zlib: add crc32c

Add zlib.crc32c(data[, value]), which computes the CRC-32C checksum
(Castagnoli polynomial, RFC 3720 section 12.1). CRC-32C has better
error detection properties than the CRC-32 of zlib.crc32() and is the
checksum required by many current protocols, formats and services,
among them:

- iSCSI header and data digests (RFC 7143)
- SCTP packet checksums (RFC 9260)
- iWARP MPA framing (RFC 5044)
- NVMe/TCP header and data digests
- ext4, Btrfs and XFS metadata checksums
- the Snappy framing format
- Apache Kafka record batches
- LevelDB and RocksDB block checksums
- TensorFlow TFRecord files
- Google Cloud Storage and Amazon S3 object checksums

Implementing any of these in JavaScript currently needs a userland
CRC-32C, which is far slower than native code.

The function mirrors zlib.crc32(): it accepts a string (encoded as
UTF-8) or an ArrayBufferView, takes an optional 32-bit unsigned
starting value so a checksum can be continued across chunks, and has a
V8 fast API path.

The checksum is computed by absl::ExtendCrc32c() from the bundled
Abseil, which is already built and linked into node, so this adds no
new dependency and no new checksum implementation. absl_crc32c is
added to the libraries linked with --shared-abseil.

Abseil selects its hardware-accelerated CRC-32C path (SSE4.2 and
PCLMULQDQ on x64, the CRC32 and PMULL extensions on arm64) at compile
time, so with node's default compiler flags the portable table-driven
implementation is used. It runs at about the same speed as zlib.crc32()
(about 6.5 GB/s on a recent x64 machine), while the hardware path
reaches about 38 GB/s. Builds whose target CPU baseline already
includes those instructions get the hardware path without changes.
Enabling it for generic builds is left out on purpose: on x64, Abseil
uses the accelerated code for unrecognized CPUs without a runtime
feature check, so compiling it in unconditionally would fault on CPUs
without SSE4.2.

Signed-off-by: Philipp Dunkel <pip@pipobscure.com>
PR-URL: https://github.com/nodejs/node/pull/66828
Reviewed-By: Matteo Collina <matteo.collina@gmail.com>
Reviewed-By: Paolo Insogna <paolo@cowtech.it>
Reviewed-By: Trivikram Kamat <trivikr.dev@gmail.com>
This commit is contained in:
Philipp Dunkel authored and GitHub committed 2026-10-20 12:33:08 +00:00
1 parent 754325cd2f
commit df2ea49e00
8 files changed
+258 -1

No files matched your search

+47
View File
@@ -0,0 +1,47 @@
'use strict';
const common = require('../common.js');
const { crc32c } = require('zlib');
// Benchmark crc32c on Buffer and String inputs across sizes.
// Iteration count is scaled inversely with input length to keep runtime sane.
// Example:
// node benchmark/zlib/crc32c.js type=buffer len=4096 n=4000000
// ./out/Release/node benchmark/zlib/crc32c.js --test
const bench = common.createBenchmark(main, {
type: ['buffer', 'string'],
len: [32, 256, 4096, 65536],
n: [4e6],
});
function makeBuffer(size) {
const buf = Buffer.allocUnsafe(size);
for (let i = 0; i < size; i++) buf[i] = (i * 1103515245 + 12345) & 0xff;
return buf;
}
function makeAsciiString(size) {
const chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_';
let out = '';
for (let i = 0, j = 0; i < size; i++, j = (j + 7) % chars.length) out += chars[j];
return out;
}
function main({ type, len, n }) {
// Scale iterations so that total processed bytes roughly constant around n*4096 bytes.
const scale = 4096 / len;
const iters = Math.max(1, Math.floor(n * scale));
const data = type === 'buffer' ? makeBuffer(len) : makeAsciiString(len);
let acc = 0;
for (let i = 0; i < Math.min(iters, 10000); i++) acc ^= crc32c(data, 0);
bench.start();
let sum = 0;
for (let i = 0; i < iters; i++) sum ^= crc32c(data, 0);
bench.end(iters);
if (sum === acc - 1) process.stderr.write('');
}