linux_dsm_epyc7002/drivers/block/zram/zcomp.c
Sergey Senozhatsky 5ef3a8b125 zram: add zstd to the supported algorithms list
Add ZSTD to the list of supported compression algorithms.

ZRAM fio perf test:

                      LZO         DEFLATE         ZSTD

#jobs1
WRITE:              (2180MB/s)   (77.2MB/s)      (1429MB/s)
WRITE:              (1617MB/s)   (77.7MB/s)      (1202MB/s)
READ:                (426MB/s)   (595MB/s)       (1181MB/s)
READ:                (422MB/s)   (572MB/s)       (1020MB/s)
READ:                (318MB/s)   (67.8MB/s)      (563MB/s)
WRITE:               (318MB/s)   (67.9MB/s)      (564MB/s)
READ:                (336MB/s)   (68.3MB/s)      (583MB/s)
WRITE:               (335MB/s)   (68.2MB/s)      (582MB/s)
#jobs2
WRITE:              (3441MB/s)   (152MB/s)       (2141MB/s)
WRITE:              (2507MB/s)   (147MB/s)       (1888MB/s)
READ:                (801MB/s)   (1146MB/s)      (1890MB/s)
READ:                (767MB/s)   (1096MB/s)      (2073MB/s)
READ:                (621MB/s)   (126MB/s)       (1009MB/s)
WRITE:               (621MB/s)   (126MB/s)       (1009MB/s)
READ:                (656MB/s)   (125MB/s)       (1075MB/s)
WRITE:               (657MB/s)   (126MB/s)       (1077MB/s)
#jobs3
WRITE:              (4772MB/s)   (225MB/s)       (3394MB/s)
WRITE:              (3905MB/s)   (211MB/s)       (2939MB/s)
READ:               (1216MB/s)   (1608MB/s)      (3218MB/s)
READ:               (1159MB/s)   (1431MB/s)      (2981MB/s)
READ:                (906MB/s)   (156MB/s)       (1457MB/s)
WRITE:               (907MB/s)   (156MB/s)       (1458MB/s)
READ:                (953MB/s)   (158MB/s)       (1595MB/s)
WRITE:               (952MB/s)   (157MB/s)       (1593MB/s)
#jobs4
WRITE:              (6036MB/s)   (265MB/s)       (4469MB/s)
WRITE:              (5059MB/s)   (263MB/s)       (3951MB/s)
READ:               (1618MB/s)   (2066MB/s)      (4276MB/s)
READ:               (1573MB/s)   (1942MB/s)      (3830MB/s)
READ:               (1202MB/s)   (227MB/s)       (1971MB/s)
WRITE:              (1200MB/s)   (227MB/s)       (1968MB/s)
READ:               (1265MB/s)   (226MB/s)       (2116MB/s)
WRITE:              (1264MB/s)   (226MB/s)       (2114MB/s)
#jobs5
WRITE:              (5339MB/s)   (233MB/s)       (3781MB/s)
WRITE:              (4298MB/s)   (234MB/s)       (3276MB/s)
READ:               (1626MB/s)   (2048MB/s)      (4081MB/s)
READ:               (1567MB/s)   (1929MB/s)      (3758MB/s)
READ:               (1174MB/s)   (205MB/s)       (1747MB/s)
WRITE:              (1173MB/s)   (204MB/s)       (1746MB/s)
READ:               (1214MB/s)   (208MB/s)       (1890MB/s)
WRITE:              (1215MB/s)   (208MB/s)       (1892MB/s)
#jobs6
WRITE:              (5666MB/s)   (270MB/s)       (4338MB/s)
WRITE:              (4828MB/s)   (267MB/s)       (3772MB/s)
READ:               (1803MB/s)   (2058MB/s)      (4946MB/s)
READ:               (1805MB/s)   (2156MB/s)      (4711MB/s)
READ:               (1334MB/s)   (235MB/s)       (2135MB/s)
WRITE:              (1335MB/s)   (235MB/s)       (2137MB/s)
READ:               (1364MB/s)   (236MB/s)       (2268MB/s)
WRITE:              (1365MB/s)   (237MB/s)       (2270MB/s)
#jobs7
WRITE:              (5474MB/s)   (270MB/s)       (4300MB/s)
WRITE:              (4666MB/s)   (266MB/s)       (3817MB/s)
READ:               (2022MB/s)   (2319MB/s)      (5472MB/s)
READ:               (1924MB/s)   (2260MB/s)      (5031MB/s)
READ:               (1369MB/s)   (242MB/s)       (2153MB/s)
WRITE:              (1370MB/s)   (242MB/s)       (2155MB/s)
READ:               (1499MB/s)   (246MB/s)       (2310MB/s)
WRITE:              (1497MB/s)   (246MB/s)       (2307MB/s)
#jobs8
WRITE:              (5558MB/s)   (273MB/s)       (4439MB/s)
WRITE:              (4763MB/s)   (271MB/s)       (3918MB/s)
READ:               (2201MB/s)   (2599MB/s)      (6062MB/s)
READ:               (2105MB/s)   (2463MB/s)      (5413MB/s)
READ:               (1490MB/s)   (252MB/s)       (2238MB/s)
WRITE:              (1488MB/s)   (252MB/s)       (2236MB/s)
READ:               (1566MB/s)   (254MB/s)       (2434MB/s)
WRITE:              (1568MB/s)   (254MB/s)       (2437MB/s)
#jobs9
WRITE:              (5120MB/s)   (264MB/s)       (4035MB/s)
WRITE:              (4531MB/s)   (267MB/s)       (3740MB/s)
READ:               (1940MB/s)   (2258MB/s)      (4986MB/s)
READ:               (2024MB/s)   (2387MB/s)      (4871MB/s)
READ:               (1343MB/s)   (246MB/s)       (2038MB/s)
WRITE:              (1342MB/s)   (246MB/s)       (2037MB/s)
READ:               (1553MB/s)   (238MB/s)       (2243MB/s)
WRITE:              (1552MB/s)   (238MB/s)       (2242MB/s)
#jobs10
WRITE:              (5345MB/s)   (271MB/s)       (3988MB/s)
WRITE:              (4750MB/s)   (254MB/s)       (3668MB/s)
READ:               (1876MB/s)   (2363MB/s)      (5150MB/s)
READ:               (1990MB/s)   (2256MB/s)      (5080MB/s)
READ:               (1355MB/s)   (250MB/s)       (2019MB/s)
WRITE:              (1356MB/s)   (251MB/s)       (2020MB/s)
READ:               (1490MB/s)   (252MB/s)       (2202MB/s)
WRITE:              (1488MB/s)   (252MB/s)       (2199MB/s)

jobs1                              perfstat
instructions                 52,065,555,710 (    0.79)    855,731,114,587 (    2.64)       54,280,709,944 (    1.40)
branches                     14,020,427,116 ( 725.847)    101,733,449,582 (1074.521)       11,170,591,067 ( 992.869)
branch-misses                    22,626,174 (   0.16%)        274,197,885 (   0.27%)           25,915,805 (   0.23%)
jobs2                              perfstat
instructions                103,633,110,402 (    0.75)  1,710,822,100,914 (    2.59)      107,879,874,104 (    1.28)
branches                     27,931,237,282 ( 679.203)    203,298,267,479 (1037.326)       22,185,350,842 ( 884.427)
branch-misses                    46,103,811 (   0.17%)        533,747,204 (   0.26%)           49,682,483 (   0.22%)
jobs3                              perfstat
instructions                154,857,283,657 (    0.76)  2,565,748,974,197 (    2.57)      161,515,435,813 (    1.31)
branches                     41,759,490,355 ( 670.529)    304,905,605,277 ( 978.765)       33,215,805,907 ( 888.003)
branch-misses                    74,263,293 (   0.18%)        759,746,240 (   0.25%)           76,841,196 (   0.23%)
jobs4                              perfstat
instructions                206,215,849,076 (    0.75)  3,420,169,460,897 (    2.60)      215,003,061,664 (    1.31)
branches                     55,632,141,739 ( 666.501)    406,394,977,433 ( 927.241)       44,214,322,251 ( 883.532)
branch-misses                   102,287,788 (   0.18%)      1,098,617,314 (   0.27%)          103,891,040 (   0.23%)
jobs5                              perfstat
instructions                258,711,315,588 (    0.67)  4,275,657,533,244 (    2.23)      269,332,235,685 (    1.08)
branches                     69,802,821,166 ( 588.823)    507,996,211,252 ( 797.036)       55,450,846,129 ( 735.095)
branch-misses                   129,217,214 (   0.19%)      1,243,284,991 (   0.24%)          173,512,278 (   0.31%)
jobs6                              perfstat
instructions                312,796,166,008 (    0.61)  5,133,896,344,660 (    2.02)      323,658,769,588 (    1.04)
branches                     84,372,488,583 ( 520.541)    610,310,494,402 ( 697.642)       66,683,292,992 ( 693.939)
branch-misses                   159,438,978 (   0.19%)      1,396,368,563 (   0.23%)          174,406,934 (   0.26%)
jobs7                              perfstat
instructions                363,211,372,930 (    0.56)  5,988,205,600,879 (    1.75)      377,824,674,156 (    0.93)
branches                     98,057,013,765 ( 463.117)    711,841,255,974 ( 598.762)       77,879,009,954 ( 600.443)
branch-misses                   199,513,153 (   0.20%)      1,507,651,077 (   0.21%)          248,203,369 (   0.32%)
jobs8                              perfstat
instructions                413,960,354,615 (    0.52)  6,842,918,558,378 (    1.45)      431,938,486,581 (    0.83)
branches                    111,812,574,884 ( 414.224)    813,299,084,518 ( 491.173)       89,062,699,827 ( 517.795)
branch-misses                   233,584,845 (   0.21%)      1,531,593,921 (   0.19%)          286,818,489 (   0.32%)
jobs9                              perfstat
instructions                465,976,220,300 (    0.53)  7,698,467,237,372 (    1.47)      486,352,600,321 (    0.84)
branches                    125,931,456,162 ( 424.063)    915,207,005,715 ( 498.192)      100,370,404,090 ( 517.439)
branch-misses                   256,992,445 (   0.20%)      1,782,809,816 (   0.19%)          345,239,380 (   0.34%)
jobs10                             perfstat
instructions                517,406,372,715 (    0.53)  8,553,527,312,900 (    1.48)      540,732,653,094 (    0.84)
branches                    139,839,780,676 ( 427.732)  1,016,737,699,389 ( 503.172)      111,696,557,638 ( 516.750)
branch-misses                   259,595,561 (   0.19%)      1,952,570,279 (   0.19%)          357,818,661 (   0.32%)

seconds elapsed        20.630411534     96.084546565    12.743373571
seconds elapsed        22.292627625     100.984155001   14.407413560
seconds elapsed        22.396016966     110.344880848   14.032201392
seconds elapsed        22.517330949     113.351459170   14.243074935
seconds elapsed        28.548305104     156.515193765   19.159286861
seconds elapsed        30.453538116     164.559937678   19.362492717
seconds elapsed        33.467108086     188.486827481   21.492612173
seconds elapsed        35.617727591     209.602677783   23.256422492
seconds elapsed        42.584239509     243.959902566   28.458540338
seconds elapsed        47.683632526     269.635248851   31.542404137

Over all, ZSTD has slower WRITE, but much faster READ (perhaps
a static compression buffer used during the test helped ZSTD a
lot), which results in faster test results.

Memory consumption (zram mm_stat file):

zram LZO mm_stat
mm_stat (jobs1): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs2): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs3): 2147483648 23068672 33558528        0 33562624        0        0
mm_stat (jobs4): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs5): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs6): 2147483648 23068672 33558528        0 33562624        0        0
mm_stat (jobs7): 2147483648 23068672 33558528        0 33566720        0        0
mm_stat (jobs8): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs9): 2147483648 23068672 33558528        0 33558528        0        0
mm_stat (jobs10): 2147483648 23068672 33558528        0 33562624        0        0

zram DEFLATE mm_stat
mm_stat (jobs1): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs2): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs3): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs4): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs5): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs6): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs7): 2147483648 16252928 25178112        0 25190400        0        0
mm_stat (jobs8): 2147483648 16252928 25178112        0 25190400        0        0
mm_stat (jobs9): 2147483648 16252928 25178112        0 25178112        0        0
mm_stat (jobs10): 2147483648 16252928 25178112        0 25178112        0        0

zram ZSTD mm_stat
mm_stat (jobs1): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs2): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs3): 2147483648 11010048 16781312        0 16785408        0        0
mm_stat (jobs4): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs5): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs6): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs7): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs8): 2147483648 11010048 16781312        0 16781312        0        0
mm_stat (jobs9): 2147483648 11010048 16781312        0 16785408        0        0
mm_stat (jobs10): 2147483648 11010048 16781312        0 16781312        0        0

==================================================================================

Official benchmarks [1]:

Compressor name         Ratio   Compression     Decompress.
zstd 1.1.3 -1           2.877   430 MB/s        1110 MB/s
zlib 1.2.8 -1           2.743   110 MB/s        400 MB/s
brotli 0.5.2 -0         2.708   400 MB/s        430 MB/s
quicklz 1.5.0 -1        2.238   550 MB/s        710 MB/s
lzo1x 2.09 -1           2.108   650 MB/s        830 MB/s
lz4 1.7.5               2.101   720 MB/s        3600 MB/s
snappy 1.1.3            2.091   500 MB/s        1650 MB/s
lzf 3.6 -1              2.077   400 MB/s        860 MB/s

Minchan said:

: I did test with my sample data and compared zstd with deflate.  zstd's
: compress ratio is lower a little bit but compression speed is much faster
: 3 times more and decompress speed is too 2 times more.  With different
: data, it is different but overall, zstd would be better for speed at the
: cost of a little lower compress ratio(about 5%) so I believe it's worth to
: replace deflate.

[1] https://github.com/facebook/zstd

Link: http://lkml.kernel.org/r/20170912050005.3247-1-sergey.senozhatsky@gmail.com
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Tested-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-15 18:21:03 -08:00

246 lines
5.9 KiB
C

/*
* Copyright (C) 2014 Sergey Senozhatsky.
*
* 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 <linux/kernel.h>
#include <linux/string.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/cpu.h>
#include <linux/crypto.h>
#include "zcomp.h"
static const char * const backends[] = {
"lzo",
#if IS_ENABLED(CONFIG_CRYPTO_LZ4)
"lz4",
#endif
#if IS_ENABLED(CONFIG_CRYPTO_DEFLATE)
"deflate",
#endif
#if IS_ENABLED(CONFIG_CRYPTO_LZ4HC)
"lz4hc",
#endif
#if IS_ENABLED(CONFIG_CRYPTO_842)
"842",
#endif
#if IS_ENABLED(CONFIG_CRYPTO_ZSTD)
"zstd",
#endif
NULL
};
static void zcomp_strm_free(struct zcomp_strm *zstrm)
{
if (!IS_ERR_OR_NULL(zstrm->tfm))
crypto_free_comp(zstrm->tfm);
free_pages((unsigned long)zstrm->buffer, 1);
kfree(zstrm);
}
/*
* allocate new zcomp_strm structure with ->tfm initialized by
* backend, return NULL on error
*/
static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
{
struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
if (!zstrm)
return NULL;
zstrm->tfm = crypto_alloc_comp(comp->name, 0, 0);
/*
* allocate 2 pages. 1 for compressed data, plus 1 extra for the
* case when compressed size is larger than the original one
*/
zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
if (IS_ERR_OR_NULL(zstrm->tfm) || !zstrm->buffer) {
zcomp_strm_free(zstrm);
zstrm = NULL;
}
return zstrm;
}
bool zcomp_available_algorithm(const char *comp)
{
int i;
i = __sysfs_match_string(backends, -1, comp);
if (i >= 0)
return true;
/*
* Crypto does not ignore a trailing new line symbol,
* so make sure you don't supply a string containing
* one.
* This also means that we permit zcomp initialisation
* with any compressing algorithm known to crypto api.
*/
return crypto_has_comp(comp, 0, 0) == 1;
}
/* show available compressors */
ssize_t zcomp_available_show(const char *comp, char *buf)
{
bool known_algorithm = false;
ssize_t sz = 0;
int i = 0;
for (; backends[i]; i++) {
if (!strcmp(comp, backends[i])) {
known_algorithm = true;
sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
"[%s] ", backends[i]);
} else {
sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
"%s ", backends[i]);
}
}
/*
* Out-of-tree module known to crypto api or a missing
* entry in `backends'.
*/
if (!known_algorithm && crypto_has_comp(comp, 0, 0) == 1)
sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
"[%s] ", comp);
sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n");
return sz;
}
struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
{
return *get_cpu_ptr(comp->stream);
}
void zcomp_stream_put(struct zcomp *comp)
{
put_cpu_ptr(comp->stream);
}
int zcomp_compress(struct zcomp_strm *zstrm,
const void *src, unsigned int *dst_len)
{
/*
* Our dst memory (zstrm->buffer) is always `2 * PAGE_SIZE' sized
* because sometimes we can endup having a bigger compressed data
* due to various reasons: for example compression algorithms tend
* to add some padding to the compressed buffer. Speaking of padding,
* comp algorithm `842' pads the compressed length to multiple of 8
* and returns -ENOSP when the dst memory is not big enough, which
* is not something that ZRAM wants to see. We can handle the
* `compressed_size > PAGE_SIZE' case easily in ZRAM, but when we
* receive -ERRNO from the compressing backend we can't help it
* anymore. To make `842' happy we need to tell the exact size of
* the dst buffer, zram_drv will take care of the fact that
* compressed buffer is too big.
*/
*dst_len = PAGE_SIZE * 2;
return crypto_comp_compress(zstrm->tfm,
src, PAGE_SIZE,
zstrm->buffer, dst_len);
}
int zcomp_decompress(struct zcomp_strm *zstrm,
const void *src, unsigned int src_len, void *dst)
{
unsigned int dst_len = PAGE_SIZE;
return crypto_comp_decompress(zstrm->tfm,
src, src_len,
dst, &dst_len);
}
int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
{
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
struct zcomp_strm *zstrm;
if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
return 0;
zstrm = zcomp_strm_alloc(comp);
if (IS_ERR_OR_NULL(zstrm)) {
pr_err("Can't allocate a compression stream\n");
return -ENOMEM;
}
*per_cpu_ptr(comp->stream, cpu) = zstrm;
return 0;
}
int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
struct zcomp_strm *zstrm;
zstrm = *per_cpu_ptr(comp->stream, cpu);
if (!IS_ERR_OR_NULL(zstrm))
zcomp_strm_free(zstrm);
*per_cpu_ptr(comp->stream, cpu) = NULL;
return 0;
}
static int zcomp_init(struct zcomp *comp)
{
int ret;
comp->stream = alloc_percpu(struct zcomp_strm *);
if (!comp->stream)
return -ENOMEM;
ret = cpuhp_state_add_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
if (ret < 0)
goto cleanup;
return 0;
cleanup:
free_percpu(comp->stream);
return ret;
}
void zcomp_destroy(struct zcomp *comp)
{
cpuhp_state_remove_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
free_percpu(comp->stream);
kfree(comp);
}
/*
* search available compressors for requested algorithm.
* allocate new zcomp and initialize it. return compressing
* backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
* if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
* case of allocation error, or any other error potentially
* returned by zcomp_init().
*/
struct zcomp *zcomp_create(const char *compress)
{
struct zcomp *comp;
int error;
if (!zcomp_available_algorithm(compress))
return ERR_PTR(-EINVAL);
comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
if (!comp)
return ERR_PTR(-ENOMEM);
comp->name = compress;
error = zcomp_init(comp);
if (error) {
kfree(comp);
return ERR_PTR(error);
}
return comp;
}