All of lore.kernel.org
 help / color / mirror / Atom feed
From: Baokun Li <libaokun@linux.alibaba.com>
To: linux-ext4@vger.kernel.org
Cc: linux-crypto@vger.kernel.org, ebiggers@kernel.org,
	ardb@kernel.org, tytso@mit.edu, adilger.kernel@dilger.ca,
	jack@suse.cz, yi.zhang@huawei.com, ojaswin@linux.ibm.com,
	ritesh.list@gmail.com, Baokun Li <libaokun@linux.alibaba.com>
Subject: [PATCH RFC 03/17] lib/crc: crc_kunit: add benchmark for crc32c_flip_range()
Date: Fri,  8 May 2026 20:15:25 +0800	[thread overview]
Message-ID: <20260508121539.4174601-4-libaokun@linux.alibaba.com> (raw)
In-Reply-To: <20260508121539.4174601-1-libaokun@linux.alibaba.com>

Add a kunit benchmark comparing crc32c_flip_range() against full crc32c
recomputation across bitmap sizes from 1KB to 64KB. The benchmark reports
per-call latency in nanoseconds and the speedup ratio.

Sample results (x86_64, Intel(R) Xeon(R) Platinum 8331C):

bitmap=1024: flip_range=48 ns, full_crc=45 ns, speedup=0.9x
bitmap=2048: flip_range=53 ns, full_crc=88 ns, speedup=1.6x
bitmap=4096: flip_range=57 ns, full_crc=182 ns, speedup=3.1x
bitmap=8192: flip_range=63 ns, full_crc=357 ns, speedup=5.6x
bitmap=16384: flip_range=68 ns, full_crc=709 ns, speedup=10.3x
bitmap=32768: flip_range=73 ns, full_crc=1421 ns, speedup=19.3x
bitmap=65536: flip_range=78 ns, full_crc=2853 ns, speedup=36.3x

Signed-off-by: Baokun Li <libaokun@linux.alibaba.com>
---
 lib/crc/tests/crc_kunit.c | 52 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/lib/crc/tests/crc_kunit.c b/lib/crc/tests/crc_kunit.c
index 46f9df5b58e4..8e8b541b37d3 100644
--- a/lib/crc/tests/crc_kunit.c
+++ b/lib/crc/tests/crc_kunit.c
@@ -554,6 +554,57 @@ static void crc32c_flip_range_test(struct kunit *test)
 	}
 }
 
+/*
+ * Benchmark crc32c_flip_range vs full crc32c recomputation
+ */
+static void crc32c_flip_range_benchmark(struct kunit *test)
+{
+	static const size_t bitmap_sizes[] = {
+		1024, 2048, 4096, 8192, 16384, 32768, 65536,
+	};
+	size_t i, j, num_iters, buflen, total_bits;
+	volatile u32 crc;
+	u64 t_flip, t_full;
+	u8 *buf;
+
+	if (!IS_ENABLED(CONFIG_CRC_BENCHMARK))
+		kunit_skip(test, "not enabled");
+
+	buf = kunit_kzalloc(test, 65536, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, buf);
+
+	for (i = 0; i < ARRAY_SIZE(bitmap_sizes); i++) {
+		buflen = bitmap_sizes[i];
+		total_bits = buflen * 8;
+		num_iters = 10000000 / (buflen + 128);
+
+		/* Benchmark crc32c_flip_range */
+		crc = crc32c(0, buf, buflen);
+		preempt_disable();
+		t_flip = ktime_get_ns();
+		for (j = 0; j < num_iters; j++)
+			crc = crc32c_flip_range(crc, total_bits, 100, 100);
+		t_flip = ktime_get_ns() - t_flip;
+		preempt_enable();
+
+		/* Benchmark full crc32c recomputation */
+		preempt_disable();
+		t_full = ktime_get_ns();
+		for (j = 0; j < num_iters; j++)
+			crc = crc32c(0, buf, buflen);
+		t_full = ktime_get_ns() - t_full;
+		preempt_enable();
+
+		kunit_info(test,
+			   "bitmap=%zu: flip_range=%llu ns, full_crc=%llu ns, speedup=%llu.%01llux\n",
+			   buflen,
+			   div64_u64(t_flip, num_iters),
+			   div64_u64(t_full, num_iters),
+			   div64_u64(t_full * 10, t_flip ? t_flip : 1) / 10,
+			   div64_u64(t_full * 10, t_flip ? t_flip : 1) % 10);
+	}
+}
+
 static struct kunit_case crc_test_cases[] = {
 #if IS_REACHABLE(CONFIG_CRC7)
 	KUNIT_CASE(crc7_be_test),
@@ -575,6 +626,7 @@ static struct kunit_case crc_test_cases[] = {
 	KUNIT_CASE(crc32c_test),
 	KUNIT_CASE(crc32c_benchmark),
 	KUNIT_CASE(crc32c_flip_range_test),
+	KUNIT_CASE(crc32c_flip_range_benchmark),
 #endif
 #if IS_REACHABLE(CONFIG_CRC64)
 	KUNIT_CASE(crc64_be_test),
-- 
2.43.7


  parent reply	other threads:[~2026-05-08 12:16 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-08 12:15 [PATCH RFC 00/17] ext4/lib-crc: LBS performance part 1 - incremental CRC32c for bitmap checksums Baokun Li
2026-05-08 12:15 ` [PATCH RFC 01/17] lib/crc: add crc32c_flip_range() for incremental CRC update Baokun Li
     [not found]   ` <20260508204019.9E5A5C2BCB0@smtp.kernel.org>
2026-05-10  9:44     ` Baokun Li
2026-05-14  3:52   ` Eric Biggers
2026-05-08 12:15 ` [PATCH RFC 02/17] lib/crc: crc_kunit: add kunit test for crc32c_flip_range() Baokun Li
2026-05-08 12:15 ` Baokun Li [this message]
     [not found]   ` <20260508205415.8B843C2BCB0@smtp.kernel.org>
2026-05-10 10:03     ` [PATCH RFC 03/17] lib/crc: crc_kunit: add benchmark " Baokun Li
2026-05-08 12:15 ` [PATCH RFC 04/17] ext4: fix incorrect block bitmap free clusters update on metadata overlap Baokun Li
     [not found]   ` <20260508211732.E50B4C2BCB0@smtp.kernel.org>
2026-05-11  6:17     ` Baokun Li
2026-05-08 12:15 ` [PATCH RFC 05/17] ext4: extract block bitmap checksum get and store helpers Baokun Li
2026-05-08 12:15 ` [PATCH RFC 06/17] ext4: add ext4_block_bitmap_csum_set_range() for incremental checksum update Baokun Li
     [not found]   ` <20260508214640.B3A74C2BCB0@smtp.kernel.org>
2026-05-11  8:09     ` Baokun Li
2026-05-11  8:31     ` Baokun Li
2026-05-08 12:15 ` [PATCH RFC 07/17] ext4: use fast incremental CRC update in ext4_mb_mark_context() Baokun Li
     [not found]   ` <20260508223130.20E7AC2BCB0@smtp.kernel.org>
2026-05-11  8:15     ` Baokun Li
2026-05-08 12:15 ` [PATCH RFC 08/17] ext4: extract inode bitmap checksum get and store helpers Baokun Li
2026-05-08 12:15 ` [PATCH RFC 09/17] ext4: add ext4_inode_bitmap_csum_set_fast() for incremental checksum update Baokun Li
     [not found]   ` <20260508225807.71D9FC2BCB0@smtp.kernel.org>
2026-05-11  8:35     ` Baokun Li
2026-05-08 12:15 ` [PATCH RFC 10/17] ext4: use fast incremental CRC update in ext4_free_inode() Baokun Li
2026-05-08 12:15 ` [PATCH RFC 11/17] ext4: fix missing bg_used_dirs_count update in fast commit replay Baokun Li
2026-05-08 12:15 ` [PATCH RFC 12/17] ext4: factor out ext4_might_init_block_bitmap() helper Baokun Li
2026-05-08 12:15 ` [PATCH RFC 13/17] ext4: use fast incremental CRC update in ext4_mark_inode_used() Baokun Li
2026-05-08 12:15 ` [PATCH RFC 14/17] ext4: rename ino to bit in __ext4_new_inode() Baokun Li
2026-05-08 12:15 ` [PATCH RFC 15/17] ext4: use fast incremental CRC update " Baokun Li
2026-05-08 12:15 ` [PATCH RFC 16/17] ext4: extract ext4_update_inode_group_desc() to reduce duplication Baokun Li
2026-05-08 12:15 ` [PATCH RFC 17/17] ext4: add ext4_get_flex_group() helper to simplify flex group lookups Baokun Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260508121539.4174601-4-libaokun@linux.alibaba.com \
    --to=libaokun@linux.alibaba.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=ardb@kernel.org \
    --cc=ebiggers@kernel.org \
    --cc=jack@suse.cz \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=ojaswin@linux.ibm.com \
    --cc=ritesh.list@gmail.com \
    --cc=tytso@mit.edu \
    --cc=yi.zhang@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.