feat: implement NUMA-aware worker pools for merge command

Replaces the global Rayon pool with per-NUMA-node thread pools that pin worker threads to their respective nodes, leveraging Linux first-touch allocation to reduce cross-NUMA memory contention and improve cache locality. Integrates the `hwlocality` crate with a vendored build, includes graceful fallbacks for single-socket or non-Linux systems, and updates dependency constraints. Also adds installation and architecture documentation, and corrects parallelism detection in the partitioner.
This commit is contained in:
Eric Coissac
2026-06-14 23:40:09 +02:00
parent f1d76f3203
commit ea767376bd
9 changed files with 654 additions and 34 deletions
+299 -5
View File
@@ -128,6 +128,12 @@ version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2ad8689a486416c401ea15715a4694de30054248ec627edbf31f49cb64ee4086"
[[package]]
name = "arrayvec"
version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
[[package]]
name = "as-slice"
version = "0.2.1"
@@ -143,6 +149,15 @@ version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
[[package]]
name = "autotools"
version = "0.2.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ef941527c41b0fc0dd48511a8154cd5fc7e29200a0ff8b7203c5d777dbc795cf"
dependencies = [
"cc",
]
[[package]]
name = "backtrace"
version = "0.3.76"
@@ -224,6 +239,15 @@ dependencies = [
"generic-array",
]
[[package]]
name = "block-buffer"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2f6c7dbe95a6ed67ad9f18e57daf93a2f034c524b99fd2b76d18fdfeb6660aa"
dependencies = [
"hybrid-array",
]
[[package]]
name = "block-pseudorand"
version = "0.1.2"
@@ -415,6 +439,15 @@ version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
[[package]]
name = "cmake"
version = "0.1.58"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c0f78a02292a74a88ac736019ab962ece0bc380e3f977bf72e376c5d78ff0678"
dependencies = [
"cc",
]
[[package]]
name = "colorchoice"
version = "1.0.5"
@@ -464,6 +497,21 @@ dependencies = [
"windows-sys 0.59.0",
]
[[package]]
name = "const-oid"
version = "0.10.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a6ef517f0926dd24a1582492c791b6a4818a4d94e789a334894aa15b0d12f55c"
[[package]]
name = "convert_case"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "633458d4ef8c78b72454de2d54fd6ab2e60f9e02be22f3c6104cdc8a4e0fceb9"
dependencies = [
"unicode-segmentation",
]
[[package]]
name = "core-foundation-sys"
version = "0.8.7"
@@ -488,6 +536,15 @@ dependencies = [
"libc",
]
[[package]]
name = "cpufeatures"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8b2a41393f66f16b0823bb79094d54ac5fbd34ab292ddafb9a0456ac9f87d201"
dependencies = [
"libc",
]
[[package]]
name = "crc32fast"
version = "1.5.0"
@@ -601,6 +658,15 @@ dependencies = [
"typenum",
]
[[package]]
name = "crypto-common"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce6e4c961d6cd6c9a86db418387425e8bdeaf05b3c8bc1411e6dca4c252f1453"
dependencies = [
"hybrid-array",
]
[[package]]
name = "csv"
version = "1.4.0"
@@ -640,14 +706,48 @@ dependencies = [
"uuid",
]
[[package]]
name = "derive_more"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d751e9e49156b02b44f9c1815bcb94b984cdcc4396ecc32521c739452808b134"
dependencies = [
"derive_more-impl",
]
[[package]]
name = "derive_more-impl"
version = "2.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "799a97264921d8623a957f6c3b9011f3b5492f557bbb7a5a19b7fa6d06ba8dcb"
dependencies = [
"convert_case",
"proc-macro2",
"quote",
"rustc_version",
"syn",
"unicode-xid",
]
[[package]]
name = "digest"
version = "0.10.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
dependencies = [
"block-buffer",
"crypto-common",
"block-buffer 0.10.4",
"crypto-common 0.1.7",
]
[[package]]
name = "digest"
version = "0.11.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1dd6dbb5841937940781866fa1281a1ff7bd3bf827091440879f9994983d5c2"
dependencies = [
"block-buffer 0.12.1",
"const-oid",
"crypto-common 0.2.2",
]
[[package]]
@@ -742,6 +842,16 @@ version = "2.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
[[package]]
name = "filetime"
version = "0.2.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c287a33c7f0a620c38e641e7f60827713987b3c0f26e8ddc9462cc69cf75759"
dependencies = [
"cfg-if",
"libc",
]
[[package]]
name = "find-msvc-tools"
version = "0.1.9"
@@ -916,6 +1026,65 @@ version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
[[package]]
name = "http"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
dependencies = [
"bytes",
"itoa",
]
[[package]]
name = "httparse"
version = "1.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
[[package]]
name = "hwlocality"
version = "1.0.0-alpha.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c2e65a48d3b300843ac84a2fe8e166bb5a5b00f30054593bcee8157e4b465fd"
dependencies = [
"arrayvec",
"bitflags 2.11.1",
"derive_more",
"errno",
"hwlocality-sys",
"libc",
"strum",
"thiserror 2.0.18",
"windows-sys 0.61.2",
]
[[package]]
name = "hwlocality-sys"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "10a83c43a772c1f774b806deb44891c2a9578eb33cec48aad513482e0da3d4d4"
dependencies = [
"autotools",
"cmake",
"flate2",
"libc",
"pkg-config",
"sha3",
"tar",
"ureq 3.3.0",
"windows-sys 0.61.2",
]
[[package]]
name = "hybrid-array"
version = "0.4.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9155a582abd142abc056962c29e3ce5ff2ad5469f4246b537ed42c5deba857da"
dependencies = [
"typenum",
]
[[package]]
name = "icu_collections"
version = "2.2.0"
@@ -1145,6 +1314,16 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "keccak"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9e24a010dd405bd7ed803e5253182815b41bf2e6a80cc3bfc066658e03a198aa"
dependencies = [
"cfg-if",
"cpufeatures 0.3.0",
]
[[package]]
name = "kodama"
version = "0.2.3"
@@ -1508,6 +1687,7 @@ name = "obikindex"
version = "0.1.0"
dependencies = [
"crossbeam-channel",
"hwlocality",
"indicatif",
"ndarray",
"obicompactvec",
@@ -1636,7 +1816,7 @@ dependencies = [
"regex",
"tracing",
"tracing-subscriber",
"ureq",
"ureq 2.12.1",
]
[[package]]
@@ -2177,6 +2357,15 @@ version = "2.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
[[package]]
name = "rustc_version"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
dependencies = [
"semver",
]
[[package]]
name = "rustix"
version = "1.1.4"
@@ -2263,6 +2452,12 @@ dependencies = [
"syn",
]
[[package]]
name = "semver"
version = "1.0.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
[[package]]
name = "serde"
version = "1.0.228"
@@ -2313,8 +2508,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
dependencies = [
"cfg-if",
"cpufeatures",
"digest",
"cpufeatures 0.2.17",
"digest 0.10.7",
]
[[package]]
name = "sha3"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "be176f1a57ce4e3d31c1a166222d9768de5954f811601fb7ca06fc8203905ce1"
dependencies = [
"digest 0.11.3",
"keccak",
]
[[package]]
@@ -2375,6 +2580,27 @@ version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
[[package]]
name = "strum"
version = "0.28.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9628de9b8791db39ceda2b119bbe13134770b56c138ec1d3af810d045c04f9bd"
dependencies = [
"strum_macros",
]
[[package]]
name = "strum_macros"
version = "0.28.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ab85eea0270ee17587ed4156089e10b9e6880ee688791d45a905f5b1ca36f664"
dependencies = [
"heck",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "subtle"
version = "2.6.1"
@@ -2470,6 +2696,17 @@ version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55937e1799185b12863d447f42597ed69d9928686b8d88a1df17376a097d8369"
[[package]]
name = "tar"
version = "0.4.46"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f6221d9a6003c78398e3b239969f352578258df48c8eb051caadae0015bc840"
dependencies = [
"filetime",
"libc",
"xattr",
]
[[package]]
name = "tempfile"
version = "3.27.0"
@@ -2645,12 +2882,24 @@ version = "1.0.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
[[package]]
name = "unicode-segmentation"
version = "1.13.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c6f5d3c3b1bf09027a88a6bc961fc00497d651009560b5463668dc81b0fa87a8"
[[package]]
name = "unicode-width"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
[[package]]
name = "unicode-xid"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
[[package]]
name = "untrusted"
version = "0.9.0"
@@ -2673,6 +2922,35 @@ dependencies = [
"webpki-roots 0.26.11",
]
[[package]]
name = "ureq"
version = "3.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dea7109cdcd5864d4eeb1b58a1648dc9bf520360d7af16ec26d0a9354bafcfc0"
dependencies = [
"base64",
"flate2",
"log",
"percent-encoding",
"rustls",
"rustls-pki-types",
"ureq-proto",
"utf8-zero",
"webpki-roots 1.0.7",
]
[[package]]
name = "ureq-proto"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e994ba84b0bd1b1b0cf92878b7ef898a5c1760108fe7b6010327e274917a808c"
dependencies = [
"base64",
"http",
"httparse",
"log",
]
[[package]]
name = "url"
version = "2.5.8"
@@ -2685,6 +2963,12 @@ dependencies = [
"serde",
]
[[package]]
name = "utf8-zero"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b8c0a043c9540bae7c578c88f91dda8bd82e59ae27c21baca69c8b191aaf5a6e"
[[package]]
name = "utf8_iter"
version = "1.0.4"
@@ -3110,6 +3394,16 @@ dependencies = [
"tap",
]
[[package]]
name = "xattr"
version = "1.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32e45ad4206f6d2479085147f02bc2ef834ac85886624a23575ae137c8aa8156"
dependencies = [
"libc",
"rustix",
]
[[package]]
name = "xxhash-rust"
version = "0.8.15"