https://github.com/torvalds/linux
Revision 4fca50d440cc5d4dc570ad5484cc0b70b381bc2a authored by Jan Kara on 08 September 2022, 09:21:24 UTC, committed by Theodore Ts'o on 22 September 2022, 02:11:34 UTC
One of the side-effects of mb_optimize_scan was that the optimized functions to select next group to try were called even before we tried the goal group. As a result we no longer allocate files close to corresponding inodes as well as we don't try to expand currently allocated extent in the same group. This results in reaim regression with workfile.disk workload of upto 8% with many clients on my test machine: baseline mb_optimize_scan Hmean disk-1 2114.16 ( 0.00%) 2099.37 ( -0.70%) Hmean disk-41 87794.43 ( 0.00%) 83787.47 * -4.56%* Hmean disk-81 148170.73 ( 0.00%) 135527.05 * -8.53%* Hmean disk-121 177506.11 ( 0.00%) 166284.93 * -6.32%* Hmean disk-161 220951.51 ( 0.00%) 207563.39 * -6.06%* Hmean disk-201 208722.74 ( 0.00%) 203235.59 ( -2.63%) Hmean disk-241 222051.60 ( 0.00%) 217705.51 ( -1.96%) Hmean disk-281 252244.17 ( 0.00%) 241132.72 * -4.41%* Hmean disk-321 255844.84 ( 0.00%) 245412.84 * -4.08%* Also this is causing huge regression (time increased by a factor of 5 or so) when untarring archive with lots of small files on some eMMC storage cards. Fix the problem by making sure we try goal group first. Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") CC: stable@kernel.org Reported-and-tested-by: Stefan Wahren <stefan.wahren@i2se.com> Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com> Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com> Link: https://lore.kernel.org/all/20220727105123.ckwrhbilzrxqpt24@quack3/ Link: https://lore.kernel.org/all/0d81a7c2-46b7-6010-62a4-3e6cfc1628d6@i2se.com/ Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20220908092136.11770-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
1 parent 7e18e42
Tip revision: 4fca50d440cc5d4dc570ad5484cc0b70b381bc2a authored by Jan Kara on 08 September 2022, 09:21:24 UTC
ext4: make mballoc try target group first even with mb_optimize_scan
ext4: make mballoc try target group first even with mb_optimize_scan
Tip revision: 4fca50d
poly1305_generic.c
/*
* Poly1305 authenticator algorithm, RFC7539
*
* Copyright (C) 2015 Martin Willi
*
* Based on public domain code by Andrew Moon and Daniel J. Bernstein.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/poly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/unaligned.h>
static int crypto_poly1305_init(struct shash_desc *desc)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
poly1305_core_init(&dctx->h);
dctx->buflen = 0;
dctx->rset = 0;
dctx->sset = false;
return 0;
}
static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen)
{
if (!dctx->sset) {
if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
poly1305_core_setkey(&dctx->core_r, src);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->rset = 2;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
dctx->s[0] = get_unaligned_le32(src + 0);
dctx->s[1] = get_unaligned_le32(src + 4);
dctx->s[2] = get_unaligned_le32(src + 8);
dctx->s[3] = get_unaligned_le32(src + 12);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
return srclen;
}
static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
unsigned int srclen)
{
unsigned int datalen;
if (unlikely(!dctx->sset)) {
datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
src += srclen - datalen;
srclen = datalen;
}
poly1305_core_blocks(&dctx->h, &dctx->core_r, src,
srclen / POLY1305_BLOCK_SIZE, 1);
}
static int crypto_poly1305_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
unsigned int bytes;
if (unlikely(dctx->buflen)) {
bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
memcpy(dctx->buf + dctx->buflen, src, bytes);
src += bytes;
srclen -= bytes;
dctx->buflen += bytes;
if (dctx->buflen == POLY1305_BLOCK_SIZE) {
poly1305_blocks(dctx, dctx->buf,
POLY1305_BLOCK_SIZE);
dctx->buflen = 0;
}
}
if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
poly1305_blocks(dctx, src, srclen);
src += srclen - (srclen % POLY1305_BLOCK_SIZE);
srclen %= POLY1305_BLOCK_SIZE;
}
if (unlikely(srclen)) {
dctx->buflen = srclen;
memcpy(dctx->buf, src, srclen);
}
return 0;
}
static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
if (unlikely(!dctx->sset))
return -ENOKEY;
poly1305_final_generic(dctx, dst);
return 0;
}
static struct shash_alg poly1305_alg = {
.digestsize = POLY1305_DIGEST_SIZE,
.init = crypto_poly1305_init,
.update = crypto_poly1305_update,
.final = crypto_poly1305_final,
.descsize = sizeof(struct poly1305_desc_ctx),
.base = {
.cra_name = "poly1305",
.cra_driver_name = "poly1305-generic",
.cra_priority = 100,
.cra_blocksize = POLY1305_BLOCK_SIZE,
.cra_module = THIS_MODULE,
},
};
static int __init poly1305_mod_init(void)
{
return crypto_register_shash(&poly1305_alg);
}
static void __exit poly1305_mod_exit(void)
{
crypto_unregister_shash(&poly1305_alg);
}
subsys_initcall(poly1305_mod_init);
module_exit(poly1305_mod_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
MODULE_DESCRIPTION("Poly1305 authenticator");
MODULE_ALIAS_CRYPTO("poly1305");
MODULE_ALIAS_CRYPTO("poly1305-generic");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...