Existing zram (zcomp) implementation has only one compression stream (buffer and algorithm private part), so in order to prevent data corruption only one write (compress operation) can use this compression stream, forcing all concurrent write operations to wait for stream lock to be released. This patch changes zcomp to keep a compression streams list of user-defined size (via sysfs device attr). Each write operation still exclusively holds compression stream, the difference is that we can have N write operations (depending on size of streams list) executing in parallel. See TEST section later in commit message for performance data. Introduce struct zcomp_strm_multi and a set of functions to manage zcomp_strm stream access. zcomp_strm_multi has a list of idle zcomp_strm structs, spinlock to protect idle list and wait queue, making it possible to perform parallel compressions. The following set of functions added: - zcomp_strm_multi_find()/zcomp_strm_multi_release() find and release a compression stream, implement required locking - zcomp_strm_multi_create()/zcomp_strm_multi_destroy() create and destroy zcomp_strm_multi zcomp ->strm_find() and ->strm_release() callbacks are set during initialisation to zcomp_strm_multi_find()/zcomp_strm_multi_release() correspondingly. Each time zcomp issues a zcomp_strm_multi_find() call, the following set of operations performed: - spin lock strm_lock - if idle list is not empty, remove zcomp_strm from idle list, spin unlock and return zcomp stream pointer to caller - if idle list is empty, current adds itself to wait queue. it will be awaken by zcomp_strm_multi_release() caller. zcomp_strm_multi_release(): - spin lock strm_lock - add zcomp stream to idle list - spin unlock, wake up sleeper Minchan Kim reported that spinlock-based locking scheme has demonstrated a severe perfomance regression for single compression stream case, comparing to mutex-based (see https://lkml.org/lkml/2014/2/18/16) base spinlock mutex ==Initial write ==Initial write ==Initial write records: 5 records: 5 records: 5 avg: 1642424.35 avg: 699610.40 avg: 1655583.71 std: 39890.95(2.43%) std: 232014.19(33.16%) std: 52293.96 max: 1690170.94 max: 1163473.45 max: 1697164.75 min: 1568669.52 min: 573429.88 min: 1553410.23 ==Rewrite ==Rewrite ==Rewrite records: 5 records: 5 records: 5 avg: 1611775.39 avg: 501406.64 avg: 1684419.11 std: 17144.58(1.06%) std: 15354.41(3.06%) std: 18367.42 max: 1641800.95 max: 531356.78 max: 1706445.84 min: 1593515.27 min: 488817.78 min: 1655335.73 When only one compression stream available, mutex with spin on owner tends to perform much better than frequent wait_event()/wake_up(). This is why single stream implemented as a special case with mutex locking. Introduce and document zram device attribute max_comp_streams. This attr shows and stores current zcomp's max number of zcomp streams (max_strm). Extend zcomp's zcomp_create() with `max_strm' parameter. `max_strm' limits the number of zcomp_strm structs in compression backend's idle list (max_comp_streams). max_comp_streams used during initialisation as follows: -- passing to zcomp_create() max_strm equals to 1 will initialise zcomp using single compression stream zcomp_strm_single (mutex-based locking). -- passing to zcomp_create() max_strm greater than 1 will initialise zcomp using multi compression stream zcomp_strm_multi (spinlock-based locking). default max_comp_streams value is 1, meaning that zram with single stream will be initialised. Later patch will introduce configuration knob to change max_comp_streams on already initialised and used zcomp. TEST iozone -t 3 -R -r 16K -s 60M -I +Z test base 1 strm (mutex) 3 strm (spinlock) ----------------------------------------------------------------------- Initial write 589286.78 583518.39 718011.05 Rewrite 604837.97 596776.38 1515125.72 Random write 584120.11 595714.58 1388850.25 Pwrite 535731.17 541117.38 739295.27 Fwrite 1418083.88 1478612.72 1484927.06 Usage example: set max_comp_streams to 4 echo 4 > /sys/block/zram0/max_comp_streams show current max_comp_streams (default value is 1). cat /sys/block/zram0/max_comp_streams Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Nitin Gupta <ngupta@vflare.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
282 lines
6.4 KiB
C
282 lines
6.4 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/slab.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/sched.h>
|
|
|
|
#include "zcomp.h"
|
|
#include "zcomp_lzo.h"
|
|
|
|
/*
|
|
* single zcomp_strm backend
|
|
*/
|
|
struct zcomp_strm_single {
|
|
struct mutex strm_lock;
|
|
struct zcomp_strm *zstrm;
|
|
};
|
|
|
|
/*
|
|
* multi zcomp_strm backend
|
|
*/
|
|
struct zcomp_strm_multi {
|
|
/* protect strm list */
|
|
spinlock_t strm_lock;
|
|
/* max possible number of zstrm streams */
|
|
int max_strm;
|
|
/* number of available zstrm streams */
|
|
int avail_strm;
|
|
/* list of available strms */
|
|
struct list_head idle_strm;
|
|
wait_queue_head_t strm_wait;
|
|
};
|
|
|
|
static struct zcomp_backend *find_backend(const char *compress)
|
|
{
|
|
if (strncmp(compress, "lzo", 3) == 0)
|
|
return &zcomp_lzo;
|
|
return NULL;
|
|
}
|
|
|
|
static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
|
|
{
|
|
if (zstrm->private)
|
|
comp->backend->destroy(zstrm->private);
|
|
free_pages((unsigned long)zstrm->buffer, 1);
|
|
kfree(zstrm);
|
|
}
|
|
|
|
/*
|
|
* allocate new zcomp_strm structure with ->private 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->private = comp->backend->create();
|
|
/*
|
|
* 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 (!zstrm->private || !zstrm->buffer) {
|
|
zcomp_strm_free(comp, zstrm);
|
|
zstrm = NULL;
|
|
}
|
|
return zstrm;
|
|
}
|
|
|
|
/*
|
|
* get idle zcomp_strm or wait until other process release
|
|
* (zcomp_strm_release()) one for us
|
|
*/
|
|
static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
|
|
{
|
|
struct zcomp_strm_multi *zs = comp->stream;
|
|
struct zcomp_strm *zstrm;
|
|
|
|
while (1) {
|
|
spin_lock(&zs->strm_lock);
|
|
if (!list_empty(&zs->idle_strm)) {
|
|
zstrm = list_entry(zs->idle_strm.next,
|
|
struct zcomp_strm, list);
|
|
list_del(&zstrm->list);
|
|
spin_unlock(&zs->strm_lock);
|
|
return zstrm;
|
|
}
|
|
/* zstrm streams limit reached, wait for idle stream */
|
|
if (zs->avail_strm >= zs->max_strm) {
|
|
spin_unlock(&zs->strm_lock);
|
|
wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
|
|
continue;
|
|
}
|
|
/* allocate new zstrm stream */
|
|
zs->avail_strm++;
|
|
spin_unlock(&zs->strm_lock);
|
|
|
|
zstrm = zcomp_strm_alloc(comp);
|
|
if (!zstrm) {
|
|
spin_lock(&zs->strm_lock);
|
|
zs->avail_strm--;
|
|
spin_unlock(&zs->strm_lock);
|
|
wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
|
|
continue;
|
|
}
|
|
break;
|
|
}
|
|
return zstrm;
|
|
}
|
|
|
|
/* add stream back to idle list and wake up waiter or free the stream */
|
|
static void zcomp_strm_multi_release(struct zcomp *comp, struct zcomp_strm *zstrm)
|
|
{
|
|
struct zcomp_strm_multi *zs = comp->stream;
|
|
|
|
spin_lock(&zs->strm_lock);
|
|
if (zs->avail_strm <= zs->max_strm) {
|
|
list_add(&zstrm->list, &zs->idle_strm);
|
|
spin_unlock(&zs->strm_lock);
|
|
wake_up(&zs->strm_wait);
|
|
return;
|
|
}
|
|
|
|
zs->avail_strm--;
|
|
spin_unlock(&zs->strm_lock);
|
|
zcomp_strm_free(comp, zstrm);
|
|
}
|
|
|
|
static void zcomp_strm_multi_destroy(struct zcomp *comp)
|
|
{
|
|
struct zcomp_strm_multi *zs = comp->stream;
|
|
struct zcomp_strm *zstrm;
|
|
|
|
while (!list_empty(&zs->idle_strm)) {
|
|
zstrm = list_entry(zs->idle_strm.next,
|
|
struct zcomp_strm, list);
|
|
list_del(&zstrm->list);
|
|
zcomp_strm_free(comp, zstrm);
|
|
}
|
|
kfree(zs);
|
|
}
|
|
|
|
static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm)
|
|
{
|
|
struct zcomp_strm *zstrm;
|
|
struct zcomp_strm_multi *zs;
|
|
|
|
comp->destroy = zcomp_strm_multi_destroy;
|
|
comp->strm_find = zcomp_strm_multi_find;
|
|
comp->strm_release = zcomp_strm_multi_release;
|
|
zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL);
|
|
if (!zs)
|
|
return -ENOMEM;
|
|
|
|
comp->stream = zs;
|
|
spin_lock_init(&zs->strm_lock);
|
|
INIT_LIST_HEAD(&zs->idle_strm);
|
|
init_waitqueue_head(&zs->strm_wait);
|
|
zs->max_strm = max_strm;
|
|
zs->avail_strm = 1;
|
|
|
|
zstrm = zcomp_strm_alloc(comp);
|
|
if (!zstrm) {
|
|
kfree(zs);
|
|
return -ENOMEM;
|
|
}
|
|
list_add(&zstrm->list, &zs->idle_strm);
|
|
return 0;
|
|
}
|
|
|
|
static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp)
|
|
{
|
|
struct zcomp_strm_single *zs = comp->stream;
|
|
mutex_lock(&zs->strm_lock);
|
|
return zs->zstrm;
|
|
}
|
|
|
|
static void zcomp_strm_single_release(struct zcomp *comp,
|
|
struct zcomp_strm *zstrm)
|
|
{
|
|
struct zcomp_strm_single *zs = comp->stream;
|
|
mutex_unlock(&zs->strm_lock);
|
|
}
|
|
|
|
static void zcomp_strm_single_destroy(struct zcomp *comp)
|
|
{
|
|
struct zcomp_strm_single *zs = comp->stream;
|
|
zcomp_strm_free(comp, zs->zstrm);
|
|
kfree(zs);
|
|
}
|
|
|
|
static int zcomp_strm_single_create(struct zcomp *comp)
|
|
{
|
|
struct zcomp_strm_single *zs;
|
|
|
|
comp->destroy = zcomp_strm_single_destroy;
|
|
comp->strm_find = zcomp_strm_single_find;
|
|
comp->strm_release = zcomp_strm_single_release;
|
|
zs = kmalloc(sizeof(struct zcomp_strm_single), GFP_KERNEL);
|
|
if (!zs)
|
|
return -ENOMEM;
|
|
|
|
comp->stream = zs;
|
|
mutex_init(&zs->strm_lock);
|
|
zs->zstrm = zcomp_strm_alloc(comp);
|
|
if (!zs->zstrm) {
|
|
kfree(zs);
|
|
return -ENOMEM;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
struct zcomp_strm *zcomp_strm_find(struct zcomp *comp)
|
|
{
|
|
return comp->strm_find(comp);
|
|
}
|
|
|
|
void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm)
|
|
{
|
|
comp->strm_release(comp, zstrm);
|
|
}
|
|
|
|
int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
|
|
const unsigned char *src, size_t *dst_len)
|
|
{
|
|
return comp->backend->compress(src, zstrm->buffer, dst_len,
|
|
zstrm->private);
|
|
}
|
|
|
|
int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
|
|
size_t src_len, unsigned char *dst)
|
|
{
|
|
return comp->backend->decompress(src, src_len, dst);
|
|
}
|
|
|
|
void zcomp_destroy(struct zcomp *comp)
|
|
{
|
|
comp->destroy(comp);
|
|
kfree(comp);
|
|
}
|
|
|
|
/*
|
|
* search available compressors for requested algorithm.
|
|
* allocate new zcomp and initialize it. return NULL
|
|
* if requested algorithm is not supported or in case
|
|
* of init error
|
|
*/
|
|
struct zcomp *zcomp_create(const char *compress, int max_strm)
|
|
{
|
|
struct zcomp *comp;
|
|
struct zcomp_backend *backend;
|
|
|
|
backend = find_backend(compress);
|
|
if (!backend)
|
|
return NULL;
|
|
|
|
comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
|
|
if (!comp)
|
|
return NULL;
|
|
|
|
comp->backend = backend;
|
|
if (max_strm > 1)
|
|
zcomp_strm_multi_create(comp, max_strm);
|
|
else
|
|
zcomp_strm_single_create(comp);
|
|
if (!comp->stream) {
|
|
kfree(comp);
|
|
return NULL;
|
|
}
|
|
return comp;
|
|
}
|