[<prev] [next>] [day] [month] [year] [list]
Message-Id: <20250830132822.7827-1-409411716@gms.tku.edu.tw>
Date: Sat, 30 Aug 2025 21:28:22 +0800
From: Guan-Chun Wu <409411716@....tku.edu.tw>
To: xiubli@...hat.com,
idryomov@...il.com
Cc: ceph-devel@...r.kernel.org,
linux-kernel@...r.kernel.org,
Guan-Chun Wu <409411716@....tku.edu.tw>
Subject: [PATCH] ceph: optimize ceph_base64_encode() with block processing
Previously, ceph_base64_encode() used a bitstream approach, handling one
input byte at a time and performing extra bit operations. While correct,
this method was suboptimal.
This patch processes input in 3-byte blocks, mapping directly to 4 output
characters. Remaining 1 or 2 bytes are handled according to standard Base64
rules. This reduces computation and improves performance.
Performance test (5 runs) for ceph_base64_encode():
64B input:
-------------------------------------------------------
| Old method | 123 | 115 | 137 | 119 | 109 | avg ~121 ns |
-------------------------------------------------------
| New method | 84 | 83 | 86 | 85 | 84 | avg ~84 ns |
-------------------------------------------------------
1KB input:
--------------------------------------------------------
| Old method | 1217 | 1150 | 1146 | 1149 | 1149 | avg ~1162 ns |
--------------------------------------------------------
| New method | 776 | 772 | 772 | 774 | 770 | avg ~773 ns |
--------------------------------------------------------
Signed-off-by: Guan-Chun Wu <409411716@....tku.edu.tw>
---
Tested on Linux 6.8.0-64-generic x86_64
with Intel Core i7-10700 @ 2.90GHz
Test is executed in the form of kernel module.
Test script:
static int encode_v1(const u8 *src, int srclen, char *dst)
{
u32 ac = 0;
int bits = 0;
int i;
char *cp = dst;
for (i = 0; i < srclen; i++) {
ac = (ac << 8) | src[i];
bits += 8;
do {
bits -= 6;
*cp++ = base64_table[(ac >> bits) & 0x3f];
} while (bits >= 6);
}
if (bits)
*cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
return cp - dst;
}
static int encode_v2(const u8 *src, int srclen, char *dst)
{
u32 ac = 0;
int i = 0;
char *cp = dst;
while (i + 2 < srclen) {
ac = ((u32)src[i] << 16) | ((u32)src[i + 1] << 8) | (u32)src[i + 2];
*cp++ = base64_table[(ac >> 18) & 0x3f];
*cp++ = base64_table[(ac >> 12) & 0x3f];
*cp++ = base64_table[(ac >> 6) & 0x3f];
*cp++ = base64_table[ac & 0x3f];
i += 3;
}
switch (srclen - i) {
case 2:
ac = ((u32)src[i] << 16) | ((u32)src[i + 1] << 8);
*cp++ = base64_table[(ac >> 18) & 0x3f];
*cp++ = base64_table[(ac >> 12) & 0x3f];
*cp++ = base64_table[(ac >> 6) & 0x3f];
break;
case 1:
ac = ((u32)src[i] << 16);
*cp++ = base64_table[(ac >> 18) & 0x3f];
*cp++ = base64_table[(ac >> 12) & 0x3f];
break;
}
return cp - dst;
}
static void run_test(const char *label, const u8 *data, int len)
{
char *dst1, *dst2;
int n1, n2;
u64 start, end;
dst1 = kmalloc(len * 2, GFP_KERNEL);
dst2 = kmalloc(len * 2, GFP_KERNEL);
if (!dst1 || !dst2) {
pr_err("%s: Failed to allocate dst buffers\n", label);
goto out;
}
pr_info("[%s] input size = %d bytes\n", label, len);
start = ktime_get_ns();
n1 = encode_v1(data, len, dst1);
end = ktime_get_ns();
pr_info("[%s] encode_v1 time: %lld ns\n", label, end - start);
start = ktime_get_ns();
n2 = encode_v2(data, len, dst2);
end = ktime_get_ns();
pr_info("[%s] encode_v2 time: %lld ns\n", label, end - start);
if (n1 != n2 || memcmp(dst1, dst2, n1) != 0)
pr_err("[%s] Mismatch detected between encode_v1 and encode_v2!\n", label);
else
pr_info("[%s] Outputs are identical.\n", label);
out:
kfree(dst1);
kfree(dst2);
}
---
fs/ceph/crypto.c | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 3b3c4d8d401e..a35570fd8ff5 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -27,20 +27,31 @@ static const char base64_table[65] =
int ceph_base64_encode(const u8 *src, int srclen, char *dst)
{
u32 ac = 0;
- int bits = 0;
- int i;
+ int i = 0;
char *cp = dst;
- for (i = 0; i < srclen; i++) {
- ac = (ac << 8) | src[i];
- bits += 8;
- do {
- bits -= 6;
- *cp++ = base64_table[(ac >> bits) & 0x3f];
- } while (bits >= 6);
+ while (i + 2 < srclen) {
+ ac = ((u32)src[i] << 16) | ((u32)src[i + 1] << 8) | (u32)src[i + 2];
+ *cp++ = base64_table[(ac >> 18) & 0x3f];
+ *cp++ = base64_table[(ac >> 12) & 0x3f];
+ *cp++ = base64_table[(ac >> 6) & 0x3f];
+ *cp++ = base64_table[ac & 0x3f];
+ i += 3;
+ }
+
+ switch (srclen - i) {
+ case 2:
+ ac = ((u32)src[i] << 16) | ((u32)src[i + 1] << 8);
+ *cp++ = base64_table[(ac >> 18) & 0x3f];
+ *cp++ = base64_table[(ac >> 12) & 0x3f];
+ *cp++ = base64_table[(ac >> 6) & 0x3f];
+ break;
+ case 1:
+ ac = ((u32)src[i] << 16);
+ *cp++ = base64_table[(ac >> 18) & 0x3f];
+ *cp++ = base64_table[(ac >> 12) & 0x3f];
+ break;
}
- if (bits)
- *cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
return cp - dst;
}
--
2.34.1
Powered by blists - more mailing lists