Disable autobatching of additions and deletions

3623: Update mini-dashboard to version v0.2.7 r=curquiza a=bidoubiwa

## Changes

* Retrieve the API Key from the url parameters (#416) `@qdequele`

## 🐛 Bug Fixes

* Fix show more button not displaying all fields (#419) `@bidoubiwa`

Thanks again to `@bidoubiwa,`     and `@qdequele!` 🎉


Co-authored-by: Charlotte Vermandel <charlottevermandel@gmail.com>

.github/uffizzi/Dockerfile

@@ -1,24 +1,3 @@
-# Compile
-FROM    rust:alpine3.16 AS compiler
-
-RUN     apk add -q --update-cache --no-cache build-base openssl-dev
-
-WORKDIR /meilisearch
-
-ARG     COMMIT_SHA
-ARG     COMMIT_DATE
-ARG     GIT_TAG
-ENV     COMMIT_SHA=${COMMIT_SHA} COMMIT_DATE=${COMMIT_DATE} VERGEN_GIT_SEMVER_LIGHTWEIGHT=${GIT_TAG}
-ENV     RUSTFLAGS="-C target-feature=-crt-static"
-
-COPY    . .
-RUN     set -eux; \
-        apkArch="$(apk --print-arch)"; \
-        if [ "$apkArch" = "aarch64" ]; then \
-            export JEMALLOC_SYS_WITH_LG_PAGE=16; \
-        fi && \
-        cargo build --release
-
 # Run
 FROM    uffizzi/ttyd:alpine
 
@@ -29,19 +8,11 @@ ENV     MEILI_NO_ANALYTICS true
 RUN     apk update --quiet \
         && apk add -q --no-cache libgcc tini curl
 
-# 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`
+COPY    target/x86_64-unknown-linux-musl/release/meilisearch /bin/meilisearch
 RUN     ln -s /bin/meilisearch /meilisearch
 
-# This directory should hold all the data related to meilisearch so we're going
-# to move our PWD in there.
-# We don't want to put the meilisearch binary
 WORKDIR /meili_data
 
-
 EXPOSE  7700/tcp
 
 ENTRYPOINT ["tini", "--"]

.github/workflows/publish-binaries.yml

@@ -96,14 +96,12 @@ jobs:
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
-    runs-on: ${{ matrix.os }}
+    runs-on: macos-12
     needs: check-version
     strategy:
-      fail-fast: false
       matrix:
         include:
-          - os: macos-12
-            target: aarch64-apple-darwin
+          - target: aarch64-apple-darwin
             asset_name: meilisearch-macos-apple-silicon
     steps:
       - name: Checkout repository
@@ -132,21 +130,29 @@ jobs:
 
   publish-aarch64:
     name: Publish binary for aarch64
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-latest
     needs: check-version
+    container:
+      # Use ubuntu-18.04 to compile with glibc 2.27
+      image: ubuntu:18.04
     strategy:
-      fail-fast: false
       matrix:
         include:
-          - build: aarch64
-            os: ubuntu-18.04
-            target: aarch64-unknown-linux-gnu
-            linker: gcc-aarch64-linux-gnu
-            use-cross: true
+          - target: aarch64-unknown-linux-gnu
             asset_name: meilisearch-linux-aarch64
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
+      - name: Install needed dependencies
+        run: |
+          apt-get update -y && apt upgrade -y
+          apt-get install -y curl build-essential gcc-aarch64-linux-gnu
+      - name: Set up Docker for cross compilation
+        run: |
+          apt-get install -y curl apt-transport-https ca-certificates software-properties-common
+          curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+          add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
+          apt-get update -y && apt-get install -y docker-ce
       - name: Installing Rust toolchain
         uses: actions-rs/toolchain@v1
         with:
@@ -154,15 +160,7 @@ jobs:
           profile: minimal
           target: ${{ matrix.target }}
           override: true
-      - name: APT update
-        run: |
-          sudo apt update
-      - name: Install target specific tools
-        if: matrix.use-cross
-        run: |
-          sudo apt-get install -y ${{ matrix.linker }}
       - name: Configure target aarch64 GNU
-        if: matrix.target == 'aarch64-unknown-linux-gnu'
         ## Environment variable is not passed using env:
         ## LD gold won't work with MUSL
         # env:
@@ -176,8 +174,10 @@ jobs:
         uses: actions-rs/cargo@v1
         with:
           command: build
-          use-cross: ${{ matrix.use-cross }}
+          use-cross: true
           args: --release --target ${{ matrix.target }}
+        env:
+          CROSS_DOCKER_IN_DOCKER: true
       - name: List target output files
         run: ls -lR ./target
       - name: Upload the binary to release

.github/workflows/uffizzi-build.yml

@@ -14,6 +14,26 @@ jobs:
       - name: checkout
         uses: actions/checkout@v3
 
+      - run: sudo apt-get install musl-tools
+
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
+          target: x86_64-unknown-linux-musl
+
+      - name: Cache dependencies
+        uses: Swatinem/rust-cache@v2.2.0
+
+      - name: Run cargo check without any default features
+        uses: actions-rs/cargo@v1
+        with:
+          command: build
+          args: --target x86_64-unknown-linux-musl --release 
+      
+      - name: Remove dockerignore so we can use the target folder in our docker build
+        run: rm -f .dockerignore
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
 

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

@@ -82,7 +82,7 @@ jobs:
     name: Use Remote Workflow to Preview on Uffizzi
     needs:
       - cache-compose-file
-    uses: UffizziCloud/preview-action/.github/workflows/reusable.yaml@desc
+    uses: UffizziCloud/preview-action/.github/workflows/reusable.yaml@v2
     with:
       # If this workflow was triggered by a PR close event, cache-key will be an empty string
       # and this reusable workflow will delete the preview deployment.
@@ -95,8 +95,8 @@ jobs:
         `meilisearch` command. You should be able to access this instance of meilisearch running in
         the preview from the link Meilisearch Endpoint link given below.
          
-        Web Terminal Endpoint : ${{ needs.cache-compose-file.outputs.expected-url }}
-        Meilisearch Endpoint : ${{ needs.cache-compose-file.outputs.expected-url }}/meilisearch
+        Web Terminal Endpoint : <uffizzi-url>
+        Meilisearch Endpoint : <uffizzi-url>/meilisearch
     permissions:
       contents: read
       pull-requests: write

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

@@ -1,4 +1,4 @@
-name: Update Meilisearch version in all Cargo.toml files
+name: Update Meilisearch version in Cargo.toml
 
 on:
   workflow_dispatch:
@@ -14,7 +14,7 @@ env:
 
 jobs:
   update-version-cargo-toml:
-    name: Update version in Cargo.toml files
+    name: Update version in Cargo.toml
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
@@ -25,7 +25,7 @@ jobs:
           override: true
       - name: Install sd
         run: cargo install sd
-      - name: Update Cargo.toml files
+      - name: Update Cargo.toml file
         run: |
           raw_new_version=$(echo $NEW_VERSION | cut -d 'v' -f 2)
           new_string="version = \"$raw_new_version\""
@@ -35,13 +35,13 @@ jobs:
       - name: Commit and push the changes to the ${{ env.NEW_BRANCH }} branch
         uses: EndBug/add-and-commit@v9
         with:
-          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml files"
+          message: "Update version for the next release (${{ env.NEW_VERSION }}) in Cargo.toml"
           new_branch: ${{ env.NEW_BRANCH }}
       - name: Create the PR pointing to ${{ github.ref_name }}
         run: |
           gh pr create \
-            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml files" \
-            --body '⚠️ This PR is automatically generated. Check the new version is the expected one before merging.' \
+            --title "Update version for the next release ($NEW_VERSION) in Cargo.toml" \
+            --body '⚠️ This PR is automatically generated. Check the new version is the expected one and Cargo.lock has been updated before merging.' \
             --label 'skip changelog' \
             --milestone $NEW_VERSION \
             --base $GITHUB_REF_NAME

Cargo.lock

@@ -410,7 +410,7 @@ checksum = "b645a089122eccb6111b4f81cbc1a49f5900ac4666bb93ac027feaecf15607bf"
 
 [[package]]
 name = "benchmarks"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "anyhow",
  "bytes",
@@ -517,12 +517,6 @@ dependencies = [
  "serde",
 ]
 
-[[package]]
-name = "build_const"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4ae4235e6dac0694637c763029ecea1a2ec9e4e06ec2729bd21ba4d9c863eb7"
-
 [[package]]
 name = "bumpalo"
 version = "3.11.1"
@@ -659,16 +653,19 @@ dependencies = [
 
 [[package]]
 name = "charabia"
-version = "0.7.0"
+version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b57f9571f611796ea38e5a9c12e5ce37476f70397b032757f8dfe0c7b9bc5637"
+checksum = "1ad3d9667a6b4e03813162c22c4d58235c2dc25d580d60837ce29199038341c9"
 dependencies = [
  "cow-utils",
  "csv",
  "deunicode",
  "fst",
+ "irg-kvariants",
  "jieba-rs",
  "lindera",
+ "lindera-ipadic",
+ "lindera-ko-dic",
  "once_cell",
  "pinyin",
  "serde",
@@ -721,14 +718,9 @@ version = "3.2.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "71655c45cb9845d3270c9d6df84ebe72b4dad3c2ba3f7023ad47c144e4e473a5"
 dependencies = [
- "atty",
  "bitflags",
- "clap_derive 3.2.18",
  "clap_lex 0.2.4",
  "indexmap",
- "once_cell",
- "strsim",
- "termcolor",
  "textwrap",
 ]
 
@@ -739,7 +731,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a7db700bc935f9e43e88d00b0850dae18a63773cfbec6d8e070fccf7fef89a39"
 dependencies = [
  "bitflags",
- "clap_derive 4.0.21",
+ "clap_derive",
  "clap_lex 0.3.0",
  "is-terminal",
  "once_cell",
@@ -747,19 +739,6 @@ dependencies = [
  "termcolor",
 ]
 
-[[package]]
-name = "clap_derive"
-version = "3.2.18"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ea0c8bce528c4be4da13ea6fead8965e95b6073585a2f05204bd8f4119f82a65"
-dependencies = [
- "heck",
- "proc-macro-error",
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "clap_derive"
 version = "4.0.21"
@@ -873,15 +852,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "crc"
-version = "1.8.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d663548de7f5cca343f1e0a48d14dcfb0e9eb4e079ec58883b7251539fa10aeb"
-dependencies = [
- "build_const",
-]
-
 [[package]]
 name = "crc32fast"
 version = "1.3.2"
@@ -1180,7 +1150,7 @@ dependencies = [
 
 [[package]]
 name = "dump"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1333,6 +1303,19 @@ dependencies = [
  "termcolor",
 ]
 
+[[package]]
+name = "env_logger"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85cdab6a89accf66733ad5a1693a4dcced6aeff64602b634530dd73c1f3ee9f0"
+dependencies = [
+ "humantime",
+ "is-terminal",
+ "log",
+ "regex",
+ "termcolor",
+]
+
 [[package]]
 name = "errno"
 version = "0.2.8"
@@ -1388,7 +1371,7 @@ dependencies = [
 
 [[package]]
 name = "file-store"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "faux",
  "tempfile",
@@ -1410,7 +1393,7 @@ dependencies = [
 
 [[package]]
 name = "filter-parser"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "insta",
  "nom",
@@ -1430,7 +1413,7 @@ dependencies = [
 
 [[package]]
 name = "flatten-serde-json"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -1907,7 +1890,7 @@ dependencies = [
 
 [[package]]
 name = "index-scheduler"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "anyhow",
  "big_s",
@@ -1921,6 +1904,7 @@ dependencies = [
  "insta",
  "log",
  "meili-snap",
+ "meilisearch-auth",
  "meilisearch-types",
  "nelson",
  "page_size 0.5.0",
@@ -1986,6 +1970,17 @@ version = "2.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "30e22bd8629359895450b59ea7a776c850561b96a3b1d31321c1949d9e6c9146"
 
+[[package]]
+name = "irg-kvariants"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c73214298363629cf9dbfc93b426808865ee3c121029778cb31b1284104fdf78"
+dependencies = [
+ "csv",
+ "once_cell",
+ "serde",
+]
+
 [[package]]
 name = "is-terminal"
 version = "0.4.2"
@@ -2054,7 +2049,7 @@ dependencies = [
 
 [[package]]
 name = "json-depth-checker"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "criterion",
  "serde_json",
@@ -2074,6 +2069,15 @@ dependencies = [
  "simple_asn1",
 ]
 
+[[package]]
+name = "kanaria"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0f9d9652540055ac4fded998a73aca97d965899077ab1212587437da44196ff"
+dependencies = [
+ "bitflags",
+]
+
 [[package]]
 name = "language-tags"
 version = "0.3.2"
@@ -2143,14 +2147,15 @@ dependencies = [
 
 [[package]]
 name = "lindera"
-version = "0.17.0"
+version = "0.21.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "082ca91ac4d1557028ace9bfb8cee1500d156a4574dda93cfcdcf4caaebb9bd7"
+checksum = "0f33a20bb9cbf95572b2d2f40d7040c8d8c7ad09ae20e1f6513db6ef2564dfc5"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
  "encoding",
+ "kanaria",
  "lindera-cc-cedict-builder",
  "lindera-core",
  "lindera-dictionary",
@@ -2159,24 +2164,27 @@ dependencies = [
  "lindera-ko-dic",
  "lindera-ko-dic-builder",
  "lindera-unidic-builder",
+ "regex",
  "serde",
  "serde_json",
  "thiserror",
+ "unicode-blocks",
+ "unicode-normalization",
+ "yada",
 ]
 
 [[package]]
 name = "lindera-cc-cedict-builder"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a8967615a6d85320ec2755e1435c36165467ba01a79026adc3f86dad1b668df3"
+checksum = "60c3b379251edadbac7a5fdb31e482274e11dae6ab6cc789d0d86cf34369cf49"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
- "clap 3.2.23",
  "csv",
  "encoding",
- "env_logger",
+ "env_logger 0.10.0",
  "glob",
  "lindera-core",
  "lindera-decompress",
@@ -2185,16 +2193,28 @@ dependencies = [
 ]
 
 [[package]]
-name = "lindera-core"
-version = "0.17.0"
+name = "lindera-compress"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0e8ed3cea13f73557a4574a179b1518670a3b70bfdad120521313b03cc89380e"
+checksum = "a8d0ea3de5625e2381cac94e518d3b56103fde56bc0dce840fe875c1e871b125"
+dependencies = [
+ "anyhow",
+ "flate2",
+ "lindera-decompress",
+]
+
+[[package]]
+name = "lindera-core"
+version = "0.21.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2281747b98fdd46bcc54ce7fdb6870dad9f67ddb3dc086c47b6704f3e1178cd5"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
  "encoding_rs",
  "log",
+ "once_cell",
  "serde",
  "thiserror",
  "yada",
@@ -2202,20 +2222,20 @@ dependencies = [
 
 [[package]]
 name = "lindera-decompress"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2badb41828f89cfa6452db0a66da77897c0a04478304de26c8b2b36613e08d43"
+checksum = "52101bd454754c506305ab897af5ac2ae41fe91e3272c1ff5c6a02a089dfaefd"
 dependencies = [
  "anyhow",
- "lzma-rs",
+ "flate2",
  "serde",
 ]
 
 [[package]]
 name = "lindera-dictionary"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e219722c9f56b920c231210e7c25d8b5d35b508e7a2fd69d368916c4b1c926f6"
+checksum = "af1c6668848f1d30d216c99093a3ed3fe125c105fa12a4aeed5a1861dc01dd52"
 dependencies = [
  "anyhow",
  "bincode",
@@ -2225,15 +2245,16 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c8e87c8362c724e8188fb7d9b6d184cac15d01369295e9bff7812b630d57e3b"
+checksum = "693098007200fa43fd5cdc9ca8740f371327369672ce812cd87a1f6344971e31"
 dependencies = [
  "bincode",
  "byteorder",
  "encoding",
  "flate2",
  "lindera-core",
+ "lindera-decompress",
  "lindera-ipadic-builder",
  "once_cell",
  "tar",
@@ -2241,19 +2262,19 @@ dependencies = [
 
 [[package]]
 name = "lindera-ipadic-builder"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1439e95852e444a116424086dc64d709c90e8af269ff7d2c2c4020f666f8dfab"
+checksum = "7b6b7240d097a8fc37ee8f90ebff02c4db0ba5325ecb0dacb6da3724596798c9"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
- "clap 3.2.23",
  "csv",
  "encoding_rs",
  "encoding_rs_io",
- "env_logger",
+ "env_logger 0.10.0",
  "glob",
+ "lindera-compress",
  "lindera-core",
  "lindera-decompress",
  "log",
@@ -2263,15 +2284,16 @@ dependencies = [
 
 [[package]]
 name = "lindera-ko-dic"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb15f949220da45872d774b7831bb030855ec083435c907499782f8558c8a203"
+checksum = "abd3c5a4addeb61ca66788a3dd1fd51093e6cd8fea1d997042ada5aa60e8cc5e"
 dependencies = [
  "bincode",
  "byteorder",
  "encoding",
  "flate2",
  "lindera-core",
+ "lindera-decompress",
  "lindera-ko-dic-builder",
  "once_cell",
  "tar",
@@ -2279,18 +2301,18 @@ dependencies = [
 
 [[package]]
 name = "lindera-ko-dic-builder"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fde5a7352f4754be4f741e90bf4dff38a12a6572ab3880d0cf688e1166b8d82b"
+checksum = "512bb1393a9281e0b13704319d1343b7931416865852d9d7b7c0178431518326"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
- "clap 3.2.23",
  "csv",
  "encoding",
- "env_logger",
+ "env_logger 0.10.0",
  "glob",
+ "lindera-compress",
  "lindera-core",
  "lindera-decompress",
  "log",
@@ -2299,17 +2321,16 @@ dependencies = [
 
 [[package]]
 name = "lindera-unidic-builder"
-version = "0.17.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1451b2ed8a7184a5f815d84f99d358c1d67297305831453dfdc0eb5d08e22b5"
+checksum = "7f575a27f8ba67c15fe16ebf7d277a0ac04e8c8a0f72670ebc2443da9d41c450"
 dependencies = [
  "anyhow",
  "bincode",
  "byteorder",
- "clap 3.2.23",
  "csv",
  "encoding",
- "env_logger",
+ "env_logger 0.10.0",
  "glob",
  "lindera-core",
  "lindera-decompress",
@@ -2398,16 +2419,6 @@ dependencies = [
  "syn",
 ]
 
-[[package]]
-name = "lzma-rs"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aba8ecb0450dfabce4ad72085eed0a75dffe8f21f7ada05638564ea9db2d7fb1"
-dependencies = [
- "byteorder",
- "crc",
-]
-
 [[package]]
 name = "manifest-dir-macros"
 version = "0.1.16"
@@ -2434,7 +2445,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
 
 [[package]]
 name = "meili-snap"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "insta",
  "md5",
@@ -2443,7 +2454,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -2466,7 +2477,7 @@ dependencies = [
  "deserr",
  "dump",
  "either",
- "env_logger",
+ "env_logger 0.9.3",
  "file-store",
  "flate2",
  "fst",
@@ -2531,7 +2542,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-auth"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "base64 0.13.1",
  "enum-iterator",
@@ -2550,7 +2561,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "actix-web",
  "anyhow",
@@ -2604,7 +2615,7 @@ dependencies = [
 
 [[package]]
 name = "milli"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "big_s",
  "bimap",
@@ -2958,7 +2969,7 @@ checksum = "478c572c3d73181ff3c2539045f6eb99e5491218eae919370993b890cdbdd98e"
 
 [[package]]
 name = "permissive-json-pointer"
-version = "1.0.0"
+version = "1.1.0"
 dependencies = [
  "big_s",
  "serde_json",
@@ -4011,6 +4022,12 @@ version = "0.3.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "099b7128301d285f79ddd55b9a83d5e6b9e97c92e0ea0daebee7263e932de992"
 
+[[package]]
+name = "unicode-blocks"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9de2be6bad6f56ce8373d377e611cbb2265de3a656138065609ce82e217aad70"
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.6"

Cargo.toml

@@ -17,7 +17,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.0.0"
+version = "1.1.0"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

benchmarks/benches/formatting.rs

@@ -29,7 +29,7 @@ fn bench_formatting(c: &mut criterion::Criterion) {
 	            (vec![Rc::new(MatchingWord::new("thedoord".to_string(), 1, true).unwrap())], vec![0, 1, 2]),
 	            (vec![Rc::new(MatchingWord::new("doord".to_string(), 1, true).unwrap())], vec![1, 2]),
         	]
-            ), TokenizerBuilder::default().build()),
+            ).unwrap(), TokenizerBuilder::default().build()),
 		},
     ];
 

config.toml

@@ -118,3 +118,13 @@ ssl_resumption = false
 ssl_tickets = false
 # Activates SSL tickets.
 # https://docs.meilisearch.com/learn/configuration/instance_options.html#ssl-tickets
+
+#############################
+### Experimental features ###
+#############################
+
+experimental_enable_metrics = false
+# Experimental metrics feature. For more information, see: <https://github.com/meilisearch/meilisearch/discussions/3518>
+# Enables the Prometheus metrics on the `GET /metrics` endpoint.
+
+

file-store/src/lib.rs

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

filter-parser/src/lib.rs

@@ -141,7 +141,7 @@ pub enum FilterCondition<'a> {
     Or(Vec<Self>),
     And(Vec<Self>),
     GeoLowerThan { point: [Token<'a>; 2], radius: Token<'a> },
-    GeoBoundingBox { top_left_point: [Token<'a>; 2], bottom_right_point: [Token<'a>; 2] },
+    GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] },
 }
 
 impl<'a> FilterCondition<'a> {
@@ -362,8 +362,8 @@ fn parse_geo_bounding_box(input: Span) -> IResult<FilterCondition> {
     }
 
     let res = FilterCondition::GeoBoundingBox {
-        top_left_point: [args[0][0].into(), args[0][1].into()],
-        bottom_right_point: [args[1][0].into(), args[1][1].into()],
+        top_right_point: [args[0][0].into(), args[0][1].into()],
+        bottom_left_point: [args[1][0].into(), args[1][1].into()],
     };
     Ok((input, res))
 }
@@ -780,7 +780,10 @@ impl<'a> std::fmt::Display for FilterCondition<'a> {
             FilterCondition::GeoLowerThan { point, radius } => {
                 write!(f, "_geoRadius({}, {}, {})", point[0], point[1], radius)
             }
-            FilterCondition::GeoBoundingBox { top_left_point, bottom_right_point } => {
+            FilterCondition::GeoBoundingBox {
+                top_right_point: top_left_point,
+                bottom_left_point: bottom_right_point,
+            } => {
                 write!(
                     f,
                     "_geoBoundingBox([{}, {}], [{}, {}])",

index-scheduler/Cargo.toml

@@ -19,6 +19,7 @@ dump = { path = "../dump" }
 enum-iterator = "1.1.3"
 file-store = { path = "../file-store" }
 log = "0.4.14"
+meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
 roaring = { version = "0.10.0", features = ["serde"] }

index-scheduler/src/autobatcher.rs

@@ -311,18 +311,9 @@ impl BatchKind {
                 })
             }
             (
-                BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
+                this @ BatchKind::DocumentOperation { .. },
                 K::DocumentDeletion,
-            ) => {
-                operation_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids,
-                })
-            }
+            ) => Break(this),
             // but we can't autobatch documents if it's not the same kind
             // this match branch MUST be AFTER the previous one
             (
@@ -345,35 +336,7 @@ impl BatchKind {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentClear { ids: deletion_ids })
             }
-            // we can autobatch the deletion and import if the index already exists
-            (
-                BatchKind::DocumentDeletion { mut deletion_ids },
-                K::DocumentImport { method, allow_index_creation, primary_key }
-            ) if index_already_exists => {
-                deletion_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids: deletion_ids,
-                })
-            }
-            // we can autobatch the deletion and import if both can't create an index
-            (
-                BatchKind::DocumentDeletion { mut deletion_ids },
-                K::DocumentImport { method, allow_index_creation, primary_key }
-            ) if !allow_index_creation => {
-                deletion_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids: deletion_ids,
-                })
-            }
-            // we can't autobatch a deletion and an import if the index does not exists but would be created by an addition
+            // we can't autobatch a deletion and an import
             (
                 this @ BatchKind::DocumentDeletion { .. },
                 K::DocumentImport { .. }
@@ -674,36 +637,36 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
 
-        // We can autobatch document addition with document deletion
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        // And the other way around
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
+        // We can't autobatch document addition with document deletion
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        // we also can't do the only way around
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
     }
 
     #[test]

index-scheduler/src/batch.rs

@@ -675,9 +675,6 @@ impl IndexScheduler {
                 }
 
                 // 3. Snapshot every indexes
-                // TODO we are opening all of the indexes it can be too much we should unload all
-                //      of the indexes we are trying to open. It would be even better to only unload
-                //      the ones that were opened by us. Or maybe use a LRU in the index mapper.
                 for result in self.index_mapper.index_mapping.iter(&rtxn)? {
                     let (name, uuid) = result?;
                     let index = self.index_mapper.index(&rtxn, name)?;
@@ -714,6 +711,14 @@ impl IndexScheduler {
                 // 5.3 Change the permission to make the snapshot readonly
                 let mut permissions = file.metadata()?.permissions();
                 permissions.set_readonly(true);
+                #[cfg(unix)]
+                {
+                    use std::os::unix::fs::PermissionsExt;
+                    #[allow(clippy::non_octal_unix_permissions)]
+                    //                     rwxrwxrwx
+                    permissions.set_mode(0b100100100);
+                }
+
                 file.set_permissions(permissions)?;
 
                 for task in &mut tasks {
@@ -788,15 +793,15 @@ impl IndexScheduler {
                 dump_tasks.flush()?;
 
                 // 3. Dump the indexes
-                for (uid, index) in self.index_mapper.indexes(&rtxn)? {
+                self.index_mapper.try_for_each_index(&rtxn, |uid, index| -> Result<()> {
                     let rtxn = index.read_txn()?;
                     let metadata = IndexMetadata {
-                        uid: uid.clone(),
+                        uid: uid.to_owned(),
                         primary_key: index.primary_key(&rtxn)?.map(String::from),
                         created_at: index.created_at(&rtxn)?,
                         updated_at: index.updated_at(&rtxn)?,
                     };
-                    let mut index_dumper = dump.create_index(&uid, &metadata)?;
+                    let mut index_dumper = dump.create_index(uid, &metadata)?;
 
                     let fields_ids_map = index.fields_ids_map(&rtxn)?;
                     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
@@ -809,9 +814,10 @@ impl IndexScheduler {
                     }
 
                     // 3.2. Dump the settings
-                    let settings = meilisearch_types::settings::settings(&index, &rtxn)?;
+                    let settings = meilisearch_types::settings::settings(index, &rtxn)?;
                     index_dumper.settings(&settings)?;
-                }
+                    Ok(())
+                })?;
 
                 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]"
@@ -827,20 +833,38 @@ impl IndexScheduler {
                 Ok(vec![task])
             }
             Batch::IndexOperation { op, must_create_index } => {
-                let index_uid = op.index_uid();
+                let index_uid = op.index_uid().to_string();
                 let index = if must_create_index {
                     // create the index if it doesn't already exist
                     let wtxn = self.env.write_txn()?;
-                    self.index_mapper.create_index(wtxn, index_uid, None)?
+                    self.index_mapper.create_index(wtxn, &index_uid, None)?
                 } else {
                     let rtxn = self.env.read_txn()?;
-                    self.index_mapper.index(&rtxn, index_uid)?
+                    self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
                 let mut index_wtxn = index.write_txn()?;
                 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
+                // stats of the index. Since the tasks have already been processed and
+                // this is a non-critical operation. If it fails, we should not fail
+                // the entire batch.
+                let res = || -> Result<()> {
+                    let index_rtxn = index.read_txn()?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    let mut wtxn = self.env.write_txn()?;
+                    self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
+                    wtxn.commit()?;
+                    Ok(())
+                }();
+
+                match res {
+                    Ok(_) => (),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
+                }
+
                 Ok(tasks)
             }
             Batch::IndexCreation { index_uid, primary_key, task } => {
@@ -871,9 +895,31 @@ impl IndexScheduler {
                     )?;
                     index_wtxn.commit()?;
                 }
+
+                // drop rtxn before starting a new wtxn on the same db
+                rtxn.commit()?;
+
                 task.status = Status::Succeeded;
                 task.details = Some(Details::IndexInfo { primary_key });
 
+                // if the update processed successfully, we're going to store the new
+                // stats of the index. Since the tasks have already been processed and
+                // this is a non-critical operation. If it fails, we should not fail
+                // the entire batch.
+                let res = || -> Result<()> {
+                    let mut wtxn = self.env.write_txn()?;
+                    let index_rtxn = index.read_txn()?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
+                    wtxn.commit()?;
+                    Ok(())
+                }();
+
+                match res {
+                    Ok(_) => (),
+                    Err(e) => error!("Could not write the stats of the index {}", e),
+                }
+
                 Ok(vec![task])
             }
             Batch::IndexDeletion { index_uid, index_has_been_created, mut tasks } => {

index-scheduler/src/index_mapper.rs

@@ -1,362 +0,0 @@
-use std::collections::hash_map::Entry;
-use std::collections::HashMap;
-use std::path::{Path, PathBuf};
-use std::sync::{Arc, RwLock};
-use std::{fs, thread};
-
-use log::error;
-use meilisearch_types::heed::types::Str;
-use meilisearch_types::heed::{Database, Env, EnvOpenOptions, RoTxn, RwTxn};
-use meilisearch_types::milli::update::IndexerConfig;
-use meilisearch_types::milli::Index;
-use synchronoise::SignalEvent;
-use time::OffsetDateTime;
-use uuid::Uuid;
-
-use self::IndexStatus::{Available, BeingDeleted, BeingResized};
-use crate::uuid_codec::UuidCodec;
-use crate::{clamp_to_page_size, Error, Result};
-
-const INDEX_MAPPING: &str = "index-mapping";
-
-/// Structure managing meilisearch's indexes.
-///
-/// It is responsible for:
-/// 1. Creating new indexes
-/// 2. Opening indexes and storing references to these opened indexes
-/// 3. Accessing indexes through their uuid
-/// 4. Mapping a user-defined name to each index uuid.
-#[derive(Clone)]
-pub struct IndexMapper {
-    /// Keep track of the opened indexes. Used mainly by the index resolver.
-    index_map: Arc<RwLock<HashMap<Uuid, IndexStatus>>>,
-
-    /// Map an index name with an index uuid currently available on disk.
-    pub(crate) index_mapping: Database<Str, UuidCodec>,
-
-    /// Path to the folder where the LMDB environments of each index are.
-    base_path: PathBuf,
-    index_size: usize,
-    pub indexer_config: Arc<IndexerConfig>,
-}
-
-/// Whether the index is available for use or is forbidden to be inserted back in the index map
-#[allow(clippy::large_enum_variant)]
-#[derive(Clone)]
-pub enum IndexStatus {
-    /// Do not insert it back in the index map as it is currently being deleted.
-    BeingDeleted,
-    /// Temporarily do not insert the index in the index map as it is currently being resized.
-    BeingResized(Arc<SignalEvent>),
-    /// You can use the index without worrying about anything.
-    Available(Index),
-}
-
-impl IndexMapper {
-    pub fn new(
-        env: &Env,
-        base_path: PathBuf,
-        index_size: usize,
-        indexer_config: IndexerConfig,
-    ) -> Result<Self> {
-        Ok(Self {
-            index_map: Arc::default(),
-            index_mapping: env.create_database(Some(INDEX_MAPPING))?,
-            base_path,
-            index_size,
-            indexer_config: Arc::new(indexer_config),
-        })
-    }
-
-    /// Create or open an index in the specified path.
-    /// The path *must* exists or an error will be thrown.
-    fn create_or_open_index(
-        &self,
-        path: &Path,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-        map_size: usize,
-    ) -> Result<Index> {
-        let mut options = EnvOpenOptions::new();
-        options.map_size(clamp_to_page_size(map_size));
-        options.max_readers(1024);
-
-        if let Some((created, updated)) = date {
-            Ok(Index::new_with_creation_dates(options, path, created, updated)?)
-        } else {
-            Ok(Index::new(options, path)?)
-        }
-    }
-
-    /// Get or create the index.
-    pub fn create_index(
-        &self,
-        mut wtxn: RwTxn,
-        name: &str,
-        date: Option<(OffsetDateTime, OffsetDateTime)>,
-    ) -> Result<Index> {
-        match self.index(&wtxn, name) {
-            Ok(index) => {
-                wtxn.commit()?;
-                Ok(index)
-            }
-            Err(Error::IndexNotFound(_)) => {
-                let uuid = Uuid::new_v4();
-                self.index_mapping.put(&mut wtxn, name, &uuid)?;
-
-                let index_path = self.base_path.join(uuid.to_string());
-                fs::create_dir_all(&index_path)?;
-
-                let index = self.create_or_open_index(&index_path, date, self.index_size)?;
-
-                wtxn.commit()?;
-                // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
-                // This is very unlikely to happen in practice.
-                // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                if self.index_map.write().unwrap().insert(uuid, Available(index.clone())).is_some()
-                {
-                    panic!("Uuid v4 conflict: index with UUID {uuid} already exists.");
-                }
-
-                Ok(index)
-            }
-            error => error,
-        }
-    }
-
-    /// Removes the index from the mapping table and the in-memory index map
-    /// but keeps the associated tasks.
-    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
-        let uuid = self
-            .index_mapping
-            .get(&wtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // Once we retrieved the UUID of the index we remove it from the mapping table.
-        assert!(self.index_mapping.delete(&mut wtxn, name)?);
-
-        wtxn.commit()?;
-        // We remove the index from the in-memory index map.
-        let closing_event = loop {
-            let mut lock = self.index_map.write().unwrap();
-            let resize_operation = match lock.insert(uuid, BeingDeleted) {
-                Some(Available(index)) => break Some(index.prepare_for_closing()),
-                // The target index is in the middle of a resize operation.
-                // Wait for this operation to complete, then try again.
-                Some(BeingResized(resize_operation)) => resize_operation.clone(),
-                // The index is already being deleted or doesn't exist.
-                // It's OK to remove it from the map again.
-                _ => break None,
-            };
-
-            // Avoiding deadlocks: we need to drop the lock before waiting for the end of the resize, which
-            // will involve operations on the very map we're locking.
-            drop(lock);
-            resize_operation.wait();
-        };
-
-        let index_map = self.index_map.clone();
-        let index_path = self.base_path.join(uuid.to_string());
-        let index_name = name.to_string();
-        thread::Builder::new()
-            .name(String::from("index_deleter"))
-            .spawn(move || {
-                // We first wait to be sure that the previously opened index is effectively closed.
-                // This can take a lot of time, this is why we do that in a seperate thread.
-                if let Some(closing_event) = closing_event {
-                    closing_event.wait();
-                }
-
-                // Then we remove the content from disk.
-                if let Err(e) = fs::remove_dir_all(&index_path) {
-                    error!(
-                        "An error happened when deleting the index {} ({}): {}",
-                        index_name, uuid, e
-                    );
-                }
-
-                // Finally we remove the entry from the index map.
-                assert!(matches!(index_map.write().unwrap().remove(&uuid), Some(BeingDeleted)));
-            })
-            .unwrap();
-
-        Ok(())
-    }
-
-    pub fn exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    /// Resizes the maximum size of the specified index to the double of its current maximum size.
-    ///
-    /// This operation involves closing the underlying environment and so can take a long time to complete.
-    ///
-    /// # Panics
-    ///
-    /// - If the Index corresponding to the passed name is concurrently being deleted/resized or cannot be found in the
-    ///   in memory hash map.
-    pub fn resize_index(&self, rtxn: &RoTxn, name: &str) -> Result<()> {
-        // fixme: factor to a function?
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // We remove the index from the in-memory index map.
-        let mut lock = self.index_map.write().unwrap();
-        // signal that will be sent when the resize operation completes
-        let resize_operation = Arc::new(SignalEvent::manual(false));
-        let index = match lock.insert(uuid, BeingResized(resize_operation)) {
-            Some(Available(index)) => index,
-            Some(previous_status) => {
-                lock.insert(uuid, previous_status);
-                panic!(
-                    "Attempting to resize index {name} that is already being resized or deleted."
-                )
-            }
-            None => {
-                panic!("Could not find the status of index {name} in the in-memory index mapper.")
-            }
-        };
-
-        drop(lock);
-
-        let resize_succeeded = (move || {
-            let current_size = index.map_size()?;
-            let new_size = current_size * 2;
-            let closing_event = index.prepare_for_closing();
-
-            log::debug!("Waiting for index {name} to close");
-
-            if !closing_event.wait_timeout(std::time::Duration::from_secs(600)) {
-                // fail after 10 minutes waiting
-                panic!("Could not resize index {name} (unable to close it)");
-            }
-
-            log::info!("Resized index {name} from {current_size} to {new_size} bytes");
-            let index_path = self.base_path.join(uuid.to_string());
-            let index = self.create_or_open_index(&index_path, None, new_size)?;
-            Ok(index)
-        })();
-
-        // Put the map back to a consistent state.
-        // Even if there was an error we don't want to leave the map in an inconsistent state as it would cause
-        // deadlocks.
-        let mut lock = self.index_map.write().unwrap();
-        let (resize_operation, resize_succeeded) = match resize_succeeded {
-            Ok(index) => {
-                // insert the resized index
-                let Some(BeingResized(resize_operation)) = lock.insert(uuid, Available(index)) else {
-                    panic!("Index state for index {name} was modified while it was being resized")
-                };
-
-                (resize_operation, Ok(()))
-            }
-            Err(error) => {
-                // there was an error, not much we can do... delete the index from the in-memory map to prevent future errors
-                let Some(BeingResized(resize_operation)) = lock.remove(&uuid) else {
-                                    panic!("Index state for index {name} was modified while it was being resized")
-                                };
-                (resize_operation, Err(error))
-            }
-        };
-
-        // drop the lock before signaling completion so that other threads don't immediately await on the lock after waking up.
-        drop(lock);
-        resize_operation.signal();
-
-        resize_succeeded
-    }
-
-    /// Return an index, may open it if it wasn't already opened.
-    pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // we clone here to drop the lock before entering the match
-        let index = loop {
-            let index = self.index_map.read().unwrap().get(&uuid).cloned();
-
-            match index {
-                Some(Available(index)) => break index,
-                Some(BeingResized(ref resize_operation)) => {
-                    // Avoiding deadlocks: no lock taken while doing this operation.
-                    resize_operation.wait();
-                    continue;
-                }
-                Some(BeingDeleted) => return Err(Error::IndexNotFound(name.to_string())),
-                // since we're lazy, it's possible that the index has not been opened yet.
-                None => {
-                    let mut index_map = self.index_map.write().unwrap();
-                    // between the read lock and the write lock it's not impossible
-                    // that someone already opened the index (eg if two search happens
-                    // at the same time), thus before opening it we check a second time
-                    // if it's not already there.
-                    // Since there is a good chance it's not already there we can use
-                    // the entry method.
-                    match index_map.entry(uuid) {
-                        Entry::Vacant(entry) => {
-                            let index_path = self.base_path.join(uuid.to_string());
-
-                            let index =
-                                self.create_or_open_index(&index_path, None, self.index_size)?;
-                            entry.insert(Available(index.clone()));
-                            break index;
-                        }
-                        Entry::Occupied(entry) => match entry.get() {
-                            Available(index) => break index.clone(),
-                            BeingResized(resize_operation) => {
-                                // Avoiding the deadlock: we drop the lock before waiting
-                                let resize_operation = resize_operation.clone();
-                                drop(index_map);
-                                resize_operation.wait();
-                                continue;
-                            }
-                            BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-                        },
-                    }
-                }
-            }
-        };
-
-        Ok(index)
-    }
-
-    /// Return all indexes, may open them if they weren't already opened.
-    pub fn indexes(&self, rtxn: &RoTxn) -> Result<Vec<(String, Index)>> {
-        self.index_mapping
-            .iter(rtxn)?
-            .map(|ret| {
-                ret.map_err(Error::from).and_then(|(name, _)| {
-                    self.index(rtxn, name).map(|index| (name.to_string(), index))
-                })
-            })
-            .collect()
-    }
-
-    /// Swap two index names.
-    pub fn swap(&self, wtxn: &mut RwTxn, lhs: &str, rhs: &str) -> Result<()> {
-        let lhs_uuid = self
-            .index_mapping
-            .get(wtxn, lhs)?
-            .ok_or_else(|| Error::IndexNotFound(lhs.to_string()))?;
-        let rhs_uuid = self
-            .index_mapping
-            .get(wtxn, rhs)?
-            .ok_or_else(|| Error::IndexNotFound(rhs.to_string()))?;
-
-        self.index_mapping.put(wtxn, lhs, &rhs_uuid)?;
-        self.index_mapping.put(wtxn, rhs, &lhs_uuid)?;
-
-        Ok(())
-    }
-
-    pub fn index_exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
-        Ok(self.index_mapping.get(rtxn, name)?.is_some())
-    }
-
-    pub fn indexer_config(&self) -> &IndexerConfig {
-        &self.indexer_config
-    }
-}

index-scheduler/src/index_mapper/index_map.rs

@@ -0,0 +1,370 @@
+/// 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, EnvOpenOptions};
+use meilisearch_types::milli::Index;
+use time::OffsetDateTime;
+use uuid::Uuid;
+
+use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
+use crate::lru::{InsertionOutcome, LruMap};
+use crate::{clamp_to_page_size, Result};
+
+/// Keep an internally consistent view of the open indexes in memory.
+///
+/// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.
+/// Indexes that are being closed (for resizing or due to cache eviction) or deleted cannot be evicted from the cache and
+/// are stored separately.
+///
+/// This view provides operations to change the state of the index as it is known in memory:
+/// open an index (making it available for queries), close an index (specifying the new size it should be opened with),
+/// delete an index.
+///
+/// External consistency with the other bits of data of an index is provided by the `IndexMapper` parent structure.
+pub struct IndexMap {
+    /// A LRU map of indexes that are in the open state and available for queries.
+    available: LruMap<Uuid, Index>,
+    /// A map of indexes that are not available for queries, either because they are being deleted
+    /// or because they are being closed.
+    ///
+    /// If they are being deleted, the UUID points to `None`.
+    unavailable: BTreeMap<Uuid, Option<ClosingIndex>>,
+
+    /// A monotonically increasing generation number, used to differentiate between multiple successive index closing requests.
+    ///
+    /// Because multiple readers could be waiting on an index to close, the following could theoretically happen:
+    ///
+    /// 1. Multiple readers wait for the index closing to occur.
+    /// 2. One of them "wins the race", takes the lock and then removes the index that finished closing from the map.
+    /// 3. The index is reopened, but must be closed again (such as being resized again).
+    /// 4. One reader that "lost the race" in (2) wakes up and tries to take the lock and remove the index from the map.
+    ///
+    /// In that situation, the index may or may not have finished closing. The `generation` field allows to remember which
+    /// closing request was made, so the reader that "lost the race" has the old generation and will need to wait again for the index
+    /// to close.
+    generation: usize,
+}
+
+#[derive(Clone)]
+pub struct ClosingIndex {
+    uuid: Uuid,
+    closing_event: EnvClosingEvent,
+    map_size: usize,
+    generation: usize,
+}
+
+impl ClosingIndex {
+    /// Waits for the index to be definitely closed.
+    ///
+    /// To avoid blocking, users should relinquish their locks to the IndexMap before calling this function.
+    ///
+    /// After the index is physically closed, the in memory map must still be updated to take this into account.
+    /// To do so, a `ReopenableIndex` is returned, that can be used to either definitely close or definitely open
+    /// the index without waiting anymore.
+    pub fn wait_timeout(self, timeout: Duration) -> Option<ReopenableIndex> {
+        self.closing_event.wait_timeout(timeout).then_some(ReopenableIndex {
+            uuid: self.uuid,
+            map_size: self.map_size,
+            generation: self.generation,
+        })
+    }
+}
+
+pub struct ReopenableIndex {
+    uuid: Uuid,
+    map_size: usize,
+    generation: usize,
+}
+
+impl ReopenableIndex {
+    /// Attempts to reopen the index, which can result in the index being reopened again or not
+    /// (e.g. if another thread already opened and closed the index again).
+    ///
+    /// Use get again on the IndexMap to get the updated status.
+    ///
+    /// Fails if the underlying index creation fails.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status                                   |
+    /// |-----------------|----------------------------------------------|
+    /// | Missing         | Missing                                      |
+    /// | BeingDeleted    | BeingDeleted                                 |
+    /// | Closing         | Available or Closing depending on generation |
+    /// | Available       | Available                                    |
+    ///
+    pub fn reopen(self, map: &mut IndexMap, path: &Path) -> Result<()> {
+        if let Closing(reopen) = map.get(&self.uuid) {
+            if reopen.generation != self.generation {
+                return Ok(());
+            }
+            map.unavailable.remove(&self.uuid);
+            map.create(&self.uuid, path, None, self.map_size)?;
+        }
+        Ok(())
+    }
+
+    /// Attempts to close the index, which may or may not result in the index being closed
+    /// (e.g. if another thread already reopened the index again).
+    ///
+    /// Use get again on the IndexMap to get the updated status.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status                                 |
+    /// |-----------------|--------------------------------------------|
+    /// | Missing         | Missing                                    |
+    /// | BeingDeleted    | BeingDeleted                               |
+    /// | Closing         | Missing or Closing depending on generation |
+    /// | Available       | Available                                  |
+    pub fn close(self, map: &mut IndexMap) {
+        if let Closing(reopen) = map.get(&self.uuid) {
+            if reopen.generation != self.generation {
+                return;
+            }
+            map.unavailable.remove(&self.uuid);
+        }
+    }
+}
+
+impl IndexMap {
+    pub fn new(cap: usize) -> IndexMap {
+        Self { unavailable: Default::default(), available: LruMap::new(cap), generation: 0 }
+    }
+
+    /// Gets the current status of an index in the map.
+    ///
+    /// If the index is available it can be accessed from the returned status.
+    pub fn get(&self, uuid: &Uuid) -> IndexStatus {
+        self.available
+            .get(uuid)
+            .map(|index| Available(index.clone()))
+            .unwrap_or_else(|| self.get_unavailable(uuid))
+    }
+
+    fn get_unavailable(&self, uuid: &Uuid) -> IndexStatus {
+        match self.unavailable.get(uuid) {
+            Some(Some(reopen)) => Closing(reopen.clone()),
+            Some(None) => BeingDeleted,
+            None => Missing,
+        }
+    }
+
+    /// Attempts to create a new index that wasn't existing before.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status |
+    /// |-----------------|------------|
+    /// | Missing         | Available  |
+    /// | BeingDeleted    | panics     |
+    /// | Closing         | panics     |
+    /// | Available       | panics     |
+    ///
+    pub fn create(
+        &mut self,
+        uuid: &Uuid,
+        path: &Path,
+        date: Option<(OffsetDateTime, OffsetDateTime)>,
+        map_size: usize,
+    ) -> Result<Index> {
+        if !matches!(self.get_unavailable(uuid), Missing) {
+            panic!("Attempt to open an index that was unavailable");
+        }
+        let index = create_or_open_index(path, date, map_size)?;
+        match self.available.insert(*uuid, index.clone()) {
+            InsertionOutcome::InsertedNew => (),
+            InsertionOutcome::Evicted(evicted_uuid, evicted_index) => {
+                self.close(evicted_uuid, evicted_index, 0);
+            }
+            InsertionOutcome::Replaced(_) => {
+                panic!("Attempt to open an index that was already opened")
+            }
+        }
+        Ok(index)
+    }
+
+    /// Increases the current generation. See documentation for this field.
+    ///
+    /// In the unlikely event that the 2^64 generations would have been exhausted, we simply wrap-around.
+    ///
+    /// For this to cause an issue, one should be able to stop a reader in time after it got a `ReopenableIndex` and before it takes the lock
+    /// to remove it from the unavailable map, and keep the reader in this frozen state for 2^64 closing of other indexes.
+    ///
+    /// This seems overwhelmingly impossible to achieve in practice.
+    fn next_generation(&mut self) -> usize {
+        self.generation = self.generation.wrapping_add(1);
+        self.generation
+    }
+
+    /// Attempts to close an index.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status    |
+    /// |-----------------|---------------|
+    /// | Missing         | Missing       |
+    /// | BeingDeleted    | BeingDeleted  |
+    /// | Closing         | Closing       |
+    /// | Available       | Closing       |
+    ///
+    pub fn close_for_resize(&mut self, uuid: &Uuid, map_size_growth: usize) {
+        let Some(index) = self.available.remove(uuid) else { return; };
+        self.close(*uuid, index, map_size_growth);
+    }
+
+    fn close(&mut self, uuid: Uuid, index: Index, map_size_growth: usize) {
+        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(uuid, Some(ClosingIndex { uuid, closing_event, map_size, generation }));
+    }
+
+    /// Attempts to delete and index.
+    ///
+    ///  `end_deletion` must be called just after.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status   | Return value                |
+    /// |-----------------|--------------|-----------------------------|
+    /// | Missing         | BeingDeleted | Ok(None)                    |
+    /// | BeingDeleted    | BeingDeleted | Err(None)                   |
+    /// | Closing         | Closing      | Err(Some(reopen))           |
+    /// | Available       | BeingDeleted | Ok(Some(env_closing_event)) |
+    pub fn start_deletion(
+        &mut self,
+        uuid: &Uuid,
+    ) -> std::result::Result<Option<EnvClosingEvent>, Option<ClosingIndex>> {
+        if let Some(index) = self.available.remove(uuid) {
+            self.unavailable.insert(*uuid, None);
+            return Ok(Some(index.prepare_for_closing()));
+        }
+        match self.unavailable.remove(uuid) {
+            Some(Some(reopen)) => Err(Some(reopen)),
+            Some(None) => Err(None),
+            None => Ok(None),
+        }
+    }
+
+    /// Marks that an index deletion finished.
+    ///
+    /// Must be used after calling `start_deletion`.
+    ///
+    /// # Status table
+    ///
+    /// | Previous Status | New Status |
+    /// |-----------------|------------|
+    /// | Missing         | Missing    |
+    /// | BeingDeleted    | Missing    |
+    /// | Closing         | panics     |
+    /// | Available       | panics     |
+    pub fn end_deletion(&mut self, uuid: &Uuid) {
+        assert!(
+            self.available.get(uuid).is_none(),
+            "Attempt to finish deletion of an index that was not being deleted"
+        );
+        // Do not panic if the index was Missing or BeingDeleted
+        assert!(
+            !matches!(self.unavailable.remove(uuid), Some(Some(_))),
+            "Attempt to finish deletion of an index that was being closed"
+        );
+    }
+}
+
+/// Create or open an index in the specified path.
+/// The path *must* exist or an error will be thrown.
+fn create_or_open_index(
+    path: &Path,
+    date: Option<(OffsetDateTime, OffsetDateTime)>,
+    map_size: usize,
+) -> Result<Index> {
+    let mut options = EnvOpenOptions::new();
+    options.map_size(clamp_to_page_size(map_size));
+    options.max_readers(1024);
+
+    if let Some((created, updated)) = date {
+        Ok(Index::new_with_creation_dates(options, path, created, updated)?)
+    } else {
+        Ok(Index::new(options, path)?)
+    }
+}
+
+/// Putting the tests of the LRU down there so we have access to the cache's private members
+#[cfg(test)]
+mod tests {
+
+    use meilisearch_types::heed::Env;
+    use meilisearch_types::Index;
+    use uuid::Uuid;
+
+    use super::super::IndexMapper;
+    use crate::tests::IndexSchedulerHandle;
+    use crate::utils::clamp_to_page_size;
+    use crate::IndexScheduler;
+
+    impl IndexMapper {
+        fn test() -> (Self, Env, IndexSchedulerHandle) {
+            let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
+            (index_scheduler.index_mapper, index_scheduler.env, handle)
+        }
+    }
+
+    fn check_first_unavailable(mapper: &IndexMapper, expected_uuid: Uuid, is_closing: bool) {
+        let index_map = mapper.index_map.read().unwrap();
+        let (uuid, state) = index_map.unavailable.first_key_value().unwrap();
+        assert_eq!(uuid, &expected_uuid);
+        assert_eq!(state.is_some(), is_closing);
+    }
+
+    #[test]
+    fn evict_indexes() {
+        let (mapper, env, _handle) = IndexMapper::test();
+        let mut uuids = vec![];
+        // LRU cap + 1
+        for i in 0..(5 + 1) {
+            let index_name = format!("index-{i}");
+            let wtxn = env.write_txn().unwrap();
+            mapper.create_index(wtxn, &index_name, None).unwrap();
+            let txn = env.read_txn().unwrap();
+            uuids.push(mapper.index_mapping.get(&txn, &index_name).unwrap().unwrap());
+        }
+        // index-0 was evicted
+        check_first_unavailable(&mapper, uuids[0], true);
+
+        // get back the evicted index
+        let wtxn = env.write_txn().unwrap();
+        mapper.create_index(wtxn, "index-0", None).unwrap();
+
+        // Least recently used is now index-1
+        check_first_unavailable(&mapper, uuids[1], true);
+    }
+
+    #[test]
+    fn resize_index() {
+        let (mapper, env, _handle) = IndexMapper::test();
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size);
+
+        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
+
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount);
+
+        mapper.resize_index(&env.read_txn().unwrap(), "index").unwrap();
+
+        let index = mapper.create_index(env.write_txn().unwrap(), "index", None).unwrap();
+        assert_index_size(index, mapper.index_base_map_size + mapper.index_growth_amount * 2);
+    }
+
+    fn assert_index_size(index: Index, expected: usize) {
+        let expected = clamp_to_page_size(expected);
+        let index_map_size = index.map_size().unwrap();
+        assert_eq!(index_map_size, expected);
+    }
+}

index-scheduler/src/index_mapper/mod.rs

@@ -0,0 +1,453 @@
+use std::path::PathBuf;
+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 uuid::Uuid;
+
+use self::index_map::IndexMap;
+use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
+use crate::uuid_codec::UuidCodec;
+use crate::{Error, Result};
+
+mod index_map;
+
+const INDEX_MAPPING: &str = "index-mapping";
+const INDEX_STATS: &str = "index-stats";
+
+/// Structure managing meilisearch's indexes.
+///
+/// It is responsible for:
+/// 1. Creating new indexes
+/// 2. Opening indexes and storing references to these opened indexes
+/// 3. Accessing indexes through their uuid
+/// 4. Mapping a user-defined name to each index uuid.
+///
+/// # Implementation notes
+///
+/// An index exists as 3 bits of data:
+/// 1. The index data on disk, that can exist in 3 states: Missing, Present, or BeingDeleted.
+/// 2. The persistent database containing the association between the index' name and its UUID,
+///    that can exist in 2 states: Missing or Present.
+/// 3. The state of the index in the in-memory `IndexMap`, that can exist in multiple states:
+///   - Missing
+///   - Available
+///   - Closing (because an index needs resizing or was evicted from the cache)
+///   - BeingDeleted
+///
+/// All of this data should be kept consistent between index operations, which is achieved by the `IndexMapper`
+/// with the use of the following primitives:
+/// - A RwLock on the `IndexMap`.
+/// - Transactions on the association database.
+/// - ClosingEvent signals emitted when closing an environment.
+#[derive(Clone)]
+pub struct IndexMapper {
+    /// Keep track of the opened indexes. Used mainly by the index resolver.
+    index_map: Arc<RwLock<IndexMap>>,
+
+    /// Map an index name with an index uuid currently available on disk.
+    pub(crate) index_mapping: Database<Str, UuidCodec>,
+    /// Map an index UUID with the cached stats associated to the index.
+    ///
+    /// Using an UUID forces to use the index_mapping table to recover the index behind a name, ensuring
+    /// consistency wrt index swapping.
+    pub(crate) index_stats: Database<UuidCodec, SerdeJson<IndexStats>>,
+
+    /// Path to the folder where the LMDB environments of each index are.
+    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.
+    index_growth_amount: usize,
+    pub indexer_config: Arc<IndexerConfig>,
+}
+
+/// Whether the index is available for use or is forbidden to be inserted back in the index map
+#[allow(clippy::large_enum_variant)]
+#[derive(Clone)]
+pub enum IndexStatus {
+    /// Not currently in the index map.
+    Missing,
+    /// Do not insert it back in the index map as it is currently being deleted.
+    BeingDeleted,
+    /// Temporarily do not insert the index in the index map as it is currently being resized/evicted from the map.
+    Closing(index_map::ClosingIndex),
+    /// You can use the index without worrying about anything.
+    Available(Index),
+}
+
+/// The statistics that can be computed from an `Index` object.
+#[derive(Serialize, Deserialize, Debug)]
+pub struct IndexStats {
+    /// Number of documents in the index.
+    pub number_of_documents: u64,
+    /// Size of the index' DB, in bytes.
+    pub database_size: u64,
+    /// Association of every field name with the number of times it occurs in the documents.
+    pub field_distribution: FieldDistribution,
+    /// Creation date of the index.
+    pub created_at: OffsetDateTime,
+    /// Date of the last update of the index.
+    pub updated_at: OffsetDateTime,
+}
+
+impl IndexStats {
+    /// Compute the stats of an index
+    ///
+    /// # Parameters
+    ///
+    /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
+    pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+        let database_size = index.on_disk_size()?;
+        Ok(IndexStats {
+            number_of_documents: index.number_of_documents(rtxn)?,
+            database_size,
+            field_distribution: index.field_distribution(rtxn)?,
+            created_at: index.created_at(rtxn)?,
+            updated_at: index.updated_at(rtxn)?,
+        })
+    }
+}
+
+impl IndexMapper {
+    pub fn new(
+        env: &Env,
+        base_path: PathBuf,
+        index_base_map_size: usize,
+        index_growth_amount: usize,
+        index_count: usize,
+        indexer_config: IndexerConfig,
+    ) -> Result<Self> {
+        Ok(Self {
+            index_map: Arc::new(RwLock::new(IndexMap::new(index_count))),
+            index_mapping: env.create_database(Some(INDEX_MAPPING))?,
+            index_stats: env.create_database(Some(INDEX_STATS))?,
+            base_path,
+            index_base_map_size,
+            index_growth_amount,
+            indexer_config: Arc::new(indexer_config),
+        })
+    }
+
+    /// Get or create the index.
+    pub fn create_index(
+        &self,
+        mut wtxn: RwTxn,
+        name: &str,
+        date: Option<(OffsetDateTime, OffsetDateTime)>,
+    ) -> Result<Index> {
+        match self.index(&wtxn, name) {
+            Ok(index) => {
+                wtxn.commit()?;
+                Ok(index)
+            }
+            Err(Error::IndexNotFound(_)) => {
+                let uuid = Uuid::new_v4();
+                self.index_mapping.put(&mut wtxn, name, &uuid)?;
+
+                let index_path = self.base_path.join(uuid.to_string());
+                fs::create_dir_all(&index_path)?;
+
+                // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
+                // This is very unlikely to happen in practice.
+                // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
+                let index = self.index_map.write().unwrap().create(
+                    &uuid,
+                    &index_path,
+                    date,
+                    self.index_base_map_size,
+                )?;
+
+                wtxn.commit()?;
+
+                Ok(index)
+            }
+            error => error,
+        }
+    }
+
+    /// Removes the index from the mapping table and the in-memory index map
+    /// but keeps the associated tasks.
+    pub fn delete_index(&self, mut wtxn: RwTxn, name: &str) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(&wtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        // Not an error if the index had no stats in cache.
+        self.index_stats.delete(&mut wtxn, &uuid)?;
+
+        // Once we retrieved the UUID of the index we remove it from the mapping table.
+        assert!(self.index_mapping.delete(&mut wtxn, name)?);
+
+        wtxn.commit()?;
+
+        let mut tries = 0;
+        // Attempts to remove the index from the in-memory index map in a loop.
+        //
+        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
+        // loop iteration.
+        //
+        // We make 100 attempts before giving up.
+        // This could happen in the following situations:
+        //
+        // 1. There is a bug preventing the index from being correctly closed, or us from detecting this.
+        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a pathological search.
+        //    This can not be caused by indexation because deleting an index happens in the scheduler itself, so cannot be concurrent with indexation.
+        //
+        // In these situations, reporting the error through a panic is in order.
+        let closing_event = loop {
+            let mut lock = self.index_map.write().unwrap();
+            match lock.start_deletion(&uuid) {
+                Ok(env_closing) => break env_closing,
+                Err(Some(reopen)) => {
+                    // drop the lock here so that we don't synchronously wait for the index to close.
+                    drop(lock);
+                    tries += 1;
+                    if tries >= 100 {
+                        panic!("Too many attempts to close index {name} prior to deletion.")
+                    }
+                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
+                        reopen
+                    } else {
+                        continue;
+                    };
+                    reopen.close(&mut self.index_map.write().unwrap());
+                    continue;
+                }
+                Err(None) => return Ok(()),
+            }
+        };
+
+        let index_map = self.index_map.clone();
+        let index_path = self.base_path.join(uuid.to_string());
+        let index_name = name.to_string();
+        thread::Builder::new()
+            .name(String::from("index_deleter"))
+            .spawn(move || {
+                // We first wait to be sure that the previously opened index is effectively closed.
+                // This can take a lot of time, this is why we do that in a separate thread.
+                if let Some(closing_event) = closing_event {
+                    closing_event.wait();
+                }
+
+                // Then we remove the content from disk.
+                if let Err(e) = fs::remove_dir_all(&index_path) {
+                    error!(
+                        "An error happened when deleting the index {} ({}): {}",
+                        index_name, uuid, e
+                    );
+                }
+
+                // Finally we remove the entry from the index map.
+                index_map.write().unwrap().end_deletion(&uuid);
+            })
+            .unwrap();
+
+        Ok(())
+    }
+
+    pub fn exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
+        Ok(self.index_mapping.get(rtxn, name)?.is_some())
+    }
+
+    /// Resizes the maximum size of the specified index to the double of its current maximum size.
+    ///
+    /// This operation involves closing the underlying environment and so can take a long time to complete.
+    ///
+    /// # Panics
+    ///
+    /// - If the Index corresponding to the passed name is concurrently being deleted/resized or cannot be found in the
+    ///   in memory hash map.
+    pub fn resize_index(&self, rtxn: &RoTxn, name: &str) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        // We remove the index from the in-memory index map.
+        self.index_map.write().unwrap().close_for_resize(&uuid, self.index_growth_amount);
+
+        Ok(())
+    }
+
+    /// Return an index, may open it if it wasn't already opened.
+    pub fn index(&self, rtxn: &RoTxn, name: &str) -> Result<Index> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, name)?
+            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
+
+        let mut tries = 0;
+        // attempts to open the index in a loop.
+        //
+        // If the index is currently being closed, we will wait for it to be closed and retry getting it in a subsequent
+        // loop iteration.
+        //
+        // We make 100 attempts before giving up.
+        // This could happen in the following situations:
+        //
+        // 1. There is a bug preventing the index from being correctly closed, or us from detecting it was.
+        // 2. A user of the index is keeping it open for more than 600 seconds. This could happen e.g. during a long indexation,
+        //    a pathological search, and so on.
+        //
+        // In these situations, reporting the error through a panic is in order.
+        let index = loop {
+            tries += 1;
+            if tries > 100 {
+                panic!("Too many spurious wake ups while trying to open the index {name}");
+            }
+
+            // we get the index here to drop the lock before entering the match
+            let index = self.index_map.read().unwrap().get(&uuid);
+
+            match index {
+                Available(index) => break index,
+                Closing(reopen) => {
+                    // Avoiding deadlocks: no lock taken while doing this operation.
+                    let reopen = if let Some(reopen) = reopen.wait_timeout(Duration::from_secs(6)) {
+                        reopen
+                    } else {
+                        continue;
+                    };
+                    let index_path = self.base_path.join(uuid.to_string());
+                    // take the lock to reopen the environment.
+                    reopen.reopen(&mut self.index_map.write().unwrap(), &index_path)?;
+                    continue;
+                }
+                BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
+                // since we're lazy, it's possible that the index has not been opened yet.
+                Missing => {
+                    let mut index_map = self.index_map.write().unwrap();
+                    // between the read lock and the write lock it's not impossible
+                    // that someone already opened the index (eg if two searches happen
+                    // at the same time), thus before opening it we check a second time
+                    // if it's not already there.
+                    match index_map.get(&uuid) {
+                        Missing => {
+                            let index_path = self.base_path.join(uuid.to_string());
+
+                            break index_map.create(
+                                &uuid,
+                                &index_path,
+                                None,
+                                self.index_base_map_size,
+                            )?;
+                        }
+                        Available(index) => break index,
+                        Closing(_) => {
+                            // the reopening will be handled in the next loop operation
+                            continue;
+                        }
+                        BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
+                    }
+                }
+            }
+        };
+
+        Ok(index)
+    }
+
+    /// Attempts `f` for each index that exists in the index mapper.
+    ///
+    /// It is preferable to use this function rather than a loop that opens all indexes, as a way to avoid having all indexes opened,
+    /// which is unsupported in general.
+    ///
+    /// Since `f` is allowed to return a result, and `Index` is cloneable, it is still possible to wrongly build e.g. a vector of
+    /// all the indexes, but this function makes it harder and so less likely to do accidentally.
+    pub fn try_for_each_index<U, V>(
+        &self,
+        rtxn: &RoTxn,
+        mut f: impl FnMut(&str, &Index) -> Result<U>,
+    ) -> Result<V>
+    where
+        V: FromIterator<U>,
+    {
+        self.index_mapping
+            .iter(rtxn)?
+            .map(|res| {
+                res.map_err(Error::from)
+                    .and_then(|(name, _)| self.index(rtxn, name).and_then(|index| f(name, &index)))
+            })
+            .collect()
+    }
+
+    /// Return the name of all indexes without opening them.
+    pub fn index_names(&self, rtxn: &RoTxn) -> Result<Vec<String>> {
+        self.index_mapping
+            .iter(rtxn)?
+            .map(|res| res.map_err(Error::from).map(|(name, _)| name.to_string()))
+            .collect()
+    }
+
+    /// Swap two index names.
+    pub fn swap(&self, wtxn: &mut RwTxn, lhs: &str, rhs: &str) -> Result<()> {
+        let lhs_uuid = self
+            .index_mapping
+            .get(wtxn, lhs)?
+            .ok_or_else(|| Error::IndexNotFound(lhs.to_string()))?;
+        let rhs_uuid = self
+            .index_mapping
+            .get(wtxn, rhs)?
+            .ok_or_else(|| Error::IndexNotFound(rhs.to_string()))?;
+
+        self.index_mapping.put(wtxn, lhs, &rhs_uuid)?;
+        self.index_mapping.put(wtxn, rhs, &lhs_uuid)?;
+
+        Ok(())
+    }
+
+    /// The stats of an index.
+    ///
+    /// If available in the cache, they are directly returned.
+    /// Otherwise, the `Index` is opened to compute the stats on the fly (the result is not cached).
+    /// The stats for an index are cached after each `Index` update.
+    pub fn stats_of(&self, rtxn: &RoTxn, index_uid: &str) -> Result<IndexStats> {
+        let uuid = self
+            .index_mapping
+            .get(rtxn, index_uid)?
+            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
+
+        match self.index_stats.get(rtxn, &uuid)? {
+            Some(stats) => Ok(stats),
+            None => {
+                let index = self.index(rtxn, index_uid)?;
+                let index_rtxn = index.read_txn()?;
+                IndexStats::new(&index, &index_rtxn)
+            }
+        }
+    }
+
+    /// Stores the new stats for an index.
+    ///
+    /// Expected usage is to compute the stats the index using `IndexStats::new`, the pass it to this function.
+    pub fn store_stats_of(
+        &self,
+        wtxn: &mut RwTxn,
+        index_uid: &str,
+        stats: &IndexStats,
+    ) -> Result<()> {
+        let uuid = self
+            .index_mapping
+            .get(wtxn, index_uid)?
+            .ok_or_else(|| Error::IndexNotFound(index_uid.to_string()))?;
+
+        self.index_stats.put(wtxn, &uuid, stats)?;
+        Ok(())
+    }
+
+    pub fn index_exists(&self, rtxn: &RoTxn, name: &str) -> Result<bool> {
+        Ok(self.index_mapping.get(rtxn, name)?.is_some())
+    }
+
+    pub fn indexer_config(&self) -> &IndexerConfig {
+        &self.indexer_config
+    }
+}

index-scheduler/src/insta_snapshot.rs

@@ -254,6 +254,16 @@ pub fn snapshot_canceled_by(
     snap
 }
 pub fn snapshot_index_mapper(rtxn: &RoTxn, mapper: &IndexMapper) -> String {
-    let names = mapper.indexes(rtxn).unwrap().into_iter().map(|(n, _)| n).collect::<Vec<_>>();
-    format!("{names:?}")
+    let mut s = String::new();
+    let names = mapper.index_names(rtxn).unwrap();
+
+    for name in names {
+        let stats = mapper.stats_of(rtxn, &name).unwrap();
+        s.push_str(&format!(
+            "{name}: {{ number_of_documents: {}, field_distribution: {:?} }}\n",
+            stats.number_of_documents, stats.field_distribution
+        ));
+    }
+
+    s
 }

index-scheduler/src/lib.rs

@@ -24,6 +24,7 @@ pub mod error;
 mod index_mapper;
 #[cfg(test)]
 mod insta_snapshot;
+mod lru;
 mod utils;
 mod uuid_codec;
 
@@ -31,7 +32,7 @@ pub type Result<T> = std::result::Result<T, Error>;
 pub type TaskId = u32;
 
 use std::ops::{Bound, RangeBounds};
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 use std::sync::atomic::AtomicBool;
 use std::sync::atomic::Ordering::Relaxed;
 use std::sync::{Arc, RwLock};
@@ -43,11 +44,9 @@ use file_store::FileStore;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{self, Database, Env, RoTxn};
-use meilisearch_types::index_uid_pattern::IndexUidPattern;
-use meilisearch_types::milli;
 use meilisearch_types::milli::documents::DocumentsBatchBuilder;
 use meilisearch_types::milli::update::IndexerConfig;
-use meilisearch_types::milli::{CboRoaringBitmapCodec, Index, RoaringBitmapCodec, BEU32};
+use meilisearch_types::milli::{self, CboRoaringBitmapCodec, Index, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
 use synchronoise::SignalEvent;
@@ -230,8 +229,12 @@ pub struct IndexSchedulerOptions {
     pub dumps_path: PathBuf,
     /// The maximum size, in bytes, of the task index.
     pub task_db_size: usize,
-    /// The maximum size, in bytes, of each meilisearch index.
-    pub index_size: usize,
+    /// The size, in bytes, with which a meilisearch index is opened the first time of each meilisearch index.
+    pub index_base_map_size: usize,
+    /// The size, in bytes, by which the map size of an index is increased when it resized due to being full.
+    pub index_growth_amount: usize,
+    /// The number of indexes that can be concurrently opened in memory.
+    pub index_count: usize,
     /// Configuration used during indexing for each meilisearch index.
     pub indexer_config: IndexerConfig,
     /// Set to `true` iff the index scheduler is allowed to automatically
@@ -361,9 +364,25 @@ impl IndexScheduler {
         std::fs::create_dir_all(&options.indexes_path)?;
         std::fs::create_dir_all(&options.dumps_path)?;
 
+        let task_db_size = clamp_to_page_size(options.task_db_size);
+        let budget = if options.indexer_config.skip_index_budget {
+            IndexBudget {
+                map_size: options.index_base_map_size,
+                index_count: options.index_count,
+                task_db_size,
+            }
+        } else {
+            Self::index_budget(
+                &options.tasks_path,
+                options.index_base_map_size,
+                task_db_size,
+                options.index_count,
+            )
+        };
+
         let env = heed::EnvOpenOptions::new()
             .max_dbs(10)
-            .map_size(clamp_to_page_size(options.task_db_size))
+            .map_size(budget.task_db_size)
             .open(options.tasks_path)?;
         let file_store = FileStore::new(&options.update_file_path)?;
 
@@ -383,7 +402,9 @@ impl IndexScheduler {
             index_mapper: IndexMapper::new(
                 &env,
                 options.indexes_path,
-                options.index_size,
+                budget.map_size,
+                options.index_growth_amount,
+                budget.index_count,
                 options.indexer_config,
             )?,
             env,
@@ -407,6 +428,75 @@ impl IndexScheduler {
         Ok(this)
     }
 
+    fn index_budget(
+        tasks_path: &Path,
+        base_map_size: usize,
+        mut task_db_size: usize,
+        max_index_count: usize,
+    ) -> IndexBudget {
+        #[cfg(windows)]
+        const DEFAULT_BUDGET: usize = 6 * 1024 * 1024 * 1024 * 1024; // 6 TiB, 1 index
+        #[cfg(not(windows))]
+        const DEFAULT_BUDGET: usize = 80 * 1024 * 1024 * 1024 * 1024; // 80 TiB, 18 indexes
+
+        let budget = if Self::is_good_heed(tasks_path, DEFAULT_BUDGET) {
+            DEFAULT_BUDGET
+        } else {
+            log::debug!("determining budget with dichotomic search");
+            utils::dichotomic_search(DEFAULT_BUDGET / 2, |map_size| {
+                Self::is_good_heed(tasks_path, map_size)
+            })
+        };
+
+        log::debug!("memmap budget: {budget}B");
+        let mut budget = budget / 2;
+        if task_db_size > (budget / 2) {
+            task_db_size = clamp_to_page_size(budget * 2 / 5);
+            log::debug!(
+                "Decreasing max size of task DB to {task_db_size}B due to constrained memory space"
+            );
+        }
+        budget -= task_db_size;
+
+        // won't be mutated again
+        let budget = budget;
+        let task_db_size = task_db_size;
+
+        log::debug!("index budget: {budget}B");
+        let mut index_count = budget / base_map_size;
+        if index_count < 2 {
+            // take a bit less than half than the budget to make sure we can always afford to open an index
+            let map_size = (budget * 2) / 5;
+            // single index of max budget
+            log::debug!("1 index of {map_size}B can be opened simultaneously.");
+            return IndexBudget { map_size, index_count: 1, task_db_size };
+        }
+        // give us some space for an additional index when the cache is already full
+        // decrement is OK because index_count >= 2.
+        index_count -= 1;
+        if index_count > max_index_count {
+            index_count = max_index_count;
+        }
+        log::debug!("Up to {index_count} indexes of {base_map_size}B opened simultaneously.");
+        IndexBudget { map_size: base_map_size, index_count, task_db_size }
+    }
+
+    fn is_good_heed(tasks_path: &Path, map_size: usize) -> bool {
+        if let Ok(env) =
+            heed::EnvOpenOptions::new().map_size(clamp_to_page_size(map_size)).open(tasks_path)
+        {
+            env.prepare_for_closing().wait();
+            true
+        } else {
+            // We're treating all errors equally here, not only allocation errors.
+            // This means there's a possiblity for the budget to lower due to errors different from allocation errors.
+            // For persistent errors, this is OK as long as the task db is then reopened normally without ignoring the error this time.
+            // For transient errors, this could lead to an instance with too low a budget.
+            // However transient errors are: 1) less likely than persistent errors 2) likely to cause other issues down the line anyway.
+            false
+        }
+    }
+
     pub fn read_txn(&self) -> Result<RoTxn> {
         self.env.read_txn().map_err(|e| e.into())
     }
@@ -460,15 +550,42 @@ impl IndexScheduler {
     ///
     /// * If the index wasn't opened before, the index will be opened.
     /// * If the index doesn't exist on disk, the `IndexNotFoundError` is thrown.
+    ///
+    /// ### Note
+    ///
+    /// As an `Index` requires a large swath of the virtual memory address space, correct usage of an `Index` does not
+    /// keep its handle for too long.
+    ///
+    /// Some configurations also can't reasonably open multiple indexes at once.
+    /// If you need to fetch information from or perform an action on all indexes,
+    /// see the `try_for_each_index` function.
     pub fn index(&self, name: &str) -> Result<Index> {
         let rtxn = self.env.read_txn()?;
         self.index_mapper.index(&rtxn, name)
     }
 
-    /// Return and open all the indexes.
-    pub fn indexes(&self) -> Result<Vec<(String, Index)>> {
+    /// Return the name of all indexes without opening them.
+    pub fn index_names(&self) -> Result<Vec<String>> {
         let rtxn = self.env.read_txn()?;
-        self.index_mapper.indexes(&rtxn)
+        self.index_mapper.index_names(&rtxn)
+    }
+
+    /// Attempts `f` for each index that exists known to the index scheduler.
+    ///
+    /// It is preferable to use this function rather than a loop that opens all indexes, as a way to avoid having all indexes opened,
+    /// which is unsupported in general.
+    ///
+    /// Since `f` is allowed to return a result, and `Index` is cloneable, it is still possible to wrongly build e.g. a vector of
+    /// all the indexes, but this function makes it harder and so less likely to do accidentally.
+    ///
+    /// If many indexes exist, this operation can take time to complete (in the order of seconds for a 1000 of indexes) as it needs to open
+    /// all the indexes.
+    pub fn try_for_each_index<U, V>(&self, f: impl FnMut(&str, &Index) -> Result<U>) -> Result<V>
+    where
+        V: FromIterator<U>,
+    {
+        let rtxn = self.env.read_txn()?;
+        self.index_mapper.try_for_each_index(&rtxn, f)
     }
 
     /// Return the task ids matched by the given query from the index scheduler's point of view.
@@ -630,13 +747,13 @@ impl IndexScheduler {
         &self,
         rtxn: &RoTxn,
         query: &Query,
-        authorized_indexes: &Option<Vec<IndexUidPattern>>,
+        filters: &meilisearch_auth::AuthFilter,
     ) -> Result<RoaringBitmap> {
         let mut tasks = self.get_task_ids(rtxn, query)?;
 
         // If the query contains a list of index uid or there is a finite list of authorized indexes,
         // then we must exclude all the kinds that aren't associated to one and only one index.
-        if query.index_uids.is_some() || authorized_indexes.is_some() {
+        if query.index_uids.is_some() || !filters.all_indexes_authorized() {
             for kind in enum_iterator::all::<Kind>().filter(|kind| !kind.related_to_one_index()) {
                 tasks -= self.get_kind(rtxn, kind)?;
             }
@@ -644,11 +761,11 @@ impl IndexScheduler {
 
         // Any task that is internally associated with a non-authorized index
         // must be discarded.
-        if let Some(authorized_indexes) = authorized_indexes {
+        if !filters.all_indexes_authorized() {
             let all_indexes_iter = self.index_tasks.iter(rtxn)?;
             for result in all_indexes_iter {
                 let (index, index_tasks) = result?;
-                if !authorized_indexes.iter().any(|p| p.matches_str(index)) {
+                if !filters.is_index_authorized(index) {
                     tasks -= index_tasks;
                 }
             }
@@ -668,12 +785,11 @@ impl IndexScheduler {
     pub fn get_tasks_from_authorized_indexes(
         &self,
         query: Query,
-        authorized_indexes: Option<Vec<IndexUidPattern>>,
+        filters: &meilisearch_auth::AuthFilter,
     ) -> Result<Vec<Task>> {
         let rtxn = self.env.read_txn()?;
 
-        let tasks =
-            self.get_task_ids_from_authorized_indexes(&rtxn, &query, &authorized_indexes)?;
+        let tasks = self.get_task_ids_from_authorized_indexes(&rtxn, &query, filters)?;
 
         let tasks = self.get_existing_tasks(
             &rtxn,
@@ -871,6 +987,18 @@ impl IndexScheduler {
             (bitmap.insert(task.uid));
         })?;
 
+        utils::insert_task_datetime(&mut wtxn, self.enqueued_at, task.enqueued_at, task.uid)?;
+
+        // we can't override the started_at & finished_at, so we must only set it if the tasks is finished and won't change
+        if matches!(task.status, Status::Succeeded | Status::Failed | Status::Canceled) {
+            if let Some(started_at) = task.started_at {
+                utils::insert_task_datetime(&mut wtxn, self.started_at, started_at, task.uid)?;
+            }
+            if let Some(finished_at) = task.finished_at {
+                utils::insert_task_datetime(&mut wtxn, self.finished_at, finished_at, task.uid)?;
+            }
+        }
+
         wtxn.commit()?;
         self.wake_up.signal();
 
@@ -1069,6 +1197,14 @@ impl IndexScheduler {
         Ok(TickOutcome::TickAgain(processed_tasks))
     }
 
+    pub fn index_stats(&self, index_uid: &str) -> Result<IndexStats> {
+        let is_indexing = self.is_index_processing(index_uid)?;
+        let rtxn = self.read_txn()?;
+        let index_stats = self.index_mapper.stats_of(&rtxn, index_uid)?;
+
+        Ok(IndexStats { is_indexing, inner_stats: index_stats })
+    }
+
     pub(crate) fn delete_persisted_task_data(&self, task: &Task) -> Result<()> {
         match task.content_uuid() {
             Some(content_file) => self.delete_update_file(content_file),
@@ -1111,6 +1247,27 @@ pub enum TickOutcome {
     WaitForSignal,
 }
 
+/// How many indexes we can afford to have open simultaneously.
+struct IndexBudget {
+    /// Map size of an index.
+    map_size: usize,
+    /// Maximum number of simultaneously opened indexes.
+    index_count: usize,
+    /// For very constrained systems we might need to reduce the base task_db_size so we can accept at least one index.
+    task_db_size: usize,
+}
+
+/// The statistics that can be computed from an `Index` object and the scheduler.
+///
+/// Compared with `index_mapper::IndexStats`, it adds the scheduling status.
+#[derive(Debug)]
+pub struct IndexStats {
+    /// Whether this index is currently performing indexation, according to the scheduler.
+    pub is_indexing: bool,
+    /// Internal stats computed from the index.
+    pub inner_stats: index_mapper::IndexStats,
+}
+
 #[cfg(test)]
 mod tests {
     use std::io::{BufWriter, Seek, Write};
@@ -1120,7 +1277,9 @@ mod tests {
     use crossbeam::channel::RecvTimeoutError;
     use file_store::File;
     use meili_snap::snapshot;
+    use meilisearch_auth::AuthFilter;
     use meilisearch_types::document_formats::DocumentFormatError;
+    use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::milli::obkv_to_json;
     use meilisearch_types::milli::update::IndexDocumentsMethod::{
         ReplaceDocuments, UpdateDocuments,
@@ -1154,6 +1313,8 @@ mod tests {
             let tempdir = TempDir::new().unwrap();
             let (sender, receiver) = crossbeam::channel::bounded(0);
 
+            let indexer_config = IndexerConfig { skip_index_budget: true, ..Default::default() };
+
             let options = IndexSchedulerOptions {
                 version_file_path: tempdir.path().join(VERSION_FILE_NAME),
                 auth_path: tempdir.path().join("auth"),
@@ -1163,8 +1324,10 @@ mod tests {
                 snapshots_path: tempdir.path().join("snapshots"),
                 dumps_path: tempdir.path().join("dumps"),
                 task_db_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
-                index_size: 1000 * 1000,   // 1 MB, we don't use MiB on purpose.
-                indexer_config: IndexerConfig::default(),
+                index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
+                index_growth_amount: 1000 * 1000, // 1 MB
+                index_count: 5,
+                indexer_config,
                 autobatching_enabled,
             };
 
@@ -1706,105 +1869,6 @@ mod tests {
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "both_task_succeeded");
     }
 
-    #[test]
-    fn document_addition_and_document_deletion() {
-        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
-
-        let content = r#"[
-            { "id": 1, "doggo": "jean bob" },
-            { "id": 2, "catto": "jorts" },
-            { "id": 3, "doggo": "bork" }
-        ]"#;
-
-        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
-        let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
-        file.persist().unwrap();
-        index_scheduler
-            .register(KindWithContent::DocumentAdditionOrUpdate {
-                index_uid: S("doggos"),
-                primary_key: Some(S("id")),
-                method: ReplaceDocuments,
-                content_file: uuid,
-                documents_count,
-                allow_index_creation: true,
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
-        index_scheduler
-            .register(KindWithContent::DocumentDeletion {
-                index_uid: S("doggos"),
-                documents_ids: vec![S("1"), S("2")],
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
-
-        handle.advance_one_successful_batch(); // The addition AND deletion should've been batched together
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_batch");
-
-        let index = index_scheduler.index("doggos").unwrap();
-        let rtxn = index.read_txn().unwrap();
-        let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
-        let field_ids = field_ids_map.ids().collect::<Vec<_>>();
-        let documents = index
-            .all_documents(&rtxn)
-            .unwrap()
-            .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
-            .collect::<Vec<_>>();
-        snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
-    }
-
-    #[test]
-    fn document_deletion_and_document_addition() {
-        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
-        index_scheduler
-            .register(KindWithContent::DocumentDeletion {
-                index_uid: S("doggos"),
-                documents_ids: vec![S("1"), S("2")],
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
-
-        let content = r#"[
-            { "id": 1, "doggo": "jean bob" },
-            { "id": 2, "catto": "jorts" },
-            { "id": 3, "doggo": "bork" }
-        ]"#;
-
-        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
-        let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
-        file.persist().unwrap();
-        index_scheduler
-            .register(KindWithContent::DocumentAdditionOrUpdate {
-                index_uid: S("doggos"),
-                primary_key: Some(S("id")),
-                method: ReplaceDocuments,
-                content_file: uuid,
-                documents_count,
-                allow_index_creation: true,
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
-
-        // The deletion should have failed because it can't create an index
-        handle.advance_one_failed_batch();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_failing_the_deletion");
-
-        // The addition should works
-        handle.advance_one_successful_batch();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_last_successful_addition");
-
-        let index = index_scheduler.index("doggos").unwrap();
-        let rtxn = index.read_txn().unwrap();
-        let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
-        let field_ids = field_ids_map.ids().collect::<Vec<_>>();
-        let documents = index
-            .all_documents(&rtxn)
-            .unwrap()
-            .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
-            .collect::<Vec<_>>();
-        snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
-    }
-
     #[test]
     fn do_not_batch_task_of_different_indexes() {
         let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
@@ -2371,38 +2435,45 @@ mod tests {
 
         let rtxn = index_scheduler.env.read_txn().unwrap();
         let query = Query { limit: Some(0), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[]");
 
         let query = Query { limit: Some(1), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
 
         let query = Query { limit: Some(2), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[1,2,]");
 
         let query = Query { from: Some(1), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,]");
 
         let query = Query { from: Some(2), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,2,]");
 
         let query = Query { from: Some(1), limit: Some(1), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[1,]");
 
         let query = Query { from: Some(1), limit: Some(2), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,]");
     }
 
@@ -2427,21 +2498,24 @@ mod tests {
         let rtxn = index_scheduler.env.read_txn().unwrap();
 
         let query = Query { statuses: Some(vec![Status::Processing]), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[0,]"); // only the processing tasks in the first tick
 
         let query = Query { statuses: Some(vec![Status::Enqueued]), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[1,2,]"); // only the enqueued tasks in the first tick
 
         let query = Query {
             statuses: Some(vec![Status::Enqueued, Status::Processing]),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,2,]"); // both enqueued and processing tasks in the first tick
 
         let query = Query {
@@ -2449,8 +2523,9 @@ mod tests {
             after_started_at: Some(start_time),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both enqueued and processing tasks in the first tick, but limited to those with a started_at
         // that comes after the start of the test, which should excludes the enqueued tasks
         snapshot!(snapshot_bitmap(&tasks), @"[0,]");
@@ -2460,8 +2535,9 @@ mod tests {
             before_started_at: Some(start_time),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both enqueued and processing tasks in the first tick, but limited to those with a started_at
         // that comes before the start of the test, which should excludes all of them
         snapshot!(snapshot_bitmap(&tasks), @"[]");
@@ -2472,8 +2548,9 @@ mod tests {
             before_started_at: Some(start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both enqueued and processing tasks in the first tick, but limited to those with a started_at
         // that comes after the start of the test and before one minute after the start of the test,
         // which should exclude the enqueued tasks and include the only processing task
@@ -2498,8 +2575,9 @@ mod tests {
             before_started_at: Some(start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both succeeded and processing tasks in the first tick, but limited to those with a started_at
         // that comes after the start of the test and before one minute after the start of the test,
         // which should include all tasks
@@ -2510,8 +2588,9 @@ mod tests {
             before_started_at: Some(start_time),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both succeeded and processing tasks in the first tick, but limited to those with a started_at
         // that comes before the start of the test, which should exclude all tasks
         snapshot!(snapshot_bitmap(&tasks), @"[]");
@@ -2522,8 +2601,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // both succeeded and processing tasks in the first tick, but limited to those with a started_at
         // that comes after the start of the second part of the test and before one minute after the
         // second start of the test, which should exclude all tasks
@@ -2541,8 +2621,9 @@ mod tests {
 
         let rtxn = index_scheduler.env.read_txn().unwrap();
 
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // we run the same query to verify that, and indeed find that the last task is matched
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
 
@@ -2552,8 +2633,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // enqueued, succeeded, or processing tasks started after the second part of the test, should
         // again only return the last task
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
@@ -2563,8 +2645,9 @@ mod tests {
 
         // now the last task should have failed
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "end");
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // so running the last query should return nothing
         snapshot!(snapshot_bitmap(&tasks), @"[]");
 
@@ -2574,8 +2657,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // but the same query on failed tasks should return the last task
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
 
@@ -2585,8 +2669,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // but the same query on failed tasks should return the last task
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
 
@@ -2597,8 +2682,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // same query but with an invalid uid
         snapshot!(snapshot_bitmap(&tasks), @"[]");
 
@@ -2609,8 +2695,9 @@ mod tests {
             before_started_at: Some(second_start_time + Duration::minutes(1)),
             ..Default::default()
         };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // same query but with a valid uid
         snapshot!(snapshot_bitmap(&tasks), @"[2,]");
     }
@@ -2640,8 +2727,9 @@ mod tests {
         let rtxn = index_scheduler.env.read_txn().unwrap();
 
         let query = Query { index_uids: Some(vec!["catto".to_owned()]), ..Default::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // only the first task associated with catto is returned, the indexSwap tasks are excluded!
         snapshot!(snapshot_bitmap(&tasks), @"[0,]");
 
@@ -2650,7 +2738,9 @@ mod tests {
             .get_task_ids_from_authorized_indexes(
                 &rtxn,
                 &query,
-                &Some(vec![IndexUidPattern::new_unchecked("doggo")]),
+                &AuthFilter::with_allowed_indexes(
+                    vec![IndexUidPattern::new_unchecked("doggo")].into_iter().collect(),
+                ),
             )
             .unwrap();
         // we have asked for only the tasks associated with catto, but are only authorized to retrieve the tasks
@@ -2662,7 +2752,9 @@ mod tests {
             .get_task_ids_from_authorized_indexes(
                 &rtxn,
                 &query,
-                &Some(vec![IndexUidPattern::new_unchecked("doggo")]),
+                &AuthFilter::with_allowed_indexes(
+                    vec![IndexUidPattern::new_unchecked("doggo")].into_iter().collect(),
+                ),
             )
             .unwrap();
         // we asked for all the tasks, but we are only authorized to retrieve the doggo tasks
@@ -2674,10 +2766,14 @@ mod tests {
             .get_task_ids_from_authorized_indexes(
                 &rtxn,
                 &query,
-                &Some(vec![
-                    IndexUidPattern::new_unchecked("catto"),
-                    IndexUidPattern::new_unchecked("doggo"),
-                ]),
+                &AuthFilter::with_allowed_indexes(
+                    vec![
+                        IndexUidPattern::new_unchecked("catto"),
+                        IndexUidPattern::new_unchecked("doggo"),
+                    ]
+                    .into_iter()
+                    .collect(),
+                ),
             )
             .unwrap();
         // we asked for all the tasks, but we are only authorized to retrieve the doggo and catto tasks
@@ -2685,8 +2781,9 @@ mod tests {
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,]");
 
         let query = Query::default();
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // we asked for all the tasks with all index authorized -> all tasks returned
         snapshot!(snapshot_bitmap(&tasks), @"[0,1,2,3,]");
     }
@@ -2717,8 +2814,9 @@ mod tests {
 
         let rtxn = index_scheduler.read_txn().unwrap();
         let query = Query { canceled_by: Some(vec![task_cancelation.uid]), ..Query::default() };
-        let tasks =
-            index_scheduler.get_task_ids_from_authorized_indexes(&rtxn, &query, &None).unwrap();
+        let tasks = index_scheduler
+            .get_task_ids_from_authorized_indexes(&rtxn, &query, &AuthFilter::default())
+            .unwrap();
         // 0 is not returned because it was not canceled, 3 is not returned because it is the uid of the
         // taskCancelation itself
         snapshot!(snapshot_bitmap(&tasks), @"[1,2,]");
@@ -2728,7 +2826,9 @@ mod tests {
             .get_task_ids_from_authorized_indexes(
                 &rtxn,
                 &query,
-                &Some(vec![IndexUidPattern::new_unchecked("doggo")]),
+                &AuthFilter::with_allowed_indexes(
+                    vec![IndexUidPattern::new_unchecked("doggo")].into_iter().collect(),
+                ),
             )
             .unwrap();
         // Return only 1 because the user is not authorized to see task 2

index-scheduler/src/lru.rs

@@ -0,0 +1,203 @@
+//! Thread-safe `Vec`-backend LRU cache using [`std::sync::atomic::AtomicU64`] for synchronization.
+
+use std::sync::atomic::{AtomicU64, Ordering};
+
+/// Thread-safe `Vec`-backend LRU cache
+#[derive(Debug)]
+pub struct Lru<T> {
+    data: Vec<(AtomicU64, T)>,
+    generation: AtomicU64,
+    cap: usize,
+}
+
+impl<T> Lru<T> {
+    /// Creates a new LRU cache with the specified capacity.
+    ///
+    /// The capacity is allocated up-front, and will never change through a [`Self::put`] operation.
+    ///
+    /// # Panics
+    ///
+    /// - If the capacity is 0.
+    /// - If the capacity exceeds `isize::MAX` bytes.
+    pub fn new(cap: usize) -> Self {
+        assert_ne!(cap, 0, "The capacity of a cache cannot be 0");
+        Self {
+            // Note: since the element of the vector contains an AtomicU64, it is definitely not zero-sized so cap will never be usize::MAX.
+            data: Vec::with_capacity(cap),
+            generation: AtomicU64::new(0),
+            cap,
+        }
+    }
+
+    /// The capacity of this LRU cache, that is the maximum number of elements it can hold before evicting elements from the cache.
+    ///
+    /// The cache will contain at most this number of elements at any given time.
+    pub fn capacity(&self) -> usize {
+        self.cap
+    }
+
+    fn next_generation(&self) -> u64 {
+        // Acquire so this "happens-before" any potential store to a data cell (with Release ordering)
+        let generation = self.generation.fetch_add(1, Ordering::Acquire);
+        generation + 1
+    }
+
+    fn next_generation_mut(&mut self) -> u64 {
+        let generation = self.generation.get_mut();
+        *generation += 1;
+        *generation
+    }
+
+    /// Add a value in the cache, evicting an older value if necessary.
+    ///
+    /// If a value was evicted from the cache, it is returned.
+    ///
+    /// # Complexity
+    ///
+    /// - If the cache is full, then linear in the capacity.
+    /// - Otherwise constant.
+    pub fn put(&mut self, value: T) -> Option<T> {
+        // no need for a memory fence: we assume that whichever mechanism provides us synchronization
+        // (very probably, a RwLock) takes care of fencing for us.
+
+        let next_generation = self.next_generation_mut();
+        let evicted = if self.is_full() { self.pop() } else { None };
+        self.data.push((AtomicU64::new(next_generation), value));
+        evicted
+    }
+
+    /// Evict the oldest value from the cache.
+    ///
+    /// If the cache is empty, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn pop(&mut self) -> Option<T> {
+        // Don't use `Iterator::min_by_key` that provides shared references to its elements,
+        // so that we can get an exclusive one.
+        // This allows to handles the `AtomicU64`s as normal integers without using atomic instructions.
+        let mut min_generation_index = None;
+        for (index, (generation, _)) in self.data.iter_mut().enumerate() {
+            let generation = *generation.get_mut();
+            if let Some((_, min_generation)) = min_generation_index {
+                if min_generation > generation {
+                    min_generation_index = Some((index, generation));
+                }
+            } else {
+                min_generation_index = Some((index, generation))
+            }
+        }
+        min_generation_index.map(|(min_index, _)| self.data.swap_remove(min_index).1)
+    }
+
+    /// The current number of elements in the cache.
+    ///
+    /// This value is guaranteed to be less than or equal to [`Self::capacity`].
+    pub fn len(&self) -> usize {
+        self.data.len()
+    }
+
+    /// Returns `true` if putting any additional element in the cache would cause the eviction of an element.
+    pub fn is_full(&self) -> bool {
+        self.len() == self.capacity()
+    }
+}
+
+pub struct LruMap<K, V>(Lru<(K, V)>);
+
+impl<K, V> LruMap<K, V>
+where
+    K: Eq,
+{
+    /// Creates a new LRU cache map with the specified capacity.
+    ///
+    /// The capacity is allocated up-front, and will never change through a [`Self::insert`] operation.
+    ///
+    /// # Panics
+    ///
+    /// - If the capacity is 0.
+    /// - If the capacity exceeds `isize::MAX` bytes.
+    pub fn new(cap: usize) -> Self {
+        Self(Lru::new(cap))
+    }
+
+    /// Gets a value in the cache map by its key.
+    ///
+    /// If no value matches, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn get(&self, key: &K) -> Option<&V> {
+        for (generation, (candidate, value)) in self.0.data.iter() {
+            if key == candidate {
+                generation.store(self.0.next_generation(), Ordering::Release);
+                return Some(value);
+            }
+        }
+        None
+    }
+
+    /// Gets a value in the cache map by its key.
+    ///
+    /// If no value matches, `None` will be returned.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn get_mut(&mut self, key: &K) -> Option<&mut V> {
+        let next_generation = self.0.next_generation_mut();
+        for (generation, (candidate, value)) in self.0.data.iter_mut() {
+            if key == candidate {
+                *generation.get_mut() = next_generation;
+                return Some(value);
+            }
+        }
+        None
+    }
+
+    /// Inserts a value in the cache map by its key, replacing any existing value and returning any evicted value.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn insert(&mut self, key: K, mut value: V) -> InsertionOutcome<K, V> {
+        match self.get_mut(&key) {
+            Some(old_value) => {
+                std::mem::swap(old_value, &mut value);
+                InsertionOutcome::Replaced(value)
+            }
+            None => match self.0.put((key, value)) {
+                Some((key, value)) => InsertionOutcome::Evicted(key, value),
+                None => InsertionOutcome::InsertedNew,
+            },
+        }
+    }
+
+    /// Removes an element from the cache map by its key, returning its value.
+    ///
+    /// Returns `None` if there was no element with this key in the cache.
+    ///
+    /// # Complexity
+    ///
+    /// - Linear in the capacity of the cache.
+    pub fn remove(&mut self, key: &K) -> Option<V> {
+        for (index, (_, (candidate, _))) in self.0.data.iter_mut().enumerate() {
+            if key == candidate {
+                return Some(self.0.data.swap_remove(index).1 .1);
+            }
+        }
+        None
+    }
+}
+
+/// The result of an insertion in a LRU map.
+pub enum InsertionOutcome<K, V> {
+    /// The key was not in the cache, the key-value pair has been inserted.
+    InsertedNew,
+    /// The key was not in the cache and an old key-value pair was evicted from the cache to make room for its insertions.
+    Evicted(K, V),
+    /// The key was already in the cache map, its value has been updated.
+    Replaced(V),
+}

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

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1755
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -23,7 +22,7 @@ canceled [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 [0,]

index-scheduler/src/snapshots/lib.rs/cancel_enqueued_task/initial_tasks_enqueued.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/aborted_indexation.snap

@@ -25,7 +25,9 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["beavero", "catto"]
+beavero: { number_of_documents: 0, field_distribution: {} }
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

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

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1859
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -27,7 +26,9 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["beavero", "catto"]
+beavero: { number_of_documents: 0, field_distribution: {} }
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 3 [1,2,]

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/first_task_processed.snap

@@ -23,7 +23,8 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_mix_of_tasks/processing_second_task_cancel_enqueued.snap

@@ -25,7 +25,8 @@ catto [0,]
 wolfo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/aborted_indexation.snap

@@ -20,7 +20,8 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

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

@@ -1,6 +1,5 @@
 ---
 source: index-scheduler/src/lib.rs
-assertion_line: 1818
 ---
 ### Autobatching Enabled = true
 ### Processing Tasks:
@@ -23,7 +22,8 @@ canceled [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 [0,]

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/cancel_task_registered.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/initial_task_processing.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_processing_task/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

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

@@ -21,7 +21,8 @@ succeeded [0,1,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 1 []

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/initial_task_processed.snap

@@ -19,7 +19,8 @@ succeeded [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 1, field_distribution: {"id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/cancel_succeeded_task/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/do_not_batch_task_of_different_indexes/all_tasks_processed.snap

@@ -27,7 +27,10 @@ doggos [0,3,]
 girafos [2,5,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["cattos", "doggos", "girafos"]
+cattos: { number_of_documents: 0, field_distribution: {} }
+doggos: { number_of_documents: 0, field_distribution: {} }
+girafos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/after_register.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/after_the_batch_creation.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition/once_everything_is_processed.snap

@@ -19,7 +19,8 @@ succeeded [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/after_processing_the_batch.snap

@@ -21,7 +21,8 @@ succeeded [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_second_task.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/before_index_creation.snap

@@ -23,7 +23,8 @@ succeeded [0,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/both_task_succeeded.snap

@@ -23,7 +23,7 @@ succeeded [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_second_task.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion/registered_the_third_task.snap

@@ -22,7 +22,7 @@ enqueued [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion_on_unexisting_index/1.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_addition_and_index_deletion_on_unexisting_index/2.snap

@@ -21,7 +21,7 @@ succeeded [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_failing_the_deletion.snap

@@ -21,7 +21,7 @@ failed [0,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_last_successful_addition.snap

@@ -22,7 +22,8 @@ failed [0,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_second_task.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/document_addition_batch_created.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/document_addition_failed.snap

@@ -19,7 +19,7 @@ failed [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_addition/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_index_creation/after_register.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_index_creation/index_creation_failed.snap

@@ -19,7 +19,7 @@ failed [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_batch_succeeded.snap

@@ -18,7 +18,8 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/after_failing_to_commit.snap

@@ -18,7 +18,8 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/document_addition_succeeded_but_index_scheduler_not_updated.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/fail_in_update_task_after_process_batch_success_for_document_addition/task_successfully_processed.snap

@@ -19,7 +19,8 @@ succeeded [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/after_batch_creation.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 index_a [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 index_a [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/registered_the_second_task.snap

@@ -20,7 +20,7 @@ index_a [0,]
 index_b [1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/insert_task_while_another_task_is_processing/registered_the_third_task.snap

@@ -22,7 +22,7 @@ index_a [0,2,]
 index_b [1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/panic_in_process_batch_for_index_creation/index_creation_failed.snap

@@ -19,7 +19,7 @@ failed [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/panic_in_process_batch_for_index_creation/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 catto [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/processed_the_first_task.snap

@@ -23,7 +23,8 @@ cattos [1,]
 doggos [0,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/processed_the_second_task.snap

@@ -23,7 +23,9 @@ cattos [1,]
 doggos [0,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["cattos", "doggos"]
+cattos: { number_of_documents: 0, field_distribution: {} }
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/processed_the_third_task.snap

@@ -23,7 +23,8 @@ cattos [1,]
 doggos [0,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["cattos"]
+cattos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/registered_the_second_task.snap

@@ -20,7 +20,7 @@ cattos [1,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_inserted_without_new_signal/registered_the_third_task.snap

@@ -22,7 +22,7 @@ cattos [1,]
 doggos [0,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/first.snap

@@ -23,7 +23,8 @@ succeeded [0,]
 doggos [0,1,2,3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/fourth.snap

@@ -23,7 +23,8 @@ succeeded [0,1,2,3,]
 doggos [0,1,2,3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggos [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/registered_the_fourth_task.snap

@@ -22,7 +22,7 @@ enqueued [0,1,2,3,]
 doggos [0,1,2,3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/registered_the_second_task.snap

@@ -20,7 +20,7 @@ enqueued [0,1,]
 doggos [0,1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/registered_the_third_task.snap

@@ -21,7 +21,7 @@ enqueued [0,1,2,]
 doggos [0,1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/second.snap

@@ -23,7 +23,8 @@ succeeded [0,1,]
 doggos [0,1,2,3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/process_tasks_without_autobatching/third.snap

@@ -23,7 +23,8 @@ succeeded [0,1,2,]
 doggos [0,1,2,3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["doggos"]
+doggos: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_canceled_by/start.snap

@@ -26,7 +26,8 @@ catto [0,2,]
 doggo [1,2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto"]
+catto: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 3 [1,2,]

index-scheduler/src/snapshots/lib.rs/query_tasks_from_and_limit/processed_all_tasks.snap

@@ -23,7 +23,10 @@ doggo [0,]
 whalo [1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto", "doggo", "whalo"]
+catto: { number_of_documents: 0, field_distribution: {} }
+doggo: { number_of_documents: 0, field_distribution: {} }
+whalo: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_from_and_limit/registered_the_first_task.snap

@@ -18,7 +18,7 @@ enqueued [0,]
 doggo [0,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_from_and_limit/registered_the_second_task.snap

@@ -20,7 +20,7 @@ doggo [0,]
 whalo [1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_from_and_limit/registered_the_third_task.snap

@@ -22,7 +22,7 @@ doggo [0,]
 whalo [1,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_simple/end.snap

@@ -24,7 +24,9 @@ doggo [1,]
 whalo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["catto", "doggo"]
+catto: { number_of_documents: 0, field_distribution: {} }
+doggo: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_simple/start.snap

@@ -22,7 +22,7 @@ doggo [1,]
 whalo [2,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/query_tasks_special_rules/start.snap

@@ -24,7 +24,7 @@ doggo [1,2,]
 whalo [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/register/everything_is_succesfully_registered.snap

@@ -23,7 +23,7 @@ catto [0,1,2,]
 doggo [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-[]
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/create_a.snap

@@ -25,7 +25,8 @@ c [2,]
 d [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a"]
+a: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/create_b.snap

@@ -25,7 +25,9 @@ c [2,]
 d [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/create_c.snap

@@ -25,7 +25,10 @@ c [2,]
 d [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/create_d.snap

@@ -25,7 +25,11 @@ c [2,]
 d [3,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/first_swap_processed.snap

@@ -28,7 +28,11 @@ c [3,4,5,]
 d [2,4,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/first_swap_registered.snap

@@ -27,7 +27,11 @@ c [2,4,]
 d [3,4,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/second_swap_processed.snap

@@ -28,7 +28,11 @@ c [1,4,5,]
 d [2,4,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/third_empty_swap_processed.snap

@@ -29,7 +29,11 @@ c [1,4,5,]
 d [2,4,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By:
 

index-scheduler/src/snapshots/lib.rs/swap_indexes/two_swaps_registered.snap

@@ -28,7 +28,11 @@ c [2,4,5,]
 d [3,4,]
 ----------------------------------------------------------------------
 ### Index Mapper:
-["a", "b", "c", "d"]
+a: { number_of_documents: 0, field_distribution: {} }
+b: { number_of_documents: 0, field_distribution: {} }
+c: { number_of_documents: 0, field_distribution: {} }
+d: { number_of_documents: 0, field_distribution: {} }
+
 ----------------------------------------------------------------------
 ### Canceled By: