fix auto-synchronization with zk

3967: Bring back changes from `release-v1.3.0` into `main` r=ManyTheFish a=curquiza

Using a temp branch because of git conflict

Co-authored-by: Cong Chen <cong.chen@ocrlabs.com>
Co-authored-by: ManyTheFish <many@meilisearch.com>
Co-authored-by: Louis Dureuil <louis@meilisearch.com>
Co-authored-by: meili-bors[bot] <89034592+meili-bors[bot]@users.noreply.github.com>
Co-authored-by: Tamo <tamo@meilisearch.com>
Co-authored-by: Kerollmops <clement@meilisearch.com>
Co-authored-by: Clément Renault <clement@meilisearch.com>

.github/workflows/test-suite.yml

@@ -30,20 +30,20 @@ jobs:
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - name: Run test with Rust stable
+      - name: Setup test with Rust stable
         if: github.event_name != 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
           override: true
-      - name: Run test with Rust nightly
+      - name: Setup test with Rust nightly
         if: github.event_name == 'schedule'
         uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -65,7 +65,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -117,17 +117,17 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: actions-rs/toolchain@v1 
-        with: 
-          toolchain: stable 
-          override: true 
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo tree without default features and check lindera is not present
         run: |
           cargo tree -f '{p} {f}' -e normal --no-default-features | grep lindera -vqz
       - name: Run cargo tree with default features and check lindera is pressent
         run: |
           cargo tree -f '{p} {f}' -e normal | grep lindera -qz
-                
+
   # We run tests in debug also, to make sure that the debug_assertions are hit
   test-debug:
     name: Run tests in debug
@@ -146,7 +146,7 @@ jobs:
           toolchain: stable
           override: true
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -165,7 +165,7 @@ jobs:
           override: true
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -184,7 +184,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.4.0
+        uses: Swatinem/rust-cache@v2.5.0
       - name: Run cargo fmt
         # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

Cargo.lock

@@ -303,6 +303,12 @@ dependencies = [
  "alloc-no-stdlib",
 ]
 
+[[package]]
+name = "allocator-api2"
+version = "0.2.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0942ffc6dcaadf03badf6e6a2d0228460359d5e34b57ccdc720b7382dfbd5ec5"
+
 [[package]]
 name = "anes"
 version = "0.1.6"
@@ -405,7 +411,7 @@ checksum = "16e62a023e7c117e27523144c5d2459f4397fcc3cab0085af8e2224f643a0193"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -416,7 +422,7 @@ checksum = "b9ccdd8f2a161be9bd5c023df56f1b2a0bd1d83872ae53b71a84a12c9bf6e842"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -603,7 +609,7 @@ checksum = "fdde5c9cd29ebd706ce1b35600920a33550e402fc998a2e53ad3b42c3c47a192"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -664,6 +670,15 @@ version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
 
+[[package]]
+name = "castaway"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a17ed5635fc8536268e5d4de1e22e81ac34419e5f052d4d51f4e01dcc263fcc"
+dependencies = [
+ "rustversion",
+]
+
 [[package]]
 name = "cc"
 version = "1.0.79"
@@ -791,10 +806,10 @@ version = "4.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "191d9573962933b4027f932c600cd252ce27a8ad5979418fe78e43c07996f27b"
 dependencies = [
- "heck",
+ "heck 0.4.1",
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -809,6 +824,17 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
 
+[[package]]
+name = "compact_str"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e33b5c3ee2b4ffa00ac2b00d1645cd9229ade668139bccf95f15fadcf374127b"
+dependencies = [
+ "castaway",
+ "itoa",
+ "ryu",
+]
+
 [[package]]
 name = "concat-arrays"
 version = "0.1.2"
@@ -832,6 +858,26 @@ dependencies = [
  "windows-sys 0.45.0",
 ]
 
+[[package]]
+name = "const_format"
+version = "0.2.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c990efc7a285731f9a4378d81aff2f0e85a2c8781a05ef0f8baa8dac54d0ff48"
+dependencies = [
+ "const_format_proc_macros",
+]
+
+[[package]]
+name = "const_format_proc_macros"
+version = "0.2.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e026b6ce194a874cb9cf32cd5772d1ef9767cc8fcb5765948d74f37a9d8b2bf6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-xid",
+]
+
 [[package]]
 name = "constant_time_eq"
 version = "0.1.5"
@@ -1224,9 +1270,9 @@ dependencies = [
 
 [[package]]
 name = "either"
-version = "1.8.1"
+version = "1.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7fcaabb2fef8c910e7f4c7ce9f67a1283a1715879a7c230ca9d6d1ae31f16d91"
+checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"
 dependencies = [
  "serde",
 ]
@@ -1336,7 +1382,7 @@ checksum = "eecf8589574ce9b895052fa12d69af7a233f99e6107f5cb8dd1044f2a17bfdcb"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -1537,7 +1583,7 @@ checksum = "89ca545a94061b6365f2c7355b4b32bd20df3ff95f02da9329b34ccc3bd6ee72"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -1715,6 +1761,19 @@ name = "hashbrown"
 version = "0.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2c6201b9ff9fd90a5a3bac2e56a830d0caa509576f0e503818ee82c181b3437a"
+dependencies = [
+ "ahash 0.8.3",
+ "allocator-api2",
+]
+
+[[package]]
+name = "hashlink"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "312f66718a2d7789ffef4f4b7b213138ed9f1eb3aa1d0d82fc99f88fb3ffd26f"
+dependencies = [
+ "hashbrown 0.14.0",
+]
 
 [[package]]
 name = "heapless"
@@ -1729,6 +1788,15 @@ dependencies = [
  "stable_deref_trait",
 ]
 
+[[package]]
+name = "heck"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6d621efb26863f0e9924c6ac577e8275e5e6b77455db64ffa6c65c904e9e132c"
+dependencies = [
+ "unicode-segmentation",
+]
+
 [[package]]
 name = "heck"
 version = "0.4.1"
@@ -1892,6 +1960,12 @@ dependencies = [
  "unicode-normalization",
 ]
 
+[[package]]
+name = "ignore-result"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "665ff4dce8edd10d490641ccb78949832f1ddbff02c584fb1f85ab888fe0e50c"
+
 [[package]]
 name = "index-scheduler"
 version = "1.3.0"
@@ -1912,6 +1986,7 @@ dependencies = [
  "meilisearch-types",
  "nelson",
  "page_size 0.5.0",
+ "puffin",
  "roaring",
  "serde",
  "serde_json",
@@ -2022,12 +2097,12 @@ dependencies = [
 
 [[package]]
 name = "is-terminal"
-version = "0.4.8"
+version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "24fddda5af7e54bf7da53067d6e802dbcc381d0a8eef629df528e3ebf68755cb"
+checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
 dependencies = [
  "hermit-abi 0.3.1",
- "rustix 0.38.2",
+ "rustix 0.38.4",
  "windows-sys 0.48.0",
 ]
 
@@ -2397,9 +2472,9 @@ checksum = "ef53942eb7bf7ff43a617b3e2c1c4a5ecf5944a7c1bc12d7ee39bbb15e5c1519"
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.3"
+version = "0.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09fc20d2ca12cb9f044c93e3bd6d32d523e6e2ec3db4f7b2939cd99026ecd3f0"
+checksum = "57bcfdad1b858c2db7c38303a6d2ad4dfaf5eb53dfeb0910128b2c26d6158503"
 
 [[package]]
 name = "lmdb-rkv-sys"
@@ -2467,6 +2542,12 @@ dependencies = [
  "syn 1.0.109",
 ]
 
+[[package]]
+name = "lz4_flex"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b8c72594ac26bfd34f2d99dfced2edfaddfe8a476e3ff2ca0eb293d925c4f83"
+
 [[package]]
 name = "manifest-dir-macros"
 version = "0.1.17"
@@ -2476,7 +2557,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -2556,6 +2637,8 @@ dependencies = [
  "pin-project-lite",
  "platform-dirs",
  "prometheus",
+ "puffin",
+ "puffin_http",
  "rand",
  "rayon",
  "regex",
@@ -2587,6 +2670,7 @@ dependencies = [
  "walkdir",
  "yaup",
  "zip",
+ "zookeeper-client",
 ]
 
 [[package]]
@@ -2596,6 +2680,7 @@ dependencies = [
  "base64 0.21.2",
  "enum-iterator",
  "hmac",
+ "log",
  "maplit",
  "meilisearch-types",
  "rand",
@@ -2605,7 +2690,9 @@ dependencies = [
  "sha2",
  "thiserror",
  "time",
+ "tokio",
  "uuid 1.3.3",
+ "zookeeper-client",
 ]
 
 [[package]]
@@ -2700,6 +2787,7 @@ dependencies = [
  "obkv",
  "once_cell",
  "ordered-float",
+ "puffin",
  "rand",
  "rand_pcg",
  "rayon",
@@ -2854,6 +2942,27 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "num_enum"
+version = "0.5.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f646caf906c20226733ed5b1374287eb97e3c2a5c227ce668c1f2ce20ae57c9"
+dependencies = [
+ "num_enum_derive",
+]
+
+[[package]]
+name = "num_enum_derive"
+version = "0.5.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dcbff9bc912032c62bf65ef1d5aea88983b420f4f839db1e9b0c281a25c9c799"
+dependencies = [
+ "proc-macro-crate",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
 [[package]]
 name = "object"
 version = "0.30.3"
@@ -3030,7 +3139,7 @@ dependencies = [
  "pest_meta",
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -3149,6 +3258,16 @@ version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
 
+[[package]]
+name = "proc-macro-crate"
+version = "1.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f4c021e1093a56626774e81216a4ce732a735e5bad4868a03f3ed65ca0c3919"
+dependencies = [
+ "once_cell",
+ "toml_edit",
+]
+
 [[package]]
 name = "proc-macro-error"
 version = "1.0.4"
@@ -3175,9 +3294,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.66"
+version = "1.0.64"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18fb31db3f9bddb2ea821cde30a9f70117e3f119938b5ee630b7403aa6e2ead9"
+checksum = "78803b62cbf1f46fde80d7c0e803111524b9877184cfe7c3033659490ac7a7da"
 dependencies = [
  "unicode-ident",
 ]
@@ -3219,10 +3338,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "106dd99e98437432fed6519dedecfade6a06a73bb7b2a1e019fdd2bee5778d94"
 
 [[package]]
-name = "quote"
-version = "1.0.31"
+name = "puffin"
+version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5fe8a65d69dd0808184ebb5f836ab526bb259db23c657efa38711b1072ee47f0"
+checksum = "76425abd4e1a0ad4bd6995dd974b52f414fca9974171df8e3708b3e660d05a21"
+dependencies = [
+ "anyhow",
+ "bincode",
+ "byteorder",
+ "cfg-if",
+ "instant",
+ "lz4_flex",
+ "once_cell",
+ "parking_lot",
+ "serde",
+]
+
+[[package]]
+name = "puffin_http"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13bffc600c35913d282ae1e96a6ffcdf36dc7a7cdb9310e0ba15914d258c8193"
+dependencies = [
+ "anyhow",
+ "crossbeam-channel",
+ "log",
+ "puffin",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.30"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5907a1b7c277254a8b15170f6e7c97cfa60ee7872a3217663bb81151e48184bb"
 dependencies = [
  "proc-macro2",
 ]
@@ -3470,14 +3618,14 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.38.2"
+version = "0.38.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aabcb0461ebd01d6b79945797c27f8529082226cb630a9865a71870ff63532a4"
+checksum = "0a962918ea88d644592894bc6dc55acc6c0956488adcebbfb6e273506b7fd6e5"
 dependencies = [
  "bitflags 2.3.3",
  "errno",
  "libc",
- "linux-raw-sys 0.4.3",
+ "linux-raw-sys 0.4.5",
  "windows-sys 0.48.0",
 ]
 
@@ -3583,9 +3731,9 @@ checksum = "bebd363326d05ec3e2f532ab7660680f3b02130d780c299bca73469d521bc0ed"
 
 [[package]]
 name = "serde"
-version = "1.0.171"
+version = "1.0.180"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "30e27d1e4fd7659406c492fd6cfaf2066ba8773de45ca75e855590f856dc34a9"
+checksum = "0ea67f183f058fe88a4e3ec6e2788e003840893b91bac4559cabedd00863b3ed"
 dependencies = [
  "serde_derive",
 ]
@@ -3610,20 +3758,20 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.171"
+version = "1.0.180"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "389894603bd18c46fa56231694f8d827779c0951a667087194cf9de94ed24682"
+checksum = "24e744d7782b686ab3b73267ef05697159cc0e5abbed3f47f9933165e5219036"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.103"
+version = "1.0.104"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d03b412469450d4404fe8499a268edd7f8b79fecb074b0d812ad64ca21f4031b"
+checksum = "076066c5f1078eac5b722a31827a8832fe108bed65dfa75e233c89f8206e976c"
 dependencies = [
  "indexmap 2.0.0",
  "itoa",
@@ -3814,6 +3962,28 @@ version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
+[[package]]
+name = "strum"
+version = "0.23.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cae14b91c7d11c9a851d3fbc80a963198998c2a64eec840477fa92d8ce9b70bb"
+dependencies = [
+ "strum_macros",
+]
+
+[[package]]
+name = "strum_macros"
+version = "0.23.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5bb0dc7ee9c15cea6199cde9a127fa16a4c5819af85395457ad72d68edc85a38"
+dependencies = [
+ "heck 0.3.3",
+ "proc-macro2",
+ "quote",
+ "rustversion",
+ "syn 1.0.109",
+]
+
 [[package]]
 name = "subtle"
 version = "2.5.0"
@@ -3833,9 +4003,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.26"
+version = "2.0.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45c3457aacde3c65315de5031ec191ce46604304d2446e803d71ade03308d970"
+checksum = "04361975b3f5e348b2189d8dc55bc942f278b2d482a6a0365de5bdd62d351567"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -3922,22 +4092,22 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.43"
+version = "1.0.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a35fc5b8971143ca348fa6df4f024d4d55264f3468c71ad1c2f365b0a4d58c42"
+checksum = "611040a08a0439f8248d1990b111c95baa9c704c805fa1f62104b39655fd7f90"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.43"
+version = "1.0.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "463fe12d7993d3b327787537ce8dd4dfa058de32fc2b195ef3cde03dc4771e8f"
+checksum = "090198534930841fab3a5d1bb637cde49e339654e606195f8d9c76eeb081dc96"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -4019,7 +4189,7 @@ checksum = "630bdcf245f78637c13ec01ffae6187cca34625e8c63150d424b59e55af2675e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
 ]
 
 [[package]]
@@ -4344,7 +4514,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
  "wasm-bindgen-shared",
 ]
 
@@ -4378,7 +4548,7 @@ checksum = "e128beba882dd1eb6200e1dc92ae6c5dbaa4311aa7bb211ca035779e5efc39f8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.26",
+ "syn 2.0.28",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
@@ -4693,6 +4863,27 @@ dependencies = [
  "zstd 0.11.2+zstd.1.5.2",
 ]
 
+[[package]]
+name = "zookeeper-client"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ade019937af9b1e2160582cb8d905bcff5d4b71da82444b7bf2ccc9c93f344f2"
+dependencies = [
+ "bytes",
+ "compact_str",
+ "const_format",
+ "either",
+ "hashbrown 0.12.3",
+ "hashlink",
+ "ignore-result",
+ "log",
+ "num_enum",
+ "static_assertions",
+ "strum",
+ "thiserror",
+ "tokio",
+]
+
 [[package]]
 name = "zstd"
 version = "0.11.2+zstd.1.5.2"

PROFILING.md

@@ -0,0 +1,19 @@
+# Profiling Meilisearch
+
+Search engine technologies are complex pieces of software that require thorough profiling tools. We chose to use [Puffin](https://github.com/EmbarkStudios/puffin), which the Rust gaming industry uses extensively. You can export and import the profiling reports using the top bar's _File_ menu options.
+
+![An example profiling with Puffin viewer](assets/profiling-example.png)
+
+## Profiling the Indexing Process
+
+When you enable the `profile-with-puffin` feature of Meilisearch, a Puffin HTTP server will run on Meilisearch and listen on the default _0.0.0.0:8585_ address. This server will record a "frame" whenever it executes the `IndexScheduler::tick` method.
+
+Once your Meilisearch is running and awaits new indexation operations, you must [install and run the `puffin_viewer` tool](https://github.com/EmbarkStudios/puffin/tree/main/puffin_viewer) to see the profiling results. I advise you to run the viewer with the `RUST_LOG=puffin_http::client=debug` environment variable to see the client trying to connect to your server.
+
+Another piece of advice on the Puffin viewer UI interface is to consider the _Merge children with same ID_ option. It can hide the exact actual timings at which events were sent. Please turn it off when you see strange gaps on the Flamegraph. It can help.
+
+## Profiling the Search Process
+
+We still need to take the time to profile the search side of the engine with Puffin. It would require time to profile the filtering phase, query parsing, creation, and execution. We could even profile the Actix HTTP server.
+
+The only issue we see is the framing system. Puffin requires a global frame-based profiling phase, which collides with Meilisearch's ability to accept and answer multiple requests on different threads simultaneously.

README.md

@@ -1,16 +1,20 @@
 <p align="center">
-  <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
-  <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-light-mode-only" target="_blank">
+    <img src="assets/meilisearch-logo-light.svg?sanitize=true#gh-light-mode-only">
+  </a>
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=logo#gh-dark-mode-only" target="_blank">
+    <img src="assets/meilisearch-logo-dark.svg?sanitize=true#gh-dark-mode-only">
+  </a>
 </p>
 
 <h4 align="center">
-  <a href="https://www.meilisearch.com">Website</a> |
+  <a href="https://www.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Website</a> |
   <a href="https://roadmap.meilisearch.com/tabs/1-under-consideration">Roadmap</a> |
-  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch">Meilisearch Cloud</a> |
-  <a href="https://blog.meilisearch.com">Blog</a> |
-  <a href="https://www.meilisearch.com/docs">Documentation</a> |
-  <a href="https://www.meilisearch.com/docs/faq">FAQ</a> |
-  <a href="https://discord.meilisearch.com">Discord</a>
+  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Meilisearch Cloud</a> |
+  <a href="https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Blog</a> |
+  <a href="https://www.meilisearch.com/docs?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Documentation</a> |
+  <a href="https://www.meilisearch.com/docs/faq?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">FAQ</a> |
+  <a href="https://discord.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=nav">Discord</a>
 </h4>
 
 <p align="center">
@@ -24,40 +28,40 @@
 Meilisearch helps you shape a delightful search experience in a snap, offering features that work out-of-the-box to speed up your workflow.
 
 <p align="center" name="demo">
-  <a href="https://where2watch.meilisearch.com/#gh-light-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-light-mode-only" target="_blank">
     <img src="assets/demo-light.gif#gh-light-mode-only" alt="A bright colored application for finding movies screening near the user">
   </a>
-  <a href="https://where2watch.meilisearch.com/#gh-dark-mode-only" target="_blank">
+  <a href="https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-gif#gh-dark-mode-only" target="_blank">
     <img src="assets/demo-dark.gif#gh-dark-mode-only" alt="A dark colored application for finding movies screening near the user">
   </a>
 </p>
 
-🔥 [**Try it!**](https://where2watch.meilisearch.com/) 🔥
+🔥 [**Try it!**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demo-link) 🔥
 
 ## ✨ Features
 
 - **Search-as-you-type:** find search results in less than 50 milliseconds
-- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
-- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
-- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting):** sort results based on price, date, or pretty much anything else your users need
-- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#synonyms):** configure synonyms to include more relevant content in your search results
-- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch):** filter and sort documents based on geographic data
-- **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
-- **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys):** control which users can access what data with API keys that allow fine-grained permissions handling
-- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens):** personalize search results for any number of application tenants
+- **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
+- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** sort results based on price, date, or pretty much anything else your users need
+- **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features#synonyms):** configure synonyms to include more relevant content in your search results
+- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** filter and sort documents based on geographic data
+- **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
+- **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** control which users can access what data with API keys that allow fine-grained permissions handling
+- **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** personalize search results for any number of application tenants
 - **Highly Customizable:** customize Meilisearch to your specific needs or use our out-of-the-box and hassle-free presets
-- **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview):** integrate Meilisearch in your technical stack with our plugins and SDKs
+- **[RESTful API](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=features):** integrate Meilisearch in your technical stack with our plugins and SDKs
 - **Easy to install, deploy, and maintain**
 
 ## 📖 Documentation
 
-You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/).
+You can consult Meilisearch's documentation at [https://www.meilisearch.com/docs](https://www.meilisearch.com/docs/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=docs).
 
 ## 🚀 Getting started
 
-For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start) guide.
+For basic instructions on how to set up Meilisearch, add documents to an index, and search for documents, take a look at our [Quick Start](https://www.meilisearch.com/docs/learn/getting_started/quick_start?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) guide.
 
-You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting) for an introduction to some of Meilisearch's most popular features.
+You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=get-started) for an introduction to some of Meilisearch's most popular features.
 
 ## ⚡ Supercharge your Meilisearch experience
 
@@ -67,29 +71,29 @@ Say goodbye to server deployment and manual updates with [Meilisearch Cloud](htt
 
 Install one of our SDKs in your project for seamless integration between Meilisearch and your favorite language or framework!
 
-Take a look at the complete [Meilisearch integration list](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks).
+Take a look at the complete [Meilisearch integration list](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-link).
 
-[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks)
+[![Logos belonging to different languages and frameworks supported by Meilisearch, including React, Ruby on Rails, Go, Rust, and PHP](assets/integrations.png)](https://www.meilisearch.com/docs/learn/what_is_meilisearch/sdks?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=sdks-logos)
 
 ## ⚙️ Advanced usage
 
-Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview) close at hand.
+Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) close at hand.
 
-We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens).
+We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
 
-Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes).
+Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
 
 ## 📊 Telemetry
 
-Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry#how-to-disable-data-collection) whenever you want.
+Meilisearch collects **anonymized** data from users to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
 
-To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
+To request deletion of collected data, please write to us at [privacy@meilisearch.com](mailto:privacy@meilisearch.com). Don't forget to include your `Instance UID` in the message, as this helps us quickly find and delete your data.
 
-If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry) of our documentation.
+If you want to know more about the kind of data we collect and what we use it for, check the [telemetry section](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) of our documentation.
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/)
+Meilisearch is a search engine created by [Meili](https://www.welcometothejungle.com/en/companies/meilisearch), a software development company based in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 

benchmarks/Cargo.toml

@@ -14,7 +14,7 @@ license.workspace = true
 anyhow = "1.0.70"
 csv = "1.2.1"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.36", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }
 
 [dev-dependencies]

docker-compose.yml

@@ -0,0 +1,37 @@
+version: "3.9"
+services:
+  zk1:
+    container_name: zk1
+    hostname: zk1
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21811:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=1
+      - ZOO_SERVERS=0.0.0.0:2888:3888,zk2:2888:3888,zk3:2888:3888
+  zk2:
+    container_name: zk2
+    hostname: zk2
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21812:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=2
+      - ZOO_SERVERS=zk1:2888:3888,0.0.0.0:2888:3888,zk3:2888:3888
+  zk3:
+    container_name: zk3
+    hostname: zk3
+    image: bitnami/zookeeper:3.7.1
+    ports:
+      - 21813:2181
+    environment:
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_SERVER_ID=3
+      - ZOO_SERVERS=zk1:2888:3888,zk2:2888:3888,0.0.0.0:2888:3888
+  zoonavigator:
+    container_name: zoonavigator
+    image: elkozmon/zoonavigator
+    ports:
+      - 9000:9000

index-scheduler/Cargo.toml

@@ -22,6 +22,7 @@ log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
+puffin = "0.16.0"
 roaring = { version = "0.10.1", features = ["serde"] }
 serde = { version = "1.0.160", features = ["derive"] }
 serde_json = { version = "1.0.95", features = ["preserve_order"] }

index-scheduler/src/batch.rs

@@ -471,6 +471,8 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(crate::tests::FailureLocation::InsideCreateBatch)?;
 
+        puffin::profile_function!();
+
         let enqueued = &self.get_status(rtxn, Status::Enqueued)?;
         let to_cancel = self.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
 
@@ -575,6 +577,9 @@ impl IndexScheduler {
             self.maybe_fail(crate::tests::FailureLocation::PanicInsideProcessBatch)?;
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
+
+        puffin::profile_function!(format!("{:?}", batch));
+
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -1111,6 +1116,8 @@ impl IndexScheduler {
         index: &'i Index,
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
+        puffin::profile_function!();
+
         match operation {
             IndexOperation::DocumentClear { mut tasks, .. } => {
                 let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;

index-scheduler/src/lib.rs

@@ -1053,6 +1053,8 @@ impl IndexScheduler {
             self.breakpoint(Breakpoint::Start);
         }
 
+        puffin::GlobalProfiler::lock().new_frame();
+
         self.cleanup_task_queue()?;
 
         let rtxn = self.env.read_txn().map_err(Error::HeedTransaction)?;

meilisearch-auth/Cargo.toml

@@ -14,6 +14,7 @@ license.workspace = true
 base64 = "0.21.0"
 enum-iterator = "1.4.0"
 hmac = "0.12.1"
+log = "0.4.19"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
@@ -23,4 +24,6 @@ serde_json = { version = "1.0.95", features = ["preserve_order"] }
 sha2 = "0.10.6"
 thiserror = "1.0.40"
 time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+tokio = { version = "1.27.0", features = ["full"] }
 uuid = { version = "1.3.1", features = ["serde", "v4"] }
+zookeeper-client = "0.4.0"

meilisearch-auth/src/error.rs

@@ -2,6 +2,7 @@ use std::error::Error;
 
 use meilisearch_types::error::{Code, ErrorCode};
 use meilisearch_types::internal_error;
+use zookeeper_client as zk;
 
 pub type Result<T> = std::result::Result<T, AuthControllerError>;
 
@@ -19,6 +20,8 @@ internal_error!(
     AuthControllerError: meilisearch_types::milli::heed::Error,
     std::io::Error,
     serde_json::Error,
+    tokio::task::JoinError,
+    zk::Error,
     std::str::Utf8Error
 );
 

meilisearch-auth/src/lib.rs

@@ -16,22 +16,119 @@ pub use store::open_auth_store_env;
 use store::{generate_key_as_hexa, HeedAuthStore};
 use time::OffsetDateTime;
 use uuid::Uuid;
+use zookeeper_client as zk;
 
 #[derive(Clone)]
 pub struct AuthController {
     store: Arc<HeedAuthStore>,
     master_key: Option<String>,
+    zk: Option<zk::Client>,
 }
 
 impl AuthController {
-    pub fn new(db_path: impl AsRef<Path>, master_key: &Option<String>) -> Result<Self> {
+    pub async fn new(
+        db_path: impl AsRef<Path>,
+        master_key: &Option<String>,
+        zk: Option<zk::Client>,
+    ) -> Result<Self> {
         let store = HeedAuthStore::new(db_path)?;
+        let controller = Self { store: Arc::new(store), master_key: master_key.clone(), zk };
 
-        if store.is_empty()? {
-            generate_default_keys(&store)?;
+        match controller.zk {
+            // setup the auth zk environment, the `auth` node
+            Some(ref zk) => {
+                let options =
+                    zk::CreateOptions::new(zk::CreateMode::Persistent, zk::Acl::anyone_all());
+                // TODO: we should catch the potential unexpected errors here https://docs.rs/zookeeper-client/latest/zookeeper_client/struct.Client.html#method.create
+                // for the moment we consider that `create` only returns Error::NodeExists.
+                match zk.create("/auth", &[], &options).await {
+                    // If the store is empty, we must generate and push the default api-keys.
+                    Ok(_) => generate_default_keys(&controller).await?,
+                    // If the node exist we should clear our DB and download all the existing api-keys
+                    Err(zk::Error::NodeExists) => {
+                        log::warn!("Auth directory already exists, we need to clear our keys + import the one in zookeeper");
+
+                        let store = controller.store.clone();
+                        tokio::task::spawn_blocking(move || store.delete_all_keys()).await??;
+                        let children = zk
+                            .list_children("/auth")
+                            .await
+                            .expect("Internal, the auth directory was deleted during execution.");
+
+                        log::info!("Importing {} api-keys", children.len());
+                        for path in children {
+                            log::info!("  Importing {}", path);
+                            match zk.get_data(&format!("/auth/{}", &path)).await {
+                                Ok((key, _stat)) => {
+                                let key = serde_json::from_slice(&key).unwrap();
+                                let store = controller.store.clone();
+                                tokio::task::spawn_blocking(move || store.put_api_key(key))
+                                    .await??;
+
+                                },
+                                Err(e) => panic!("{e}")
+                            }
+                            // else the file was deleted while we were inserting the key. We ignore it.
+                            // TODO: What happens if someone updates the files before we have the time
+                            //       to setup the watcher
+                        }
+                    }
+                    e @ Err(
+                        zk::Error::NoNode
+                        | zk::Error::NoChildrenForEphemerals
+                        | zk::Error::InvalidAcl,
+                    ) => unreachable!("{e:?}"),
+                    Err(e) => {
+                        panic!("{e}")
+                    }
+                }
+                // TODO: Race condition above:
+                //       What happens if two node join exactly at the same moment:
+                //       One will create the dir
+                //       The second one will delete its DB, load nothing and install a watcher
+                //       The first one will push its keys and should wake up and update the second one.
+                //     / BUT, if the second one delete its DB and the first one push its files before the second one install the watcher we're fucked
+
+                // Zookeeper Event listener loop
+                let controller_clone = controller.clone();
+                let mut watcher = zk.watch("/auth", zk::AddWatchMode::PersistentRecursive).await?;
+                let czk = zk.clone();
+                tokio::spawn(async move {
+                    let zk = czk;
+                    loop {
+                        let zk::WatchedEvent { event_type, session_state, path } =
+                            dbg!(watcher.changed().await);
+
+                        match event_type {
+                            zk::EventType::Session => panic!("Session error {:?}", session_state),
+                            // a key is deleted from zk
+                            zk::EventType::NodeDeleted => {
+                                // TODO: ugly unwraps
+                                let uuid = path.strip_prefix("/auth/").unwrap();
+                                let uuid = Uuid::parse_str(&uuid).unwrap();
+                                log::info!("The key {} has been deleted", uuid);
+                                dbg!(controller_clone.store.delete_api_key(uuid).unwrap());
+                            }
+                            zk::EventType::NodeCreated | zk::EventType::NodeDataChanged => {
+                                let (key, stat) = zk.get_data(&path).await.unwrap();
+                                let key: Key = serde_json::from_slice(&key).unwrap();
+                                log::info!("The key {} has been deleted", key.uid);
+                                
+                                dbg!(controller_clone.store.put_api_key(key).unwrap());
+                            }
+                            zk::EventType::NodeChildrenChanged => panic!("Got the unexpected NodeChildrenChanged event, what is it used for?"),
+                        }
+                    }
+                });
+            }
+            None => {
+                if controller.store.is_empty()? {
+                    generate_default_keys(&controller).await?;
+                }
+            }
         }
 
-        Ok(Self { store: Arc::new(store), master_key: master_key.clone() })
+        Ok(controller)
     }
 
     /// Return `Ok(())` if the auth controller is able to access one of its database.
@@ -50,14 +147,27 @@ impl AuthController {
         self.store.used_size()
     }
 
-    pub fn create_key(&self, create_key: CreateApiKey) -> Result<Key> {
+    pub async fn create_key(&self, create_key: CreateApiKey) -> Result<Key> {
         match self.store.get_api_key(create_key.uid)? {
             Some(_) => Err(AuthControllerError::ApiKeyAlreadyExists(create_key.uid.to_string())),
-            None => self.store.put_api_key(create_key.to_key()),
+            None => self.put_key(create_key.to_key()).await,
         }
     }
 
-    pub fn update_key(&self, uid: Uuid, patch: PatchApiKey) -> Result<Key> {
+    pub async fn put_key(&self, key: Key) -> Result<Key> {
+        let store = self.store.clone();
+        // TODO: we may commit only after zk persisted the keys
+        let key = tokio::task::spawn_blocking(move || store.put_api_key(key)).await??;
+        if let Some(ref zk) = self.zk {
+            let options = zk::CreateOptions::new(zk::CreateMode::Persistent, zk::Acl::anyone_all());
+
+            zk.create(&format!("/auth/{}", key.uid), &serde_json::to_vec_pretty(&key)?, &options)
+                .await?;
+        }
+        Ok(key)
+    }
+
+    pub async fn update_key(&self, uid: Uuid, patch: PatchApiKey) -> Result<Key> {
         let mut key = self.get_key(uid)?;
         match patch.description {
             Setting::NotSet => (),
@@ -68,7 +178,14 @@ impl AuthController {
             name => key.name = name.set(),
         };
         key.updated_at = OffsetDateTime::now_utc();
-        self.store.put_api_key(key)
+        let store = self.store.clone();
+        // TODO: we may commit only after zk persisted the keys
+        let key = tokio::task::spawn_blocking(move || store.put_api_key(key)).await??;
+        if let Some(ref zk) = self.zk {
+            zk.set_data(&format!("/auth/{}", key.uid), &serde_json::to_vec_pretty(&key)?, None)
+                .await?;
+        }
+        Ok(key)
     }
 
     pub fn get_key(&self, uid: Uuid) -> Result<Key> {
@@ -109,8 +226,13 @@ impl AuthController {
         self.store.list_api_keys()
     }
 
-    pub fn delete_key(&self, uid: Uuid) -> Result<()> {
-        if self.store.delete_api_key(uid)? {
+    pub async fn delete_key(&self, uid: Uuid) -> Result<()> {
+        let store = self.store.clone();
+        let deleted = tokio::task::spawn_blocking(move || store.delete_api_key(uid)).await??;
+        if deleted {
+            if let Some(ref zk) = self.zk {
+                zk.delete(&format!("/auth/{}", uid), None).await?;
+            }
             Ok(())
         } else {
             Err(AuthControllerError::ApiKeyNotFound(uid.to_string()))
@@ -159,7 +281,7 @@ impl AuthController {
         self.store.delete_all_keys()
     }
 
-    /// Delete all the keys in the DB.
+    /// Insert a key in the DB without any check on its validity
     pub fn raw_insert_key(&mut self, key: Key) -> Result<()> {
         self.store.put_api_key(key)?;
         Ok(())
@@ -304,9 +426,9 @@ pub struct IndexSearchRules {
     pub filter: Option<serde_json::Value>,
 }
 
-fn generate_default_keys(store: &HeedAuthStore) -> Result<()> {
-    store.put_api_key(Key::default_admin())?;
-    store.put_api_key(Key::default_search())?;
+async fn generate_default_keys(controller: &AuthController) -> Result<()> {
+    controller.put_key(Key::default_admin()).await?;
+    controller.put_key(Key::default_search()).await?;
 
     Ok(())
 }

meilisearch/Cargo.toml

@@ -58,7 +58,7 @@ lazy_static = "1.4.0"
 log = "0.4.17"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.36", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.15.0"
 obkv = "0.2.0"
@@ -69,6 +69,8 @@ permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.9"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
+puffin = "0.16.0"
+puffin_http = { version = "0.13.0", optional = true }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
@@ -103,6 +105,7 @@ walkdir = "2.3.3"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
 termcolor = "1.2.0"
+zookeeper-client = "0.4.0"
 
 [dev-dependencies]
 actix-rt = "2.8.0"
@@ -133,7 +136,18 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
-mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
+profile-with-puffin = ["dep:puffin_http"]
+mini-dashboard = [
+    "actix-web-static-files",
+    "static-files",
+    "anyhow",
+    "cargo_toml",
+    "hex",
+    "reqwest",
+    "sha-1",
+    "tempfile",
+    "zip",
+]
 chinese = ["meilisearch-types/chinese"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]

meilisearch/src/analytics/segment_analytics.rs

@@ -312,6 +312,7 @@ impl From<Opt> for Infos {
             config_file_path,
             #[cfg(all(not(debug_assertions), feature = "analytics"))]
                 no_analytics: _,
+            zk_url: _,
         } = options;
 
         let schedule_snapshot = match schedule_snapshot {

meilisearch/src/lib.rs

@@ -39,6 +39,7 @@ use meilisearch_types::versioning::{check_version_file, create_version_file};
 use meilisearch_types::{compression, milli, VERSION_FILE_NAME};
 pub use option::Opt;
 use option::ScheduleSnapshot;
+use zookeeper_client as zk;
 
 use crate::error::MeilisearchHttpError;
 
@@ -136,14 +137,17 @@ enum OnFailure {
     KeepDb,
 }
 
-pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
+pub async fn setup_meilisearch(
+    opt: &Opt,
+    zk: Option<zk::Client>,
+) -> anyhow::Result<(Arc<IndexScheduler>, Arc<AuthController>)> {
     let empty_db = is_empty_db(&opt.db_path);
     let (index_scheduler, auth_controller) = if let Some(ref snapshot_path) = opt.import_snapshot {
         let snapshot_path_exists = snapshot_path.exists();
         // the db is empty and the snapshot exists, import it
         if empty_db && snapshot_path_exists {
             match compression::from_tar_gz(snapshot_path, &opt.db_path) {
-                Ok(()) => open_or_create_database_unchecked(opt, OnFailure::RemoveDb)?,
+                Ok(()) => open_or_create_database_unchecked(opt, OnFailure::RemoveDb, zk).await?,
                 Err(e) => {
                     std::fs::remove_dir_all(&opt.db_path)?;
                     return Err(e);
@@ -160,14 +164,14 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
             bail!("snapshot doesn't exist at {}", snapshot_path.display())
         // the snapshot and the db exist, and we can ignore the snapshot because of the ignore_snapshot_if_db_exists flag
         } else {
-            open_or_create_database(opt, empty_db)?
+            open_or_create_database(opt, empty_db, zk).await?
         }
     } else if let Some(ref path) = opt.import_dump {
         let src_path_exists = path.exists();
         // the db is empty and the dump exists, import it
         if empty_db && src_path_exists {
             let (mut index_scheduler, mut auth_controller) =
-                open_or_create_database_unchecked(opt, OnFailure::RemoveDb)?;
+                open_or_create_database_unchecked(opt, OnFailure::RemoveDb, zk).await?;
             match import_dump(&opt.db_path, path, &mut index_scheduler, &mut auth_controller) {
                 Ok(()) => (index_scheduler, auth_controller),
                 Err(e) => {
@@ -187,10 +191,10 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         // the dump and the db exist and we can ignore the dump because of the ignore_dump_if_db_exists flag
         // or, the dump is missing but we can ignore that because of the ignore_missing_dump flag
         } else {
-            open_or_create_database(opt, empty_db)?
+            open_or_create_database(opt, empty_db, zk).await?
         }
     } else {
-        open_or_create_database(opt, empty_db)?
+        open_or_create_database(opt, empty_db, zk).await?
     };
 
     // We create a loop in a thread that registers snapshotCreation tasks
@@ -214,13 +218,14 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
 }
 
 /// Try to start the IndexScheduler and AuthController without checking the VERSION file or anything.
-fn open_or_create_database_unchecked(
+async fn open_or_create_database_unchecked(
     opt: &Opt,
     on_failure: OnFailure,
+    zk: Option<zk::Client>,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     // we don't want to create anything in the data.ms yet, thus we
     // wrap our two builders in a closure that'll be executed later.
-    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key);
+    let auth_controller = AuthController::new(&opt.db_path, &opt.master_key, zk);
     let instance_features = opt.to_instance_features();
     let index_scheduler_builder = || -> anyhow::Result<_> {
         Ok(IndexScheduler::new(IndexSchedulerOptions {
@@ -245,7 +250,7 @@ fn open_or_create_database_unchecked(
 
     match (
         index_scheduler_builder(),
-        auth_controller.map_err(anyhow::Error::from),
+        auth_controller.await.map_err(anyhow::Error::from),
         create_version_file(&opt.db_path).map_err(anyhow::Error::from),
     ) {
         (Ok(i), Ok(a), Ok(())) => Ok((i, a)),
@@ -259,15 +264,16 @@ fn open_or_create_database_unchecked(
 }
 
 /// Ensure you're in a valid state and open the IndexScheduler + AuthController for you.
-fn open_or_create_database(
+async fn open_or_create_database(
     opt: &Opt,
     empty_db: bool,
+    zk: Option<zk::Client>,
 ) -> anyhow::Result<(IndexScheduler, AuthController)> {
     if !empty_db {
         check_version_file(&opt.db_path)?;
     }
 
-    open_or_create_database_unchecked(opt, OnFailure::KeepDb)
+    open_or_create_database_unchecked(opt, OnFailure::KeepDb, zk).await
 }
 
 fn import_dump(

meilisearch/src/main.rs

@@ -12,6 +12,7 @@ use meilisearch::analytics::Analytics;
 use meilisearch::{analytics, create_app, prototype_name, setup_meilisearch, Opt};
 use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
 use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
+use zookeeper_client as zk;
 
 #[global_allocator]
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
@@ -30,6 +31,10 @@ fn setup(opt: &Opt) -> anyhow::Result<()> {
 async fn main() -> anyhow::Result<()> {
     let (opt, config_read_from) = Opt::try_build()?;
 
+    #[cfg(feature = "profile-with-puffin")]
+    let _server = puffin_http::Server::new(&format!("0.0.0.0:{}", puffin_http::DEFAULT_PORT))?;
+    puffin::set_scopes_on(cfg!(feature = "profile-with-puffin"));
+
     anyhow::ensure!(
         !(cfg!(windows) && opt.experimental_reduce_indexing_memory_usage),
         "The `experimental-reduce-indexing-memory-usage` flag is not supported on Windows"
@@ -59,7 +64,11 @@ async fn main() -> anyhow::Result<()> {
         _ => (),
     }
 
-    let (index_scheduler, auth_controller) = setup_meilisearch(&opt)?;
+    let zk = match opt.zk_url {
+        Some(ref url) => Some(zk::Client::connect(url).await.unwrap()),
+        None => None,
+    };
+    let (index_scheduler, auth_controller) = setup_meilisearch(&opt, zk).await?;
 
     #[cfg(all(not(debug_assertions), feature = "analytics"))]
     let analytics = if !opt.no_analytics {

meilisearch/src/option.rs

@@ -28,6 +28,7 @@ const MEILI_DB_PATH: &str = "MEILI_DB_PATH";
 const MEILI_HTTP_ADDR: &str = "MEILI_HTTP_ADDR";
 const MEILI_MASTER_KEY: &str = "MEILI_MASTER_KEY";
 const MEILI_ENV: &str = "MEILI_ENV";
+const MEILI_ZK_URL: &str = "MEILI_ZK_URL";
 #[cfg(all(not(debug_assertions), feature = "analytics"))]
 const MEILI_NO_ANALYTICS: &str = "MEILI_NO_ANALYTICS";
 const MEILI_HTTP_PAYLOAD_SIZE_LIMIT: &str = "MEILI_HTTP_PAYLOAD_SIZE_LIMIT";
@@ -154,6 +155,11 @@ pub struct Opt {
     #[serde(default = "default_env")]
     pub env: String,
 
+    /// Sets the HTTP address and port used to communicate with the zookeeper cluster.
+    /// If ran locally, the default url is `http://localhost:2181/`.
+    #[clap(long, env = MEILI_ZK_URL)]
+    pub zk_url: Option<String>,
+
     /// Deactivates Meilisearch's built-in telemetry when provided.
     ///
     /// Meilisearch automatically collects data from all instances that do not opt out using this flag.
@@ -368,6 +374,7 @@ impl Opt {
             http_addr,
             master_key,
             env,
+            zk_url,
             max_index_size: _,
             max_task_db_size: _,
             http_payload_size_limit,
@@ -401,6 +408,9 @@ impl Opt {
             export_to_env_if_not_present(MEILI_MASTER_KEY, master_key);
         }
         export_to_env_if_not_present(MEILI_ENV, env);
+        if let Some(zk_url) = zk_url {
+            export_to_env_if_not_present(MEILI_ZK_URL, zk_url);
+        }
         #[cfg(all(not(debug_assertions), feature = "analytics"))]
         {
             export_to_env_if_not_present(MEILI_NO_ANALYTICS, no_analytics.to_string());
@@ -715,6 +725,10 @@ fn default_env() -> String {
     DEFAULT_ENV.to_string()
 }
 
+pub fn default_zk_url() -> String {
+    DEFAULT_HTTP_ADDR.to_string()
+}
+
 fn default_max_index_size() -> Byte {
     Byte::from_bytes(INDEX_SIZE)
 }

meilisearch/src/routes/api_key.rs

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

meilisearch/tests/common/server.rs

@@ -39,7 +39,7 @@ impl Server {
 
         let options = default_settings(dir.path());
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await.unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir) }
@@ -54,7 +54,7 @@ impl Server {
 
         options.master_key = Some("MASTER_KEY".to_string());
 
-        let (index_scheduler, auth) = setup_meilisearch(&options).unwrap();
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await.unwrap();
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Server { service, _dir: Some(dir) }
@@ -67,7 +67,7 @@ impl Server {
     }
 
     pub async fn new_with_options(options: Opt) -> Result<Self, anyhow::Error> {
-        let (index_scheduler, auth) = setup_meilisearch(&options)?;
+        let (index_scheduler, auth) = setup_meilisearch(&options, None).await?;
         let service = Service { index_scheduler, auth, options, api_key: None };
 
         Ok(Server { service, _dir: None })

milli/Cargo.toml

@@ -65,13 +65,16 @@ filter-parser = { path = "../filter-parser" }
 # documents words self-join
 itertools = "0.10.5"
 
+# profiling
+puffin = "0.16.0"
+
 # logging
 log = "0.4.17"
 logging_timer = "1.1.0"
 csv = "1.2.1"
 
 [dev-dependencies]
-mimalloc = { version = "0.1.29", default-features = false }
+mimalloc = { version = "0.1.37", default-features = false }
 big_s = "1.0.2"
 insta = "1.29.0"
 maplit = "1.0.2"

milli/src/update/clear_documents.rs

@@ -15,6 +15,8 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
     }
 
     pub fn execute(self) -> Result<u64> {
+        puffin::profile_function!();
+
         self.index.set_updated_at(self.wtxn, &OffsetDateTime::now_utc())?;
         let Index {
             env: _env,

milli/src/update/delete_documents.rs

@@ -109,6 +109,8 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
         Some(docid)
     }
     pub fn execute(self) -> Result<DocumentDeletionResult> {
+        puffin::profile_function!();
+
         let DetailedDocumentDeletionResult { deleted_documents, remaining_documents } =
             self.execute_inner()?;
 

milli/src/update/index_documents/enrich.rs

@@ -31,6 +31,8 @@ pub fn enrich_documents_batch<R: Read + Seek>(
     autogenerate_docids: bool,
     reader: DocumentsBatchReader<R>,
 ) -> Result<StdResult<EnrichedDocumentsBatchReader<R>, UserError>> {
+    puffin::profile_function!();
+
     let (mut cursor, mut documents_batch_index) = reader.into_cursor_and_fields_index();
 
     let mut external_ids = tempfile::tempfile().map(grenad::Writer::new)?;

milli/src/update/index_documents/extract/extract_docid_word_positions.rs

@@ -30,6 +30,8 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
     stop_words: Option<&fst::Set<&[u8]>>,
     max_positions_per_attributes: Option<u32>,
 ) -> Result<(RoaringBitmap, grenad::Reader<File>, ScriptLanguageDocidsMap)> {
+    puffin::profile_function!();
+
     let max_positions_per_attributes = max_positions_per_attributes
         .map_or(MAX_POSITION_PER_ATTRIBUTE, |max| max.min(MAX_POSITION_PER_ATTRIBUTE));
     let max_memory = indexer.max_memory_by_thread();

milli/src/update/index_documents/extract/extract_facet_number_docids.rs

@@ -20,6 +20,8 @@ pub fn extract_facet_number_docids<R: io::Read + io::Seek>(
     docid_fid_facet_number: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut facet_number_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_facet_string_docids.rs

@@ -18,6 +18,8 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
     docid_fid_facet_string: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut facet_string_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_fid_docid_facet_values.rs

@@ -34,6 +34,8 @@ pub fn extract_fid_docid_facet_values<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     faceted_fields: &HashSet<FieldId>,
 ) -> Result<ExtractedFacetValues> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_docid_facet_numbers_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs

@@ -22,6 +22,8 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut fid_word_count_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_geo_points.rs

@@ -19,6 +19,8 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
     primary_key_id: FieldId,
     (lat_fid, lng_fid): (FieldId, FieldId),
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let mut writer = create_writer(
         indexer.chunk_compression_type,
         indexer.chunk_compression_level,

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -19,6 +19,8 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     primary_key_id: FieldId,
     vectors_fid: FieldId,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let mut writer = create_writer(
         indexer.chunk_compression_type,
         indexer.chunk_compression_level,

milli/src/update/index_documents/extract/extract_word_docids.rs

@@ -27,6 +27,8 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     exact_attributes: &HashSet<FieldId>,
 ) -> Result<(grenad::Reader<File>, grenad::Reader<File>)> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_word_fid_docids.rs

@@ -15,6 +15,8 @@ pub fn extract_word_fid_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_fid_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs

@@ -21,6 +21,8 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_pair_proximity_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/extract_word_position_docids.rs

@@ -18,6 +18,8 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
     docid_word_positions: grenad::Reader<R>,
     indexer: GrenadParameters,
 ) -> Result<grenad::Reader<File>> {
+    puffin::profile_function!();
+
     let max_memory = indexer.max_memory_by_thread();
 
     let mut word_position_docids_sorter = create_sorter(

milli/src/update/index_documents/extract/mod.rs

@@ -52,6 +52,8 @@ pub(crate) fn data_from_obkv_documents(
     max_positions_per_attributes: Option<u32>,
     exact_attributes: HashSet<FieldId>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     original_obkv_chunks
         .par_bridge()
         .map(|original_documents_chunk| {
@@ -238,11 +240,13 @@ fn spawn_extraction_task<FE, FS, M>(
     M::Output: Send,
 {
     rayon::spawn(move || {
+        puffin::profile_scope!("extract_multiple_chunks", name);
         let chunks: Result<M> =
             chunks.into_par_iter().map(|chunk| extract_fn(chunk, indexer)).collect();
         rayon::spawn(move || match chunks {
             Ok(chunks) => {
                 debug!("merge {} database", name);
+                puffin::profile_scope!("merge_multiple_chunks", name);
                 let reader = chunks.merge(merge_fn, &indexer);
                 let _ = lmdb_writer_sx.send(reader.map(serialize_fn));
             }

milli/src/update/index_documents/helpers/grenad_helpers.rs

@@ -214,6 +214,7 @@ pub fn sorter_into_lmdb_database(
     sorter: Sorter<MergeFn>,
     merge: MergeFn,
 ) -> Result<()> {
+    puffin::profile_function!();
     debug!("Writing MTBL sorter...");
     let before = Instant::now();
 

milli/src/update/index_documents/mod.rs

@@ -137,6 +137,8 @@ where
         mut self,
         reader: DocumentsBatchReader<R>,
     ) -> Result<(Self, StdResult<u64, UserError>)> {
+        puffin::profile_function!();
+
         // Early return when there is no document to add
         if reader.is_empty() {
             return Ok((self, Ok(0)));
@@ -175,6 +177,8 @@ where
         mut self,
         to_delete: Vec<String>,
     ) -> Result<(Self, StdResult<u64, UserError>)> {
+        puffin::profile_function!();
+
         // Early return when there is no document to add
         if to_delete.is_empty() {
             return Ok((self, Ok(0)));
@@ -194,6 +198,8 @@ where
 
     #[logging_timer::time("IndexDocuments::{}")]
     pub fn execute(mut self) -> Result<DocumentAdditionResult> {
+        puffin::profile_function!();
+
         if self.added_documents == 0 {
             let number_of_documents = self.index.number_of_documents(self.wtxn)?;
             return Ok(DocumentAdditionResult { indexed_documents: 0, number_of_documents });
@@ -232,6 +238,8 @@ where
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         let TransformOutput {
             primary_key,
             fields_ids_map,
@@ -322,6 +330,7 @@ where
 
         // Run extraction pipeline in parallel.
         pool.install(|| {
+            puffin::profile_scope!("extract_and_send_grenad_chunks");
             // split obkv file into several chunks
             let original_chunk_iter =
                 grenad_obkv_into_chunks(original_documents, pool_params, documents_chunk_size);
@@ -477,6 +486,8 @@ where
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         // Merged databases are already been indexed, we start from this count;
         let mut databases_seen = MERGED_DATABASE_COUNT;
 
@@ -511,26 +522,36 @@ where
             return Err(Error::InternalError(InternalError::AbortedIndexation));
         }
 
-        let current_prefix_fst = self.index.words_prefixes_fst(self.wtxn)?;
+        let current_prefix_fst;
+        let common_prefix_fst_words_tmp;
+        let common_prefix_fst_words: Vec<_>;
+        let new_prefix_fst_words;
+        let del_prefix_fst_words;
 
-        // We retrieve the common words between the previous and new prefix word fst.
-        let common_prefix_fst_words = fst_stream_into_vec(
-            previous_words_prefixes_fst.op().add(&current_prefix_fst).intersection(),
-        );
-        let common_prefix_fst_words: Vec<_> = common_prefix_fst_words
-            .as_slice()
-            .linear_group_by_key(|x| x.chars().next().unwrap())
-            .collect();
+        {
+            puffin::profile_scope!("compute_prefix_diffs");
 
-        // We retrieve the newly added words between the previous and new prefix word fst.
-        let new_prefix_fst_words = fst_stream_into_vec(
-            current_prefix_fst.op().add(&previous_words_prefixes_fst).difference(),
-        );
+            current_prefix_fst = self.index.words_prefixes_fst(self.wtxn)?;
 
-        // We compute the set of prefixes that are no more part of the prefix fst.
-        let del_prefix_fst_words = fst_stream_into_hashset(
-            previous_words_prefixes_fst.op().add(&current_prefix_fst).difference(),
-        );
+            // We retrieve the common words between the previous and new prefix word fst.
+            common_prefix_fst_words_tmp = fst_stream_into_vec(
+                previous_words_prefixes_fst.op().add(&current_prefix_fst).intersection(),
+            );
+            common_prefix_fst_words = common_prefix_fst_words_tmp
+                .as_slice()
+                .linear_group_by_key(|x| x.chars().next().unwrap())
+                .collect();
+
+            // We retrieve the newly added words between the previous and new prefix word fst.
+            new_prefix_fst_words = fst_stream_into_vec(
+                current_prefix_fst.op().add(&previous_words_prefixes_fst).difference(),
+            );
+
+            // We compute the set of prefixes that are no more part of the prefix fst.
+            del_prefix_fst_words = fst_stream_into_hashset(
+                previous_words_prefixes_fst.op().add(&current_prefix_fst).difference(),
+            );
+        }
 
         databases_seen += 1;
         (self.progress)(UpdateIndexingStep::MergeDataIntoFinalDatabase {
@@ -668,6 +689,8 @@ fn execute_word_prefix_docids(
     common_prefix_fst_words: &[&[String]],
     del_prefix_fst_words: &HashSet<Vec<u8>>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     let cursor = reader.into_cursor()?;
     let mut builder = WordPrefixDocids::new(txn, word_docids_db, word_prefix_docids_db);
     builder.chunk_compression_type = indexer_config.chunk_compression_type;

milli/src/update/index_documents/transform.rs

@@ -558,6 +558,8 @@ impl<'a, 'i> Transform<'a, 'i> {
     where
         F: Fn(UpdateIndexingStep) + Sync,
     {
+        puffin::profile_function!();
+
         let primary_key = self
             .index
             .primary_key(wtxn)?

milli/src/update/index_documents/typed_chunk.rs

@@ -46,6 +46,66 @@ pub(crate) enum TypedChunk {
     ScriptLanguageDocids(HashMap<(Script, Language), RoaringBitmap>),
 }
 
+impl TypedChunk {
+    pub fn to_debug_string(&self) -> String {
+        match self {
+            TypedChunk::FieldIdDocidFacetStrings(grenad) => {
+                format!("FieldIdDocidFacetStrings {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdDocidFacetNumbers(grenad) => {
+                format!("FieldIdDocidFacetNumbers {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::Documents(grenad) => {
+                format!("Documents {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdWordcountDocids(grenad) => {
+                format!("FieldIdWordcountDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::NewDocumentsIds(grenad) => {
+                format!("NewDocumentsIds {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordDocids { word_docids_reader, exact_word_docids_reader } => format!(
+                "WordDocids {{ word_docids_reader: {}, exact_word_docids_reader: {} }}",
+                word_docids_reader.len(),
+                exact_word_docids_reader.len()
+            ),
+            TypedChunk::WordPositionDocids(grenad) => {
+                format!("WordPositionDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordFidDocids(grenad) => {
+                format!("WordFidDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::WordPairProximityDocids(grenad) => {
+                format!("WordPairProximityDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetStringDocids(grenad) => {
+                format!("FieldIdFacetStringDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetNumberDocids(grenad) => {
+                format!("FieldIdFacetNumberDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetExistsDocids(grenad) => {
+                format!("FieldIdFacetExistsDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetIsNullDocids(grenad) => {
+                format!("FieldIdFacetIsNullDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::FieldIdFacetIsEmptyDocids(grenad) => {
+                format!("FieldIdFacetIsEmptyDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::GeoPoints(grenad) => {
+                format!("GeoPoints {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::VectorPoints(grenad) => {
+                format!("VectorPoints {{ number_of_entries: {} }}", grenad.len())
+            }
+            TypedChunk::ScriptLanguageDocids(grenad) => {
+                format!("ScriptLanguageDocids {{ number_of_entries: {} }}", grenad.len())
+            }
+        }
+    }
+}
+
 /// Write typed chunk in the corresponding LMDB database of the provided index.
 /// Return new documents seen.
 pub(crate) fn write_typed_chunk_into_index(
@@ -54,6 +114,8 @@ pub(crate) fn write_typed_chunk_into_index(
     wtxn: &mut RwTxn,
     index_is_empty: bool,
 ) -> Result<(RoaringBitmap, bool)> {
+    puffin::profile_function!(typed_chunk.to_debug_string());
+
     let mut is_merged_database = false;
     match typed_chunk {
         TypedChunk::Documents(obkv_documents_iter) => {
@@ -350,6 +412,8 @@ where
     FS: for<'a> Fn(&'a [u8], &'a mut Vec<u8>) -> Result<&'a [u8]>,
     FM: Fn(&[u8], &[u8], &mut Vec<u8>) -> Result<()>,
 {
+    puffin::profile_function!(format!("number of entries: {}", data.len()));
+
     let mut buffer = Vec::new();
     let database = database.remap_types::<ByteSlice, ByteSlice>();
 
@@ -392,6 +456,8 @@ where
     FS: for<'a> Fn(&'a [u8], &'a mut Vec<u8>) -> Result<&'a [u8]>,
     FM: Fn(&[u8], &[u8], &mut Vec<u8>) -> Result<()>,
 {
+    puffin::profile_function!(format!("number of entries: {}", data.len()));
+
     if !index_is_empty {
         return write_entries_into_database(
             data,

milli/src/update/prefix_word_pairs/mod.rs

@@ -50,6 +50,8 @@ impl<'t, 'u, 'i> PrefixWordPairsProximityDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&'a [String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
+
         index_word_prefix_database(
             self.wtxn,
             self.index.word_pair_proximity_docids,

milli/src/update/prefix_word_pairs/prefix_word.rs

@@ -27,6 +27,8 @@ pub fn index_prefix_word_database(
     chunk_compression_type: CompressionType,
     chunk_compression_level: Option<u32>,
 ) -> Result<()> {
+    puffin::profile_function!();
+
     let max_proximity = max_proximity - 1;
     debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
 

milli/src/update/prefix_word_pairs/word_prefix.rs

@@ -191,6 +191,7 @@ pub fn index_word_prefix_database(
     chunk_compression_type: CompressionType,
     chunk_compression_level: Option<u32>,
 ) -> Result<()> {
+    puffin::profile_function!();
     debug!("Computing and writing the word prefix pair proximity docids into LMDB on disk...");
 
     // Make a prefix trie from the common prefixes that are shorter than self.max_prefix_length

milli/src/update/settings.rs

@@ -303,6 +303,8 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
         FP: Fn(UpdateIndexingStep) + Sync,
         FA: Fn() -> bool + Sync,
     {
+        puffin::profile_function!();
+
         let fields_ids_map = self.index.fields_ids_map(self.wtxn)?;
         // if the settings are set before any document update, we don't need to do anything, and
         // will set the primary key during the first document addition.

milli/src/update/word_prefix_docids.rs

@@ -45,6 +45,8 @@ impl<'t, 'u, 'i> WordPrefixDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&[String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
+
         // It is forbidden to keep a mutable reference into the database
         // and write into it at the same time, therefore we write into another file.
         let mut prefix_docids_sorter = create_sorter(

milli/src/update/words_prefix_integer_docids.rs

@@ -50,6 +50,7 @@ impl<'t, 'u, 'i> WordPrefixIntegerDocids<'t, 'u, 'i> {
         common_prefix_fst_words: &[&[String]],
         del_prefix_fst_words: &HashSet<Vec<u8>>,
     ) -> Result<()> {
+        puffin::profile_function!();
         debug!("Computing and writing the word levels integers docids into LMDB on disk...");
 
         let mut prefix_integer_docids_sorter = create_sorter(

milli/src/update/words_prefixes_fst.rs

@@ -42,6 +42,8 @@ impl<'t, 'u, 'i> WordsPrefixesFst<'t, 'u, 'i> {
 
     #[logging_timer::time("WordsPrefixesFst::{}")]
     pub fn execute(self) -> Result<()> {
+        puffin::profile_function!();
+
         let words_fst = self.index.words_fst(self.wtxn)?;
 
         let mut current_prefix = vec![SmallString32::new(); self.max_prefix_length];