mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-31 02:18:27 +00:00
Compare commits
12 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 8d3185dec6 | |||
| bb14667c81 | |||
| 983ad2c011 | |||
| bcff95b109 | |||
| dfbb5f5ade | |||
| 12ee5ca626 | |||
| fcef32bfd3 | |||
| 3863189b16 | |||
| c858e25494 | |||
| cf9a8bf91d | |||
| 7357d63e87 | |||
| 624a75edf7 |
@@ -0,0 +1,21 @@
|
||||
# Keep Node's Linux x64 addons compatible with pre-Haswell CPUs.
|
||||
# lance-linalg dispatches hot vector kernels to newer SIMD tiers at runtime.
|
||||
[env]
|
||||
LANCEDB_NODE_ENFORCE_X86_64_V2 = "1"
|
||||
|
||||
[target.x86_64-unknown-linux-gnu]
|
||||
rustflags = [
|
||||
"-C",
|
||||
"target-cpu=x86-64-v2",
|
||||
"-C",
|
||||
"target-feature=-avx,-avx2,-fma,-f16c",
|
||||
]
|
||||
|
||||
# Preserve the workspace's dynamic C runtime configuration for musl.
|
||||
[target.x86_64-unknown-linux-musl]
|
||||
rustflags = [
|
||||
"-C",
|
||||
"target-cpu=x86-64-v2",
|
||||
"-C",
|
||||
"target-feature=-crt-static,-avx,-avx2,-fma,-f16c",
|
||||
]
|
||||
@@ -12,6 +12,10 @@ categories.workspace = true
|
||||
[lib]
|
||||
crate-type = ["cdylib"]
|
||||
|
||||
[[test]]
|
||||
name = "x86_64_v2_build_flags"
|
||||
path = "build_support/x86_64_v2.rs"
|
||||
|
||||
[dependencies]
|
||||
async-trait.workspace = true
|
||||
arrow-ipc.workspace = true
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
import * as tmp from "tmp";
|
||||
|
||||
import { connect } from "../lancedb";
|
||||
import {
|
||||
Field,
|
||||
FixedSizeList,
|
||||
Float32,
|
||||
Int32,
|
||||
Schema,
|
||||
makeArrowTable,
|
||||
} from "../lancedb/arrow";
|
||||
|
||||
test("cosine vector search runs on the pre-Haswell build baseline", async () => {
|
||||
const tmpDir = tmp.dirSync({ unsafeCleanup: true });
|
||||
|
||||
try {
|
||||
const db = await connect(tmpDir.name);
|
||||
const schema = new Schema([
|
||||
new Field("id", new Int32(), false),
|
||||
new Field(
|
||||
"vector",
|
||||
new FixedSizeList(3, new Field("item", new Float32(), false)),
|
||||
false,
|
||||
),
|
||||
]);
|
||||
const data = makeArrowTable(
|
||||
[
|
||||
{ id: 1, vector: [1, 0, 0] },
|
||||
{ id: 2, vector: [0, 1, 0] },
|
||||
],
|
||||
{ schema },
|
||||
);
|
||||
const table = await db.createTable("vectors", data);
|
||||
|
||||
const results = await table
|
||||
.vectorSearch([1, 0, 0])
|
||||
.distanceType("cosine")
|
||||
.limit(1)
|
||||
.toArray();
|
||||
|
||||
expect(results).toHaveLength(1);
|
||||
expect(results[0].id).toBe(1);
|
||||
expect(results[0]._distance).toBeCloseTo(0);
|
||||
} finally {
|
||||
tmpDir.removeCallback();
|
||||
}
|
||||
}, 60_000);
|
||||
@@ -3,6 +3,29 @@
|
||||
|
||||
extern crate napi_build;
|
||||
|
||||
use std::env;
|
||||
|
||||
#[path = "build_support/x86_64_v2.rs"]
|
||||
mod x86_64_v2;
|
||||
|
||||
const ENFORCE_BASELINE: &str = "LANCEDB_NODE_ENFORCE_X86_64_V2";
|
||||
|
||||
fn main() {
|
||||
napi_build::setup();
|
||||
println!("cargo:rerun-if-env-changed={ENFORCE_BASELINE}");
|
||||
println!("cargo:rerun-if-env-changed=CARGO_ENCODED_RUSTFLAGS");
|
||||
|
||||
let is_linux_x64 = env::var("CARGO_CFG_TARGET_ARCH").as_deref() == Ok("x86_64")
|
||||
&& env::var("CARGO_CFG_TARGET_OS").as_deref() == Ok("linux");
|
||||
let is_release = env::var("PROFILE").as_deref() == Ok("release");
|
||||
let is_node_build = env::var(ENFORCE_BASELINE).as_deref() == Ok("1");
|
||||
|
||||
if !is_linux_x64 || (!is_release && !is_node_build) {
|
||||
return;
|
||||
}
|
||||
|
||||
let encoded_rustflags = env::var("CARGO_ENCODED_RUSTFLAGS").unwrap_or_default();
|
||||
x86_64_v2::validate_encoded_rustflags(&encoded_rustflags).unwrap_or_else(|error| {
|
||||
panic!("Linux x64 Node addons must use the x86-64-v2 baseline; {error}")
|
||||
});
|
||||
}
|
||||
|
||||
@@ -0,0 +1,430 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use std::collections::{BTreeMap, BTreeSet};
|
||||
|
||||
const SAFE_TARGET_CPUS: [&str; 2] = ["x86-64", "x86-64-v2"];
|
||||
const BASELINE_FEATURES: [&str; 9] = [
|
||||
"cmpxchg16b",
|
||||
"fxsr",
|
||||
"popcnt",
|
||||
"sse",
|
||||
"sse2",
|
||||
"sse3",
|
||||
"sse4.1",
|
||||
"sse4.2",
|
||||
"ssse3",
|
||||
];
|
||||
|
||||
pub(crate) fn validate_encoded_rustflags(encoded: &str) -> Result<(), String> {
|
||||
let mut target_cpu = None;
|
||||
let mut feature_states = BTreeMap::new();
|
||||
let mut required_disables = BTreeSet::new();
|
||||
let mut unsupported_features = BTreeSet::new();
|
||||
|
||||
for option in codegen_options(encoded)? {
|
||||
let Some((name, value)) = option.split_once('=') else {
|
||||
continue;
|
||||
};
|
||||
|
||||
let name = name.replace('_', "-");
|
||||
match name.as_str() {
|
||||
"target-cpu" => target_cpu = Some(value),
|
||||
"target-feature" => {
|
||||
for toggle in value.split(',').filter(|toggle| !toggle.is_empty()) {
|
||||
let (enabled, feature) = match toggle.as_bytes()[0] {
|
||||
b'+' => (true, &toggle[1..]),
|
||||
b'-' => (false, &toggle[1..]),
|
||||
_ => return Err(format!("invalid target feature flag: {toggle}")),
|
||||
};
|
||||
|
||||
feature_states.insert(feature, enabled);
|
||||
if enabled && !BASELINE_FEATURES.contains(&feature) {
|
||||
match feature {
|
||||
// These are inherited from the workspace configuration and
|
||||
// explicitly canceled by the Node configuration. Account for
|
||||
// their implied AVX prerequisite as well as the named feature.
|
||||
"avx" => {
|
||||
required_disables.insert("avx");
|
||||
}
|
||||
"avx2" => {
|
||||
required_disables.extend(["avx", "avx2"]);
|
||||
}
|
||||
"f16c" => {
|
||||
required_disables.extend(["avx", "f16c"]);
|
||||
}
|
||||
"fma" => {
|
||||
required_disables.extend(["avx", "fma"]);
|
||||
}
|
||||
_ => {
|
||||
unsupported_features.insert(feature);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
// LLVM arguments can independently alter the target feature set and
|
||||
// cannot be proven safe by inspecting rustc's target options.
|
||||
"llvm-args" => return Err("LLVM arguments can override the CPU baseline".to_owned()),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(cpu) = target_cpu.filter(|cpu| !SAFE_TARGET_CPUS.contains(cpu)) {
|
||||
return Err(format!(
|
||||
"effective target CPU is {}, expected x86-64-v2 or lower",
|
||||
cpu
|
||||
));
|
||||
}
|
||||
|
||||
if !unsupported_features.is_empty() {
|
||||
return Err(format!(
|
||||
"features above v2: {}",
|
||||
unsupported_features
|
||||
.into_iter()
|
||||
.collect::<Vec<_>>()
|
||||
.join(", ")
|
||||
));
|
||||
}
|
||||
|
||||
let not_disabled = required_disables
|
||||
.into_iter()
|
||||
.filter(|feature| feature_states.get(feature) != Some(&false))
|
||||
.collect::<Vec<_>>();
|
||||
if !not_disabled.is_empty() {
|
||||
return Err(format!(
|
||||
"inherited features not fully disabled: {}",
|
||||
not_disabled.join(", ")
|
||||
));
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn codegen_options(encoded: &str) -> Result<Vec<&str>, String> {
|
||||
let arguments = encoded.split('\u{1f}').collect::<Vec<_>>();
|
||||
if arguments.iter().any(|argument| argument.starts_with('@')) {
|
||||
return Err("rustc response-file arguments cannot be validated".to_owned());
|
||||
}
|
||||
|
||||
let mut options = Vec::new();
|
||||
let mut index = 0;
|
||||
|
||||
while index < arguments.len() {
|
||||
let argument = arguments[index];
|
||||
if argument == "--cfg" {
|
||||
index += 1;
|
||||
let cfg = arguments
|
||||
.get(index)
|
||||
.copied()
|
||||
.ok_or_else(|| "missing value after --cfg".to_owned())?;
|
||||
reject_builtin_target_feature_cfg(cfg)?;
|
||||
} else if let Some(cfg) = argument.strip_prefix("--cfg=") {
|
||||
reject_builtin_target_feature_cfg(cfg)?;
|
||||
} else if argument == "-C" || argument == "--codegen" {
|
||||
index += 1;
|
||||
let option = arguments
|
||||
.get(index)
|
||||
.copied()
|
||||
.ok_or_else(|| format!("missing value after {argument}"))?;
|
||||
options.push(option.trim_start_matches('='));
|
||||
} else if let Some(option) = argument.strip_prefix("-C") {
|
||||
if !option.is_empty() {
|
||||
options.push(option.trim_start_matches('='));
|
||||
}
|
||||
} else if let Some(option) = argument.strip_prefix("--codegen=") {
|
||||
options.push(option);
|
||||
}
|
||||
index += 1;
|
||||
}
|
||||
|
||||
Ok(options)
|
||||
}
|
||||
|
||||
fn reject_builtin_target_feature_cfg(cfg: &str) -> Result<(), String> {
|
||||
let key = cfg.split_once('=').map_or(cfg, |(key, _)| key);
|
||||
if key.contains("/*") || key.contains("//") {
|
||||
return Err("comment-bearing cfgs cannot be validated".to_owned());
|
||||
}
|
||||
if !key.is_ascii() {
|
||||
return Err("non-ASCII cfg keys cannot be validated".to_owned());
|
||||
}
|
||||
|
||||
let name = key.trim();
|
||||
let name = name.strip_prefix("r#").unwrap_or(name);
|
||||
if name == "target_feature" {
|
||||
return Err("built-in target_feature cfgs can override runtime CPU detection".to_owned());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn encoded(arguments: &[&str]) -> String {
|
||||
arguments.join("\u{1f}")
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_merged_workspace_and_node_flags() {
|
||||
let flags = encoded(&[
|
||||
"-C",
|
||||
"target-cpu=haswell",
|
||||
"-C",
|
||||
"target-feature=+avx2,+fma,+f16c",
|
||||
"-C",
|
||||
"target-cpu=x86-64-v2",
|
||||
"-C",
|
||||
"target-feature=-avx,-avx2,-fma,-f16c",
|
||||
]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_non_merging_v2_boundary() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64-v2"]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_default_cpu_with_non_codegen_flags() {
|
||||
let flags = encoded(&["-D", "warnings"]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_unrelated_custom_cfg() {
|
||||
let flags = encoded(&["--cfg=tokio_unstable"]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_comment_like_syntax_in_cfg_value() {
|
||||
let flags = encoded(&[r#"--cfg=endpoint="https://example.com/*""#]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_explicit_x86_64_v1_cpu() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64"]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn accepts_musl_dynamic_crt_configuration() {
|
||||
let flags = encoded(&[
|
||||
"-C",
|
||||
"target-cpu=haswell",
|
||||
"-C",
|
||||
"target-feature=-crt-static,+avx2,+fma,+f16c",
|
||||
"-C",
|
||||
"target-cpu=x86-64-v2",
|
||||
"-C",
|
||||
"target-feature=-crt-static,-avx,-avx2,-fma,-f16c",
|
||||
]);
|
||||
|
||||
assert_eq!(validate_encoded_rustflags(&flags), Ok(()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_feature_omitted_from_target_cfg() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64-v2", "-Ctarget-feature=+apxf"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("features above v2: apxf".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_underscore_spelling_above_baseline_feature() {
|
||||
let flags = encoded(&["-Ctarget_cpu=x86-64-v2", "-Ctarget_feature=+apxf"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("features above v2: apxf".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unexpected_above_baseline_feature() {
|
||||
let flags = encoded(&[
|
||||
"--codegen=target-cpu=x86-64-v2",
|
||||
"--codegen",
|
||||
"target-feature=+bmi2",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("features above v2: bmi2".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_cpu_above_v2() {
|
||||
let flags = encoded(&["-Ctarget-cpu=haswell"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("effective target CPU is haswell, expected x86-64-v2 or lower".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_incompletely_disabled_feature_implications() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64-v2", "-Ctarget-feature=+avx2,-avx2"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("inherited features not fully disabled: avx".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_llvm_feature_overrides() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64-v2", "-Cllvm-args=-mattr=+apxf"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("LLVM arguments can override the CPU baseline".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_underscore_spelling_llvm_feature_overrides() {
|
||||
let flags = encoded(&["-Ctarget_cpu=x86-64-v2", "-Cllvm_args=-mattr=+apxf"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("LLVM arguments can override the CPU baseline".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_response_file_arguments() {
|
||||
let flags = encoded(&["-Ctarget-cpu=x86-64-v2", "@flags.rsp"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("rustc response-file arguments cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_split_builtin_target_feature_cfg() {
|
||||
let flags = encoded(&[
|
||||
"-Ctarget-cpu=x86-64-v2",
|
||||
"--cfg",
|
||||
r#"target_feature="avx2""#,
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("built-in target_feature cfgs can override runtime CPU detection".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_equals_builtin_target_feature_cfg() {
|
||||
let flags = encoded(&[
|
||||
"-Ctarget-cpu=x86-64-v2",
|
||||
r#"--cfg=target_feature="avx2""#,
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("built-in target_feature cfgs can override runtime CPU detection".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_raw_identifier_builtin_target_feature_cfg() {
|
||||
let flags = encoded(&[
|
||||
"-Ctarget-cpu=x86-64-v2",
|
||||
r#"--cfg=r#target_feature="avx2""#,
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("built-in target_feature cfgs can override runtime CPU detection".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_block_comment_after_cfg_name() {
|
||||
let flags = encoded(&[
|
||||
"--cfg",
|
||||
r#"target_feature/*gate*/="avx2""#,
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("comment-bearing cfgs cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_block_comment_before_cfg_name() {
|
||||
let flags = encoded(&[
|
||||
r#"--cfg=/*gate*/target_feature="avx2""#,
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("comment-bearing cfgs cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_line_comment_cfg_trivia() {
|
||||
let flags = encoded(&[
|
||||
"--cfg",
|
||||
"target_feature// gate\n=\"avx2\"",
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("comment-bearing cfgs cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_leading_bom_in_cfg_key() {
|
||||
let flags = encoded(&[
|
||||
"--cfg",
|
||||
"\u{feff}target_feature=\"avx2\"",
|
||||
"-Aexplicit_builtin_cfgs_in_flags",
|
||||
]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("non-ASCII cfg keys cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_non_ascii_pattern_whitespace_in_cfg_key() {
|
||||
for whitespace in ['\u{200e}', '\u{200f}'] {
|
||||
let cfg = format!("{whitespace}target_feature=\"avx2\"");
|
||||
let flags = encoded(&["--cfg", &cfg, "-Aexplicit_builtin_cfgs_in_flags"]);
|
||||
|
||||
assert_eq!(
|
||||
validate_encoded_rustflags(&flags),
|
||||
Err("non-ASCII cfg keys cannot be validated".to_owned())
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,37 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
const assert = require("node:assert/strict");
|
||||
const fs = require("node:fs");
|
||||
const os = require("node:os");
|
||||
const path = require("node:path");
|
||||
|
||||
const { connect } = require("../dist");
|
||||
|
||||
async function main() {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), "lancedb-cpu-"));
|
||||
|
||||
try {
|
||||
const db = await connect(tmpDir);
|
||||
const table = await db.createTable("vectors", [
|
||||
{ id: 1, vector: [1, 0, 0] },
|
||||
{ id: 2, vector: [0, 1, 0] },
|
||||
]);
|
||||
const results = await table
|
||||
.vectorSearch([1, 0, 0])
|
||||
.distanceType("cosine")
|
||||
.limit(1)
|
||||
.toArray();
|
||||
|
||||
assert.equal(results.length, 1);
|
||||
assert.equal(results[0].id, 1);
|
||||
assert.ok(Math.abs(results[0]._distance) < 1e-6);
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { force: true, recursive: true });
|
||||
}
|
||||
}
|
||||
|
||||
main().catch((error) => {
|
||||
console.error(error);
|
||||
process.exitCode = 1;
|
||||
});
|
||||
@@ -88,6 +88,7 @@
|
||||
"lint-fix": "biome check --write . && biome format --write .",
|
||||
"prepublishOnly": "napi prepublish -t npm",
|
||||
"test": "jest --verbose",
|
||||
"test:pre-haswell": "node ci/pre_haswell_smoke.js",
|
||||
"integration": "S3_TEST=1 pnpm test",
|
||||
"universal": "napi universalize",
|
||||
"version": "napi version"
|
||||
|
||||
@@ -707,6 +707,9 @@ class LanceDBConnection(DBConnection):
|
||||
self._namespace_client_properties = namespace_client_properties
|
||||
if _inner is not None:
|
||||
self._conn = _inner
|
||||
# Native-derived wrappers resolve this in their async reconstruction
|
||||
# path so construction never synchronously re-enters LOOP.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client = None
|
||||
return
|
||||
|
||||
@@ -756,11 +759,14 @@ class LanceDBConnection(DBConnection):
|
||||
# storage_options. Also, this class really shouldn't be holding any state
|
||||
# beyond _conn.
|
||||
self._conn = AsyncConnection(LOOP.run(do_connect()))
|
||||
# Keep property access synchronous so debugger introspection cannot wait on
|
||||
# the background loop while that thread is suspended at a breakpoint.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client: Optional[LanceNamespace] = None
|
||||
|
||||
@property
|
||||
def read_consistency_interval(self) -> Optional[timedelta]:
|
||||
return LOOP.run(self._conn.get_read_consistency_interval())
|
||||
return self._read_consistency_interval
|
||||
|
||||
@property
|
||||
def session(self) -> Optional[Session]:
|
||||
@@ -771,8 +777,16 @@ class LanceDBConnection(DBConnection):
|
||||
return self._conn.uri
|
||||
|
||||
@classmethod
|
||||
def from_inner(cls, inner: LanceDbConnection):
|
||||
return cls(None, _inner=inner)
|
||||
def from_inner(
|
||||
cls,
|
||||
inner: LanceDbConnection,
|
||||
read_consistency_interval: Optional[timedelta],
|
||||
):
|
||||
return cls(
|
||||
None,
|
||||
read_consistency_interval=read_consistency_interval,
|
||||
_inner=inner,
|
||||
)
|
||||
|
||||
def __repr__(self) -> str:
|
||||
return f"{self.__class__.__name__}(uri={self._conn.uri!r})"
|
||||
|
||||
@@ -226,7 +226,7 @@ class PermutationBuilder:
|
||||
|
||||
async def do_execute():
|
||||
inner_tbl = await self._async.execute()
|
||||
return LanceTable.from_inner(inner_tbl)
|
||||
return await LanceTable.from_inner(inner_tbl)
|
||||
|
||||
return LOOP.run(do_execute())
|
||||
|
||||
|
||||
@@ -2182,11 +2182,15 @@ class LanceTable(Table):
|
||||
return self.name
|
||||
|
||||
@classmethod
|
||||
def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import LanceDBConnection
|
||||
async def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import AsyncConnection, LanceDBConnection
|
||||
|
||||
async_tbl = AsyncTable(tbl)
|
||||
conn = LanceDBConnection.from_inner(tbl.database())
|
||||
inner_conn = tbl.database()
|
||||
read_consistency_interval = await AsyncConnection(
|
||||
inner_conn
|
||||
).get_read_consistency_interval()
|
||||
conn = LanceDBConnection.from_inner(inner_conn, read_consistency_interval)
|
||||
return cls(
|
||||
conn,
|
||||
async_tbl.name,
|
||||
|
||||
@@ -77,6 +77,23 @@ def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
|
||||
|
||||
|
||||
def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.db import LanceDBConnection
|
||||
|
||||
consistency_interval = timedelta(seconds=5)
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=consistency_interval)
|
||||
db_from_inner = LanceDBConnection.from_inner(db._inner, consistency_interval)
|
||||
|
||||
def fail_run(*args, **kwargs):
|
||||
raise AssertionError("properties should not use the Python background loop")
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_run)
|
||||
|
||||
assert db.read_consistency_interval == consistency_interval
|
||||
assert db_from_inner.read_consistency_interval == consistency_interval
|
||||
|
||||
|
||||
def test_ingest_pd(tmp_path):
|
||||
db = lancedb.connect(tmp_path)
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@ import math
|
||||
import pytest
|
||||
|
||||
from lancedb import DBConnection, Table, connect
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.permutation import Permutation, Permutations, permutation_builder
|
||||
|
||||
|
||||
@@ -31,6 +32,25 @@ def test_split_random_ratios(mem_db):
|
||||
assert 65 <= split_1_count <= 75 # ~70% ± tolerance
|
||||
|
||||
|
||||
def test_execute_does_not_reenter_background_loop(tmp_path, monkeypatch):
|
||||
import threading
|
||||
|
||||
db = connect(tmp_path)
|
||||
tbl = db.create_table("test_table", pa.table({"x": range(10)}))
|
||||
original_run = LOOP.run
|
||||
|
||||
def fail_on_reentry(future):
|
||||
assert threading.current_thread() is not LOOP.thread
|
||||
return original_run(future)
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_on_reentry)
|
||||
|
||||
permutation_tbl = permutation_builder(tbl).execute()
|
||||
|
||||
assert permutation_tbl.count_rows() == 10
|
||||
assert permutation_tbl._conn.read_consistency_interval is None
|
||||
|
||||
|
||||
def test_split_random_counts(mem_db):
|
||||
"""Test random splitting with absolute counts."""
|
||||
tbl = mem_db.create_table(
|
||||
|
||||
@@ -6,6 +6,7 @@ import os
|
||||
import sys
|
||||
import threading
|
||||
import warnings
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from datetime import date, datetime, timedelta
|
||||
from time import sleep
|
||||
from typing import List
|
||||
@@ -2124,6 +2125,27 @@ def test_delete(mem_db: DBConnection):
|
||||
assert table.to_arrow()["id"].to_pylist() == [1]
|
||||
|
||||
|
||||
def test_concurrent_deletes_are_thread_safe(mem_db: DBConnection):
|
||||
num_workers = 8
|
||||
table = mem_db.create_table(
|
||||
"my_table", data=[{"id": row_id} for row_id in range(num_workers)]
|
||||
)
|
||||
barrier = threading.Barrier(num_workers)
|
||||
|
||||
def delete(row_id: int):
|
||||
barrier.wait()
|
||||
return table.delete(f"id = {row_id}")
|
||||
|
||||
with ThreadPoolExecutor(max_workers=num_workers) as pool:
|
||||
results = list(pool.map(delete, range(num_workers)))
|
||||
|
||||
assert all(result.num_deleted_rows == 1 for result in results)
|
||||
assert sorted(result.version for result in results) == list(
|
||||
range(2, num_workers + 2)
|
||||
)
|
||||
assert table.count_rows() == 0
|
||||
|
||||
|
||||
def test_delete_expr(mem_db: DBConnection):
|
||||
table = mem_db.create_table(
|
||||
"my_table",
|
||||
|
||||
@@ -745,6 +745,9 @@ impl Table {
|
||||
|
||||
#[allow(private_interfaces)]
|
||||
pub fn delete(self_: PyRef<'_, Self>, condition: PredicateArg) -> PyResult<Bound<'_, PyAny>> {
|
||||
// Do not hold the Python borrow across the await. The cloned Rust table
|
||||
// handle is thread-safe and allows deletes on the same Python table to
|
||||
// run concurrently without PyO3 reporting "Already borrowed".
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let result = match &condition {
|
||||
|
||||
Reference in New Issue
Block a user