Use an experimental feature to avoid copying 64k in memory

This commit is contained in:
Clément Renault 2024-07-03 17:51:53 +02:00
parent 9a05f191b7
commit f73d95de9a
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
5 changed files with 79 additions and 121 deletions

192
Cargo.lock generated
View File

@ -247,17 +247,6 @@ version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
[[package]]
name = "aes"
version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
dependencies = [
"cfg-if",
"cipher",
"cpufeatures",
]
[[package]]
name = "ahash"
version = "0.8.11"
@ -495,12 +484,6 @@ version = "0.22.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "base64ct"
version = "1.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8c3c1a368f70d6cf7302d78f8f7093da241fb8e8807c05cc9e51a125895a6d5b"
[[package]]
name = "benchmarks"
version = "1.9.0"
@ -657,9 +640,9 @@ dependencies = [
[[package]]
name = "bumpalo"
version = "3.15.4"
version = "3.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7ff69b9dd49fd426c69a0db9fc04dd934cdb6645ff000864d98f7e2af8830eaa"
checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
[[package]]
name = "byte-unit"
@ -718,27 +701,6 @@ dependencies = [
"bytes",
]
[[package]]
name = "bzip2"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bdb116a6ef3f6c3698828873ad02c3014b3c85cadb88496095628e3ef1e347f8"
dependencies = [
"bzip2-sys",
"libc",
]
[[package]]
name = "bzip2-sys"
version = "0.1.11+1.0.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc"
dependencies = [
"cc",
"libc",
"pkg-config",
]
[[package]]
name = "camino"
version = "1.1.6"
@ -768,7 +730,7 @@ dependencies = [
"safetensors",
"thiserror",
"yoke",
"zip",
"zip 0.6.6",
]
[[package]]
@ -949,16 +911,6 @@ dependencies = [
"half 1.8.2",
]
[[package]]
name = "cipher"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
dependencies = [
"crypto-common",
"inout",
]
[[package]]
name = "clang-sys"
version = "1.7.0"
@ -1052,12 +1004,6 @@ dependencies = [
"windows-sys 0.45.0",
]
[[package]]
name = "constant_time_eq"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "245097e9a4535ee1e3e3931fcfcd55a796a44c643e8596ff6566d68f09b87bbc"
[[package]]
name = "convert_case"
version = "0.4.0"
@ -1117,9 +1063,9 @@ dependencies = [
[[package]]
name = "crc32fast"
version = "1.4.0"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b3855a8a784b474f333699ef2bbca9db2c4a1f6d9088a90a2d25b1eb53111eaa"
checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3"
dependencies = [
"cfg-if",
]
@ -1218,9 +1164,9 @@ dependencies = [
[[package]]
name = "crossbeam-utils"
version = "0.8.19"
version = "0.8.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "248e3bacc7dc6baa3b21e405ee045c3047101a49145e7e9eca583ab4c2ca5345"
checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
[[package]]
name = "crunchy"
@ -1562,6 +1508,17 @@ dependencies = [
"winapi",
]
[[package]]
name = "displaydoc"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.60",
]
[[package]]
name = "doc-comment"
version = "0.3.3"
@ -1837,9 +1794,9 @@ dependencies = [
[[package]]
name = "flate2"
version = "1.0.28"
version = "1.0.30"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "46303f565772937ffe1d394a4fac6f411c6013172fadde9dcdb1e147a086940e"
checksum = "5f54427cfd1c7829e2a139fcefea601bf088ebca651d2bf53ebc600eac295dae"
dependencies = [
"crc32fast",
"miniz_oxide",
@ -2508,15 +2465,6 @@ dependencies = [
"unicode-width",
]
[[package]]
name = "inout"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a0c10553d664a4d0bcff9f4215d0aac67a639cc68ef660840afe309b807bc9f5"
dependencies = [
"generic-array",
]
[[package]]
name = "insta"
version = "1.34.0"
@ -3209,6 +3157,12 @@ dependencies = [
"scopeguard",
]
[[package]]
name = "lockfree-object-pool"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9374ef4228402d4b7e403e5838cb880d9ee663314b0a900d5a6aabf0c213552e"
[[package]]
name = "log"
version = "0.4.21"
@ -3353,7 +3307,7 @@ dependencies = [
"uuid",
"walkdir",
"yaup",
"zip",
"zip 2.1.3",
]
[[package]]
@ -3421,9 +3375,9 @@ dependencies = [
[[package]]
name = "memchr"
version = "2.7.1"
version = "2.7.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
[[package]]
name = "memmap2"
@ -3819,17 +3773,6 @@ dependencies = [
"windows-targets 0.48.1",
]
[[package]]
name = "password-hash"
version = "0.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7676374caaee8a325c9e7a2ae557f216c5563a171d6997b0ef8a65af35147700"
dependencies = [
"base64ct",
"rand_core",
"subtle",
]
[[package]]
name = "paste"
version = "1.0.14"
@ -3851,18 +3794,6 @@ version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "498a099351efa4becc6a19c72aa9270598e8fd274ca47052e37455241c88b696"
[[package]]
name = "pbkdf2"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "83a0692ec44e4cf1ef28ca317f14f8f07da2d95ec3fa01f86e4467b725e60917"
dependencies = [
"digest",
"hmac",
"password-hash",
"sha2",
]
[[package]]
name = "peeking_take_while"
version = "0.1.2"
@ -4732,6 +4663,12 @@ dependencies = [
"libc",
]
[[package]]
name = "simd-adler32"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d66dc143e6b11c1eddc06d5c423cfc97062865baf299914ab64caa38182078fe"
[[package]]
name = "similar"
version = "2.2.1"
@ -5099,9 +5036,9 @@ dependencies = [
[[package]]
name = "time"
version = "0.3.34"
version = "0.3.36"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8248b6521bb14bc45b4067159b9b6ad792e2d6d754d6c41fb50e29fefe38749"
checksum = "5dfd88e563464686c916c7e46e623e520ddc6d79fa6641390f2e3fa86e83e885"
dependencies = [
"deranged",
"itoa",
@ -5122,9 +5059,9 @@ checksum = "ef927ca75afb808a4d64dd374f00a2adf8d0fcff8e7b184af886c3c87ec4a3f3"
[[package]]
name = "time-macros"
version = "0.2.17"
version = "0.2.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7ba3a3ef41e6672a2f0f001392bb5dcd3ff0a9992d618ca761a11c3121547774"
checksum = "3f252a68540fde3a3877aeea552b832b40ab9a69e318efd078774a01ddee1ccf"
dependencies = [
"num-conv",
"time-core",
@ -6157,9 +6094,9 @@ dependencies = [
[[package]]
name = "zeroize"
version = "1.7.0"
version = "1.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "525b4ec142c6b68a2d10f01f7bbf6755599ca3f81ea53b8431b7dd348f5fdb2d"
checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"
[[package]]
name = "zerovec"
@ -6176,36 +6113,57 @@ version = "0.6.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "760394e246e4c28189f19d488c058bf16f564016aefac5d32bb1f3b51d5e9261"
dependencies = [
"aes",
"byteorder",
"bzip2",
"constant_time_eq",
"crc32fast",
"crossbeam-utils",
]
[[package]]
name = "zip"
version = "2.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "775a2b471036342aa69bc5a602bc889cb0a06cda00477d0c69566757d5553d39"
dependencies = [
"arbitrary",
"crc32fast",
"crossbeam-utils",
"displaydoc",
"flate2",
"hmac",
"pbkdf2",
"sha1",
"time",
"zstd",
"indexmap",
"memchr",
"thiserror",
"zopfli",
]
[[package]]
name = "zopfli"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5019f391bac5cf252e93bbcc53d039ffd62c7bfb7c150414d61369afe57e946"
dependencies = [
"bumpalo",
"crc32fast",
"lockfree-object-pool",
"log",
"once_cell",
"simd-adler32",
]
[[package]]
name = "zstd"
version = "0.11.2+zstd.1.5.2"
version = "0.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "20cc960326ece64f010d2d2107537f26dc589a6573a316bd5b1dba685fa5fde4"
checksum = "2d789b1514203a1120ad2429eae43a7bd32b90976a7bb8a05f7ec02fa88cc23a"
dependencies = [
"zstd-safe",
]
[[package]]
name = "zstd-safe"
version = "5.0.2+zstd.1.5.2"
version = "7.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1d2a5585e04f9eea4b2a3d1eca508c4dee9592a89ef6f450c11719da0726f4db"
checksum = "1cd99b45c6bc03a018c8b8a86025678c87e55526064e38f9df301989dce7ec0a"
dependencies = [
"libc",
"zstd-sys",
]

View File

@ -27,7 +27,7 @@ roaring = "0.10.2"
anyhow = "1.0.79"
bytes = "1.5.0"
convert_case = "0.6.0"
flate2 = "1.0.28"
flate2 = "1.0.30"
reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
[features]

View File

@ -130,7 +130,7 @@ reqwest = { version = "0.11.23", features = [
sha-1 = { version = "0.10.1", optional = true }
static-files = { version = "0.2.3", optional = true }
tempfile = { version = "3.9.0", optional = true }
zip = { version = "0.6.6", optional = true }
zip = { version = "2.1.3", default-features = false, features = ["deflate"], optional = true }
[features]
default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]

View File

@ -38,7 +38,7 @@ heed = { version = "0.20.1", default-features = false, features = [
indexmap = { version = "2.1.0", features = ["serde"] }
json-depth-checker = { path = "../json-depth-checker" }
levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
zstd = { version = "0.11.2", features = ["zdict_builder"] }
zstd = { version = "0.13.1", features = ["zdict_builder", "experimental"] }
memmap2 = "0.7.1"
obkv = "0.2.1"
once_cell = "1.19.0"

View File

@ -374,7 +374,7 @@ impl Index {
&self,
rtxn: &'t RoTxn,
) -> heed::Result<Option<DecoderDictionary<'t>>> {
self.document_compression_raw_dictionary(rtxn).map(|opt| opt.map(DecoderDictionary::copy))
self.document_compression_raw_dictionary(rtxn).map(|opt| opt.map(DecoderDictionary::new))
}
pub fn document_compression_dictionary(