exposes all the s3 arguments

add a lot of comments and logs

.cargo/config.toml

@@ -1,2 +0,0 @@
-[alias]
-xtask = "run --release --package xtask --"

.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
 
@@ -27,23 +29,6 @@ Related spec: WIP
 - [ ] If prototype validated, merge changes into `main`
 - [ ] Update the spec
 
-### Reminders when modifying the Setting API
-
-<!--- Special steps to remind when adding a new index setting -->
-
-- [ ] Ensure the new setting route is at least tested by the [`test_setting_routes` macro](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/tests/settings/get_settings.rs#L276)
-- [ ] Ensure Analytics are fully implemented
-  - [ ] `/settings/my-new-setting` configurated in the [`make_setting_routes` macro](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/src/routes/indexes/settings.rs#L141-L165)
-  - [ ] global `/settings` route configurated in the [`update_all` function](https://github.com/meilisearch/meilisearch/blob/5204c0b60b384cbc79621b6b2176fca086069e8e/meilisearch/src/routes/indexes/settings.rs#L655-L751)
-- [ ] Ensure the dump serializing is consistent with the `/settings` route serializing, e.g., enums case can be different (`camelCase` in route and `PascalCase` in the dump)
-
-#### Special cases when adding a setting for an experimental feature
-
-- [ ] ⚠️ API stability: The setting does not appear on the main settings route when the feature has never been enabled (e.g. mark it `Unset` when returned from the index in this situation. See [an example](https://github.com/meilisearch/meilisearch/blob/7a89abd2a025606a42f8b219e539117eb2eb029f/meilisearch-types/src/settings.rs#L608))
-- [ ] The setting cannot be set when the feature is disabled, either by the main settings route or the subroute (see [`validate_settings` function](https://github.com/meilisearch/meilisearch/blob/7a89abd2a025606a42f8b219e539117eb2eb029f/meilisearch/src/routes/indexes/settings.rs#L811))
-- [ ] If possible, the setting is reset when the feature is disabled (hard if it requires reindexing)
-
 ## Impacted teams
 
 <!---Ping the related teams. Ask for the engine manager if any hesitation-->
-<!---@meilisearch/docs-team when there is any API change, e.g. settings addition-->

.github/workflows/bench-manual.yml

@@ -1,30 +0,0 @@
-name: Bench (manual)
-
-on:
-    workflow_dispatch:
-        inputs:
-            workload:
-                description: 'The path to the workloads to execute (workloads/...)'
-                required: true
-                default: 'workloads/movies.json'
-
-env:
-    WORKLOAD_NAME: ${{ github.event.inputs.workload }}
-
-jobs:
-    benchmarks:
-        name: Run and upload benchmarks
-        runs-on: benchmarks
-        timeout-minutes: 180 # 3h
-        steps:
-            - uses: actions/checkout@v3
-            - uses: actions-rs/toolchain@v1
-              with:
-                profile: minimal
-                toolchain: stable
-                override: true
-
-            - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
-              run: |
-               cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Manual [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- ${WORKLOAD_NAME}
-

.github/workflows/bench-pr.yml

@@ -1,46 +0,0 @@
-name: Bench (PR)
-on:
-    issue_comment:
-        types: [created]
-
-permissions:
-    issues: write
-
-env:
-    GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-
-jobs:
-    run-benchmarks-on-comment:
-      if: startsWith(github.event.comment.body, '/bench')
-      name: Run and upload benchmarks
-      runs-on: benchmarks
-      timeout-minutes: 180 # 3h
-      steps:
-        - name: Check for Command
-          id: command
-          uses: xt0rted/slash-command-action@v2
-          with:
-              command: bench
-              reaction-type: "rocket"
-              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 }}
-
-        - uses: actions-rs/toolchain@v1
-          with:
-            profile: minimal
-            toolchain: stable
-            override: true
-
-        - name: Run benchmarks on PR ${{ github.event.issue.id }}
-          run: |
-            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "[Comment](${{ github.event.comment.url }}) on [#${{github.event.issue.id}}](${{ github.event.issue.url }})" -- ${{ steps.command.outputs.command-arguments }}

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

@@ -1,25 +0,0 @@
-name: Indexing bench (push)
-
-on:
-    push:
-        branches:
-            - main
-
-jobs:
-    benchmarks:
-        name: Run and upload benchmarks
-        runs-on: benchmarks
-        timeout-minutes: 180 # 3h
-        steps:
-          - uses: actions/checkout@v3
-          - uses: actions-rs/toolchain@v1
-            with:
-              profile: minimal
-              toolchain: stable
-              override: true
-
-          # Run benchmarks
-          - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
-            run: |
-              cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Push on `main` [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- workloads/*.json
-

.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
@@ -97,7 +97,7 @@ jobs:
       - name: Send CI information to Cloud team
         # Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
         if: github.event_name == 'push'
-        uses: peter-evans/repository-dispatch@v3
+        uses: peter-evans/repository-dispatch@v2
         with:
           token: ${{ secrets.MEILI_BOT_GH_PAT }}
           repository: meilisearch/meilisearch-cloud

.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:
@@ -22,7 +21,7 @@ jobs:
     outputs:
       docker-image: ${{ steps.define-image.outputs.docker-image }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Define the Docker image we need to use
         id: define-image
         run: |
@@ -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: ${{ needs.define-docker-image.outputs.docker-image }}
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-dotnet
-      - name: Setup .NET Core
-        uses: actions/setup-dotnet@v4
-        with:
-          dotnet-version: "6.0.x"
-      - name: Install dependencies
-        run: dotnet restore
-      - name: Build
-        run: dotnet build --configuration Release --no-restore
-      - name: Meilisearch (latest version) setup with Docker
-        run: docker compose up -d
-      - name: Run tests
-        run: dotnet test --no-restore --verbosity normal
-
-  meilisearch-dart-tests:
-    needs: define-docker-image
-    name: Dart SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-dart
-      - uses: dart-lang/setup-dart@v1
-        with:
-          sdk: 'latest'
-      - name: Install dependencies
-        run: dart pub get
-      - name: Run integration tests
-        run: dart test --concurrency=4
-
-  meilisearch-go-tests:
-    needs: define-docker-image
-    name: Go SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - name: Set up Go
-        uses: actions/setup-go@v5
-        with:
-          go-version: stable
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-go
-      - name: Get dependencies
-        run: |
-          go get -v -t -d ./...
-          if [ -f Gopkg.toml ]; then
-            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-            dep ensure
-          fi
-      - name: Run integration tests
-        run: go test -v ./...
-
-  meilisearch-java-tests:
-    needs: define-docker-image
-    name: Java SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ 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@v4
-        with:
-          repository: meilisearch/meilisearch-java
-      - name: Set up Java
-        uses: actions/setup-java@v4
-        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
@@ -156,11 +44,11 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         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
@@ -191,11 +106,13 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           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
@@ -220,11 +137,11 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-python
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
       - name: Install pipenv
         uses: dschep/install-pipenv-action@v1
       - 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: ${{ env.MEILI_NO_ANALYTICS }}
+        ports:
+          - '7700:7700'
+    steps:
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: stable
+      - uses: actions/checkout@v3
+        with:
+          repository: meilisearch/meilisearch-go
+      - name: Get dependencies
+        run: |
+          go get -v -t -d ./...
+          if [ -f Gopkg.toml ]; then
+            curl https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
+            dep ensure
+          fi
+      - name: Run integration tests
+        run: go test -v ./...
+
   meilisearch-ruby-tests:
     needs: define-docker-image
     name: Ruby SDK tests
@@ -245,7 +192,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-ruby
       - name: Set up Ruby 3
@@ -270,117 +217,10 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-rust
       - name: Build
         run: cargo build --verbose
       - name: Run tests
         run: cargo test --verbose
-
-  meilisearch-swift-tests:
-    needs: define-docker-image
-    name: Swift SDK tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-swift
-      - name: Run tests
-        run: swift test
-
-########################
-## FRONT-END PLUGINS ##
-########################
-
-  meilisearch-js-plugins-tests:
-    needs: define-docker-image
-    name: meilisearch-js-plugins tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-js-plugins
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          cache: yarn
-      - name: Install dependencies
-        run: yarn install
-      - name: Run tests
-        run: yarn test
-      - name: Build all the playgrounds and the packages
-        run: yarn build
-
-########################
-## BACK-END PLUGINS ###
-########################
-
-  meilisearch-rails-tests:
-    needs: define-docker-image
-    name: meilisearch-rails tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
-        env:
-          MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
-          MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
-        ports:
-          - '7700:7700'
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: meilisearch/meilisearch-rails
-      - name: Set up Ruby 3
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: 3
-          bundler-cache: true
-      - name: Run tests
-        run: bundle exec rspec
-
-  meilisearch-symfony-tests:
-    needs: define-docker-image
-    name: meilisearch-symfony tests
-    runs-on: ubuntu-latest
-    services:
-      meilisearch:
-        image: getmeili/meilisearch:${{ 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@v4
-        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

@@ -31,12 +31,19 @@ jobs:
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
       - name: Setup test with Rust stable
+        if: github.event_name != 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
           override: true
+      - name: Setup test with Rust nightly
+        if: github.event_name == 'schedule'
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -58,11 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.1
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
-          override: true
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -75,12 +78,12 @@ jobs:
           args: --locked --release --all
 
   test-all-features:
-    name: Tests almost 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
@@ -91,19 +94,23 @@ jobs:
         with:
           toolchain: stable
           override: true
-      - name: Run cargo build with almost all features
-        run: |
-          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
-      - name: Run cargo test with almost all features
-        run: |
-          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
+      - name: Run cargo build with all features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --workspace --locked --release --all-features
+      - name: Run cargo test with all features
+        uses: actions-rs/cargo@v1
+        with:
+          command: test
+          args: --workspace --locked --release --all-features
 
   test-disabled-tokenization:
     name: Test disabled tokenization
     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
@@ -116,10 +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
@@ -142,7 +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:
@@ -157,11 +161,11 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.75.0
+          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:
@@ -180,7 +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

.gitignore

@@ -9,8 +9,6 @@
 /data.ms
 /snapshots
 /dumps
-/bench
-/_xtask_benchmark.ms
 
 # Snapshots
 ## ... large

CONTRIBUTING.md

@@ -75,12 +75,6 @@ If you get a "Too many open files" error you might want to increase the open fil
 ulimit -Sn 3000
 ```
 
-#### Build tools
-
-Meilisearch follows the [cargo xtask](https://github.com/matklad/cargo-xtask) workflow to provide some build tools.
-
-Run `cargo xtask --help` from the root of the repository to find out what is available.
-
 ## Git Guidelines
 
 ### Git Branches

Cargo.toml

@@ -2,7 +2,6 @@
 resolver = "2"
 members = [
     "meilisearch",
-    "meilitool",
     "meilisearch-types",
     "meilisearch-auth",
     "meili-snap",
@@ -16,16 +15,11 @@ members = [
     "json-depth-checker",
     "benchmarks",
     "fuzzers",
-    "tracing-trace",
-    "xtask", "build-info",
 ]
 
 [workspace.package]
-version = "1.7.1"
-authors = [
-    "Quentin de Quelen <quentin@dequelen.me>",
-    "Clément Renault <clement@meilisearch.com>",
-]
+version = "1.3.0"
+authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"
 readme = "README.md"
@@ -42,24 +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

@@ -1,14 +1,14 @@
 # Compile
-FROM    rust:1.75.0-alpine3.18 AS compiler
+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
 ARG     GIT_TAG
-ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
+ENV     VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
 ENV     RUSTFLAGS="-C target-feature=-crt-static"
 
 COPY    . .
@@ -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

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019-2024 Meili SAS
+Copyright (c) 2019-2022 Meili SAS
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

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.
 

README.md

@@ -41,10 +41,10 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 ## ✨ Features
 
 - **Search-as-you-type:** find search results in less than 50 milliseconds
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** get relevant matches even when queries contain typos and misspellings
-- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your users' search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
+- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
 - **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/configuration/synonyms?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** configure synonyms to include more relevant content in your search results
+- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#synonyms):** configure synonyms to include more relevant content in your search results
 - **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
 - **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
 - **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
@@ -61,6 +61,8 @@ You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs
 
 For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
+You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) for an introduction to some of Meilisearch's most popular features.
+
 ## ⚡ Supercharge your Meilisearch experience
 
 Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=github&utm_medium=meilisearch). No credit card required.
@@ -99,7 +101,7 @@ Meilisearch is a search engine created by [Meili](https://www.welcometothejungle
 
 - For feature requests, please visit our [product repository](https://github.com/meilisearch/product/discussions)
 - Found a bug? Open an [issue](https://github.com/meilisearch/meilisearch/issues)!
-- Want to be part of our Discord community? [Join us!](https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+- Want to be part of our Discord community? [Join us!](https://discord.gg/meilisearch)
 
 Thank you for your support!
 

assets/grafana-dashboard.json

@@ -106,7 +106,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "meilisearch_index_count{job=\"$job\", instance=\"$instance\"}",
+          "expr": "meilisearch_index_count{job=\"meilisearch\", instance=\"$instance\"}",
           "interval": "",
           "legendFormat": "",
           "range": true,
@@ -165,7 +165,7 @@
             "type": "prometheus"
           },
           "editorMode": "builder",
-          "expr": "meilisearch_index_docs_count{job=\"$job\", index=\"$Index\", instance=\"$instance\"}",
+          "expr": "meilisearch_index_docs_count{job=\"meilisearch\", index=\"$Index\", instance=\"$instance\"}",
           "hide": false,
           "range": true,
           "refId": "A"
@@ -228,7 +228,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"$job\"}[1h]))",
+          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"meilisearch\"}[1h]))",
           "interval": "",
           "legendFormat": "",
           "range": true,
@@ -288,7 +288,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"$job\"}[24h]))",
+          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"meilisearch\"}[24h]))",
           "interval": "",
           "legendFormat": "",
           "range": true,
@@ -348,7 +348,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"$job\"}[30d]))",
+          "expr": "round(increase(meilisearch_http_requests_total{method=\"POST\", path=\"/indexes/$Index/search\", job=\"meilisearch\"}[30d]))",
           "interval": "",
           "legendFormat": "",
           "range": true,
@@ -447,7 +447,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "meilisearch_db_size_bytes{job=\"$job\", instance=\"$instance\"}",
+          "expr": "meilisearch_db_size_bytes{job=\"meilisearch\", instance=\"$instance\"}",
           "interval": "",
           "legendFormat": "Database size on disk",
           "range": true,
@@ -458,7 +458,7 @@
             "type": "prometheus"
           },
           "editorMode": "builder",
-          "expr": "meilisearch_used_db_size_bytes{job=\"$job\", instance=\"$instance\"}",
+          "expr": "meilisearch_used_db_size_bytes{job=\"meilisearch\", instance=\"$instance\"}",
           "hide": false,
           "legendFormat": "Used bytes",
           "range": true,
@@ -553,7 +553,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "rate(meilisearch_http_response_time_seconds_sum{instance=\"$instance\", job=\"$job\"}[5m]) / rate(meilisearch_http_response_time_seconds_count[5m])",
+          "expr": "rate(meilisearch_http_response_time_seconds_sum{instance=\"$instance\", job=\"meilisearch\"}[5m]) / rate(meilisearch_http_response_time_seconds_count[5m])",
           "interval": "",
           "legendFormat": "{{method}} {{path}}",
           "range": true,
@@ -646,7 +646,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "rate(meilisearch_http_requests_total{instance=\"$instance\", job=\"$job\"}[5m])",
+          "expr": "rate(meilisearch_http_requests_total{instance=\"$instance\", job=\"meilisearch\"}[5m])",
           "interval": "",
           "legendFormat": "{{method}} {{path}}",
           "range": true,
@@ -744,7 +744,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "sum by(le) (increase(meilisearch_http_response_time_seconds_bucket{path=\"/indexes/$Index/search\", instance=\"$instance\", job=\"$job\"}[30s]))",
+          "expr": "sum by(le) (increase(meilisearch_http_response_time_seconds_bucket{path=\"/indexes/$Index/search\", instance=\"$instance\", job=\"meilisearch\"}[30s]))",
           "format": "heatmap",
           "interval": "",
           "legendFormat": "{{le}}",
@@ -854,7 +854,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"$job\", kind=\"statuses\"}",
+          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"meilisearch\", kind=\"statuses\"}",
           "interval": "",
           "legendFormat": "{{value}} ",
           "range": true,
@@ -947,7 +947,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"$job\", kind=\"types\"}",
+          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"meilisearch\", kind=\"types\"}",
           "interval": "",
           "legendFormat": "{{value}} ",
           "range": true,
@@ -1040,7 +1040,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"$job\", kind=\"indexes\"}",
+          "expr": "meilisearch_nb_tasks{instance=\"$instance\", job=\"meilisearch\", kind=\"indexes\"}",
           "interval": "",
           "legendFormat": "{{value}} ",
           "range": true,
@@ -1161,7 +1161,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "rate(process_cpu_seconds_total{job=\"$job\", instance=\"$instance\"}[1m])",
+          "expr": "rate(process_cpu_seconds_total{job=\"meilisearch\", instance=\"$instance\"}[1m])",
           "interval": "",
           "legendFormat": "process",
           "range": true,
@@ -1264,7 +1264,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "process_resident_memory_bytes{job=\"$job\", instance=\"$instance\"} / 1024 / 1024",
+          "expr": "process_resident_memory_bytes{job=\"meilisearch\", instance=\"$instance\"} / 1024 / 1024",
           "interval": "",
           "legendFormat": "process",
           "range": true,
@@ -1342,33 +1342,6 @@
         "skipUrlSync": false,
         "sort": 0,
         "type": "query"
-      },
-      {
-        "current": {
-          "selected": true,
-          "text": "meilisearch",
-          "value": "meilisearch"
-        },
-        "datasource": {
-          "type": "prometheus"
-        },
-        "definition": "label_values(job)",
-        "description": "Prometheus job_name from scrape config (default is meilisearch)",
-        "hide": 0,
-        "includeAll": false,
-        "label": "Job",
-        "multi": false,
-        "name": "job",
-        "options": [],
-        "query": {
-          "query": "label_values(job)",
-          "refId": "StandardVariableQuery"
-        },
-        "refresh": 1,
-        "regex": "",
-        "skipUrlSync": false,
-        "sort": 0,
-        "type": "query"
       }
     ]
   },

benchmarks/Cargo.toml

@@ -11,24 +11,24 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.79"
-csv = "1.3.0"
+anyhow = "1.0.70"
+csv = "1.2.1"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.39", default-features = false }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+mimalloc = { version = "0.1.37", default-features = false }
+serde_json = { version = "1.0.95", features = ["preserve_order"] }
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.2"
+roaring = "0.10.1"
 
 [build-dependencies]
-anyhow = "1.0.79"
-bytes = "1.5.0"
+anyhow = "1.0.70"
+bytes = "1.4.0"
 convert_case = "0.6.0"
-flate2 = "1.0.28"
-reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
+flate2 = "1.0.25"
+reqwest = { version = "0.11.16", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

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;
@@ -36,7 +38,7 @@ fn setup_index() -> Index {
 }
 
 fn setup_settings<'t>(
-    wtxn: &mut RwTxn<'t>,
+    wtxn: &mut RwTxn<'t, '_>,
     index: &'t Index,
     primary_key: &str,
     searchable_fields: &[&str],
@@ -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();
             },
         )
     });

build-info/Cargo.toml

@@ -1,18 +0,0 @@
-[package]
-name = "build-info"
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-homepage.workspace = true
-readme.workspace = true
-edition.workspace = true
-license.workspace = true
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-time = { version = "0.3.34", features = ["parsing"] }
-
-[build-dependencies]
-anyhow = "1.0.80"
-vergen-git2 = "1.0.0-beta.2"

build-info/build.rs

@@ -1,22 +0,0 @@
-fn main() {
-    if let Err(err) = emit_git_variables() {
-        println!("cargo:warning=vergen: {}", err);
-    }
-}
-
-fn emit_git_variables() -> anyhow::Result<()> {
-    // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
-    // in the corresponding GitHub workflow (publish_docker.yml).
-    // This is due to the Dockerfile building the binary outside of the git directory.
-    let mut builder = vergen_git2::Git2Builder::default();
-
-    builder.branch(true);
-    builder.commit_timestamp(true);
-    builder.commit_message(true);
-    builder.describe(true, true, None);
-    builder.sha(false);
-
-    let git2 = builder.build()?;
-
-    vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
-}

build-info/src/lib.rs

@@ -1,203 +0,0 @@
-use time::format_description::well_known::Iso8601;
-
-#[derive(Debug, Clone)]
-pub struct BuildInfo {
-    pub branch: Option<&'static str>,
-    pub describe: Option<DescribeResult>,
-    pub commit_sha1: Option<&'static str>,
-    pub commit_msg: Option<&'static str>,
-    pub commit_timestamp: Option<time::OffsetDateTime>,
-}
-
-impl BuildInfo {
-    pub fn from_build() -> Self {
-        let branch: Option<&'static str> = option_env!("VERGEN_GIT_BRANCH");
-        let describe = DescribeResult::from_build();
-        let commit_sha1 = option_env!("VERGEN_GIT_SHA");
-        let commit_msg = option_env!("VERGEN_GIT_COMMIT_MESSAGE");
-        let commit_timestamp = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP");
-
-        let commit_timestamp = commit_timestamp.and_then(|commit_timestamp| {
-            time::OffsetDateTime::parse(commit_timestamp, &Iso8601::DEFAULT).ok()
-        });
-
-        Self { branch, describe, commit_sha1, commit_msg, commit_timestamp }
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
-pub enum DescribeResult {
-    Prototype { name: &'static str },
-    Release { version: &'static str, major: u64, minor: u64, patch: u64 },
-    Prerelease { version: &'static str, major: u64, minor: u64, patch: u64, rc: u64 },
-    NotATag { describe: &'static str },
-}
-
-impl DescribeResult {
-    pub fn new(describe: &'static str) -> Self {
-        if let Some(name) = prototype_name(describe) {
-            Self::Prototype { name }
-        } else if let Some(release) = release_version(describe) {
-            release
-        } else if let Some(prerelease) = prerelease_version(describe) {
-            prerelease
-        } else {
-            Self::NotATag { describe }
-        }
-    }
-
-    pub fn from_build() -> Option<Self> {
-        let describe: &'static str = option_env!("VERGEN_GIT_DESCRIBE")?;
-        Some(Self::new(describe))
-    }
-
-    pub fn as_tag(&self) -> Option<&'static str> {
-        match self {
-            DescribeResult::Prototype { name } => Some(name),
-            DescribeResult::Release { version, .. } => Some(version),
-            DescribeResult::Prerelease { version, .. } => Some(version),
-            DescribeResult::NotATag { describe: _ } => None,
-        }
-    }
-
-    pub fn as_prototype(&self) -> Option<&'static str> {
-        match self {
-            DescribeResult::Prototype { name } => Some(name),
-            DescribeResult::Release { .. }
-            | DescribeResult::Prerelease { .. }
-            | DescribeResult::NotATag { .. } => None,
-        }
-    }
-}
-
-/// Parses the input as a prototype name.
-///
-/// Returns `Some(prototype_name)` if the following conditions are met on this value:
-///
-/// 1. starts with `prototype-`,
-/// 2. ends with `-<some_number>`,
-/// 3. does not end with `<some_number>-<some_number>`.
-///
-/// Otherwise, returns `None`.
-fn prototype_name(describe: &'static str) -> Option<&'static str> {
-    if !describe.starts_with("prototype-") {
-        return None;
-    }
-
-    let mut rsplit_prototype = describe.rsplit('-');
-    // last component MUST be a number
-    rsplit_prototype.next()?.parse::<u64>().ok()?;
-    // before than last component SHALL NOT be a number
-    rsplit_prototype.next()?.parse::<u64>().err()?;
-
-    Some(describe)
-}
-
-fn release_version(describe: &'static str) -> Option<DescribeResult> {
-    if !describe.starts_with('v') {
-        return None;
-    }
-
-    // full release version don't contain a `-`
-    if describe.contains('-') {
-        return None;
-    }
-
-    // full release version parse as vX.Y.Z, with X, Y, Z numbers.
-    let mut dots = describe[1..].split('.');
-    let major: u64 = dots.next()?.parse().ok()?;
-    let minor: u64 = dots.next()?.parse().ok()?;
-    let patch: u64 = dots.next()?.parse().ok()?;
-
-    if dots.next().is_some() {
-        return None;
-    }
-
-    Some(DescribeResult::Release { version: describe, major, minor, patch })
-}
-
-fn prerelease_version(describe: &'static str) -> Option<DescribeResult> {
-    // prerelease version is in the shape vM.N.P-rc.C
-    let mut hyphen = describe.rsplit('-');
-    let prerelease = hyphen.next()?;
-    if !prerelease.starts_with("rc.") {
-        return None;
-    }
-
-    let rc: u64 = prerelease[3..].parse().ok()?;
-
-    let release = hyphen.next()?;
-
-    let DescribeResult::Release { version: _, major, minor, patch } = release_version(release)?
-    else {
-        return None;
-    };
-
-    Some(DescribeResult::Prerelease { version: describe, major, minor, patch, rc })
-}
-
-#[cfg(test)]
-mod test {
-    use super::DescribeResult;
-
-    fn assert_not_a_tag(describe: &'static str) {
-        assert_eq!(DescribeResult::NotATag { describe }, DescribeResult::new(describe))
-    }
-
-    fn assert_proto(describe: &'static str) {
-        assert_eq!(DescribeResult::Prototype { name: describe }, DescribeResult::new(describe))
-    }
-
-    fn assert_release(describe: &'static str, major: u64, minor: u64, patch: u64) {
-        assert_eq!(
-            DescribeResult::Release { version: describe, major, minor, patch },
-            DescribeResult::new(describe)
-        )
-    }
-
-    fn assert_prerelease(describe: &'static str, major: u64, minor: u64, patch: u64, rc: u64) {
-        assert_eq!(
-            DescribeResult::Prerelease { version: describe, major, minor, patch, rc },
-            DescribeResult::new(describe)
-        )
-    }
-
-    #[test]
-    fn not_a_tag() {
-        assert_not_a_tag("whatever-fuzzy");
-        assert_not_a_tag("whatever-fuzzy-5-ggg-dirty");
-        assert_not_a_tag("whatever-fuzzy-120-ggg-dirty");
-
-        // technically a tag, but not a proto nor a version, so not parsed as a tag
-        assert_not_a_tag("whatever");
-
-        // dirty version
-        assert_not_a_tag("v1.7.0-1-ggga-dirty");
-        assert_not_a_tag("v1.7.0-rc.1-1-ggga-dirty");
-
-        // after version
-        assert_not_a_tag("v1.7.0-1-ggga");
-        assert_not_a_tag("v1.7.0-rc.1-1-ggga");
-
-        // after proto
-        assert_not_a_tag("protoype-tag-0-1-ggga");
-        assert_not_a_tag("protoype-tag-0-1-ggga-dirty");
-    }
-
-    #[test]
-    fn prototype() {
-        assert_proto("prototype-tag-0");
-        assert_proto("prototype-tag-10");
-        assert_proto("prototype-long-name-tag-10");
-    }
-
-    #[test]
-    fn release() {
-        assert_release("v1.7.2", 1, 7, 2);
-    }
-
-    #[test]
-    fn prerelease() {
-        assert_prerelease("v1.7.2-rc.3", 1, 7, 2, 3);
-    }
-}

config.toml

@@ -129,6 +129,3 @@ experimental_enable_metrics = false
 
 # Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
 experimental_reduce_indexing_memory_usage = false
-
-# Experimentally reduces the maximum number of tasks that will be processed at once, see: <https://github.com/orgs/meilisearch/discussions/713>
-# experimental_max_number_of_batched_tasks = 100

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/Cargo.toml

@@ -11,22 +11,22 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.79"
-flate2 = "1.0.28"
-http = "0.2.11"
+anyhow = "1.0.70"
+flate2 = "1.0.25"
+http = "0.2.9"
+log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-once_cell = "1.19.0"
-regex = "1.10.2"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tracing = "0.1.40"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+once_cell = "1.17.1"
+regex = "1.7.3"
+roaring = { version = "0.10.1", features = ["serde"] }
+serde = { version = "1.0.160", features = ["derive"] }
+serde_json = { version = "1.0.95", features = ["preserve_order"] }
+tar = "0.4.38"
+tempfile = "3.5.0"
+thiserror = "1.0.40"
+time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+uuid = { version = "1.3.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

dump/src/lib.rs

@@ -262,12 +262,8 @@ 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,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::Set(FacetingSettings {
                 max_values_per_facet: Setting::Set(111),
@@ -276,7 +272,6 @@ pub(crate) mod test {
                 ),
             }),
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()

dump/src/reader/compat/v1_to_v2.rs

@@ -120,7 +120,7 @@ impl From<v1::settings::Settings> for v2::Settings<v2::Unchecked> {
                                 criterion.as_ref().map(ToString::to_string)
                             }
                             Err(()) => {
-                                tracing::warn!(
+                                log::warn!(
                                     "Could not import the following ranking rule: `{}`.",
                                     ranking_rule
                                 );
@@ -152,11 +152,11 @@ impl From<v1::update::UpdateStatus> for Option<v2::updates::UpdateStatus> {
         use v2::updates::UpdateStatus as UpdateStatusV2;
         Some(match source {
             UpdateStatusV1::Enqueued { content } => {
-                tracing::warn!(
+                log::warn!(
                     "Cannot import task {} (importing enqueued tasks from v1 dumps is unsupported)",
                     content.update_id
                 );
-                tracing::warn!("Task will be skipped in the queue of imported tasks.");
+                log::warn!("Task will be skipped in the queue of imported tasks.");
 
                 return None;
             }
@@ -229,7 +229,7 @@ impl From<v1::update::UpdateType> for Option<v2::updates::UpdateMeta> {
         Some(match source {
             v1::update::UpdateType::ClearAll => v2::updates::UpdateMeta::ClearDocuments,
             v1::update::UpdateType::Customs => {
-                tracing::warn!("Ignoring task with type 'Customs' that is no longer supported");
+                log::warn!("Ignoring task with type 'Customs' that is no longer supported");
                 return None;
             }
             v1::update::UpdateType::DocumentsAddition { .. } => {
@@ -296,7 +296,7 @@ impl From<v1::settings::RankingRule> for Option<v2::settings::Criterion> {
             v1::settings::RankingRule::Proximity => Some(v2::settings::Criterion::Proximity),
             v1::settings::RankingRule::Attribute => Some(v2::settings::Criterion::Attribute),
             v1::settings::RankingRule::WordsPosition => {
-                tracing::warn!("Removing the 'WordsPosition' ranking rule that is no longer supported, please check the resulting ranking rules of your indexes");
+                log::warn!("Removing the 'WordsPosition' ranking rule that is no longer supported, please check the resulting ranking rules of your indexes");
                 None
             }
             v1::settings::RankingRule::Exactness => Some(v2::settings::Criterion::Exactness),

dump/src/reader/compat/v2_to_v3.rs

@@ -1,3 +1,4 @@
+use std::convert::TryInto;
 use std::str::FromStr;
 
 use time::OffsetDateTime;
@@ -145,8 +146,8 @@ impl From<v2::updates::UpdateStatus> for v3::updates::UpdateStatus {
                         started_processing_at: processing.started_processing_at,
                     }),
                     Err(e) => {
-                        tracing::warn!("Error with task {}: {}", processing.from.update_id, e);
-                        tracing::warn!("Task will be marked as `Failed`.");
+                        log::warn!("Error with task {}: {}", processing.from.update_id, e);
+                        log::warn!("Task will be marked as `Failed`.");
                         v3::updates::UpdateStatus::Failed(v3::updates::Failed {
                             from: v3::updates::Processing {
                                 from: v3::updates::Enqueued {
@@ -171,8 +172,8 @@ impl From<v2::updates::UpdateStatus> for v3::updates::UpdateStatus {
                         enqueued_at: enqueued.enqueued_at,
                     }),
                     Err(e) => {
-                        tracing::warn!("Error with task {}: {}", enqueued.update_id, e);
-                        tracing::warn!("Task will be marked as `Failed`.");
+                        log::warn!("Error with task {}: {}", enqueued.update_id, e);
+                        log::warn!("Task will be marked as `Failed`.");
                         v3::updates::UpdateStatus::Failed(v3::updates::Failed {
                             from: v3::updates::Processing {
                                 from: v3::updates::Enqueued {
@@ -352,7 +353,7 @@ impl From<String> for v3::Code {
             "malformed_payload" => v3::Code::MalformedPayload,
             "missing_payload" => v3::Code::MissingPayload,
             other => {
-                tracing::warn!("Unknown error code {}", other);
+                log::warn!("Unknown error code {}", other);
                 v3::Code::UnretrievableErrorCode
             }
         }

dump/src/reader/compat/v3_to_v4.rs

@@ -76,20 +76,20 @@ impl CompatV3ToV4 {
                         let index_uid = match index_uid {
                             Some(uid) => uid,
                             None => {
-                                tracing::warn!(
+                                log::warn!(
                                     "Error while importing the update {}.",
                                     task.update.id()
                                 );
-                                tracing::warn!(
+                                log::warn!(
                                     "The index associated to the uuid `{}` could not be retrieved.",
                                     task.uuid.to_string()
                                 );
                                 if task.update.is_finished() {
                                     // we're fucking with his history but not his data, that's ok-ish.
-                                    tracing::warn!("The index-uuid will be set as `unknown`.");
+                                    log::warn!("The index-uuid will be set as `unknown`.");
                                     String::from("unknown")
                                 } else {
-                                    tracing::warn!("The task will be ignored.");
+                                    log::warn!("The task will be ignored.");
                                     return None;
                                 }
                             }

dump/src/reader/compat/v4_to_v5.rs

@@ -305,7 +305,7 @@ impl From<v4::ResponseError> for v5::ResponseError {
             "invalid_api_key_expires_at" => v5::Code::InvalidApiKeyExpiresAt,
             "invalid_api_key_description" => v5::Code::InvalidApiKeyDescription,
             other => {
-                tracing::warn!("Unknown error code {}", other);
+                log::warn!("Unknown error code {}", other);
                 v5::Code::UnretrievableErrorCode
             }
         };

dump/src/reader/compat/v5_to_v6.rs

@@ -304,7 +304,7 @@ impl From<v5::ResponseError> for v6::ResponseError {
             "immutable_field" => v6::Code::BadRequest,
             "api_key_already_exists" => v6::Code::ApiKeyAlreadyExists,
             other => {
-                tracing::warn!("Unknown error code {}", other);
+                log::warn!("Unknown error code {}", other);
                 v6::Code::UnretrievableErrorCode
             }
         };
@@ -329,7 +329,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                                     new_ranking_rules.push(new_rule);
                                 }
                                 Err(_) => {
-                                    tracing::warn!("Error while importing settings. The ranking rule `{rule}` does not exist anymore.")
+                                    log::warn!("Error while importing settings. The ranking rule `{rule}` does not exist anymore.")
                                 }
                             }
                         }
@@ -340,12 +340,8 @@ 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(),
-            proximity_precision: v6::Setting::NotSet,
             typo_tolerance: match settings.typo_tolerance {
                 v5::Setting::Set(typo) => v6::Setting::Set(v6::TypoTolerance {
                     enabled: typo.enabled.into(),
@@ -378,7 +374,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,
             },
-            embedders: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
     }

dump/src/reader/mod.rs

@@ -13,12 +13,12 @@ use crate::{Result, Version};
 
 mod compat;
 
-mod v1;
-mod v2;
-mod v3;
-mod v4;
-mod v5;
-mod v6;
+pub(self) mod v1;
+pub(self) mod v2;
+pub(self) mod v3;
+pub(self) mod v4;
+pub(self) mod v5;
+pub(self) mod v6;
 
 pub type Document = serde_json::Map<String, serde_json::Value>;
 pub type UpdateFile = dyn Iterator<Item = Result<Document>>;
@@ -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/v1/settings.rs

@@ -56,7 +56,8 @@ pub enum RankingRule {
     Desc(String),
 }
 
-static ASC_DESC_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"(asc|desc)\(([\w_-]+)\)").unwrap());
+static ASC_DESC_REGEX: Lazy<Regex> =
+    Lazy::new(|| Regex::new(r#"(asc|desc)\(([\w_-]+)\)"#).unwrap());
 
 impl FromStr for RankingRule {
     type Err = ();

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),
-        }
-    }
 }

dump/src/reader/v3/errors.rs

@@ -1,6 +1,5 @@
 use serde::{Deserialize, Serialize};
 
-#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v4/errors.rs

@@ -95,7 +95,6 @@ impl fmt::Display for ErrorType {
     }
 }
 
-#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v5/errors.rs

@@ -31,7 +31,6 @@ impl ResponseError {
     }
 }
 
-#[allow(clippy::enum_variant_names)]
 #[derive(Deserialize, Debug, Clone, Copy)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub enum Code {

dump/src/reader/v6/mod.rs

@@ -2,10 +2,10 @@ use std::fs::{self, File};
 use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
 
+use log::debug;
 pub use meilisearch_types::milli;
 use tempfile::TempDir;
 use time::OffsetDateTime;
-use tracing::debug;
 use uuid::Uuid;
 
 use super::Document;

file-store/Cargo.toml

@@ -11,10 +11,9 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-tracing = "0.1.40"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+tempfile = "3.5.0"
+thiserror = "1.0.40"
+uuid = { version = "1.3.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-faux = "0.1.10"
+faux = "0.1.9"

file-store/src/lib.rs

@@ -1,5 +1,5 @@
 use std::fs::File as StdFile;
-use std::io::Write;
+use std::ops::{Deref, DerefMut};
 use std::path::{Path, PathBuf};
 use std::str::FromStr;
 
@@ -42,7 +42,7 @@ impl FileStore {
         let file = NamedTempFile::new_in(&self.path)?;
         let uuid = Uuid::new_v4();
         let path = self.path.join(uuid.to_string());
-        let update_file = File { file: Some(file), path };
+        let update_file = File { file, path };
 
         Ok((uuid, update_file))
     }
@@ -53,7 +53,7 @@ impl FileStore {
         let file = NamedTempFile::new_in(&self.path)?;
         let uuid = Uuid::from_u128(uuid);
         let path = self.path.join(uuid.to_string());
-        let update_file = File { file: Some(file), path };
+        let update_file = File { file, path };
 
         Ok((uuid, update_file))
     }
@@ -61,13 +61,7 @@ impl FileStore {
     /// Returns the file corresponding to the requested uuid.
     pub fn get_update(&self, uuid: Uuid) -> Result<StdFile> {
         let path = self.get_update_path(uuid);
-        let file = match StdFile::open(path) {
-            Ok(file) => file,
-            Err(e) => {
-                tracing::error!("Can't access update file {uuid}: {e}");
-                return Err(e.into());
-            }
-        };
+        let file = StdFile::open(path)?;
         Ok(file)
     }
 
@@ -102,12 +96,8 @@ impl FileStore {
 
     pub fn delete(&self, uuid: Uuid) -> Result<()> {
         let path = self.path.join(uuid.to_string());
-        if let Err(e) = std::fs::remove_file(path) {
-            tracing::error!("Can't delete file {uuid}: {e}");
-            Err(e.into())
-        } else {
-            Ok(())
-        }
+        std::fs::remove_file(path)?;
+        Ok(())
     }
 
     /// List the Uuids of the files in the FileStore
@@ -132,37 +122,27 @@ impl FileStore {
 
 pub struct File {
     path: PathBuf,
-    file: Option<NamedTempFile>,
+    file: NamedTempFile,
 }
 
 impl File {
-    pub fn dry_file() -> Result<Self> {
-        Ok(Self { path: PathBuf::new(), file: None })
-    }
-
     pub fn persist(self) -> Result<()> {
-        if let Some(file) = self.file {
-            file.persist(&self.path)?;
-        }
+        self.file.persist(&self.path)?;
         Ok(())
     }
 }
 
-impl Write for File {
-    fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
-        if let Some(file) = self.file.as_mut() {
-            file.write(buf)
-        } else {
-            Ok(buf.len())
-        }
-    }
+impl Deref for File {
+    type Target = NamedTempFile;
 
-    fn flush(&mut self) -> std::io::Result<()> {
-        if let Some(file) = self.file.as_mut() {
-            file.flush()
-        } else {
-            Ok(())
-        }
+    fn deref(&self) -> &Self::Target {
+        &self.file
+    }
+}
+
+impl DerefMut for File {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.file
     }
 }
 

filter-parser/Cargo.toml

@@ -13,8 +13,7 @@ license.workspace = true
 
 [dependencies]
 nom = "7.1.3"
-nom_locate = "4.2.0"
-unescaper = "0.1.3"
+nom_locate = "4.1.0"
 
 [dev-dependencies]
-insta = "1.34.0"
+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 {
@@ -270,8 +253,8 @@ pub mod test {
             ("aaaa", "", rtok("", "aaaa"), "aaaa"),
             (r#"aa"aa"#, r#""aa"#, rtok("", "aa"), "aa"),
             (r#"aa\"aa"#, r#""#, rtok("", r#"aa\"aa"#), r#"aa"aa"#),
-            (r"aa\\\aa", r#""#, rtok("", r"aa\\\aa"), r"aa\\\aa"),
-            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r"aa\\"), r"aa\\"),
+            (r#"aa\\\aa"#, r#""#, rtok("", r#"aa\\\aa"#), r#"aa\\\aa"#),
+            (r#"aa\\"\aa"#, r#""\aa"#, rtok("", r#"aa\\"#), r#"aa\\"#),
             (r#"aa\\\"\aa"#, r#""#, rtok("", r#"aa\\\"\aa"#), r#"aa\\"\aa"#),
             (r#"\"\""#, r#""#, rtok("", r#"\"\""#), r#""""#),
         ];
@@ -301,12 +284,12 @@ pub mod test {
         );
         // simple quote
         assert_eq!(
-            unescape(Span::new_extra(r"Hello \'World\'", ""), '\''),
+            unescape(Span::new_extra(r#"Hello \'World\'"#, ""), '\''),
             r#"Hello 'World'"#.to_string()
         );
         assert_eq!(
-            unescape(Span::new_extra(r"Hello \\\'World\\\'", ""), '\''),
-            r"Hello \\'World\\'".to_string()
+            unescape(Span::new_extra(r#"Hello \\\'World\\\'"#, ""), '\''),
+            r#"Hello \\'World\\'"#.to_string()
         );
     }
 
@@ -335,19 +318,19 @@ 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#"'Hello \\\'world\\\''"#, r#"Hello \\'world\\'"#, true),
             (r#"'I\'m "super" tamo'"#, r#"I'm "super" tamo"#, true),
-            (r"'\'\''", r#"''"#, true),
+            (r#"'\'\''"#, r#"''"#, true),
         ];
 
         for (input, expected, escaped) in test_case {
@@ -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

@@ -11,10 +11,10 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-arbitrary = { version = "1.3.2", features = ["derive"] }
-clap = { version = "4.4.17", features = ["derive"] }
-fastrand = "2.0.1"
+arbitrary = { version = "1.3.0", features = ["derive"] }
+clap = { version = "4.3.0", features = ["derive"] }
+fastrand = "1.9.0"
 milli = { path = "../milli" }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tempfile = "3.9.0"
+serde = { version = "1.0.160", features = ["derive"] }
+serde_json = { version = "1.0.95", features = ["preserve_order"] }
+tempfile = "3.5.0"

fuzzers/src/bin/fuzz-indexing.rs

@@ -113,7 +113,7 @@ fn main() {
                             index.documents(&wtxn, res.documents_ids).unwrap();
                             progression.fetch_add(1, Ordering::Relaxed);
                         }
-                        wtxn.abort();
+                        wtxn.abort().unwrap();
                     });
                     if let err @ Err(_) = handle.join() {
                         stop.store(true, Ordering::Relaxed);

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

@@ -11,37 +11,34 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.79"
+anyhow = "1.0.70"
 bincode = "1.3.3"
-csv = "1.3.0"
+csv = "1.2.1"
 derive_builder = "0.12.0"
 dump = { path = "../dump" }
-enum-iterator = "1.5.0"
+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"] }
-rayon = "1.8.1"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
+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"] }
 synchronoise = "1.0.1"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = [
-    "serde-well-known",
-    "formatting",
-    "parsing",
-    "macros",
-] }
-tracing = "0.1.40"
-ureq = "2.9.1"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+tempfile = "3.5.0"
+thiserror = "1.0.40"
+time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+uuid = { version = "1.3.1", features = ["serde", "v4"] }
+tokio = { version = "1.27.0", features = ["full"] }
+zookeeper = "0.8.0"
+parking_lot = "0.12.1"
+rust-s3 = { version = "0.33.0", default-features = false, features = ["sync-rustls-tls"] }
 
 [dev-dependencies]
 big_s = "1.0.2"
-crossbeam = "0.8.4"
-insta = { version = "1.34.0", features = ["json", "redactions"] }
+crossbeam = "0.8.2"
+insta = { version = "1.29.0", features = ["json", "redactions"] }
 meili-snap = { path = "../meili-snap" }
+nelson = { git = "https://github.com/meilisearch/nelson.git", rev = "675f13885548fb415ead8fbb447e9e6d9314000a"}

index-scheduler/src/batch.rs

@@ -19,19 +19,20 @@ 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};
 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};
+use meilisearch_types::milli::{self, Filter, BEU32};
 use meilisearch_types::settings::{apply_settings_to_builder, Settings, Unchecked};
 use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
 use meilisearch_types::{compression, Index, VERSION_FILE_NAME};
@@ -42,7 +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.
 ///
@@ -59,13 +60,17 @@ pub(crate) enum Batch {
         /// The list of tasks that were processing when this task cancelation appeared.
         previous_processing_tasks: RoaringBitmap,
     },
-    TaskDeletions(Vec<Task>),
+    TaskDeletion(Task),
     SnapshotCreation(Vec<Task>),
     Dump(Task),
     IndexOperation {
         op: IndexOperation,
         must_create_index: bool,
     },
+    IndexDocumentDeletionByFilter {
+        index_uid: String,
+        task: Task,
+    },
     IndexCreation {
         index_uid: String,
         primary_key: Option<String>,
@@ -103,9 +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,
@@ -142,27 +149,23 @@ pub(crate) enum IndexOperation {
 
 impl Batch {
     /// Return the task ids associated with this batch.
-    pub fn ids(&self) -> RoaringBitmap {
+    pub fn ids(&self) -> Vec<TaskId> {
         match self {
             Batch::TaskCancelation { task, .. }
+            | Batch::TaskDeletion(task)
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
-            | Batch::IndexUpdate { task, .. } => {
-                RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
-            }
-            Batch::SnapshotCreation(tasks)
-            | Batch::TaskDeletions(tasks)
-            | Batch::IndexDeletion { tasks, .. } => {
-                RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
+            | 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, .. } => {
-                    RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
-                }
-                IndexOperation::IndexDocumentDeletionByFilter { task, .. } => {
-                    RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
+                    tasks.iter().map(|task| task.uid).collect()
                 }
                 IndexOperation::SettingsAndDocumentOperation {
                     document_import_tasks: tasks,
@@ -173,11 +176,9 @@ impl Batch {
                     cleared_tasks: tasks,
                     settings_tasks: other,
                     ..
-                } => RoaringBitmap::from_iter(tasks.iter().chain(other).map(|task| task.uid)),
+                } => tasks.iter().chain(other).map(|task| task.uid).collect(),
             },
-            Batch::IndexSwap { task } => {
-                RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
-            }
+            Batch::IndexSwap { task } => vec![task.uid],
         }
     }
 
@@ -186,37 +187,44 @@ impl Batch {
         use Batch::*;
         match self {
             TaskCancelation { .. }
-            | TaskDeletions(_)
+            | TaskDeletion(_)
             | SnapshotCreation(_)
             | Dump(_)
             | IndexSwap { .. } => None,
             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::TaskDeletions(_) => 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![],
+            },
         }
     }
 }
@@ -225,7 +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, .. }
@@ -234,28 +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
@@ -281,12 +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!(),
@@ -342,27 +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,
                 }))
             }
@@ -521,7 +496,6 @@ impl IndexScheduler {
     /// 3. We get the *next* snapshot to process.
     /// 4. We get the *next* dump to process.
     /// 5. We get the *next* tasks to process for a specific index.
-    #[tracing::instrument(level = "trace", skip(self, rtxn), target = "indexing::scheduler")]
     pub(crate) fn create_next_batch(&self, rtxn: &RoTxn) -> Result<Option<Batch>> {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
@@ -535,8 +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,
@@ -546,9 +519,9 @@ impl IndexScheduler {
 
         // 2. we get the next task to delete
         let to_delete = self.get_kind(rtxn, Kind::TaskDeletion)? & enqueued;
-        if !to_delete.is_empty() {
-            let tasks = self.get_existing_tasks(rtxn, to_delete)?;
-            return Ok(Some(Batch::TaskDeletions(tasks)));
+        if let Some(task_id) = to_delete.min() {
+            let task = self.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
+            return Ok(Some(Batch::TaskDeletion(task)));
         }
 
         // 3. we batch the snapshot.
@@ -591,9 +564,7 @@ impl IndexScheduler {
         let index_tasks = self.index_tasks(rtxn, index_name)? & enqueued;
 
         // If autobatching is disabled we only take one task at a time.
-        // Otherwise, we take only a maximum of tasks to create batches.
-        let tasks_limit =
-            if self.autobatching_enabled { self.max_number_of_batched_tasks } else { 1 };
+        let tasks_limit = if self.autobatching_enabled { usize::MAX } else { 1 };
 
         let enqueued = index_tasks
             .into_iter()
@@ -627,7 +598,6 @@ impl IndexScheduler {
     /// The list of tasks that were processed. The metadata of each task in the returned
     /// list is updated accordingly, with the exception of the its date fields
     /// [`finished_at`](meilisearch_types::tasks::Task::finished_at) and [`started_at`](meilisearch_types::tasks::Task::started_at).
-    #[tracing::instrument(level = "trace", skip(self, batch), target = "indexing::scheduler", fields(batch=batch.to_string()))]
     pub(crate) fn process_batch(&self, batch: Batch) -> Result<Vec<Task>> {
         #[cfg(test)]
         {
@@ -636,7 +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 } => {
@@ -677,10 +647,9 @@ impl IndexScheduler {
                     Ok(()) => {
                         for content_uuid in canceled_tasks_content_uuids {
                             if let Err(error) = self.delete_update_file(content_uuid) {
-                                tracing::error!(
-                                    file_content_uuid = %content_uuid,
-                                    %error,
-                                    "Failed deleting content file"
+                                error!(
+                                    "We failed deleting the content file indentified as {}: {}",
+                                    content_uuid, error
                                 )
                             }
                         }
@@ -690,43 +659,31 @@ impl IndexScheduler {
 
                 Ok(vec![task])
             }
-            Batch::TaskDeletions(mut tasks) => {
+            Batch::TaskDeletion(mut task) => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
-                let mut matched_tasks = RoaringBitmap::new();
-
-                for task in tasks.iter() {
+                let matched_tasks =
                     if let KindWithContent::TaskDeletion { tasks, query: _ } = &task.kind {
-                        matched_tasks |= tasks;
+                        tasks
                     } else {
                         unreachable!()
-                    }
-                }
-
-                let mut wtxn = self.env.write_txn()?;
-                let mut deleted_tasks = self.delete_matched_tasks(&mut wtxn, &matched_tasks)?;
-                wtxn.commit()?;
-
-                for task in tasks.iter_mut() {
-                    task.status = Status::Succeeded;
-                    let KindWithContent::TaskDeletion { tasks, query: _ } = &task.kind else {
-                        unreachable!()
                     };
 
-                    let deleted_tasks_count = deleted_tasks.intersection_len(tasks);
-                    deleted_tasks -= tasks;
+                let mut wtxn = self.env.write_txn()?;
+                let deleted_tasks_count = self.delete_matched_tasks(&mut wtxn, matched_tasks)?;
 
-                    match &mut task.details {
-                        Some(Details::TaskDeletion {
-                            matched_tasks: _,
-                            deleted_tasks,
-                            original_filter: _,
-                        }) => {
-                            *deleted_tasks = Some(deleted_tasks_count);
-                        }
-                        _ => unreachable!(),
+                task.status = Status::Succeeded;
+                match &mut task.details {
+                    Some(Details::TaskDeletion {
+                        matched_tasks: _,
+                        deleted_tasks,
+                        original_filter: _,
+                    }) => {
+                        *deleted_tasks = Some(deleted_tasks_count);
                     }
+                    _ => unreachable!(),
                 }
-                Ok(tasks)
+                wtxn.commit()?;
+                Ok(vec![task])
             }
             Batch::SnapshotCreation(mut tasks) => {
                 fs::create_dir_all(&self.snapshots_path)?;
@@ -738,7 +695,7 @@ impl IndexScheduler {
 
                 // 2. Snapshot the index-scheduler LMDB env
                 //
-                // When we call copy_to_file, LMDB opens a read transaction by itself,
+                // When we call copy_to_path, LMDB opens a read transaction by itself,
                 // we can't provide our own. It is an issue as we would like to know
                 // the update files to copy but new ones can be enqueued between the copy
                 // of the env and the new transaction we open to retrieve the enqueued tasks.
@@ -751,7 +708,7 @@ impl IndexScheduler {
                 // 2.1 First copy the LMDB env of the index-scheduler
                 let dst = temp_snapshot_dir.path().join("tasks");
                 fs::create_dir_all(&dst)?;
-                self.env.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                self.env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 2.2 Create a read transaction on the index-scheduler
                 let rtxn = self.env.read_txn()?;
@@ -776,7 +733,7 @@ impl IndexScheduler {
                     let index = self.index_mapper.index(&rtxn, name)?;
                     let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
                     fs::create_dir_all(&dst)?;
-                    index.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                    index.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
                 }
 
                 drop(rtxn);
@@ -789,7 +746,7 @@ impl IndexScheduler {
                     .map_size(1024 * 1024 * 1024) // 1 GiB
                     .max_dbs(2)
                     .open(&self.auth_path)?;
-                auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                auth.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
                 // 5. Copy and tarball the flat snapshot
                 // 5.1 Find the original name of the database
@@ -845,10 +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();
@@ -869,9 +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)?;
 
@@ -911,9 +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)?;
@@ -926,16 +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))?;
@@ -956,27 +900,8 @@ 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.index_mapper
-                    .set_currently_updating_index(Some((index_uid.clone(), index.clone())));
-
                 let mut index_wtxn = index.write_txn()?;
-
-                let mut tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
-
-                if index.is_corrupted(&index_wtxn)? {
-                    tracing::error!("Aborting task due to corrupted index");
-                    index_wtxn.abort();
-                    for task in tasks.iter_mut() {
-                        task.status = Status::Failed;
-                        task.error = Some(Error::CorruptedIndex.into());
-                    }
-
-                    return Ok(tasks);
-                }
-
-                index.check_document_facet_consistency(&index_wtxn)?.check();
-
+                let tasks = self.apply_index_operation(&mut index_wtxn, &index, op)?;
                 index_wtxn.commit()?;
 
                 // if the update processed successfully, we're going to store the new
@@ -994,14 +919,56 @@ impl IndexScheduler {
 
                 match res {
                     Ok(_) => (),
-                    Err(e) => tracing::error!(
-                        error = &e as &dyn std::error::Error,
-                        "Could not write the stats of the index"
-                    ),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
                 }
 
                 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)? {
@@ -1025,7 +992,7 @@ impl IndexScheduler {
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.must_stop_processing.clone();
                     builder.execute(
-                        |indexing_step| tracing::debug!(update = ?indexing_step),
+                        |indexing_step| debug!("update: {:?}", indexing_step),
                         || must_stop_processing.get(),
                     )?;
                     index_wtxn.commit()?;
@@ -1052,10 +1019,7 @@ impl IndexScheduler {
 
                 match res {
                     Ok(_) => (),
-                    Err(e) => tracing::error!(
-                        error = &e as &dyn std::error::Error,
-                        "Could not write the stats of the index"
-                    ),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
                 }
 
                 Ok(vec![task])
@@ -1150,7 +1114,7 @@ impl IndexScheduler {
         for task_id in &index_lhs_task_ids | &index_rhs_task_ids {
             let mut task = self.get_task(wtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
             swap_index_uid_in_task(&mut task, (lhs, rhs));
-            self.all_tasks.put(wtxn, &task_id, &task)?;
+            self.all_tasks.put(wtxn, &BEU32::new(task_id), &task)?;
         }
 
         // 4. remove the task from indexuid = before_name
@@ -1174,14 +1138,9 @@ impl IndexScheduler {
     ///
     /// ## Return
     /// The list of processed tasks.
-    #[tracing::instrument(
-        level = "trace",
-        skip(self, index_wtxn, index),
-        target = "indexing::scheduler"
-    )]
     fn apply_index_operation<'i>(
         &self,
-        index_wtxn: &mut RwTxn<'i>,
+        index_wtxn: &mut RwTxn<'i, '_>,
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
@@ -1239,7 +1198,7 @@ impl IndexScheduler {
                                 milli::update::Settings::new(index_wtxn, index, indexer_config);
                             builder.set_primary_key(primary_key);
                             builder.execute(
-                                |indexing_step| tracing::debug!(update = ?indexing_step),
+                                |indexing_step| debug!("update: {:?}", indexing_step),
                                 || must_stop_processing.clone().get(),
                             )?;
                             primary_key_has_been_set = true;
@@ -1249,16 +1208,12 @@ impl IndexScheduler {
 
                 let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
 
-                let embedder_configs = index.embedding_configs(index_wtxn)?;
-                // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
-                let embedders = self.embedders(embedder_configs)?;
-
                 let mut builder = milli::update::IndexDocuments::new(
                     index_wtxn,
                     index,
                     indexer_config,
                     config,
-                    |indexing_step| tracing::trace!(?indexing_step, "Update"),
+                    |indexing_step| debug!("update: {:?}", indexing_step),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1271,8 +1226,6 @@ impl IndexScheduler {
                             let (new_builder, user_result) = builder.add_documents(reader)?;
                             builder = new_builder;
 
-                            builder = builder.with_embedders(embedders.clone());
-
                             let received_documents =
                                 if let Some(Details::DocumentAdditionOrUpdate {
                                     received_documents,
@@ -1307,8 +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
@@ -1319,18 +1271,30 @@ 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());
+                                }
+                            }
                         }
                     }
                 }
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
                     let addition = builder.execute()?;
-                    tracing::info!(indexing_result = ?addition, "document indexing done");
+                    info!("document addition done: {:?}", addition);
                 } else if primary_key_has_been_set {
                     // Everything failed but we've set a primary key.
                     // We need to remove it.
@@ -1338,60 +1302,30 @@ impl IndexScheduler {
                         milli::update::Settings::new(index_wtxn, index, indexer_config);
                     builder.reset_primary_key();
                     builder.execute(
-                        |indexing_step| tracing::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!()
-                    };
+            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);
+                });
 
-                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!();
-                };
+                let DocumentDeletionResult { deleted_documents, .. } = builder.execute()?;
 
-                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());
-                    }
+                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();
@@ -1409,7 +1343,7 @@ impl IndexScheduler {
 
                 let must_stop_processing = self.must_stop_processing.clone();
                 builder.execute(
-                    |indexing_step| tracing::debug!(update = ?indexing_step),
+                    |indexing_step| debug!("update: {:?}", indexing_step),
                     || must_stop_processing.get(),
                 )?;
 
@@ -1483,14 +1417,10 @@ impl IndexScheduler {
     /// Delete each given task from all the databases (if it is deleteable).
     ///
     /// Return the number of tasks that were actually deleted.
-    fn delete_matched_tasks(
-        &self,
-        wtxn: &mut RwTxn,
-        matched_tasks: &RoaringBitmap,
-    ) -> Result<RoaringBitmap> {
+    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;
@@ -1539,9 +1469,10 @@ impl IndexScheduler {
         }
 
         for task in to_delete_tasks.iter() {
-            self.all_tasks.delete(wtxn, &task)?;
+            self.all_tasks.delete(wtxn, &BEU32::new(task))?;
         }
         for canceled_by in affected_canceled_by {
+            let canceled_by = BEU32::new(canceled_by);
             if let Some(mut tasks) = self.canceled_by.get(wtxn, &canceled_by)? {
                 tasks -= &to_delete_tasks;
                 if tasks.is_empty() {
@@ -1552,7 +1483,7 @@ impl IndexScheduler {
             }
         }
 
-        Ok(to_delete_tasks)
+        Ok(to_delete_tasks.len())
     }
 
     /// Cancel each given task from all the databases (if it is cancelable).
@@ -1589,47 +1520,29 @@ impl IndexScheduler {
             task.details = task.details.map(|d| d.to_failed());
             self.update_task(wtxn, &task)?;
         }
-        self.canceled_by.put(wtxn, &cancel_task_id, &tasks_to_cancel)?;
+        self.canceled_by.put(wtxn, &BEU32::new(cancel_task_id), &tasks_to_cancel)?;
 
         Ok(content_files_to_delete)
     }
 }
 
-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| tracing::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

@@ -48,8 +48,6 @@ impl From<DateField> for Code {
 pub enum Error {
     #[error("{1}")]
     WithCustomErrorCode(Code, Box<Self>),
-    #[error("Received bad task id: {received} should be >= to {expected}.")]
-    BadTaskId { received: TaskId, expected: TaskId },
     #[error("Index `{0}` not found.")]
     IndexNotFound(String),
     #[error("Index `{0}` already exists.")]
@@ -110,8 +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),
@@ -138,8 +134,6 @@ pub enum Error {
     CreateBatch(Box<Self>),
     #[error("Corrupted task queue.")]
     CorruptedTaskQueue,
-    #[error("Corrupted index.")]
-    CorruptedIndex,
     #[error(transparent)]
     TaskDatabaseUpdate(Box<Self>),
     #[error(transparent)]
@@ -165,7 +159,6 @@ impl Error {
         match self {
             Error::IndexNotFound(_)
             | Error::WithCustomErrorCode(_, _)
-            | Error::BadTaskId { .. }
             | Error::IndexAlreadyExists(_)
             | Error::SwapDuplicateIndexFound(_)
             | Error::SwapDuplicateIndexesFound(_)
@@ -182,7 +175,6 @@ impl Error {
             | Error::TaskNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
-            | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli(_)
@@ -194,7 +186,6 @@ impl Error {
             | Error::Anyhow(_) => true,
             Error::CreateBatch(_)
             | Error::CorruptedTaskQueue
-            | Error::CorruptedIndex
             | Error::TaskDatabaseUpdate(_)
             | Error::HeedTransaction(_) => false,
             #[cfg(test)]
@@ -211,7 +202,6 @@ impl ErrorCode for Error {
     fn error_code(&self) -> Code {
         match self {
             Error::WithCustomErrorCode(code, _) => *code,
-            Error::BadTaskId { .. } => Code::BadRequest,
             Error::IndexNotFound(_) => Code::IndexNotFound,
             Error::IndexAlreadyExists(_) => Code::IndexAlreadyExists,
             Error::SwapDuplicateIndexesFound(_) => Code::InvalidSwapDuplicateIndexFound,
@@ -245,10 +235,6 @@ impl ErrorCode for Error {
             Error::CorruptedDump => Code::Internal,
             Error::TaskDatabaseUpdate(_) => Code::Internal,
             Error::CreateBatch(_) => Code::Internal,
-            Error::CorruptedIndex => 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;
@@ -11,94 +9,73 @@ 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 {
         self.runtime
     }
 
+    pub fn check_score_details(&self) -> Result<()> {
+        if self.runtime.score_details {
+            Ok(())
+        } else {
+            Err(FeatureNotEnabledError {
+                disabled_action: "Computing score details",
+                feature: "score details",
+                issue_link: "https://github.com/meilisearch/product/discussions/674",
+            }
+            .into())
+        }
+    }
+
     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())
         }
     }
 
-    pub fn check_logs_route(&self) -> Result<()> {
-        if self.runtime.logs_route {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Modifying logs through the `/logs/*` routes",
-                feature: "logs route",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/721",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_vector(&self, disabled_action: &'static str) -> Result<()> {
+    pub fn check_vector(&self) -> Result<()> {
         if self.runtime.vector_store {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action,
+                disabled_action: "Passing `vector` as a query parameter",
                 feature: "vector store",
                 issue_link: "https://github.com/meilisearch/product/discussions/677",
             }
             .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,
-            logs_route: instance_features.logs_route || persisted_features.logs_route,
-            ..persisted_features
-        }));
-
-        Ok(Self { persisted: runtime_features_db, runtime })
+        Ok(Self { runtime: runtime_features, instance: instance_features })
     }
 
     pub fn put_runtime_features(
@@ -106,25 +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

@@ -1,8 +1,12 @@
+/// the map size to use when we don't succeed in reading it in indexes.
+const DEFAULT_MAP_SIZE: usize = 10 * 1024 * 1024 * 1024; // 10 GiB
+
 use std::collections::BTreeMap;
 use std::path::Path;
 use std::time::Duration;
 
-use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
+use meilisearch_types::heed::flags::Flags;
+use meilisearch_types::heed::{EnvClosingEvent, EnvOpenOptions};
 use meilisearch_types::milli::Index;
 use time::OffsetDateTime;
 use uuid::Uuid;
@@ -232,7 +236,7 @@ impl IndexMap {
         enable_mdb_writemap: bool,
         map_size_growth: usize,
     ) {
-        let map_size = index.map_size() + map_size_growth;
+        let map_size = index.map_size().unwrap_or(DEFAULT_MAP_SIZE) + map_size_growth;
         let closing_event = index.prepare_for_closing();
         let generation = self.next_generation();
         self.unavailable.insert(
@@ -291,6 +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.
@@ -305,7 +314,7 @@ fn create_or_open_index(
     options.map_size(clamp_to_page_size(map_size));
     options.max_readers(1024);
     if enable_mdb_writemap {
-        unsafe { options.flags(EnvFlags::WRITE_MAP) };
+        unsafe { options.flag(Flags::MdbWriteMap) };
     }
 
     if let Some((created, updated)) = date {
@@ -331,7 +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)
         }
     }
 
@@ -384,7 +394,7 @@ mod tests {
 
     fn assert_index_size(index: Index, expected: usize) {
         let expected = clamp_to_page_size(expected);
-        let index_map_size = index.map_size();
+        let index_map_size = index.map_size().unwrap();
         assert_eq!(index_map_size, expected);
     }
 }

index-scheduler/src/index_mapper/mod.rs

@@ -3,13 +3,13 @@ use std::sync::{Arc, RwLock};
 use std::time::Duration;
 use std::{fs, thread};
 
+use log::error;
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
-use tracing::error;
 use uuid::Uuid;
 
 use self::index_map::IndexMap;
@@ -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.
@@ -69,10 +69,6 @@ pub struct IndexMapper {
     /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.
     enable_mdb_writemap: bool,
     pub indexer_config: Arc<IndexerConfig>,
-
-    /// A few types of long running batches of tasks that act on a single index set this field
-    /// so that a handle to the index is available from other threads (search) in an optimized manner.
-    currently_updating_index: Arc<RwLock<Option<(String, Index)>>>,
 }
 
 /// Whether the index is available for use or is forbidden to be inserted back in the index map
@@ -139,7 +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))?;
@@ -154,8 +150,7 @@ impl IndexMapper {
             index_base_map_size,
             index_growth_amount,
             enable_mdb_writemap,
-            indexer_config: Arc::new(indexer_config),
-            currently_updating_index: Default::default(),
+            indexer_config,
         })
     }
 
@@ -308,14 +303,6 @@ impl IndexMapper {
 
     /// Return an index, may open it if it wasn't already opened.
     pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
-        if let Some((current_name, current_index)) =
-            self.currently_updating_index.read().unwrap().as_ref()
-        {
-            if current_name == name {
-                return Ok(current_index.clone());
-            }
-        }
-
         let uuid = self
             .index_mapping
             .get(rtxn, name)?
@@ -441,6 +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.
@@ -487,8 +479,4 @@ impl IndexMapper {
     pub fn indexer_config(&self) -> &IndexerConfig {
         &self.indexer_config
     }
-
-    pub fn set_currently_updating_index(&self, index: Option<(String, Index)>) {
-        *self.currently_updating_index.write().unwrap() = index;
-    }
 }

index-scheduler/src/insta_snapshot.rs

@@ -1,21 +1,22 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
+use std::ops::Deref;
 
-use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
+use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 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,
-        cleanup_enabled: _,
         must_stop_processing: _,
         processing_tasks,
         file_store,
@@ -31,26 +32,23 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         index_mapper,
         features: _,
         max_number_of_tasks: _,
-        max_number_of_batched_tasks: _,
-        puffin_frame: _,
         wake_up: _,
         dumps_path: _,
         snapshots_path: _,
         auth_path: _,
         version_file_path: _,
-        webhook_url: _,
-        webhook_authorization_header: _,
         test_breakpoint_sdr: _,
         planned_failures: _,
         run_loop_iteration: _,
-        embedders: _,
-    } = 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));
@@ -119,7 +117,7 @@ pub fn snapshot_bitmap(r: &RoaringBitmap) -> String {
     snap
 }
 
-pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Task>>) -> String {
+pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<OwnedType<BEU32>, SerdeJson<Task>>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
@@ -129,7 +127,10 @@ pub fn snapshot_all_tasks(rtxn: &RoTxn, db: Database<BEU32, SerdeJson<Task>>) ->
     snap
 }
 
-pub fn snapshot_date_db(rtxn: &RoTxn, db: Database<BEI128, CboRoaringBitmapCodec>) -> String {
+pub fn snapshot_date_db(
+    rtxn: &RoTxn,
+    db: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
+) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {
@@ -249,7 +250,10 @@ pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringBitmapCodec>)
     }
     snap
 }
-pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec>) -> String {
+pub fn snapshot_canceled_by(
+    rtxn: &RoTxn,
+    db: Database<OwnedType<BEU32>, RoaringBitmapCodec>,
+) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
     for next in iter {

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/snapshots/lib.rs/task_deletion_delete_same_task_twice/task_deletion_processed.snap

@@ -34,10 +34,12 @@ catto: { number_of_documents: 1, field_distribution: {"id": 1} }
 [timestamp] [3,]
 ----------------------------------------------------------------------
 ### Started At:
-[timestamp] [2,3,]
+[timestamp] [2,]
+[timestamp] [3,]
 ----------------------------------------------------------------------
 ### Finished At:
-[timestamp] [2,3,]
+[timestamp] [2,]
+[timestamp] [3,]
 ----------------------------------------------------------------------
 ### File Store:
 00000000-0000-0000-0000-000000000001

index-scheduler/src/snapshots/lib.rs/test_disable_auto_deletion_of_tasks/task_deletion_have_not_been_enqueued.snap

@@ -1,90 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-[
-  {
-    "uid": 0,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "succeeded",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 1,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": {
-      "message": "Index `doggo` already exists.",
-      "code": "index_already_exists",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#index_already_exists"
-    },
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "failed",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 2,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "enqueued",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 3,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "enqueued",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  }
-]

index-scheduler/src/snapshots/lib.rs/test_disable_auto_deletion_of_tasks/task_queue_is_full.snap

@@ -1,90 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-[
-  {
-    "uid": 0,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "succeeded",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 1,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": {
-      "message": "Index `doggo` already exists.",
-      "code": "index_already_exists",
-      "type": "invalid_request",
-      "link": "https://docs.meilisearch.com/errors#index_already_exists"
-    },
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "failed",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 2,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "enqueued",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  },
-  {
-    "uid": 3,
-    "enqueuedAt": "[date]",
-    "startedAt": "[date]",
-    "finishedAt": "[date]",
-    "error": null,
-    "canceledBy": null,
-    "details": {
-      "IndexInfo": {
-        "primary_key": null
-      }
-    },
-    "status": "enqueued",
-    "kind": {
-      "indexCreation": {
-        "index_uid": "doggo",
-        "primary_key": null
-      }
-    }
-  }
-]

index-scheduler/src/utils.rs

@@ -3,22 +3,22 @@
 use std::collections::{BTreeSet, HashSet};
 use std::ops::Bound;
 
-use meilisearch_types::heed::types::DecodeIgnore;
+use meilisearch_types::heed::types::{DecodeIgnore, OwnedType};
 use meilisearch_types::heed::{Database, RoTxn, RwTxn};
-use meilisearch_types::milli::CboRoaringBitmapCodec;
+use meilisearch_types::milli::{CboRoaringBitmapCodec, BEU32};
 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()
     }
 
     pub(crate) fn last_task_id(&self, rtxn: &RoTxn) -> Result<Option<TaskId>> {
-        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k + 1))
+        Ok(self.all_tasks.remap_data_type::<DecodeIgnore>().last(rtxn)?.map(|(k, _)| k.get() + 1))
     }
 
     pub(crate) fn next_task_id(&self, rtxn: &RoTxn) -> Result<TaskId> {
@@ -26,7 +26,7 @@ impl IndexScheduler {
     }
 
     pub(crate) fn get_task(&self, rtxn: &RoTxn, task_id: TaskId) -> Result<Option<Task>> {
-        Ok(self.all_tasks.get(rtxn, &task_id)?)
+        Ok(self.all_tasks.get(rtxn, &BEU32::new(task_id))?)
     }
 
     /// Convert an iterator to a `Vec` of tasks. The tasks MUST exist or a
@@ -88,7 +88,7 @@ impl IndexScheduler {
             }
         }
 
-        self.all_tasks.put(wtxn, &task.uid, task)?;
+        self.all_tasks.put(wtxn, &BEU32::new(task.uid), task)?;
         Ok(())
     }
 
@@ -169,11 +169,11 @@ impl IndexScheduler {
 
 pub(crate) fn insert_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = time.unix_timestamp_nanos();
+    let timestamp = BEI128::new(time.unix_timestamp_nanos());
     let mut task_ids = database.get(wtxn, &timestamp)?.unwrap_or_default();
     task_ids.insert(task_id);
     database.put(wtxn, &timestamp, &RoaringBitmap::from_iter(task_ids))?;
@@ -182,11 +182,11 @@ pub(crate) fn insert_task_datetime(
 
 pub(crate) fn remove_task_datetime(
     wtxn: &mut RwTxn,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
     time: OffsetDateTime,
     task_id: TaskId,
 ) -> Result<()> {
-    let timestamp = time.unix_timestamp_nanos();
+    let timestamp = BEI128::new(time.unix_timestamp_nanos());
     if let Some(mut existing) = database.get(wtxn, &timestamp)? {
         existing.remove(task_id);
         if existing.is_empty() {
@@ -202,7 +202,7 @@ pub(crate) fn remove_task_datetime(
 pub(crate) fn keep_tasks_within_datetimes(
     rtxn: &RoTxn,
     tasks: &mut RoaringBitmap,
-    database: Database<BEI128, CboRoaringBitmapCodec>,
+    database: Database<OwnedType<BEI128>, CboRoaringBitmapCodec>,
     after: Option<OffsetDateTime>,
     before: Option<OffsetDateTime>,
 ) -> Result<()> {
@@ -213,8 +213,8 @@ pub(crate) fn keep_tasks_within_datetimes(
         (Some(after), Some(before)) => (Bound::Excluded(*after), Bound::Excluded(*before)),
     };
     let mut collected_task_ids = RoaringBitmap::new();
-    let start = map_bound(start, |b| b.unix_timestamp_nanos());
-    let end = map_bound(end, |b| b.unix_timestamp_nanos());
+    let start = map_bound(start, |b| BEI128::new(b.unix_timestamp_nanos()));
+    let end = map_bound(end, |b| BEI128::new(b.unix_timestamp_nanos()));
     let iter = database.range(rtxn, &(start, end))?;
     for r in iter {
         let (_timestamp, task_ids) = r?;
@@ -331,12 +331,15 @@ 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();
+
             let task_index_uid = task.index_uid().map(ToOwned::to_owned);
 
             let Task {
@@ -352,36 +355,39 @@ 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.enqueued_at.get(&rtxn, &enqueued_at.unix_timestamp_nanos()).unwrap().unwrap();
+            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, &started_at.unix_timestamp_nanos())
+                    .get(&rtxn, &BEI128::new(started_at.unix_timestamp_nanos()))
                     .unwrap()
                     .unwrap();
                 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, &finished_at.unix_timestamp_nanos())
+                    .get(&rtxn, &BEI128::new(finished_at.unix_timestamp_nanos()))
                     .unwrap()
                     .unwrap();
                 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 } => {
@@ -422,7 +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()
@@ -530,23 +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()

index-scheduler/src/uuid_codec.rs

@@ -1,6 +1,7 @@
 use std::borrow::Cow;
+use std::convert::TryInto;
 
-use meilisearch_types::heed::{BoxedError, BytesDecode, BytesEncode};
+use meilisearch_types::heed::{BytesDecode, BytesEncode};
 use uuid::Uuid;
 
 /// A heed codec for value of struct Uuid.
@@ -9,15 +10,15 @@ pub struct UuidCodec;
 impl<'a> BytesDecode<'a> for UuidCodec {
     type DItem = Uuid;
 
-    fn bytes_decode(bytes: &'a [u8]) -> Result<Self::DItem, BoxedError> {
-        bytes.try_into().map(Uuid::from_bytes).map_err(Into::into)
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        bytes.try_into().ok().map(Uuid::from_bytes)
     }
 }
 
 impl BytesEncode<'_> for UuidCodec {
     type EItem = Uuid;
 
-    fn bytes_encode(item: &Self::EItem) -> Result<Cow<[u8]>, BoxedError> {
-        Ok(Cow::Borrowed(item.as_bytes()))
+    fn bytes_encode(item: &Self::EItem) -> Option<Cow<[u8]>> {
+        Some(Cow::Borrowed(item.as_bytes()))
     }
 }

meili-snap/Cargo.toml

@@ -11,6 +11,6 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-insta = { version = "^1.34.0", features = ["json", "redactions"] }
+insta = { version = "^1.29.0", features = ["json", "redactions"] }
 md5 = "0.7.0"
-once_cell = "1.19"
+once_cell = "1.17"

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

@@ -11,16 +11,18 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-base64 = "0.21.7"
-enum-iterator = "1.5.0"
+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"
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-sha2 = "0.10.8"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+roaring = { version = "0.10.1", features = ["serde"] }
+serde = { version = "1.0.160", features = ["derive"] }
+serde_json = { version = "1.0.95", features = ["preserve_order"] }
+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

@@ -1,22 +1,20 @@
 use std::borrow::Cow;
 use std::cmp::Reverse;
 use std::collections::HashSet;
+use std::convert::{TryFrom, TryInto};
 use std::fs::create_dir_all;
 use std::path::Path;
-use std::result::Result as StdResult;
 use std::str;
 use std::str::FromStr;
 use std::sync::Arc;
 
 use hmac::{Hmac, Mac};
-use meilisearch_types::heed::BoxedError;
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::keys::KeyId;
 use meilisearch_types::milli;
-use meilisearch_types::milli::heed::types::{Bytes, DecodeIgnore, SerdeJson};
+use meilisearch_types::milli::heed::types::{ByteSlice, DecodeIgnore, SerdeJson};
 use meilisearch_types::milli::heed::{Database, Env, EnvOpenOptions, RwTxn};
 use sha2::Sha256;
-use thiserror::Error;
 use time::OffsetDateTime;
 use uuid::fmt::Hyphenated;
 use uuid::Uuid;
@@ -32,7 +30,7 @@ const KEY_ID_ACTION_INDEX_EXPIRATION_DB_NAME: &str = "keyid-action-index-expirat
 #[derive(Clone)]
 pub struct HeedAuthStore {
     env: Arc<Env>,
-    keys: Database<Bytes, SerdeJson<Key>>,
+    keys: Database<ByteSlice, SerdeJson<Key>>,
     action_keyid_index_expiration: Database<KeyIdActionCodec, SerdeJson<Option<OffsetDateTime>>>,
     should_close_on_drop: bool,
 }
@@ -131,9 +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]);
                 }
@@ -278,7 +273,7 @@ impl HeedAuthStore {
     fn delete_key_from_inverted_db(&self, wtxn: &mut RwTxn, key: &KeyId) -> Result<()> {
         let mut iter = self
             .action_keyid_index_expiration
-            .remap_types::<Bytes, DecodeIgnore>()
+            .remap_types::<ByteSlice, DecodeIgnore>()
             .prefix_iter_mut(wtxn, key.as_bytes())?;
         while iter.next().transpose()?.is_some() {
             // safety: we don't keep references from inside the LMDB database.
@@ -296,24 +291,23 @@ pub struct KeyIdActionCodec;
 impl<'a> milli::heed::BytesDecode<'a> for KeyIdActionCodec {
     type DItem = (KeyId, Action, Option<&'a [u8]>);
 
-    fn bytes_decode(bytes: &'a [u8]) -> StdResult<Self::DItem, BoxedError> {
-        let (key_id_bytes, action_bytes) = try_split_array_at(bytes).ok_or(SliceTooShortError)?;
-        let (&action_byte, index) =
-            match try_split_array_at(action_bytes).ok_or(SliceTooShortError)? {
-                ([action], []) => (action, None),
-                ([action], index) => (action, Some(index)),
-            };
+    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
+        let (key_id_bytes, action_bytes) = try_split_array_at(bytes)?;
+        let (action_bytes, index) = match try_split_array_at(action_bytes)? {
+            (action, []) => (action, None),
+            (action, index) => (action, Some(index)),
+        };
         let key_id = Uuid::from_bytes(*key_id_bytes);
-        let action = Action::from_repr(action_byte).ok_or(InvalidActionError { action_byte })?;
+        let action = Action::from_repr(u8::from_be_bytes(*action_bytes))?;
 
-        Ok((key_id, action, index))
+        Some((key_id, action, index))
     }
 }
 
 impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
     type EItem = (&'a KeyId, &'a Action, Option<&'a [u8]>);
 
-    fn bytes_encode((key_id, action, index): &Self::EItem) -> StdResult<Cow<[u8]>, BoxedError> {
+    fn bytes_encode((key_id, action, index): &Self::EItem) -> Option<Cow<[u8]>> {
         let mut bytes = Vec::new();
 
         bytes.extend_from_slice(key_id.as_bytes());
@@ -323,20 +317,10 @@ impl<'a> milli::heed::BytesEncode<'a> for KeyIdActionCodec {
             bytes.extend_from_slice(index);
         }
 
-        Ok(Cow::Owned(bytes))
+        Some(Cow::Owned(bytes))
     }
 }
 
-#[derive(Error, Debug)]
-#[error("the slice is too short")]
-pub struct SliceTooShortError;
-
-#[derive(Error, Debug)]
-#[error("cannot construct a valid Action from {action_byte}")]
-pub struct InvalidActionError {
-    pub action_byte: u8,
-}
-
 pub fn generate_key_as_hexa(uid: Uuid, master_key: &[u8]) -> String {
     // format uid as hyphenated allowing user to generate their own keys.
     let mut uid_buffer = [0; Hyphenated::LENGTH];

meilisearch-types/Cargo.toml

@@ -11,31 +11,31 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.4.1", default-features = false }
-anyhow = "1.0.79"
+actix-web = { version = "4.3.1", default-features = false }
+anyhow = "1.0.70"
 convert_case = "0.6.0"
-csv = "1.3.0"
-deserr = { version = "0.6.1", features = ["actix-web"] }
-either = { version = "1.9.0", features = ["serde"] }
-enum-iterator = "1.5.0"
+csv = "1.2.1"
+deserr = "0.5.0"
+either = { version = "1.8.1", features = ["serde"] }
+enum-iterator = "1.4.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
+flate2 = "1.0.25"
 fst = "0.4.7"
-memmap2 = "0.7.1"
+memmap2 = "0.5.10"
 milli = { path = "../milli" }
-roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.195", features = ["derive"] }
+roaring = { version = "0.10.1", features = ["serde"] }
+serde = { version = "1.0.160", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = "1.0.111"
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tokio = "1.35"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
+serde_json = "1.0.95"
+tar = "0.4.38"
+tempfile = "3.5.0"
+thiserror = "1.0.40"
+time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+tokio = "1.27"
+uuid = { version = "1.3.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-insta = "1.34.0"
+insta = "1.29.0"
 meili-snap = { path = "../meili-snap" }
 
 [features]
@@ -50,9 +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"]
-# allow vietnamese specialized tokenization
-vietnamese = ["milli/vietnamese"]

meilisearch-types/src/deserr/mod.rs

@@ -188,4 +188,3 @@ merge_with_error_impl_take_error_message!(ParseOffsetDateTimeError);
 merge_with_error_impl_take_error_message!(ParseTaskKindError);
 merge_with_error_impl_take_error_message!(ParseTaskStatusError);
 merge_with_error_impl_take_error_message!(IndexUidFormatError);
-merge_with_error_impl_take_error_message!(InvalidSearchSemanticRatio);

meilisearch-types/src/document_formats.rs

@@ -1,6 +1,7 @@
+use std::borrow::Borrow;
 use std::fmt::{self, Debug, Display};
 use std::fs::File;
-use std::io::{self, BufWriter, Write};
+use std::io::{self, Seek, Write};
 use std::marker::PhantomData;
 
 use memmap2::MmapOptions;
@@ -41,7 +42,7 @@ impl Display for DocumentFormatError {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
             Self::Io(e) => write!(f, "{e}"),
-            Self::MalformedPayload(me, b) => match me {
+            Self::MalformedPayload(me, b) => match me.borrow() {
                 Error::Json(se) => {
                     let mut message = match se.classify() {
                         Category::Data => {
@@ -104,8 +105,8 @@ impl ErrorCode for DocumentFormatError {
 }
 
 /// Reads CSV from input and write an obkv batch to writer.
-pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
+pub fn read_csv(file: &File, writer: impl Write + Seek, delimiter: u8) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(writer);
     let mmap = unsafe { MmapOptions::new().map(file)? };
     let csv = csv::ReaderBuilder::new().delimiter(delimiter).from_reader(mmap.as_ref());
     builder.append_csv(csv).map_err(|e| (PayloadType::Csv { delimiter }, e))?;
@@ -116,9 +117,9 @@ pub fn read_csv(file: &File, writer: impl Write, delimiter: u8) -> Result<u64> {
     Ok(count as u64)
 }
 
-/// Reads JSON from temporary file and write an obkv batch to writer.
-pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
+/// Reads JSON from temporary file  and write an obkv batch to writer.
+pub fn read_json(file: &File, writer: impl Write + Seek) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(writer);
     let mmap = unsafe { MmapOptions::new().map(file)? };
     let mut deserializer = serde_json::Deserializer::from_slice(&mmap);
 
@@ -151,8 +152,8 @@ pub fn read_json(file: &File, writer: impl Write) -> Result<u64> {
 }
 
 /// Reads JSON from temporary file  and write an obkv batch to writer.
-pub fn read_ndjson(file: &File, writer: impl Write) -> Result<u64> {
-    let mut builder = DocumentsBatchBuilder::new(BufWriter::new(writer));
+pub fn read_ndjson(file: &File, writer: impl Write + Seek) -> Result<u64> {
+    let mut builder = DocumentsBatchBuilder::new(writer);
     let mmap = unsafe { MmapOptions::new().map(file)? };
 
     for result in serde_json::Deserializer::from_slice(&mmap).into_iter() {

meilisearch-types/src/error.rs

@@ -222,8 +222,6 @@ InvalidVectorsType                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
-InvalidEmbedder                       , InvalidRequest       , BAD_REQUEST ;
-InvalidHybridQuery                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
@@ -235,7 +233,6 @@ InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchSemanticRatio            , InvalidRequest       , BAD_REQUEST ;
 InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
@@ -255,18 +252,13 @@ InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsProximityPrecision     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFaceting               , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsFilterableAttributes   , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsPagination             , InvalidRequest       , BAD_REQUEST ;
-InvalidSettingsEmbedders              , InvalidRequest       , BAD_REQUEST ;
 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 ;
@@ -299,20 +291,15 @@ MissingFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
 MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
-MissingSearchHybrid                   , InvalidRequest       , BAD_REQUEST ;
 MissingSwapIndexes                    , InvalidRequest       , BAD_REQUEST ;
 MissingTaskFilters                    , InvalidRequest       , BAD_REQUEST ;
 NoSpaceLeftOnDevice                   , System               , UNPROCESSABLE_ENTITY;
 PayloadTooLarge                       , InvalidRequest       , PAYLOAD_TOO_LARGE ;
 TaskNotFound                          , InvalidRequest       , NOT_FOUND ;
 TooManyOpenFiles                      , System               , UNPROCESSABLE_ENTITY ;
-TooManyVectors                        , InvalidRequest       , BAD_REQUEST ;
 UnretrievableDocument                 , Internal             , BAD_REQUEST ;
 UnretrievableErrorCode                , InvalidRequest       , BAD_REQUEST ;
-UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
-
-// Experimental features
-VectorEmbeddingError                  , InvalidRequest       , BAD_REQUEST
+UnsupportedMediaType                  , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE
 }
 
 impl ErrorCode for JoinError {
@@ -334,6 +321,7 @@ 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,
@@ -345,16 +333,6 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidDocumentId { .. } | UserError::TooManyDocumentIds { .. } => {
                         Code::InvalidDocumentId
                     }
-                    UserError::MissingDocumentField(_) => Code::InvalidDocumentFields,
-                    UserError::InvalidFieldForSource { .. }
-                    | UserError::MissingFieldForSource { .. }
-                    | UserError::InvalidOpenAiModel { .. }
-                    | UserError::InvalidOpenAiModelDimensions { .. }
-                    | UserError::InvalidOpenAiModelDimensionsMax { .. }
-                    | UserError::InvalidSettingsDimensions { .. }
-                    | UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
-                    UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
-                    UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
                     UserError::NoPrimaryKeyCandidateFound => Code::IndexPrimaryKeyNoCandidateFound,
                     UserError::MultiplePrimaryKeyCandidatesFound { .. } => {
                         Code::IndexPrimaryKeyMultipleCandidatesFound
@@ -372,15 +350,11 @@ impl ErrorCode for milli::Error {
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
-                    UserError::InvalidVectorsMapType { .. } => Code::InvalidVectorsType,
                     UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
-                    UserError::TooManyVectors(_, _) => Code::TooManyVectors,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance
                     }
-                    UserError::InvalidEmbedder(_) => Code::InvalidEmbedder,
-                    UserError::VectorEmbeddingError(_) => Code::VectorEmbeddingError,
                 }
             }
         }
@@ -410,11 +384,11 @@ impl ErrorCode for HeedError {
             HeedError::Mdb(MdbError::Invalid) => Code::InvalidStoreFile,
             HeedError::Io(e) => e.error_code(),
             HeedError::Mdb(_)
-            | HeedError::Encoding(_)
-            | HeedError::Decoding(_)
+            | HeedError::Encoding
+            | HeedError::Decoding
             | HeedError::InvalidDatabaseTyping
             | HeedError::DatabaseClosing
-            | HeedError::BadOpenOptions { .. } => Code::Internal,
+            | HeedError::BadOpenOptions => Code::Internal,
         }
     }
 }
@@ -468,15 +442,6 @@ impl fmt::Display for DeserrParseIntError {
     }
 }
 
-impl fmt::Display for deserr_codes::InvalidSearchSemanticRatio {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(
-            f,
-            "the value of `semanticRatio` is invalid, expected a float between `0.0` and `1.0`."
-        )
-    }
-}
-
 #[macro_export]
 macro_rules! internal_error {
     ($target:ty : $($other:path), *) => {

meilisearch-types/src/features.rs

@@ -3,14 +3,11 @@ use serde::{Deserialize, Serialize};
 #[derive(Serialize, Deserialize, Debug, Clone, Copy, Default, PartialEq, Eq)]
 #[serde(rename_all = "camelCase", default)]
 pub struct RuntimeTogglableFeatures {
+    pub score_details: bool,
     pub vector_store: bool,
-    pub metrics: bool,
-    pub logs_route: bool,
-    pub export_puffin_reports: bool,
 }
 
 #[derive(Default, Debug, Clone, Copy)]
 pub struct InstanceTogglableFeatures {
     pub metrics: bool,
-    pub logs_route: bool,
 }

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

@@ -8,7 +8,6 @@ use std::str::FromStr;
 
 use deserr::{DeserializeError, Deserr, ErrorKind, MergeWithError, ValuePointerRef};
 use fst::IntoStreamer;
-use milli::proximity::ProximityPrecision;
 use milli::update::Setting;
 use milli::{Criterion, CriterionError, Index, DEFAULT_VALUES_PER_FACET};
 use serde::{Deserialize, Serialize, Serializer};
@@ -172,24 +171,12 @@ 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")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsDistinctAttribute>)]
     pub distinct_attribute: Setting<String>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsProximityPrecision>)]
-    pub proximity_precision: Setting<ProximityPrecisionView>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default, error = DeserrJsonError<InvalidSettingsTypoTolerance>)]
     pub typo_tolerance: Setting<TypoSettings>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
@@ -199,10 +186,6 @@ pub struct Settings<T> {
     #[deserr(default, error = DeserrJsonError<InvalidSettingsPagination>)]
     pub pagination: Setting<PaginationSettings>,
 
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default, error = DeserrJsonError<InvalidSettingsEmbedders>)]
-    pub embedders: Setting<BTreeMap<String, Setting<milli::vector::settings::EmbeddingSettings>>>,
-
     #[serde(skip)]
     #[deserr(skip)]
     pub _kind: PhantomData<T>,
@@ -218,15 +201,10 @@ 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,
-            proximity_precision: Setting::Reset,
             typo_tolerance: Setting::Reset,
             faceting: Setting::Reset,
             pagination: Setting::Reset,
-            embedders: Setting::Reset,
             _kind: PhantomData,
         }
     }
@@ -239,16 +217,11 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
-            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
-            embedders,
             ..
         } = self;
 
@@ -259,16 +232,11 @@ impl Settings<Checked> {
             sortable_attributes,
             ranking_rules,
             stop_words,
-            non_separator_tokens,
-            separator_tokens,
-            dictionary,
             synonyms,
             distinct_attribute,
-            proximity_precision,
             typo_tolerance,
             faceting,
             pagination,
-            embedders,
             _kind: PhantomData,
         }
     }
@@ -306,33 +274,13 @@ 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,
-            proximity_precision: self.proximity_precision,
             typo_tolerance: self.typo_tolerance,
             faceting: self.faceting,
             pagination: self.pagination,
-            embedders: self.embedders,
             _kind: PhantomData,
         }
     }
-
-    pub fn validate(self) -> Result<Self, milli::Error> {
-        self.validate_embedding_settings()
-    }
-
-    fn validate_embedding_settings(mut self) -> Result<Self, milli::Error> {
-        let Setting::Set(mut configs) = self.embedders else { return Ok(self) };
-        for (name, config) in configs.iter_mut() {
-            let config_to_check = std::mem::take(config);
-            let checked_config = milli::update::validate_embedding_settings(config_to_check, name)?;
-            *config = checked_config
-        }
-        self.embedders = Setting::Set(configs);
-        Ok(self)
-    }
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -387,28 +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(),
@@ -421,12 +347,6 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match settings.proximity_precision {
-        Setting::Set(ref precision) => builder.set_proximity_precision((*precision).into()),
-        Setting::Reset => builder.reset_proximity_precision(),
-        Setting::NotSet => (),
-    }
-
     match settings.typo_tolerance {
         Setting::Set(ref value) => {
             match value.enabled {
@@ -513,12 +433,6 @@ pub fn apply_settings_to_builder(
         Setting::Reset => builder.reset_pagination_max_total_hits(),
         Setting::NotSet => (),
     }
-
-    match settings.embedders.clone() {
-        Setting::Set(value) => builder.set_embedder_settings(value),
-        Setting::Reset => builder.reset_embedder_settings(),
-        Setting::NotSet => (),
-    }
 }
 
 pub fn settings(
@@ -545,16 +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 proximity_precision = index.proximity_precision(rtxn)?.map(ProximityPrecisionView::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)?),
@@ -577,10 +490,7 @@ pub fn settings(
 
     let faceting = FacetingSettings {
         max_values_per_facet: Setting::Set(
-            index
-                .max_values_per_facet(rtxn)?
-                .map(|x| x as usize)
-                .unwrap_or(DEFAULT_VALUES_PER_FACET),
+            index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET),
         ),
         sort_facet_values_by: Setting::Set(
             index
@@ -593,20 +503,10 @@ pub fn settings(
 
     let pagination = PaginationSettings {
         max_total_hits: Setting::Set(
-            index
-                .pagination_max_total_hits(rtxn)?
-                .map(|x| x as usize)
-                .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
+            index.pagination_max_total_hits(rtxn)?.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS),
         ),
     };
 
-    let embedders: BTreeMap<_, _> = index
-        .embedding_configs(rtxn)?
-        .into_iter()
-        .map(|(name, config)| (name, Setting::Set(config.into())))
-        .collect();
-    let embedders = if embedders.is_empty() { Setting::NotSet } else { Setting::Set(embedders) };
-
     Ok(Settings {
         displayed_attributes: match displayed_attributes {
             Some(attrs) => Setting::Set(attrs),
@@ -620,19 +520,14 @@ 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,
         },
-        proximity_precision: Setting::Set(proximity_precision.unwrap_or_default()),
         synonyms: Setting::Set(synonyms),
         typo_tolerance: Setting::Set(typo_tolerance),
         faceting: Setting::Set(faceting),
         pagination: Setting::Set(pagination),
-        embedders,
         _kind: PhantomData,
     })
 }
@@ -733,32 +628,6 @@ impl From<RankingRuleView> for Criterion {
     }
 }
 
-#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Deserr, Serialize, Deserialize)]
-#[serde(deny_unknown_fields, rename_all = "camelCase")]
-#[deserr(error = DeserrJsonError<InvalidSettingsProximityPrecision>, rename_all = camelCase, deny_unknown_fields)]
-pub enum ProximityPrecisionView {
-    #[default]
-    ByWord,
-    ByAttribute,
-}
-
-impl From<ProximityPrecision> for ProximityPrecisionView {
-    fn from(value: ProximityPrecision) -> Self {
-        match value {
-            ProximityPrecision::ByWord => ProximityPrecisionView::ByWord,
-            ProximityPrecision::ByAttribute => ProximityPrecisionView::ByAttribute,
-        }
-    }
-}
-impl From<ProximityPrecisionView> for ProximityPrecision {
-    fn from(value: ProximityPrecisionView) -> Self {
-        match value {
-            ProximityPrecisionView::ByWord => ProximityPrecision::ByWord,
-            ProximityPrecisionView::ByAttribute => ProximityPrecision::ByAttribute,
-        }
-    }
-}
-
 #[cfg(test)]
 pub(crate) mod test {
     use super::*;
@@ -773,16 +642,11 @@ 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,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 
@@ -799,16 +663,11 @@ 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,
-            proximity_precision: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
             faceting: Setting::NotSet,
             pagination: Setting::NotSet,
-            embedders: Setting::NotSet,
             _kind: PhantomData::<Unchecked>,
         };
 

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

@@ -13,14 +13,14 @@ license.workspace = true
 default-run = "meilisearch"
 
 [dependencies]
-actix-cors = "0.7.0"
-actix-http = { version = "3.5.1", default-features = false, features = [
+actix-cors = "0.6.4"
+actix-http = { version = "3.3.1", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
     "rustls",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.4.1", default-features = false, features = [
+actix-web = { version = "4.3.1", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
@@ -28,115 +28,116 @@ actix-web = { version = "4.4.1", default-features = false, features = [
     "rustls",
 ] }
 actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
-anyhow = { version = "1.0.79", features = ["backtrace"] }
+anyhow = { version = "1.0.70", features = ["backtrace"] }
 async-stream = "0.3.5"
-async-trait = "0.1.77"
-bstr = "1.9.0"
+async-trait = "0.1.68"
+bstr = "1.4.0"
 byte-unit = { version = "4.0.19", default-features = false, features = [
     "std",
     "serde",
 ] }
-bytes = "1.5.0"
-clap = { version = "4.4.17", features = ["derive", "env"] }
-crossbeam-channel = "0.5.11"
-deserr = { version = "0.6.1", features = ["actix-web"] }
+bytes = "1.4.0"
+clap = { version = "4.2.1", features = ["derive", "env"] }
+crossbeam-channel = "0.5.8"
+deserr = "0.5.0"
 dump = { path = "../dump" }
-either = "1.9.0"
+either = "1.8.1"
+env_logger = "0.10.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.28"
+flate2 = "1.0.25"
 fst = "0.4.7"
-futures = "0.3.30"
-futures-util = "0.3.30"
-http = "0.2.11"
+futures = "0.3.28"
+futures-util = "0.3.28"
+http = "0.2.9"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.1.0", features = ["serde"] }
-is-terminal = "0.4.10"
-itertools = "0.11.0"
+indexmap = { version = "1.9.3", features = ["serde-1"] }
+is-terminal = "0.4.8"
+itertools = "0.10.5"
 jsonwebtoken = "8.3.0"
 lazy_static = "1.4.0"
+log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.39", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 mime = "0.3.17"
-num_cpus = "1.16.0"
-obkv = "0.2.1"
-once_cell = "1.19.0"
-ordered-float = "4.2.0"
+num_cpus = "1.15.0"
+obkv = "0.2.0"
+once_cell = "1.17.1"
+ordered-float = "3.7.0"
 parking_lot = "0.12.1"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
-pin-project-lite = "0.2.13"
+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 = "1.8.0"
-regex = "1.10.2"
-reqwest = { version = "0.11.23", features = [
+rayon = "1.7.0"
+regex = "1.7.3"
+reqwest = { version = "0.11.16", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
 rustls = "0.20.8"
 rustls-pemfile = "1.0.2"
-segment = { version = "0.2.3", optional = true }
-serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.111", features = ["preserve_order"] }
-sha2 = "0.10.8"
-siphasher = "1.0.0"
-slice-group-by = "0.3.1"
+rust-s3 = { version = "0.33.0", default-features = false, features = ["sync-rustls-tls"] }
+segment = { version = "0.2.2", optional = true }
+serde = { version = "1.0.160", features = ["derive"] }
+serde_json = { version = "1.0.95", features = ["preserve_order"] }
+sha2 = "0.10.6"
+siphasher = "0.3.10"
+slice-group-by = "0.3.0"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.30.5"
-tar = "0.4.40"
-tempfile = "3.9.0"
-thiserror = "1.0.56"
-time = { version = "0.3.31", features = [
+sysinfo = "0.28.4"
+tar = "0.4.38"
+tempfile = "3.5.0"
+thiserror = "1.0.40"
+time = { version = "0.3.20", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = { version = "1.35.1", features = ["full"] }
-tokio-stream = "0.1.14"
-toml = "0.8.8"
-uuid = { version = "1.6.1", features = ["serde", "v4"] }
-walkdir = "2.4.0"
+tokio = { version = "1.27.0", features = ["full"] }
+tokio-stream = "0.1.12"
+toml = "0.7.3"
+uuid = { version = "1.3.1", features = ["serde", "v4"] }
+walkdir = "2.3.3"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
-termcolor = "1.4.1"
-url = { version = "2.5.0", features = ["serde"] }
-tracing = "0.1.40"
-tracing-subscriber = { version = "0.3.18", features = ["json"] }
-tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
-tracing-actix-web = "0.7.9"
-build-info = { version = "1.7.0", path = "../build-info" }
+termcolor = "1.2.0"
+zookeeper = "0.8.0"
 
 [dev-dependencies]
-actix-rt = "2.9.0"
+actix-rt = "2.8.0"
 assert-json-diff = "2.0.2"
-brotli = "3.4.0"
-insta = "1.34.0"
-manifest-dir-macros = "0.1.18"
+brotli = "3.3.4"
+insta = "1.29.0"
+manifest-dir-macros = "0.1.16"
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }
-temp-env = "0.3.6"
-urlencoding = "2.1.3"
+temp-env = "0.3.3"
+urlencoding = "2.1.2"
 yaup = "0.2.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.79", optional = true }
-cargo_toml = { version = "0.18.0", optional = true }
+anyhow = { version = "1.0.70", optional = true }
+cargo_toml = { version = "0.15.2", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.23", features = [
+reqwest = { version = "0.11.16", features = [
     "blocking",
     "rustls-tls",
 ], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.3", optional = true }
-tempfile = { version = "3.9.0", optional = true }
-zip = { version = "0.6.6", optional = true }
+tempfile = { version = "3.5.0", optional = true }
+vergen = { version = "7.5.1", default-features = false, features = ["git"] }
+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",
@@ -153,9 +154,7 @@ hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]
 thai = ["meilisearch-types/thai"]
 greek = ["meilisearch-types/greek"]
-khmer = ["meilisearch-types/khmer"]
-vietnamese = ["meilisearch-types/vietnamese"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.13/build.zip"
-sha1 = "e20cc9b390003c6c844f4b8bcc5c5013191a77ff"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.11/build.zip"
+sha1 = "83cd44ed1e5f97ecb581dc9f958a63f4ccc982d9"

meilisearch/build.rs

@@ -1,4 +1,17 @@
+use vergen::{vergen, Config, SemverKind};
+
 fn main() {
+    // Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
+    // in the corresponding GitHub workflow (publish_docker.yml).
+    // This is due to the Dockerfile building the binary outside of the git directory.
+    let mut config = Config::default();
+    // allow using non-annotated tags
+    *config.git_mut().semver_kind_mut() = SemverKind::Lightweight;
+
+    if let Err(e) = vergen(config) {
+        println!("cargo:warning=vergen: {}", e);
+    }
+
     #[cfg(feature = "mini-dashboard")]
     mini_dashboard::setup_mini_dashboard().expect("Could not load the mini-dashboard assets");
 }

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

@@ -12,8 +12,6 @@ pub enum MeilisearchHttpError {
     #[error("A Content-Type header is missing. Accepted values for the Content-Type header are: {}",
             .0.iter().map(|s| format!("`{}`", s)).collect::<Vec<_>>().join(", "))]
     MissingContentType(Vec<String>),
-    #[error("The `/logs/stream` route is currently in use by someone else.")]
-    AlreadyUsedLogRoute,
     #[error("The Content-Type `{0}` does not support the use of a csv delimiter. The csv delimiter can only be used with the Content-Type `text/csv`.")]
     CsvDelimiterWithWrongContentType(String),
     #[error(
@@ -53,15 +51,12 @@ pub enum MeilisearchHttpError {
     DocumentFormat(#[from] DocumentFormatError),
     #[error(transparent)]
     Join(#[from] JoinError),
-    #[error("Invalid request: missing `hybrid` parameter when both `q` and `vector` are present.")]
-    MissingSearchHybrid,
 }
 
 impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
         match self {
             MeilisearchHttpError::MissingContentType(_) => Code::MissingContentType,
-            MeilisearchHttpError::AlreadyUsedLogRoute => Code::BadRequest,
             MeilisearchHttpError::CsvDelimiterWithWrongContentType(_) => Code::InvalidContentType,
             MeilisearchHttpError::MissingPayload(_) => Code::MissingPayload,
             MeilisearchHttpError::InvalidContentType(_, _) => Code::InvalidContentType,
@@ -79,7 +74,6 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
             MeilisearchHttpError::Join(_) => Code::Internal,
-            MeilisearchHttpError::MissingSearchHybrid => Code::MissingSearchHybrid,
         }
     }
 }

meilisearch/src/extractors/sequential_extractor.rs

@@ -131,7 +131,6 @@ gen_seq! { SeqFromRequestFut3; A B C }
 gen_seq! { SeqFromRequestFut4; A B C D }
 gen_seq! { SeqFromRequestFut5; A B C D E }
 gen_seq! { SeqFromRequestFut6; A B C D E F }
-gen_seq! { SeqFromRequestFut7; A B C D E F G }
 
 pin_project! {
     #[project = ExtractProj]

meilisearch/src/lib.rs

@@ -29,6 +29,7 @@ use error::PayloadError;
 use extractors::payload::PayloadConfig;
 use http::header::CONTENT_TYPE;
 use index_scheduler::{IndexScheduler, IndexSchedulerOptions};
+use log::error;
 use meilisearch_auth::AuthController;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use meilisearch_types::milli::update::{IndexDocumentsConfig, IndexDocumentsMethod};
@@ -38,8 +39,9 @@ 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 tracing::{error, info_span};
-use tracing_subscriber::filter::Targets;
+use s3::creds::Credentials;
+use s3::{Bucket, Region};
+use zookeeper::ZooKeeper;
 
 use crate::error::MeilisearchHttpError;
 
@@ -87,35 +89,10 @@ fn is_empty_db(db_path: impl AsRef<Path>) -> bool {
     }
 }
 
-/// The handle used to update the logs at runtime. Must be accessible from the `main.rs` and the `route/logs.rs`.
-pub type LogRouteHandle =
-    tracing_subscriber::reload::Handle<LogRouteType, tracing_subscriber::Registry>;
-
-pub type LogRouteType = tracing_subscriber::filter::Filtered<
-    Option<Box<dyn tracing_subscriber::Layer<tracing_subscriber::Registry> + Send + Sync>>,
-    Targets,
-    tracing_subscriber::Registry,
->;
-
-pub type SubscriberForSecondLayer = tracing_subscriber::layer::Layered<
-    tracing_subscriber::reload::Layer<LogRouteType, tracing_subscriber::Registry>,
-    tracing_subscriber::Registry,
->;
-
-pub type LogStderrHandle =
-    tracing_subscriber::reload::Handle<LogStderrType, SubscriberForSecondLayer>;
-
-pub type LogStderrType = tracing_subscriber::filter::Filtered<
-    Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
-    Targets,
-    SubscriberForSecondLayer,
->;
-
 pub fn create_app(
     index_scheduler: Data<IndexScheduler>,
     auth_controller: Data<AuthController>,
     opt: Opt,
-    logs: (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
     enable_dashboard: bool,
 ) -> actix_web::App<
@@ -134,14 +111,16 @@ pub fn create_app(
                 index_scheduler.clone(),
                 auth_controller.clone(),
                 &opt,
-                logs,
                 analytics.clone(),
             )
         })
         .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()
@@ -150,62 +129,27 @@ pub fn create_app(
             .allow_any_method()
             .max_age(86_400), // 24h
     )
-    .wrap(tracing_actix_web::TracingLogger::<AwebTracingLogger>::new())
+    .wrap(actix_web::middleware::Logger::default())
     .wrap(actix_web::middleware::Compress::default())
     .wrap(actix_web::middleware::NormalizePath::new(actix_web::middleware::TrailingSlash::Trim))
 }
 
-struct AwebTracingLogger;
-
-impl tracing_actix_web::RootSpanBuilder for AwebTracingLogger {
-    fn on_request_start(request: &actix_web::dev::ServiceRequest) -> tracing::Span {
-        use tracing::field::Empty;
-
-        let conn_info = request.connection_info();
-        let headers = request.headers();
-        let user_agent = headers
-            .get(http::header::USER_AGENT)
-            .map(|value| String::from_utf8_lossy(value.as_bytes()).into_owned())
-            .unwrap_or_default();
-        info_span!("HTTP request", method = %request.method(), host = conn_info.host(), route = %request.path(), query_parameters = %request.query_string(), %user_agent, status_code = Empty, error = Empty)
-    }
-
-    fn on_request_end<B: MessageBody>(
-        span: tracing::Span,
-        outcome: &Result<ServiceResponse<B>, actix_web::Error>,
-    ) {
-        match &outcome {
-            Ok(response) => {
-                let code: i32 = response.response().status().as_u16().into();
-                span.record("status_code", code);
-
-                if let Some(error) = response.response().error() {
-                    // use the status code already constructed for the outgoing HTTP response
-                    span.record("error", &tracing::field::display(error.as_response_error()));
-                }
-            }
-            Err(error) => {
-                let code: i32 = error.error_response().status().as_u16().into();
-                span.record("status_code", code);
-                span.record("error", &tracing::field::display(error.as_response_error()));
-            }
-        };
-    }
-}
-
 enum OnFailure {
     RemoveDb,
     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);
@@ -222,14 +166,14 @@ 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) => {
@@ -249,10 +193,10 @@ 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
@@ -261,17 +205,12 @@ 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, None, false)
-                {
-                    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))
@@ -281,38 +220,52 @@ 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()),
-            webhook_authorization_header: opt.task_webhook_authorization_header.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()?,
-            autobatching_enabled: true,
-            cleanup_enabled: !opt.experimental_replication_parameters,
-            max_number_of_tasks: 1_000_000,
-            max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
-            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(
+                Bucket::new(
+                    opt.s3_bucket.as_deref().unwrap(),
+                    Region::Custom { region: opt.s3_region.clone(), endpoint: url.clone() },
+                    Credentials {
+                        access_key: opt.s3_access_key.clone(),
+                        secret_key: opt.s3_secret_key.clone(),
+                        security_token: opt.s3_security_token.clone(),
+                        session_token: None,
+                        expiration: None,
+                    },
+                )
+                .unwrap()
+                .with_path_style(),
+            )
+        }),
+    }))
+    .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),
     ) {
@@ -330,12 +283,13 @@ 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(
@@ -345,18 +299,19 @@ 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() {
-        tracing::info!(
-            version = ?dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
-            %date,
-            "Importing a dump of meilisearch"
+        log::info!(
+            "Importing a dump of meilisearch `{:?}` from the {}",
+            dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
+            date
         );
     } else {
-        tracing::info!(
-            version = ?dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
-            "Importing a dump of meilisearch",
+        log::info!(
+            "Importing a dump of meilisearch `{:?}`",
+            dump_reader.version(), // TODO: get the meilisearch version instead of the dump version
         );
     }
 
@@ -390,7 +345,7 @@ fn import_dump(
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
-        tracing::info!("Importing index `{}`.", metadata.uid);
+        log::info!("Importing index `{}`.", metadata.uid);
 
         let date = Some((metadata.created_at, metadata.updated_at));
         let index = index_scheduler.create_raw_index(&metadata.uid, date)?;
@@ -404,15 +359,14 @@ fn import_dump(
         }
 
         // 4.2 Import the settings.
-        tracing::info!("Importing the settings.");
+        log::info!("Importing the settings.");
         let settings = index_reader.settings()?;
         apply_settings_to_builder(&settings, &mut builder);
-        builder
-            .execute(|indexing_step| tracing::debug!("update: {:?}", indexing_step), || false)?;
+        builder.execute(|indexing_step| log::debug!("update: {:?}", indexing_step), || false)?;
 
         // 4.3 Import the documents.
         // 4.3.1 We need to recreate the grenad+obkv format accepted by the index.
-        tracing::info!("Importing the documents.");
+        log::info!("Importing the documents.");
         let file = tempfile::tempfile()?;
         let mut builder = DocumentsBatchBuilder::new(BufWriter::new(file));
         for document in index_reader.documents()? {
@@ -426,9 +380,6 @@ fn import_dump(
         let reader = BufReader::new(file);
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
-        let embedder_configs = index.embedding_configs(&wtxn)?;
-        let embedders = index_scheduler.embedders(embedder_configs)?;
-
         let builder = milli::update::IndexDocuments::new(
             &mut wtxn,
             &index,
@@ -437,18 +388,15 @@ fn import_dump(
                 update_method: IndexDocumentsMethod::ReplaceDocuments,
                 ..Default::default()
             },
-            |indexing_step| tracing::trace!("update: {:?}", indexing_step),
+            |indexing_step| log::debug!("update: {:?}", indexing_step),
             || false,
         )?;
 
-        let builder = builder.with_embedders(embedders);
-
         let (builder, user_result) = builder.add_documents(reader)?;
-        let user_result = user_result?;
-        tracing::info!(documents_found = user_result, "{} documents found.", user_result);
+        log::info!("{} documents found.", user_result?);
         builder.execute()?;
         wtxn.commit()?;
-        tracing::info!("All documents successfully imported.");
+        log::info!("All documents successfully imported.");
     }
 
     let mut index_scheduler_dump = index_scheduler.register_dumped_task()?;
@@ -466,7 +414,6 @@ pub fn configure_data(
     index_scheduler: Data<IndexScheduler>,
     auth: Data<AuthController>,
     opt: &Opt,
-    (logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
 ) {
     let http_payload_size_limit = opt.http_payload_size_limit.get_bytes() as usize;
@@ -474,12 +421,8 @@ pub fn configure_data(
         .app_data(index_scheduler)
         .app_data(auth)
         .app_data(web::Data::from(analytics))
-        .app_data(web::Data::new(logs_route))
-        .app_data(web::Data::new(logs_stderr))
-        .app_data(web::Data::new(opt.clone()))
         .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) {
@@ -536,3 +479,30 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
 pub fn dashboard(config: &mut web::ServiceConfig, _enable_frontend: bool) {
     config.service(web::resource("/").route(web::get().to(routes::running)));
 }
+
+/// Parses the output of
+/// [`VERGEN_GIT_SEMVER_LIGHTWEIGHT`](https://docs.rs/vergen/latest/vergen/struct.Git.html#instructions)
+///  as a prototype name.
+///
+/// Returns `Some(prototype_name)` if the following conditions are met on this value:
+///
+/// 1. starts with `prototype-`,
+/// 2. ends with `-<some_number>`,
+/// 3. does not end with `<some_number>-<some_number>`.
+///
+/// Otherwise, returns `None`.
+pub fn prototype_name() -> Option<&'static str> {
+    let prototype: &'static str = option_env!("VERGEN_GIT_SEMVER_LIGHTWEIGHT")?;
+
+    if !prototype.starts_with("prototype-") {
+        return None;
+    }
+
+    let mut rsplit_prototype = prototype.rsplit('-');
+    // last component MUST be a number
+    rsplit_prototype.next()?.parse::<u64>().ok()?;
+    // before than last component SHALL NOT be a number
+    rsplit_prototype.next()?.parse::<u64>().err()?;
+
+    Some(prototype)
+}

meilisearch/src/main.rs

@@ -1,8 +1,8 @@
 use std::env;
-use std::io::{stderr, LineWriter, Write};
+use std::io::{stderr, Write};
 use std::path::PathBuf;
-use std::str::FromStr;
 use std::sync::Arc;
+use std::time::Duration;
 
 use actix_web::http::KeepAlive;
 use actix_web::web::Data;
@@ -10,81 +10,38 @@ use actix_web::HttpServer;
 use index_scheduler::IndexScheduler;
 use is_terminal::IsTerminal;
 use meilisearch::analytics::Analytics;
-use meilisearch::option::LogMode;
-use meilisearch::{
-    analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
-    LogStderrType, Opt, SubscriberForSecondLayer,
-};
+use meilisearch::{analytics, create_app, prototype_name, setup_meilisearch, Opt};
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
-use mimalloc::MiMalloc;
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
-use tracing::level_filters::LevelFilter;
-use tracing_subscriber::layer::SubscriberExt as _;
-use tracing_subscriber::Layer;
+use zookeeper::ZooKeeper;
 
 #[global_allocator]
-static ALLOC: MiMalloc = MiMalloc;
-
-fn default_log_route_layer() -> LogRouteType {
-    None.with_filter(tracing_subscriber::filter::Targets::new().with_target("", LevelFilter::OFF))
-}
-
-fn default_log_stderr_layer(opt: &Opt) -> LogStderrType {
-    let layer = tracing_subscriber::fmt::layer()
-        .with_writer(|| LineWriter::new(std::io::stderr()))
-        .with_span_events(tracing_subscriber::fmt::format::FmtSpan::CLOSE);
-
-    let layer = match opt.experimental_logs_mode {
-        LogMode::Human => Box::new(layer)
-            as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
-        LogMode::Json => Box::new(layer.json())
-            as Box<dyn tracing_subscriber::Layer<SubscriberForSecondLayer> + Send + Sync>,
-    };
-
-    layer.with_filter(
-        tracing_subscriber::filter::Targets::new()
-            .with_target("", LevelFilter::from_str(&opt.log_level.to_string()).unwrap()),
-    )
-}
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
 /// does all the setup before meilisearch is launched
-fn setup(opt: &Opt) -> anyhow::Result<(LogRouteHandle, LogStderrHandle)> {
-    let (route_layer, route_layer_handle) =
-        tracing_subscriber::reload::Layer::new(default_log_route_layer());
-    let route_layer: tracing_subscriber::reload::Layer<_, _> = route_layer;
+fn setup(opt: &Opt) -> anyhow::Result<()> {
+    let mut log_builder = env_logger::Builder::new();
+    log_builder.parse_filters(&opt.log_level.to_string());
 
-    let (stderr_layer, stderr_layer_handle) =
-        tracing_subscriber::reload::Layer::new(default_log_stderr_layer(opt));
-    let route_layer: tracing_subscriber::reload::Layer<_, _> = route_layer;
+    log_builder.init();
 
-    let subscriber = tracing_subscriber::registry().with(route_layer).with(stderr_layer);
-
-    // set the subscriber as the default for the application
-    tracing::subscriber::set_global_default(subscriber).unwrap();
-
-    Ok((route_layer_handle, stderr_layer_handle))
-}
-
-fn on_panic(info: &std::panic::PanicInfo) {
-    let info = info.to_string().replace('\n', " ");
-    tracing::error!(%info);
+    Ok(())
 }
 
 #[actix_web::main]
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
-    std::env::var("MEILI_LOUIS_PUSHOVER_USER").expect("MEILI_LOUIS_PUSHOVER_USER not set");
-    std::env::var("MEILI_LOUIS_PUSHOVER_APP").expect("MEILI_LOUIS_PUSHOVER_APP not set");
-
-    std::panic::set_hook(Box::new(on_panic));
+    #[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"
     );
 
-    let log_handle = setup(&opt)?;
+    setup(&opt)?;
 
     match (opt.env.as_ref(), &opt.master_key) {
         ("production", Some(master_key)) if master_key.len() < MASTER_KEY_MIN_SIZE => {
@@ -108,7 +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 {
@@ -122,7 +82,7 @@ async fn main() -> anyhow::Result<()> {
 
     print_launch_resume(&opt, analytics.clone(), config_read_from);
 
-    run_http(index_scheduler, auth_controller, opt, log_handle, analytics).await?;
+    run_http(index_scheduler, auth_controller, opt, analytics).await?;
 
     Ok(())
 }
@@ -131,7 +91,6 @@ async fn run_http(
     index_scheduler: Arc<IndexScheduler>,
     auth_controller: Arc<AuthController>,
     opt: Opt,
-    logs: (LogRouteHandle, LogStderrHandle),
     analytics: Arc<dyn Analytics>,
 ) -> anyhow::Result<()> {
     let enable_dashboard = &opt.env == "development";
@@ -144,7 +103,6 @@ async fn run_http(
             index_scheduler.clone(),
             auth_controller.clone(),
             opt.clone(),
-            logs.clone(),
             analytics.clone(),
             enable_dashboard,
         )
@@ -166,8 +124,8 @@ pub fn print_launch_resume(
     analytics: Arc<dyn Analytics>,
     config_read_from: Option<PathBuf>,
 ) {
-    let build_info = build_info::BuildInfo::from_build();
-
+    let commit_sha = option_env!("VERGEN_GIT_SHA").unwrap_or("unknown");
+    let commit_date = option_env!("VERGEN_GIT_COMMIT_TIMESTAMP").unwrap_or("unknown");
     let protocol =
         if opt.ssl_cert_path.is_some() && opt.ssl_key_path.is_some() { "https" } else { "http" };
     let ascii_name = r#"
@@ -192,18 +150,10 @@ pub fn print_launch_resume(
     eprintln!("Database path:\t\t{:?}", opt.db_path);
     eprintln!("Server listening on:\t\"{}://{}\"", protocol, opt.http_addr);
     eprintln!("Environment:\t\t{:?}", opt.env);
-    eprintln!("Commit SHA:\t\t{:?}", build_info.commit_sha1.unwrap_or("unknown"));
-    eprintln!(
-        "Commit date:\t\t{:?}",
-        build_info
-            .commit_timestamp
-            .and_then(|commit_timestamp| commit_timestamp
-                .format(&time::format_description::well_known::Rfc3339)
-                .ok())
-            .unwrap_or("unknown".into())
-    );
+    eprintln!("Commit SHA:\t\t{:?}", commit_sha.to_string());
+    eprintln!("Commit date:\t\t{:?}", commit_date.to_string());
     eprintln!("Package version:\t{:?}", env!("CARGO_PKG_VERSION").to_string());
-    if let Some(prototype) = build_info.describe.and_then(|describe| describe.as_prototype()) {
+    if let Some(prototype) = prototype_name() {
         eprintln!("Prototype:\t\t{:?}", prototype);
     }
 

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

@@ -1,3 +1,4 @@
+use std::convert::TryFrom;
 use std::env::VarError;
 use std::ffi::OsStr;
 use std::fmt::Display;
@@ -19,8 +20,7 @@ use rustls::server::{
 use rustls::RootCertStore;
 use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use serde::{Deserialize, Serialize};
-use sysinfo::{MemoryRefreshKind, RefreshKind, System};
-use url::Url;
+use sysinfo::{RefreshKind, System, SystemExt};
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
 
@@ -28,9 +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";
-const MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER: &str = "MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER";
-#[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";
@@ -50,19 +55,15 @@ const MEILI_IGNORE_MISSING_DUMP: &str = "MEILI_IGNORE_MISSING_DUMP";
 const MEILI_IGNORE_DUMP_IF_DB_EXISTS: &str = "MEILI_IGNORE_DUMP_IF_DB_EXISTS";
 const MEILI_DUMP_DIR: &str = "MEILI_DUMP_DIR";
 const MEILI_LOG_LEVEL: &str = "MEILI_LOG_LEVEL";
-const MEILI_EXPERIMENTAL_LOGS_MODE: &str = "MEILI_EXPERIMENTAL_LOGS_MODE";
-const MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS: &str = "MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS";
-const MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE: &str = "MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE";
 const MEILI_EXPERIMENTAL_ENABLE_METRICS: &str = "MEILI_EXPERIMENTAL_ENABLE_METRICS";
 const MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE: &str =
     "MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE";
-const MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS: &str =
-    "MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS";
 
 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;
@@ -80,39 +81,6 @@ const DEFAULT_LOG_EVERY_N: usize = 100_000;
 pub const INDEX_SIZE: u64 = 2 * 1024 * 1024 * 1024 * 1024; // 2 TiB
 pub const TASK_DB_SIZE: u64 = 20 * 1024 * 1024 * 1024; // 20 GiB
 
-#[derive(Debug, Default, Clone, Copy, Serialize, Deserialize)]
-#[serde(rename_all = "UPPERCASE")]
-pub enum LogMode {
-    #[default]
-    Human,
-    Json,
-}
-
-impl Display for LogMode {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self {
-            LogMode::Human => Display::fmt("HUMAN", f),
-            LogMode::Json => Display::fmt("JSON", f),
-        }
-    }
-}
-
-impl FromStr for LogMode {
-    type Err = LogModeError;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        match s.trim().to_lowercase().as_str() {
-            "human" => Ok(LogMode::Human),
-            "json" => Ok(LogMode::Json),
-            _ => Err(LogModeError(s.to_owned())),
-        }
-    }
-}
-
-#[derive(Debug, thiserror::Error)]
-#[error("Unsupported log mode level `{0}`. Supported values are `HUMAN` and `JSON`.")]
-pub struct LogModeError(String);
-
 #[derive(Debug, Default, Clone, Copy, Serialize, Deserialize)]
 #[serde(rename_all = "UPPERCASE")]
 pub enum LogLevel {
@@ -194,20 +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>,
 
-    /// The Authorization header to send on the webhook URL whenever a task finishes so a third party can be notified.
-    #[clap(long, env = MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER)]
-    pub task_webhook_authorization_header: 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,
@@ -344,40 +334,11 @@ pub struct Opt {
     #[serde(default)]
     pub experimental_enable_metrics: bool,
 
-    /// Experimental logs mode feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/723>
-    ///
-    /// Change the mode of the logs on the console.
-    #[clap(long, env = MEILI_EXPERIMENTAL_LOGS_MODE, default_value_t)]
-    #[serde(default)]
-    pub experimental_logs_mode: LogMode,
-
-    /// Experimental logs route feature. For more information, see: <https://github.com/orgs/meilisearch/discussions/721>
-    ///
-    /// Enables the log routes on the `POST /logs/stream`, `POST /logs/stderr` endpoints, and the `DELETE /logs/stream` to stop receiving logs.
-    #[clap(long, env = MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE)]
-    #[serde(default)]
-    pub experimental_enable_logs_route: bool,
-
-    /// Enable multiple features that helps you to run meilisearch in a replicated context.
-    /// For more information, see: <https://github.com/orgs/meilisearch/discussions/725>
-    ///
-    /// - /!\ Disable the automatic clean up of old processed tasks, you're in charge of that now
-    /// - Lets you specify a custom task ID upon registering a task
-    /// - Lets you execute dry-register a task (get an answer from the route but nothing is actually registered in meilisearch and it won't be processed)
-    #[clap(long, env = MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS)]
-    #[serde(default)]
-    pub experimental_replication_parameters: bool,
-
     /// Experimental RAM reduction during indexing, do not use in production, see: <https://github.com/meilisearch/product/discussions/652>
     #[clap(long, env = MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE)]
     #[serde(default)]
     pub experimental_reduce_indexing_memory_usage: bool,
 
-    /// Experimentally reduces the maximum number of tasks that will be processed at once, see: <https://github.com/orgs/meilisearch/discussions/713>
-    #[clap(long, env = MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS, default_value_t = default_limit_batched_tasks())]
-    #[serde(default = "default_limit_batched_tasks")]
-    pub experimental_max_number_of_batched_tasks: usize,
-
     #[serde(flatten)]
     #[clap(flatten)]
     pub indexer_options: IndexerOpts,
@@ -445,12 +406,16 @@ impl Opt {
             http_addr,
             master_key,
             env,
-            task_webhook_url,
-            task_webhook_authorization_header,
+            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,
-            experimental_max_number_of_batched_tasks,
             ssl_cert_path,
             ssl_key_path,
             ssl_auth_path,
@@ -470,13 +435,10 @@ 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,
-            experimental_logs_mode,
-            experimental_enable_logs_route,
-            experimental_replication_parameters,
-            experimental_reduce_indexing_memory_usage,
+            experimental_enable_metrics: enable_metrics_route,
+            experimental_reduce_indexing_memory_usage: reduce_indexing_memory_usage,
         } = self;
         export_to_env_if_not_present(MEILI_DB_PATH, db_path);
         export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -484,17 +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);
         }
-        if let Some(task_webhook_authorization_header) = task_webhook_authorization_header {
-            export_to_env_if_not_present(
-                MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER,
-                task_webhook_authorization_header,
-            );
+        if let Some(s3_url) = s3_url {
+            export_to_env_if_not_present(MEILI_S3_URL, s3_url);
         }
-
-        #[cfg(feature = "analytics")]
+        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());
         }
@@ -502,10 +473,6 @@ impl Opt {
             MEILI_HTTP_PAYLOAD_SIZE_LIMIT,
             http_payload_size_limit.to_string(),
         );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
-            experimental_max_number_of_batched_tasks.to_string(),
-        );
         if let Some(ssl_cert_path) = ssl_cert_path {
             export_to_env_if_not_present(MEILI_SSL_CERT_PATH, ssl_cert_path);
         }
@@ -530,23 +497,11 @@ impl Opt {
         export_to_env_if_not_present(MEILI_LOG_LEVEL, log_level.to_string());
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_ENABLE_METRICS,
-            experimental_enable_metrics.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_LOGS_MODE,
-            experimental_logs_mode.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_REPLICATION_PARAMETERS,
-            experimental_replication_parameters.to_string(),
-        );
-        export_to_env_if_not_present(
-            MEILI_EXPERIMENTAL_ENABLE_LOGS_ROUTE,
-            experimental_enable_logs_route.to_string(),
+            enable_metrics_route.to_string(),
         );
         export_to_env_if_not_present(
             MEILI_EXPERIMENTAL_REDUCE_INDEXING_MEMORY_USAGE,
-            experimental_reduce_indexing_memory_usage.to_string(),
+            reduce_indexing_memory_usage.to_string(),
         );
         indexer_options.export_to_env();
     }
@@ -598,10 +553,7 @@ impl Opt {
     }
 
     pub(crate) fn to_instance_features(&self) -> InstanceTogglableFeatures {
-        InstanceTogglableFeatures {
-            metrics: self.experimental_enable_metrics,
-            logs_route: self.experimental_enable_logs_route,
-        }
+        InstanceTogglableFeatures { metrics: self.experimental_enable_metrics }
     }
 }
 
@@ -659,7 +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()
@@ -710,8 +662,8 @@ impl MaxMemory {
 
 /// Returns the total amount of bytes available or `None` if this system isn't supported.
 fn total_memory_bytes() -> Option<u64> {
-    if sysinfo::IS_SUPPORTED_SYSTEM {
-        let memory_kind = RefreshKind::new().with_memory(MemoryRefreshKind::new().with_ram());
+    if System::IS_SUPPORTED {
+        let memory_kind = RefreshKind::new().with_memory();
         let mut system = System::new_with_specifics(memory_kind);
         system.refresh_memory();
         Some(system.total_memory())
@@ -827,6 +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)
 }
@@ -839,10 +795,6 @@ fn default_http_payload_size_limit() -> Byte {
     Byte::from_str(DEFAULT_HTTP_PAYLOAD_SIZE_LIMIT).unwrap()
 }
 
-fn default_limit_batched_tasks() -> usize {
-    usize::MAX
-}
-
 fn default_snapshot_dir() -> PathBuf {
     PathBuf::from(DEFAULT_SNAPSHOT_DIR)
 }

meilisearch/src/routes/api_key.rs

@@ -10,7 +10,7 @@ use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{Code, ResponseError};
-use meilisearch_types::keys::{CreateApiKey, Key, PatchApiKey};
+use meilisearch_types::keys::{Action, CreateApiKey, Key, PatchApiKey};
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
 use uuid::Uuid;
@@ -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())
 }