump_path)?;
+    let index_scheduler = index_scheduler.inner();
     let mut dump_reader = dump::DumpReader::open(reader)?;
 
     if let Some(date) = dump_reader.date() {
@@ -363,7 +384,7 @@ fn import_dump(
                 update_method: IndexDocumentsMethod::ReplaceDocuments,
                 ..Default::default()
             },
-            |indexing_step| log::trace!("update: {:?}", indexing_step),
+            |indexing_step| log::debug!("update: {:?}", indexing_step),
             || false,
         )?;
 
@@ -398,7 +419,6 @@ pub fn configure_data(
         .app_data(web::Data::from(analytics))
         .app_data(
             web::JsonConfig::default()
-                .limit(http_payload_size_limit)
                 .content_type(|mime| mime == mime::APPLICATION_JSON)
                 .error_handler(|err, req: &HttpRequest| match err {
                     JsonPayloadError::ContentType => match req.headers().get(CONTENT_TYPE) {

meilisearch/src/main.rs

@@ -2,6 +2,7 @@ use std::env;
 use std::io::{stderr, Write};
 use std::path::PathBuf;
 use std::sync::Arc;
+use std::time::Duration;
 
 use actix_web::http::KeepAlive;
 use actix_web::web::Data;
@@ -12,6 +13,7 @@ use meilisearch::analytics::Analytics;
 use meilisearch::{analytics, create_app, prototype_name, setup_meilisearch, Opt};
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
+use zookeeper::ZooKeeper;
 
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
@@ -30,6 +32,10 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
+    #[cfg(feature = "profile-with-puffin")]
+    let _server = puffin_http::Server::new(&format!("0.0.0.0:{}", puffin_http::DEFAULT_PORT))?;
+    puffin::set_scopes_on(cfg!(feature = "profile-with-puffin"));
+
     anyhow::ensure!(
         !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
         "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"
@@ -59,7 +65,10 @@ async fn main() -> anyhow::Result<()> {
         _ => (),
     }
 
-    let (index_scheduler, auth_controller) = setup_meilisearch(&opt)?;
+    let timeout = Duration::from_millis(2500);
+    let zookeeper =
+        opt.zk_url.as_ref().map(|url| Arc::new(ZooKeeper::connect(url, timeout, drop).unwrap()));
+    let (index_scheduler, auth_controller) = setup_meilisearch(&opt, zookeeper).await?;
 
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
     let analytics = if !opt.no_analytics {

meilisearch/src/middleware.rs

@@ -3,10 +3,8 @@
 use std::future::{ready, Ready};
 
 use actix_web::dev::{self, Service, ServiceRequest, ServiceResponse, Transform};
-use actix_web::web::Data;
 use actix_web::Error;
 use futures_util::future::LocalBoxFuture;
-use index_scheduler::IndexScheduler;
 use prometheus::HistogramTimer;
 
 pub struct RouteMetrics;
@@ -49,27 +47,19 @@ where
 
     fn call(&self, req: ServiceRequest) -> Self::Future {
         let mut histogram_timer: Option<HistogramTimer> = None;
-
-        // calling unwrap here is safe because index scheduler is added to app data while creating actix app.
-        // also, the tests will fail if this is not present.
-        let index_scheduler = req.app_data::<Data<IndexScheduler>>().unwrap();
-        let features = index_scheduler.features();
-
-        if features.check_metrics().is_ok() {
-            let request_path = req.path();
-            let is_registered_resource = req.resource_map().has_resource(request_path);
-            if is_registered_resource {
-                let request_method = req.method().to_string();
-                histogram_timer = Some(
-                    crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
-                        .with_label_values(&[&request_method, request_path])
-                        .start_timer(),
-                );
-                crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+        let request_path = req.path();
+        let is_registered_resource = req.resource_map().has_resource(request_path);
+        if is_registered_resource {
+            let request_method = req.method().to_string();
+            histogram_timer = Some(
+                crate::metrics::MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS
                     .with_label_values(&[&request_method, request_path])
-                    .inc();
-            }
-        };
+                    .start_timer(),
+            );
+            crate::metrics::MEILISEARCH_HTTP_REQUESTS_TOTAL
+                .with_label_values(&[&request_method, request_path])
+                .inc();
+        }
 
         let fut = self.service.call(req);
 

meilisearch/src/option.rs

@@ -21,7 +21,6 @@ use rustls::RootCertStore;
 use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use serde::{Deserialize, Serialize};
 use sysinfo::{RefreshKind, System, SystemExt};
-use url::Url;
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
 
@@ -29,8 +28,14 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
 const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
 const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
-const MEILI_TASK_WEBHOOK_URL: &str = "MEILI_TASK_WEBHOOK_URL";
-#[cfg(feature = "analytics")]
+const MEILI_ZK_URL: &str = "MEILI_ZK_URL";
+const MEILI_S3_URL: &str = "MEILI_S3_URL";
+const MEILI_S3_BUCKET: &str = "MEILI_S3_BUCKET";
+const MEILI_S3_ACCESS_KEY: &str = "MEILI_S3_ACCESS_KEY";
+const MEILI_S3_SECRET_KEY: &str = "MEILI_S3_SECRET_KEY";
+const MEILI_S3_SECURITY_TOKEN: &str = "MEILI_S3_SECURITY_TOKEN";
+const MEILI_S3_REGION: &str = "MEILI_S3_REGION";
+#[cfg(all(not(debug_assertions), feature = "analytics"))]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
 const MEILI_SSL_CERT_PATH: &str = "MEILI_SSL_CERT_PATH";
@@ -58,6 +63,7 @@ const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
 const DEFAULT_HTTP_ADDR: &str = "localhost:7700";
 const DEFAULT_ENV: &str = "development";
+const DEFAULT_S3_REGION: &str = "eu-central-1";
 const DEFAULT_HTTP_PAYLOAD_SIZE_LIMIT: &str = "100 MB";
 const DEFAULT_SNAPSHOT_DIR: &str = "snapshots/";
 const DEFAULT_SNAPSHOT_INTERVAL_SEC: u64 = 86400;
@@ -156,16 +162,42 @@ pub struct Opt {
     #[serde(default = "default_env")]
     pub env: String,
 
-    /// Called whenever a task finishes so a third party can be notified.
-    #[clap(long, env = MEILI_TASK_WEBHOOK_URL)]
-    pub task_webhook_url: Option<Url>,
+    /// Sets the HTTP address and port used to communicate with the zookeeper cluster.
+    /// If ran locally, the default url is `http://localhost:2181/`.
+    #[clap(long, env = MEILI_ZK_URL)]
+    pub zk_url: Option<String>,
+
+    /// Sets the address and port used to communicate with the S3 bucket.
+    #[clap(long, env = MEILI_S3_URL)]
+    pub s3_url: Option<String>,
+
+    /// Sets the region used to communicate with the s3 bucket.
+    #[clap(long, env = MEILI_S3_REGION, default_value_t = default_s3_region())]
+    #[serde(default = "default_s3_region")]
+    pub s3_region: String,
+
+    /// Sets the S3 bucket name to use.
+    #[clap(long, env = MEILI_S3_BUCKET)]
+    pub s3_bucket: Option<String>,
+
+    /// Set the S3 access key. If used you must also set the secret key.
+    #[clap(long, env = MEILI_S3_ACCESS_KEY)]
+    pub s3_access_key: Option<String>,
+
+    /// Set the S3 secret key. If used you must also set the access key.
+    #[clap(long, env = MEILI_S3_SECRET_KEY)]
+    pub s3_secret_key: Option<String>,
+
+    /// Security token, can't be used with access key and secret key.
+    #[clap(long, env = MEILI_S3_SECURITY_TOKEN)]
+    pub s3_security_token: Option<String>,
 
     /// Deactivates Meilisearch's built-in telemetry when provided.
     ///
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
     /// All gathered data is used solely for the purpose of improving Meilisearch, and can be deleted
     /// at any time.
-    #[cfg(feature = "analytics")]
+    #[cfg(all(not(debug_assertions), feature = "analytics"))]
     #[serde(default)] // we can't send true
     #[clap(long, env = MEILI_NO_ANALYTICS)]
     pub no_analytics: bool,
@@ -374,7 +406,13 @@ impl Opt {
             http_addr,
             master_key,
             env,
-            task_webhook_url,
+            zk_url,
+            s3_url,
+            s3_region,
+            s3_bucket,
+            s3_access_key,
+            s3_secret_key,
+            s3_security_token,
             max_index_size: _,
             max_task_db_size: _,
             http_payload_size_limit,
@@ -397,7 +435,7 @@ impl Opt {
             ignore_missing_dump: _,
             ignore_dump_if_db_exists: _,
             config_file_path: _,
-            #[cfg(feature = "analytics")]
+            #[cfg(all(not(debug_assertions), feature = "analytics"))]
             no_analytics,
             experimental_enable_metrics: enable_metrics_route,
             experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
@@ -408,11 +446,26 @@ impl Opt {
             export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
         }
         export_to_env_if_not_present(MEILI_ENV, env);
-        if let Some(task_webhook_url) = task_webhook_url {
-            export_to_env_if_not_present(MEILI_TASK_WEBHOOK_URL, task_webhook_url.to_string());
+        if let Some(zk_url) = zk_url {
+            export_to_env_if_not_present(MEILI_ZK_URL, zk_url);
         }
-
-        #[cfg(feature = "analytics")]
+        if let Some(s3_url) = s3_url {
+            export_to_env_if_not_present(MEILI_S3_URL, s3_url);
+        }
+        export_to_env_if_not_present(MEILI_S3_REGION, s3_region);
+        if let Some(s3_bucket) = s3_bucket {
+            export_to_env_if_not_present(MEILI_S3_BUCKET, s3_bucket);
+        }
+        if let Some(s3_access_key) = s3_access_key {
+            export_to_env_if_not_present(MEILI_S3_ACCESS_KEY, s3_access_key);
+        }
+        if let Some(s3_secret_key) = s3_secret_key {
+            export_to_env_if_not_present(MEILI_S3_SECRET_KEY, s3_secret_key);
+        }
+        if let Some(s3_security_token) = s3_security_token {
+            export_to_env_if_not_present(MEILI_S3_SECURITY_TOKEN, s3_security_token);
+        }
+        #[cfg(all(not(debug_assertions), feature = "analytics"))]
         {
             export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
         }
@@ -558,7 +611,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
         Ok(Self {
             log_every_n: Some(DEFAULT_LOG_EVERY_N),
             max_memory: other.max_indexing_memory.map(|b| b.get_bytes() as usize),
-            thread_pool: Some(thread_pool),
+            thread_pool: Some(Arc::new(thread_pool)),
             max_positions_per_attributes: None,
             skip_index_budget: other.skip_index_budget,
             ..Default::default()
@@ -726,6 +779,10 @@ fn default_env() -> String {
     DEFAULT_ENV.to_string()
 }
 
+fn default_s3_region() -> String {
+    DEFAULT_S3_REGION.to_string()
+}
+
 fn default_max_index_size() -> Byte {
     Byte::from_bytes(INDEX_SIZE)
 }

meilisearch/src/routes/api_key.rs

@@ -41,14 +41,10 @@ pub async fn create_api_key(
     _req: HttpRequest,
 ) -> Result<HttpResponse, ResponseError> {
     let v = body.into_inner();
-    let res = tokio::task::spawn_blocking(move || -> Result<_, AuthControllerError> {
-        let key = auth_controller.create_key(v)?;
-        Ok(KeyView::from_key(key, &auth_controller))
-    })
-    .await
-    .map_err(|e| ResponseError::from_msg(e.to_string(), Code::Internal))??;
+    let key = auth_controller.create_key(v)?;
+    let key = KeyView::from_key(key, &auth_controller);
 
-    Ok(HttpResponse::Created().json(res))
+    Ok(HttpResponse::Created().json(key))
 }
 
 #[derive(Deserr, Debug, Clone, Copy)]
@@ -110,17 +106,11 @@ pub async fn patch_api_key(
 ) -> Result<HttpResponse, ResponseError> {
     let key = path.into_inner().key;
     let patch_api_key = body.into_inner();
-    let res = tokio::task::spawn_blocking(move || -> Result<_, AuthControllerError> {
-        let uid =
-            Uuid::parse_str(&key).or_else(|_| auth_controller.get_uid_from_encoded_key(&key))?;
-        let key = auth_controller.update_key(uid, patch_api_key)?;
+    let uid = Uuid::parse_str(&key).or_else(|_| auth_controller.get_uid_from_encoded_key(&key))?;
+    let key = auth_controller.update_key(uid, patch_api_key)?;
+    let key = KeyView::from_key(key, &auth_controller);
 
-        Ok(KeyView::from_key(key, &auth_controller))
-    })
-    .await
-    .map_err(|e| ResponseError::from_msg(e.to_string(), Code::Internal))??;
-
-    Ok(HttpResponse::Ok().json(res))
+    Ok(HttpResponse::Ok().json(key))
 }
 
 pub async fn delete_api_key(
@@ -128,13 +118,8 @@ pub async fn delete_api_key(
     path: web::Path<AuthParam>,
 ) -> Result<HttpResponse, ResponseError> {
     let key = path.into_inner().key;
-    tokio::task::spawn_blocking(move || {
-        let uid =
-            Uuid::parse_str(&key).or_else(|_| auth_controller.get_uid_from_encoded_key(&key))?;
-        auth_controller.delete_key(uid)
-    })
-    .await
-    .map_err(|e| ResponseError::from_msg(e.to_string(), Code::Internal))??;
+    let uid = Uuid::parse_str(&key).or_else(|_| auth_controller.get_uid_from_encoded_key(&key))?;
+    auth_controller.delete_key(uid)?;
 
     Ok(HttpResponse::NoContent().finish())
 }

meilisearch/src/routes/dump.rs

@@ -29,8 +29,7 @@ pub async fn create_dump(
         keys: auth_controller.list_keys()?,
         instance_uid: analytics.instance_uid().cloned(),
     };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))

meilisearch/src/routes/features.rs

@@ -29,12 +29,12 @@ async fn get_features(
     >,
     req: HttpRequest,
     analytics: Data<dyn Analytics>,
-) -> HttpResponse {
-    let features = index_scheduler.features();
+) -> Result<HttpResponse, ResponseError> {
+    let features = index_scheduler.features()?;
 
     analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
     debug!("returns: {:?}", features.runtime_features());
-    HttpResponse::Ok().json(features.runtime_features())
+    Ok(HttpResponse::Ok().json(features.runtime_features()))
 }
 
 #[derive(Debug, Deserr)]
@@ -44,10 +44,6 @@ pub struct RuntimeTogglableFeatures {
     pub score_details: Option<bool>,
     #[deserr(default)]
     pub vector_store: Option<bool>,
-    #[deserr(default)]
-    pub metrics: Option<bool>,
-    #[deserr(default)]
-    pub export_puffin_reports: Option<bool>,
 }
 
 async fn patch_features(
@@ -59,39 +55,29 @@ async fn patch_features(
     req: HttpRequest,
     analytics: Data<dyn Analytics>,
 ) -> Result<HttpResponse, ResponseError> {
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
 
     let old_features = features.runtime_features();
+
     let new_features = meilisearch_types::features::RuntimeTogglableFeatures {
         score_details: new_features.0.score_details.unwrap_or(old_features.score_details),
         vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
-        metrics: new_features.0.metrics.unwrap_or(old_features.metrics),
-        export_puffin_reports: new_features
-            .0
-            .export_puffin_reports
-            .unwrap_or(old_features.export_puffin_reports),
     };
 
     // explicitly destructure for analytics rather than using the `Serialize` implementation, because
     // the it renames to camelCase, which we don't want for analytics.
     // **Do not** ignore fields with `..` or `_` here, because we want to add them in the future.
-    let meilisearch_types::features::RuntimeTogglableFeatures {
-        score_details,
-        vector_store,
-        metrics,
-        export_puffin_reports,
-    } = new_features;
+    let meilisearch_types::features::RuntimeTogglableFeatures { score_details, vector_store } =
+        new_features;
 
     analytics.publish(
         "Experimental features Updated".to_string(),
         json!({
             "score_details": score_details,
             "vector_store": vector_store,
-            "metrics": metrics,
-            "export_puffin_reports": export_puffin_reports,
         }),
         Some(&req),
     );
-    index_scheduler.put_runtime_features(new_features)?;
+    index_scheduler.inner().put_runtime_features(new_features)?;
     Ok(HttpResponse::Ok().json(new_features))
 }

meilisearch/src/routes/indexes/documents.rs

@@ -1,4 +1,4 @@
-use std::io::ErrorKind;
+use std::io::{BufReader, ErrorKind, Seek, SeekFrom};
 
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
@@ -129,8 +129,7 @@ pub async fn delete_document(
         index_uid: index_uid.to_string(),
         documents_ids: vec![document_id],
     };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
 }
@@ -396,11 +395,12 @@ async fn document_addition(
         return Err(MeilisearchHttpError::MissingPayload(format));
     }
 
-    if let Err(e) = buffer.seek(std::io::SeekFrom::Start(0)).await {
+    if let Err(e) = buffer.seek(SeekFrom::Start(0)).await {
         return Err(MeilisearchHttpError::Payload(ReceivePayload(Box::new(e))));
     }
 
     let read_file = buffer.into_inner().into_std().await;
+    let s3 = index_scheduler.s3.clone();
     let documents_count = tokio::task::spawn_blocking(move || {
         let documents_count = match format {
             PayloadType::Json => read_json(&read_file, update_file.as_file_mut())?,
@@ -409,8 +409,16 @@ async fn document_addition(
             }
             PayloadType::Ndjson => read_ndjson(&read_file, update_file.as_file_mut())?,
         };
+
+        if let Some(s3) = s3 {
+            update_file.seek(SeekFrom::Start(0)).unwrap();
+            let mut reader = BufReader::new(&*update_file);
+            s3.put_object_multipart(format!("update-files/{}", uuid), &mut reader)?;
+        }
+
         // we NEED to persist the file here because we moved the `udpate_file` in another task.
         update_file.persist()?;
+
         Ok(documents_count)
     })
     .await;
@@ -445,7 +453,7 @@ async fn document_addition(
     };
 
     let scheduler = index_scheduler.clone();
-    let task = match tokio::task::spawn_blocking(move || scheduler.register(task)).await? {
+    let task = match scheduler.register(task) {
         Ok(task) => task,
         Err(e) => {
             index_scheduler.delete_update_file(uuid)?;
@@ -476,8 +484,7 @@ pub async fn delete_documents_batch(
 
     let task =
         KindWithContent::DocumentDeletion { index_uid: index_uid.to_string(), documents_ids: ids };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -512,8 +519,7 @@ pub async fn delete_documents_by_filter(
     .map_err(|err| ResponseError::from_msg(err.message, Code::InvalidDocumentFilter))?;
     let task = KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr: filter };
 
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -529,8 +535,7 @@ pub async fn clear_all_documents(
     analytics.delete_documents(DocumentDeletionKind::ClearAll, &req);
 
     let task = KindWithContent::DocumentClear { index_uid: index_uid.to_string() };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -612,8 +617,8 @@ fn retrieve_document<S: AsRef<str>>(
     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
 
     let internal_id = index
-        .external_documents_ids()
-        .get(&txn, doc_id)?
+        .external_documents_ids(&txn)?
+        .get(doc_id.as_bytes())
         .ok_or_else(|| MeilisearchHttpError::DocumentNotFound(doc_id.to_string()))?;
 
     let document = index

meilisearch/src/routes/indexes/facet_search.rs

@@ -68,7 +68,7 @@ pub async fn search(
     }
 
     let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(&index, search_query, facet_query, facet_name, features)
     })

meilisearch/src/routes/indexes/mod.rs

@@ -135,8 +135,7 @@ pub async fn create_index(
         );
 
         let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
-        let task: SummarizedTaskView =
-            tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+        let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
         Ok(HttpResponse::Accepted().json(task))
     } else {
@@ -203,8 +202,7 @@ pub async fn update_index(
         primary_key: body.primary_key,
     };
 
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -216,8 +214,7 @@ pub async fn delete_index(
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
     let task = KindWithContent::IndexDeletion { index_uid: index_uid.into_inner() };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/routes/indexes/search.rs

@@ -157,7 +157,7 @@ pub async fn search_with_url_query(
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
     let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
     let search_result =
         tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
     if let Ok(ref search_result) = search_result {
@@ -192,7 +192,7 @@ pub async fn search_with_post(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
     let search_result =
         tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
     if let Ok(ref search_result) = search_result {

meilisearch/src/routes/indexes/settings.rs

@@ -55,10 +55,7 @@ macro_rules! make_setting_route {
                     is_deletion: true,
                     allow_index_creation,
                 };
-                let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task))
-                        .await??
-                        .into();
+                let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
                 debug!("returns: {:?}", task);
                 Ok(HttpResponse::Accepted().json(task))
@@ -97,10 +94,7 @@ macro_rules! make_setting_route {
                     is_deletion: false,
                     allow_index_creation,
                 };
-                let task: SummarizedTaskView =
-                    tokio::task::spawn_blocking(move || index_scheduler.register(task))
-                        .await??
-                        .into();
+                let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
                 debug!("returns: {:?}", task);
                 Ok(HttpResponse::Accepted().json(task))
@@ -310,81 +304,6 @@ make_setting_route!(
     }
 );
 
-make_setting_route!(
-    "/non-separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
-    >,
-    non_separator_tokens,
-    "nonSeparatorTokens",
-    analytics,
-    |non_separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "nonSeparatorTokens Updated".to_string(),
-            json!({
-                "non_separator_tokens": {
-                    "total": non_separator_tokens.as_ref().map(|non_separator_tokens| non_separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
-make_setting_route!(
-    "/separator-tokens",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
-    >,
-    separator_tokens,
-    "separatorTokens",
-    analytics,
-    |separator_tokens: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "separatorTokens Updated".to_string(),
-            json!({
-                "separator_tokens": {
-                    "total": separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
-make_setting_route!(
-    "/dictionary",
-    put,
-    std::collections::BTreeSet<String>,
-    meilisearch_types::deserr::DeserrJsonError<
-        meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
-    >,
-    dictionary,
-    "dictionary",
-    analytics,
-    |dictionary: &Option<std::collections::BTreeSet<String>>, req: &HttpRequest| {
-        use serde_json::json;
-
-        analytics.publish(
-            "dictionary Updated".to_string(),
-            json!({
-                "dictionary": {
-                    "total": dictionary.as_ref().map(|dictionary| dictionary.len()),
-                },
-            }),
-            Some(req),
-        );
-    }
-);
-
 make_setting_route!(
     "/synonyms",
     put,
@@ -541,9 +460,6 @@ generate_configure!(
     searchable_attributes,
     distinct_attribute,
     stop_words,
-    separator_tokens,
-    non_separator_tokens,
-    dictionary,
     synonyms,
     ranking_rules,
     typo_tolerance,
@@ -664,8 +580,7 @@ pub async fn update_all(
         is_deletion: false,
         allow_index_creation,
     };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))
@@ -700,8 +615,7 @@ pub async fn delete_all(
         is_deletion: true,
         allow_index_creation,
     };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+    let task: SummarizedTaskView = index_scheduler.register(task)?.into();
 
     debug!("returns: {:?}", task);
     Ok(HttpResponse::Accepted().json(task))

meilisearch/src/routes/metrics.rs

@@ -19,7 +19,7 @@ pub async fn get_metrics(
     index_scheduler: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<IndexScheduler>>,
     auth_controller: Data<AuthController>,
 ) -> Result<HttpResponse, ResponseError> {
-    index_scheduler.features().check_metrics()?;
+    index_scheduler.features()?.check_metrics()?;
     let auth_filters = index_scheduler.filters();
     if !auth_filters.all_indexes_authorized() {
         let mut error = ResponseError::from(AuthenticationError::InvalidToken);

meilisearch/src/routes/mod.rs

@@ -24,7 +24,6 @@ pub mod features;
 pub mod indexes;
 mod metrics;
 mod multi_search;
-mod snapshot;
 mod swap_indexes;
 pub mod tasks;
 
@@ -33,7 +32,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::resource("/health").route(web::get().to(get_health)))
         .service(web::scope("/keys").configure(api_key::configure))
         .service(web::scope("/dumps").configure(dump::configure))
-        .service(web::scope("/snapshots").configure(snapshot::configure))
         .service(web::resource("/stats").route(web::get().to(get_stats)))
         .service(web::resource("/version").route(web::get().to(get_version)))
         .service(web::scope("/indexes").configure(indexes::configure))

meilisearch/src/routes/multi_search.rs

@@ -41,7 +41,7 @@ pub async fn multi_search_with_post(
     let queries = params.into_inner().queries;
 
     let mut multi_aggregate = MultiSearchAggregator::from_queries(&queries, &req);
-    let features = index_scheduler.features();
+    let features = index_scheduler.features()?;
 
     // Explicitly expect a `(ResponseError, usize)` for the error type rather than `ResponseError` only,
     // so that `?` doesn't work if it doesn't use `with_index`, ensuring that it is not forgotten in case of code

meilisearch/src/routes/snapshot.rs

@@ -1,32 +0,0 @@
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::tasks::KindWithContent;
-use serde_json::json;
-
-use crate::analytics::Analytics;
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-use crate::routes::SummarizedTaskView;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(SeqHandler(create_snapshot))));
-}
-
-pub async fn create_snapshot(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SNAPSHOTS_CREATE }>, Data<IndexScheduler>>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    analytics.publish("Snapshot Created".to_string(), json!({}), Some(&req));
-
-    let task = KindWithContent::SnapshotCreation;
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
-
-    debug!("returns: {:?}", task);
-    Ok(HttpResponse::Accepted().json(task))
-}

meilisearch/src/routes/swap_indexes.rs

@@ -60,7 +60,8 @@ pub async fn swap_indexes(
     }
 
     let task = KindWithContent::IndexSwap { swaps };
-    let task: SummarizedTaskView =
-        tokio::task::spawn_blocking(move || index_scheduler.register(task)).await??.into();
+
+    let task = index_scheduler.register(task)?;
+    let task: SummarizedTaskView = task.into();
     Ok(HttpResponse::Accepted().json(task))
 }

meilisearch/src/routes/tasks.rs

@@ -8,15 +8,16 @@ use meilisearch_types::deserr::DeserrQueryParamError;
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{InvalidTaskDateError, ResponseError};
 use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::settings::{Settings, Unchecked};
 use meilisearch_types::star_or::{OptionStarOr, OptionStarOrList};
-use meilisearch_types::task_view::TaskView;
-use meilisearch_types::tasks::{Kind, KindWithContent, Status};
+use meilisearch_types::tasks::{
+    serialize_duration, Details, IndexSwap, Kind, KindWithContent, Status, Task,
+};
 use serde::Serialize;
 use serde_json::json;
 use time::format_description::well_known::Rfc3339;
 use time::macros::format_description;
 use time::{Date, Duration, OffsetDateTime, Time};
-use tokio::task;
 
 use super::SummarizedTaskView;
 use crate::analytics::Analytics;
@@ -35,6 +36,140 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     .service(web::resource("/cancel").route(web::post().to(SeqHandler(cancel_tasks))))
     .service(web::resource("/{task_id}").route(web::get().to(SeqHandler(get_task))));
 }
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TaskView {
+    pub uid: TaskId,
+    #[serde(default)]
+    pub index_uid: Option<String>,
+    pub status: Status,
+    #[serde(rename = "type")]
+    pub kind: Kind,
+    pub canceled_by: Option<TaskId>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub details: Option<DetailsView>,
+    pub error: Option<ResponseError>,
+    #[serde(serialize_with = "serialize_duration", default)]
+    pub duration: Option<Duration>,
+    #[serde(with = "time::serde::rfc3339")]
+    pub enqueued_at: OffsetDateTime,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub started_at: Option<OffsetDateTime>,
+    #[serde(with = "time::serde::rfc3339::option", default)]
+    pub finished_at: Option<OffsetDateTime>,
+}
+
+impl TaskView {
+    pub fn from_task(task: &Task) -> TaskView {
+        TaskView {
+            uid: task.uid,
+            index_uid: task.index_uid().map(ToOwned::to_owned),
+            status: task.status,
+            kind: task.kind.as_kind(),
+            canceled_by: task.canceled_by,
+            details: task.details.clone().map(DetailsView::from),
+            error: task.error.clone(),
+            duration: task.started_at.zip(task.finished_at).map(|(start, end)| end - start),
+            enqueued_at: task.enqueued_at,
+            started_at: task.started_at,
+            finished_at: task.finished_at,
+        }
+    }
+}
+
+#[derive(Default, Debug, PartialEq, Eq, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DetailsView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub received_documents: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub indexed_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub primary_key: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub provided_ids: Option<usize>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_documents: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub matched_tasks: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub canceled_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub deleted_tasks: Option<Option<u64>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub original_filter: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub dump_uid: Option<Option<String>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    #[serde(flatten)]
+    pub settings: Option<Box<Settings<Unchecked>>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub swaps: Option<Vec<IndexSwap>>,
+}
+
+impl From<Details> for DetailsView {
+    fn from(details: Details) -> Self {
+        match details {
+            Details::DocumentAdditionOrUpdate { received_documents, indexed_documents } => {
+                DetailsView {
+                    received_documents: Some(received_documents),
+                    indexed_documents: Some(indexed_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::SettingsUpdate { settings } => {
+                DetailsView { settings: Some(settings), ..DetailsView::default() }
+            }
+            Details::IndexInfo { primary_key } => {
+                DetailsView { primary_key: Some(primary_key), ..DetailsView::default() }
+            }
+            Details::DocumentDeletion {
+                provided_ids: received_document_ids,
+                deleted_documents,
+            } => DetailsView {
+                provided_ids: Some(received_document_ids),
+                deleted_documents: Some(deleted_documents),
+                original_filter: Some(None),
+                ..DetailsView::default()
+            },
+            Details::DocumentDeletionByFilter { original_filter, deleted_documents } => {
+                DetailsView {
+                    provided_ids: Some(0),
+                    original_filter: Some(Some(original_filter)),
+                    deleted_documents: Some(deleted_documents),
+                    ..DetailsView::default()
+                }
+            }
+            Details::ClearAll { deleted_documents } => {
+                DetailsView { deleted_documents: Some(deleted_documents), ..DetailsView::default() }
+            }
+            Details::TaskCancelation { matched_tasks, canceled_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    canceled_tasks: Some(canceled_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::TaskDeletion { matched_tasks, deleted_tasks, original_filter } => {
+                DetailsView {
+                    matched_tasks: Some(matched_tasks),
+                    deleted_tasks: Some(deleted_tasks),
+                    original_filter: Some(Some(original_filter)),
+                    ..DetailsView::default()
+                }
+            }
+            Details::Dump { dump_uid } => {
+                DetailsView { dump_uid: Some(dump_uid), ..DetailsView::default() }
+            }
+            Details::IndexSwap { swaps } => {
+                DetailsView { swaps: Some(swaps), ..Default::default() }
+            }
+        }
+    }
+}
+
 #[derive(Debug, Deserr)]
 #[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
 pub struct TasksFilterQuery {
@@ -189,15 +324,12 @@ async fn cancel_tasks(
 
     let query = params.into_query();
 
-    let (tasks, _) = index_scheduler.get_task_ids_from_authorized_indexes(
-        &index_scheduler.read_txn()?,
-        &query,
-        index_scheduler.filters(),
-    )?;
+    let (tasks, _) =
+        index_scheduler.get_task_ids_from_authorized_indexes(&query, index_scheduler.filters())?;
     let task_cancelation =
         KindWithContent::TaskCancelation { query: format!("?{}", req.query_string()), tasks };
 
-    let task = task::spawn_blocking(move || index_scheduler.register(task_cancelation)).await??;
+    let task = index_scheduler.register(task_cancelation)?;
     let task: SummarizedTaskView = task.into();
 
     Ok(HttpResponse::Ok().json(task))
@@ -234,15 +366,12 @@ async fn delete_tasks(
     );
     let query = params.into_query();
 
-    let (tasks, _) = index_scheduler.get_task_ids_from_authorized_indexes(
-        &index_scheduler.read_txn()?,
-        &query,
-        index_scheduler.filters(),
-    )?;
+    let (tasks, _) =
+        index_scheduler.get_task_ids_from_authorized_indexes(&query, index_scheduler.filters())?;
     let task_deletion =
         KindWithContent::TaskDeletion { query: format!("?{}", req.query_string()), tasks };
 
-    let task = task::spawn_blocking(move || index_scheduler.register(task_deletion)).await??;
+    let task = index_scheduler.register(task_deletion)?;
     let task: SummarizedTaskView = task.into();
 
     Ok(HttpResponse::Ok().json(task))

meilisearch/src/search.rs

@@ -491,20 +491,6 @@ pub fn perform_search(
         tokenizer_builder.allow_list(&script_lang_map);
     }
 
-    let separators = index.allowed_separators(&rtxn)?;
-    let separators: Option<Vec<_>> =
-        separators.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref separators) = separators {
-        tokenizer_builder.separators(separators);
-    }
-
-    let dictionary = index.dictionary(&rtxn)?;
-    let dictionary: Option<Vec<_>> =
-        dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
-    if let Some(ref dictionary) = dictionary {
-        tokenizer_builder.words_dict(dictionary);
-    }
-
     let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
     formatter_builder.crop_marker(query.crop_marker);
     formatter_builder.highlight_prefix(query.highlight_pre_tag);
@@ -680,7 +666,6 @@ fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option
         .map_err(InternalError::SerdeJson)?;
     Ok(vectors
         .into_iter()
-        .flatten()
         .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
         .max()
         .map(OrderedFloat::into_inner))

meilisearch/tests/auth/api_keys.rs

@@ -1,7 +1,8 @@
 use std::{thread, time};
 
-use crate::common::{Server, Value};
-use crate::json;
+use serde_json::{json, Value};
+
+use crate::common::Server;
 
 #[actix_rt::test]
 async fn add_valid_api_key() {
@@ -161,7 +162,7 @@ async fn add_valid_api_key_null_description() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["products"],
         "actions": ["documents.add"],
         "expiresAt": "2050-11-13T00:00:00"
@@ -364,7 +365,7 @@ async fn error_add_api_key_invalid_index_uids() {
     server.use_api_key("MASTER_KEY");
 
     let content = json!({
-        "description": json!(null),
+        "description": Value::Null,
         "indexes": ["invalid index # / \\name with spaces"],
         "actions": [
             "documents.add"
@@ -421,7 +422,7 @@ async fn error_add_api_key_invalid_parameters_actions() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r###"
     {
-      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
@@ -506,7 +507,7 @@ async fn error_add_api_key_invalid_parameters_uid() {
 async fn error_add_api_key_parameters_uid_already_exist() {
     let mut server = Server::new_auth().await;
     server.use_api_key("MASTER_KEY");
-    let content: Value = json!({
+    let content = json!({
         "uid": "4bc0887a-0e41-4f3b-935d-0c451dcee9c8",
         "indexes": ["products"],
         "actions": ["search"],
@@ -1145,7 +1146,7 @@ async fn patch_api_key_description() {
     meili_snap::snapshot!(code, @"200 OK");
 
     // Remove the description
-    let content = json!({ "description": null });
+    let content = json!({ "description": serde_json::Value::Null });
 
     let (response, code) = server.patch_api_key(&uid, content).await;
     meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]", ".uid" => "[ignored]", ".key" => "[ignored]" }), @r###"

meilisearch/tests/auth/authorization.rs

@@ -2,13 +2,11 @@ use std::collections::{HashMap, HashSet};
 
 use ::time::format_description::well_known::Rfc3339;
 use maplit::{hashmap, hashset};
-use meilisearch::Opt;
 use once_cell::sync::Lazy;
-use tempfile::TempDir;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
-use crate::common::{default_settings, Server, Value};
-use crate::json;
+use crate::common::Server;
 
 pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'static str>>> =
     Lazy::new(|| {
@@ -56,7 +54,6 @@ pub static AUTHORIZATIONS: Lazy<HashMap<(&'static str, &'static str), HashSet<&'
             ("GET",     "/indexes/products/stats") =>                          hashset!{"stats.get", "stats.*", "*"},
             ("GET",     "/stats") =>                                           hashset!{"stats.get", "stats.*", "*"},
             ("POST",    "/dumps") =>                                           hashset!{"dumps.create", "dumps.*", "*"},
-            ("POST",    "/snapshots") =>                                       hashset!{"snapshots.create", "snapshots.*", "*"},
             ("GET",     "/version") =>                                         hashset!{"version", "*"},
             ("GET",     "/metrics") =>                                         hashset!{"metrics.get", "metrics.*", "*"},
             ("PATCH",   "/keys/mykey/") =>                                     hashset!{"keys.update", "*"},
@@ -197,9 +194,7 @@ async fn access_authorized_master_key() {
 
 #[actix_rt::test]
 async fn access_authorized_restricted_index() {
-    let dir = TempDir::new().unwrap();
-    let enable_metrics = Opt { experimental_enable_metrics: true, ..default_settings(dir.path()) };
-    let mut server = Server::new_auth_with_options(enable_metrics, dir).await;
+    let mut server = Server::new_auth().await;
     for ((method, route), actions) in AUTHORIZATIONS.iter() {
         for action in actions {
             // create a new API key letting only the needed action.

meilisearch/tests/auth/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 use uuid::Uuid;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn create_api_key_bad_description() {
@@ -90,7 +90,7 @@ async fn create_api_key_bad_actions() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

meilisearch/tests/auth/mod.rs

@@ -7,9 +7,9 @@ mod tenant_token;
 mod tenant_token_multi_search;
 
 use actix_web::http::StatusCode;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 impl Server {
     pub fn use_api_key(&mut self, api_key: impl AsRef<str>) {

meilisearch/tests/auth/tenant_token.rs

@@ -3,11 +3,11 @@ use std::collections::HashMap;
 use ::time::format_description::well_known::Rfc3339;
 use maplit::hashmap;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::{ALL_ACTIONS, AUTHORIZATIONS};
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 fn generate_tenant_token(
     parent_uid: impl AsRef<str>,
@@ -233,31 +233,31 @@ async fn search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
     ];
 
@@ -386,7 +386,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -398,7 +398,7 @@ async fn error_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -428,15 +428,15 @@ async fn error_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null)
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null)
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -444,7 +444,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -456,7 +456,7 @@ async fn error_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {

meilisearch/tests/auth/tenant_token_multi_search.rs

@@ -3,11 +3,11 @@ use std::collections::HashMap;
 use ::time::format_description::well_known::Rfc3339;
 use maplit::hashmap;
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use time::{Duration, OffsetDateTime};
 
 use super::authorization::ALL_ACTIONS;
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 fn generate_tenant_token(
     parent_uid: impl AsRef<str>,
@@ -512,31 +512,31 @@ async fn single_search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
     ];
 
@@ -564,31 +564,31 @@ async fn multi_search_authorized_simple_token() {
         },
         hashmap! {
             "searchRules" => json!({"*": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"*": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}, "products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales", "products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sa*", "pro*"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
     ];
 
@@ -823,7 +823,7 @@ async fn error_single_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -835,7 +835,7 @@ async fn error_single_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -864,7 +864,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -876,7 +876,7 @@ async fn error_multi_search_token_forbidden_parent_key() {
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": null}),
+            "searchRules" => json!({"sales": Value::Null, "products": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -919,15 +919,15 @@ async fn error_single_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -935,7 +935,7 @@ async fn error_single_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -947,7 +947,7 @@ async fn error_single_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
+            "searchRules" => json!({"sales": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -978,15 +978,15 @@ async fn error_multi_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"products": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"products": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"products": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["products"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
@@ -998,15 +998,15 @@ async fn error_multi_search_forbidden_token() {
         },
         hashmap! {
             "searchRules" => json!({"sales": {}}),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         hashmap! {
-            "searchRules" => json!({"sales": null}),
-            "exp" => json!(null),
+            "searchRules" => json!({"sales": Value::Null}),
+            "exp" => Value::Null
         },
         hashmap! {
             "searchRules" => json!(["sales"]),
-            "exp" => json!(null),
+            "exp" => Value::Null
         },
         // expired token
         hashmap! {
@@ -1014,7 +1014,7 @@ async fn error_multi_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"*": null}),
+            "searchRules" => json!({"*": Value::Null}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
@@ -1026,7 +1026,7 @@ async fn error_multi_search_forbidden_token() {
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {
-            "searchRules" => json!({"sales": null, "products": {}}),
+            "searchRules" => json!({"sales": Value::Null, "products": {}}),
             "exp" => json!((OffsetDateTime::now_utc() - Duration::hours(1)).unix_timestamp())
         },
         hashmap! {

meilisearch/tests/common/index.rs

@@ -3,13 +3,12 @@ use std::panic::{catch_unwind, resume_unwind, UnwindSafe};
 use std::time::Duration;
 
 use actix_web::http::StatusCode;
+use serde_json::{json, Value};
 use tokio::time::sleep;
 use urlencoding::encode as urlencode;
 
 use super::encoder::Encoder;
 use super::service::Service;
-use super::Value;
-use crate::json;
 
 pub struct Index<'a> {
     pub uid: String,
@@ -243,9 +242,7 @@ impl Index<'_> {
 
     pub async fn delete_batch(&self, ids: Vec<u64>) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/documents/delete-batch", urlencode(self.uid.as_ref()));
-        self.service
-            .post_encoded(url, serde_json::to_value(&ids).unwrap().into(), self.encoder)
-            .await
+        self.service.post_encoded(url, serde_json::to_value(&ids).unwrap(), self.encoder).await
     }
 
     pub async fn delete_batch_raw(&self, body: Value) -> (Value, StatusCode) {

meilisearch/tests/common/mod.rs

@@ -3,85 +3,9 @@ pub mod index;
 pub mod server;
 pub mod service;
 
-use std::fmt::{self, Display};
-
-#[allow(unused)]
 pub use index::{GetAllDocumentsOptions, GetDocumentOptions};
-use meili_snap::json_string;
-use serde::{Deserialize, Serialize};
-#[allow(unused)]
 pub use server::{default_settings, Server};
 
-#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
-pub struct Value(pub serde_json::Value);
-
-impl Value {
-    pub fn uid(&self) -> u64 {
-        if let Some(uid) = self["uid"].as_u64() {
-            uid
-        } else if let Some(uid) = self["taskUid"].as_u64() {
-            uid
-        } else {
-            panic!("Didn't find any task id in: {self}");
-        }
-    }
-}
-
-impl From<serde_json::Value> for Value {
-    fn from(value: serde_json::Value) -> Self {
-        Value(value)
-    }
-}
-
-impl std::ops::Deref for Value {
-    type Target = serde_json::Value;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl PartialEq<serde_json::Value> for Value {
-    fn eq(&self, other: &serde_json::Value) -> bool {
-        &self.0 == other
-    }
-}
-
-impl PartialEq<Value> for serde_json::Value {
-    fn eq(&self, other: &Value) -> bool {
-        self == &other.0
-    }
-}
-
-impl PartialEq<&str> for Value {
-    fn eq(&self, other: &&str) -> bool {
-        self.0.eq(other)
-    }
-}
-
-impl Display for Value {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "{}",
-            json_string!(self, { ".enqueuedAt" => "[date]", ".processedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]" })
-        )
-    }
-}
-
-impl From<Vec<Value>> for Value {
-    fn from(value: Vec<Value>) -> Self {
-        Self(value.into_iter().map(|value| value.0).collect::<serde_json::Value>())
-    }
-}
-
-#[macro_export]
-macro_rules! json {
-    ($($json:tt)+) => {
-        $crate::common::Value(serde_json::json!($($json)+))
-    };
-}
-
 /// Performs a search test on both post and get routes
 #[macro_export]
 macro_rules! test_post_get_search {

meilisearch/tests/common/server.rs

@@ -11,14 +11,13 @@ use clap::Parser;
 use meilisearch::option::{IndexerOpts, MaxMemory, Opt};
 use meilisearch::{analytics, create_app, setup_meilisearch};
 use once_cell::sync::Lazy;
+use serde_json::{json, Value};
 use tempfile::TempDir;
 use tokio::time::sleep;
 
 use super::index::Index;
 use super::service::Service;
 use crate::common::encoder::Encoder;
-use crate::common::Value;
-use crate::json;
 
 pub struct Server {
     pub service: Service,
@@ -40,7 +39,7 @@ impl Server {
 
         let options = default_settings(dir.path());
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await.unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir) }
@@ -55,7 +54,7 @@ impl Server {
 
         options.master_key = Some("MASTER_KEY".to_string());
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await.unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir) }
@@ -68,7 +67,7 @@ impl Server {
     }
 
     pub async fn new_with_options(options: Opt) -> Result<Self, anyhow::Error> {
-        let (index_scheduler, auth) = setup_meilisearch(&options)?;
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await?;
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Ok(Server { service, _dir: None })
@@ -157,10 +156,6 @@ impl Server {
         self.service.post("/dumps", json!(null)).await
     }
 
-    pub async fn create_snapshot(&self) -> (Value, StatusCode) {
-        self.service.post("/snapshots", json!(null)).await
-    }
-
     pub async fn index_swap(&self, value: Value) -> (Value, StatusCode) {
         self.service.post("/swap-indexes", value).await
     }
@@ -202,10 +197,6 @@ impl Server {
     pub async fn set_features(&self, value: Value) -> (Value, StatusCode) {
         self.service.patch("/experimental-features", value).await
     }
-
-    pub async fn get_metrics(&self) -> (Value, StatusCode) {
-        self.service.get("/metrics").await
-    }
 }
 
 pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
@@ -213,7 +204,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
         db_path: dir.as_ref().join("db"),
         dump_dir: dir.as_ref().join("dumps"),
         env: "development".to_owned(),
-        #[cfg(feature = "analytics")]
+        #[cfg(all(not(debug_assertions), feature = "analytics"))]
         no_analytics: true,
         max_index_size: Byte::from_unit(100.0, ByteUnit::MiB).unwrap(),
         max_task_db_size: Byte::from_unit(1.0, ByteUnit::GiB).unwrap(),
@@ -225,7 +216,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
             skip_index_budget: true,
             ..Parser::parse_from(None as Option<&str>)
         },
-        experimental_enable_metrics: false,
+        experimental_enable_metrics: true,
         ..Parser::parse_from(None as Option<&str>)
     }
 }

meilisearch/tests/common/service.rs

@@ -7,9 +7,9 @@ use actix_web::test::TestRequest;
 use index_scheduler::IndexScheduler;
 use meilisearch::{analytics, create_app, Opt};
 use meilisearch_auth::AuthController;
+use serde_json::Value;
 
 use crate::common::encoder::Encoder;
-use crate::common::Value;
 
 pub struct Service {
     pub index_scheduler: Arc<IndexScheduler>,

meilisearch/tests/content_type.rs

@@ -3,8 +3,9 @@
 mod common;
 
 use actix_web::test;
+use serde_json::{json, Value};
 
-use crate::common::{Server, Value};
+use crate::common::Server;
 
 enum HttpVerb {
     Put,

meilisearch/tests/documents/add_documents.rs

@@ -1,11 +1,11 @@
 use actix_web::test;
 use meili_snap::{json_string, snapshot};
+use serde_json::{json, Value};
 use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 
 use crate::common::encoder::Encoder;
-use crate::common::{GetAllDocumentsOptions, Server, Value};
-use crate::json;
+use crate::common::{GetAllDocumentsOptions, Server};
 
 /// This is the basic usage of our API and every other tests uses the content-type application/json
 #[actix_rt::test]

meilisearch/tests/documents/delete_documents.rs

@@ -1,7 +1,7 @@
 use meili_snap::{json_string, snapshot};
+use serde_json::json;
 
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 #[actix_rt::test]
 async fn delete_one_document_unexisting_index() {
@@ -154,19 +154,6 @@ async fn delete_document_by_filter() {
         )
         .await;
     index.wait_task(1).await;
-
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 4,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 3,
-        "id": 4
-      }
-    }
-    "###);
-
     let (response, code) =
         index.delete_document_by_filter(json!({ "filter": "color = blue"})).await;
     snapshot!(code, @"202 Accepted");
@@ -201,18 +188,6 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 2,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 1,
-        "id": 2
-      }
-    }
-    "###);
-
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"
@@ -266,18 +241,6 @@ async fn delete_document_by_filter() {
     }
     "###);
 
-    let (stats, _) = index.stats().await;
-    snapshot!(json_string!(stats), @r###"
-    {
-      "numberOfDocuments": 1,
-      "isIndexing": false,
-      "fieldDistribution": {
-        "color": 1,
-        "id": 1
-      }
-    }
-    "###);
-
     let (documents, code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(documents), @r###"
@@ -397,7 +360,7 @@ async fn delete_document_by_complex_filter() {
       "canceledBy": null,
       "details": {
         "providedIds": 0,
-        "deletedDocuments": 2,
+        "deletedDocuments": 4,
         "originalFilter": "[[\"color = green\",\"color NOT EXISTS\"]]"
       },
       "error": null,

meilisearch/tests/documents/errors.rs

@@ -1,8 +1,8 @@
 use meili_snap::*;
+use serde_json::json;
 use urlencoding::encode;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn get_all_documents_bad_offset() {

meilisearch/tests/documents/get_documents.rs

@@ -1,11 +1,11 @@
 use actix_web::test;
 use http::header::ACCEPT_ENCODING;
 use meili_snap::*;
+use serde_json::{json, Value};
 use urlencoding::encode as urlencode;
 
 use crate::common::encoder::Encoder;
-use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server, Value};
-use crate::json;
+use crate::common::{GetAllDocumentsOptions, GetDocumentOptions, Server};
 
 // TODO: partial test since we are testing error, amd error is not yet fully implemented in
 // transplant
@@ -40,7 +40,7 @@ async fn get_document() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(None).await;
-    let documents = json!([
+    let documents = serde_json::json!([
         {
             "id": 0,
             "nested": { "content": "foobar" },
@@ -53,7 +53,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "id": 0,
             "nested": { "content": "foobar" },
         })
@@ -64,7 +64,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "id": 0,
         })
     );
@@ -75,7 +75,7 @@ async fn get_document() {
     assert_eq!(code, 200);
     assert_eq!(
         response,
-        json!({
+        serde_json::json!({
             "nested": { "content": "foobar" },
         })
     );
@@ -122,7 +122,7 @@ async fn get_all_documents_no_options() {
     assert_eq!(code, 200);
     let arr = response["results"].as_array().unwrap();
     assert_eq!(arr.len(), 20);
-    let first = json!({
+    let first = serde_json::json!({
         "id":0,
         "isActive":false,
         "balance":"$2,668.55",

meilisearch/tests/documents/update_documents.rs

@@ -1,8 +1,7 @@
-use meili_snap::snapshot;
+use serde_json::json;
 
 use crate::common::encoder::Encoder;
 use crate::common::{GetAllDocumentsOptions, Server};
-use crate::json;
 
 #[actix_rt::test]
 async fn error_document_update_create_index_bad_uid() {
@@ -85,13 +84,7 @@ async fn update_document() {
 
     let (response, code) = index.get_document(1, None).await;
     assert_eq!(code, 200);
-    snapshot!(response, @r###"
-    {
-      "doc_id": 1,
-      "content": "foo",
-      "other": "bar"
-    }
-    "###);
+    assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
 }
 
 #[actix_rt::test]
@@ -129,13 +122,7 @@ async fn update_document_gzip_encoded() {
 
     let (response, code) = index.get_document(1, None).await;
     assert_eq!(code, 200);
-    snapshot!(response, @r###"
-    {
-      "doc_id": 1,
-      "content": "foo",
-      "other": "bar"
-    }
-    "###);
+    assert_eq!(response.to_string(), r##"{"doc_id":1,"content":"foo","other":"bar"}"##);
 }
 
 #[actix_rt::test]

meilisearch/tests/features/mod.rs

@@ -1,8 +1,6 @@
-use meilisearch::Opt;
-use tempfile::TempDir;
+use serde_json::json;
 
-use crate::common::{default_settings, Server};
-use crate::json;
+use crate::common::Server;
 
 /// Feature name to test against.
 /// This will have to be changed by a different one when that feature is stabilized.
@@ -19,9 +17,7 @@ async fn experimental_features() {
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
       "scoreDetails": false,
-      "vectorStore": false,
-      "metrics": false,
-      "exportPuffinReports": false
+      "vectorStore": false
     }
     "###);
 
@@ -31,9 +27,7 @@ async fn experimental_features() {
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
       "scoreDetails": false,
-      "vectorStore": true,
-      "metrics": false,
-      "exportPuffinReports": false
+      "vectorStore": true
     }
     "###);
 
@@ -43,9 +37,7 @@ async fn experimental_features() {
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
       "scoreDetails": false,
-      "vectorStore": true,
-      "metrics": false,
-      "exportPuffinReports": false
+      "vectorStore": true
     }
     "###);
 
@@ -56,9 +48,7 @@ async fn experimental_features() {
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
       "scoreDetails": false,
-      "vectorStore": true,
-      "metrics": false,
-      "exportPuffinReports": false
+      "vectorStore": true
     }
     "###);
 
@@ -69,73 +59,11 @@ async fn experimental_features() {
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
       "scoreDetails": false,
-      "vectorStore": true,
-      "metrics": false,
-      "exportPuffinReports": false
+      "vectorStore": true
     }
     "###);
 }
 
-#[actix_rt::test]
-async fn experimental_feature_metrics() {
-    // instance flag for metrics enables metrics at startup
-    let dir = TempDir::new().unwrap();
-    let enable_metrics = Opt { experimental_enable_metrics: true, ..default_settings(dir.path()) };
-    let server = Server::new_with_options(enable_metrics).await.unwrap();
-
-    let (response, code) = server.get_features().await;
-
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
-    {
-      "scoreDetails": false,
-      "vectorStore": false,
-      "metrics": true,
-      "exportPuffinReports": false
-    }
-    "###);
-
-    let (response, code) = server.get_metrics().await;
-    meili_snap::snapshot!(code, @"200 OK");
-
-    // metrics are not returned in json format
-    // so the test server will return null
-    meili_snap::snapshot!(response, @"null");
-
-    // disabling metrics results in invalid request
-    let (response, code) = server.set_features(json!({"metrics": false})).await;
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(response["metrics"], @"false");
-
-    let (response, code) = server.get_metrics().await;
-    meili_snap::snapshot!(code, @"400 Bad Request");
-    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
-    {
-      "message": "Getting metrics requires enabling the `metrics` experimental feature. See https://github.com/meilisearch/product/discussions/625",
-      "code": "feature_not_enabled",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
-    }
-    "###);
-
-    // enabling metrics via HTTP results in valid request
-    let (response, code) = server.set_features(json!({"metrics": true})).await;
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(response["metrics"], @"true");
-
-    let (response, code) = server.get_metrics().await;
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(response, @"null");
-
-    // startup without flag respects persisted metrics value
-    let disable_metrics =
-        Opt { experimental_enable_metrics: false, ..default_settings(dir.path()) };
-    let server_no_flag = Server::new_with_options(disable_metrics).await.unwrap();
-    let (response, code) = server_no_flag.get_metrics().await;
-    meili_snap::snapshot!(code, @"200 OK");
-    meili_snap::snapshot!(response, @"null");
-}
-
 #[actix_rt::test]
 async fn errors() {
     let server = Server::new().await;
@@ -146,7 +74,7 @@ async fn errors() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
-      "message": "Unknown field `NotAFeature`: expected one of `scoreDetails`, `vectorStore`, `metrics`, `exportPuffinReports`",
+      "message": "Unknown field `NotAFeature`: expected one of `scoreDetails`, `vectorStore`",
       "code": "bad_request",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#bad_request"

meilisearch/tests/index/create_index.rs

@@ -2,10 +2,10 @@ use actix_web::http::header::ContentType;
 use actix_web::test;
 use http::header::ACCEPT_ENCODING;
 use meili_snap::{json_string, snapshot};
+use serde_json::{json, Value};
 
 use crate::common::encoder::Encoder;
-use crate::common::{Server, Value};
-use crate::json;
+use crate::common::Server;
 
 #[actix_rt::test]
 async fn create_index_no_primary_key() {
@@ -21,7 +21,7 @@ async fn create_index_no_primary_key() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -38,7 +38,7 @@ async fn create_index_with_gzip_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -86,7 +86,7 @@ async fn create_index_with_zlib_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -103,7 +103,7 @@ async fn create_index_with_brotli_encoded_request() {
 
     assert_eq!(response["status"], "succeeded");
     assert_eq!(response["type"], "indexCreation");
-    assert_eq!(response["details"]["primaryKey"], json!(null));
+    assert_eq!(response["details"]["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]
@@ -136,7 +136,7 @@ async fn create_index_with_invalid_primary_key() {
 
     let (response, code) = index.get().await;
     assert_eq!(code, 200);
-    assert_eq!(response["primaryKey"], json!(null));
+    assert_eq!(response["primaryKey"], Value::Null);
 }
 
 #[actix_rt::test]

meilisearch/tests/index/delete_index.rs

@@ -1,5 +1,6 @@
+use serde_json::json;
+
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn create_and_delete_index() {

meilisearch/tests/index/errors.rs

@@ -1,7 +1,7 @@
 use meili_snap::*;
+use serde_json::json;
 
 use crate::common::Server;
-use crate::json;
 
 #[actix_rt::test]
 async fn get_indexes_bad_offset() {