mirror of
https://github.com/torvalds/linux
synced 2024-10-26 13:19:27 +00:00
deb0bdeb2f
Some of fields in zram->stats are protected by zram->lock which is rather coarse-grained so let's use atomic operation without explict locking. This patch is ready for removing dependency of zram->lock in read path which is very coarse-grained rw_semaphore. Of course, this patch adds new atomic operation so it might make slow but my 12CPU test couldn't spot any regression. All gain/lose is marginal within stddev. iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0 ==Initial write ==Initial write records: 50 records: 50 avg: 412875.17 avg: 415638.23 std: 38543.12 (9.34%) std: 36601.11 (8.81%) max: 521262.03 max: 502976.72 min: 343263.13 min: 351389.12 ==Rewrite ==Rewrite records: 50 records: 50 avg: 416640.34 avg: 397914.33 std: 60798.92 (14.59%) std: 46150.42 (11.60%) max: 543057.07 max: 522669.17 min: 304071.67 min: 316588.77 ==Read ==Read records: 50 records: 50 avg: 4147338.63 avg: 4070736.51 std: 179333.25 (4.32%) std: 223499.89 (5.49%) max: 4459295.28 max: 4539514.44 min: 3753057.53 min: 3444686.31 ==Re-read ==Re-read records: 50 records: 50 avg: 4096706.71 avg: 4117218.57 std: 229735.04 (5.61%) std: 171676.25 (4.17%) max: 4430012.09 max: 4459263.94 min: 2987217.80 min: 3666904.28 ==Reverse Read ==Reverse Read records: 50 records: 50 avg: 4062763.83 avg: 4078508.32 std: 186208.46 (4.58%) std: 172684.34 (4.23%) max: 4401358.78 max: 4424757.22 min: 3381625.00 min: 3679359.94 ==Stride read ==Stride read records: 50 records: 50 avg: 4094933.49 avg: 4082170.22 std: 185710.52 (4.54%) std: 196346.68 (4.81%) max: 4478241.25 max: 4460060.97 min: 3732593.23 min: 3584125.78 ==Random read ==Random read records: 50 records: 50 avg: 4031070.04 avg: 4074847.49 std: 192065.51 (4.76%) std: 206911.33 (5.08%) max: 4356931.16 max: 4399442.56 min: 3481619.62 min: 3548372.44 ==Mixed workload ==Mixed workload records: 50 records: 50 avg: 149925.73 avg: 149675.54 std: 7701.26 (5.14%) std: 6902.09 (4.61%) max: 191301.56 max: 175162.05 min: 133566.28 min: 137762.87 ==Random write ==Random write records: 50 records: 50 avg: 404050.11 avg: 393021.47 std: 58887.57 (14.57%) std: 42813.70 (10.89%) max: 601798.09 max: 524533.43 min: 325176.99 min: 313255.34 ==Pwrite ==Pwrite records: 50 records: 50 avg: 411217.70 avg: 411237.96 std: 43114.99 (10.48%) std: 33136.29 (8.06%) max: 530766.79 max: 471899.76 min: 320786.84 min: 317906.94 ==Pread ==Pread records: 50 records: 50 avg: 4154908.65 avg: 4087121.92 std: 151272.08 (3.64%) std: 219505.04 (5.37%) max: 4459478.12 max: 4435857.38 min: 3730512.41 min: 3101101.67 Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
121 lines
3.2 KiB
C
121 lines
3.2 KiB
C
/*
|
|
* Compressed RAM block device
|
|
*
|
|
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
|
|
* 2012, 2013 Minchan Kim
|
|
*
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
* You can choose the licence that better fits your requirements.
|
|
*
|
|
* Released under the terms of 3-clause BSD License
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
*
|
|
*/
|
|
|
|
#ifndef _ZRAM_DRV_H_
|
|
#define _ZRAM_DRV_H_
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/zsmalloc.h>
|
|
|
|
/*
|
|
* Some arbitrary value. This is just to catch
|
|
* invalid value for num_devices module parameter.
|
|
*/
|
|
static const unsigned max_num_devices = 32;
|
|
|
|
/*-- Configurable parameters */
|
|
|
|
/*
|
|
* Pages that compress to size greater than this are stored
|
|
* uncompressed in memory.
|
|
*/
|
|
static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
|
|
|
|
/*
|
|
* NOTE: max_zpage_size must be less than or equal to:
|
|
* ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
|
|
* always return failure.
|
|
*/
|
|
|
|
/*-- End of configurable params */
|
|
|
|
#define SECTOR_SHIFT 9
|
|
#define SECTOR_SIZE (1 << SECTOR_SHIFT)
|
|
#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
|
|
#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
|
|
#define ZRAM_LOGICAL_BLOCK_SHIFT 12
|
|
#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
|
|
#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
|
|
(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
|
|
|
|
/* Flags for zram pages (table[page_no].flags) */
|
|
enum zram_pageflags {
|
|
/* Page consists entirely of zeros */
|
|
ZRAM_ZERO,
|
|
|
|
__NR_ZRAM_PAGEFLAGS,
|
|
};
|
|
|
|
/*-- Data structures */
|
|
|
|
/* Allocated for each disk page */
|
|
struct table {
|
|
unsigned long handle;
|
|
u16 size; /* object size (excluding header) */
|
|
u8 count; /* object ref count (not yet used) */
|
|
u8 flags;
|
|
} __aligned(4);
|
|
|
|
struct zram_stats {
|
|
atomic64_t compr_size; /* compressed size of pages stored */
|
|
atomic64_t num_reads; /* failed + successful */
|
|
atomic64_t num_writes; /* --do-- */
|
|
atomic64_t failed_reads; /* should NEVER! happen */
|
|
atomic64_t failed_writes; /* can happen when memory is too low */
|
|
atomic64_t invalid_io; /* non-page-aligned I/O requests */
|
|
atomic64_t notify_free; /* no. of swap slot free notifications */
|
|
atomic_t pages_zero; /* no. of zero filled pages */
|
|
atomic_t pages_stored; /* no. of pages currently stored */
|
|
atomic_t good_compress; /* % of pages with compression ratio<=50% */
|
|
atomic_t bad_compress; /* % of pages with compression ratio>=75% */
|
|
};
|
|
|
|
struct zram_meta {
|
|
void *compress_workmem;
|
|
void *compress_buffer;
|
|
struct table *table;
|
|
struct zs_pool *mem_pool;
|
|
};
|
|
|
|
struct zram_slot_free {
|
|
unsigned long index;
|
|
struct zram_slot_free *next;
|
|
};
|
|
|
|
struct zram {
|
|
struct zram_meta *meta;
|
|
struct rw_semaphore lock; /* protect compression buffers, table,
|
|
* reads and writes
|
|
*/
|
|
|
|
struct work_struct free_work; /* handle pending free request */
|
|
struct zram_slot_free *slot_free_rq; /* list head of free request */
|
|
|
|
struct request_queue *queue;
|
|
struct gendisk *disk;
|
|
int init_done;
|
|
/* Prevent concurrent execution of device init, reset and R/W request */
|
|
struct rw_semaphore init_lock;
|
|
/*
|
|
* This is the limit on amount of *uncompressed* worth of data
|
|
* we can store in a disk.
|
|
*/
|
|
u64 disksize; /* bytes */
|
|
spinlock_t slot_free_lock;
|
|
|
|
struct zram_stats stats;
|
|
};
|
|
#endif
|