linux/drivers/block/zram/zram_drv.h
Minchan Kim e46e33152e zram: remove zram->lock in read path and change it with mutex
Finally, we separated zram->lock dependency from 32bit stat/ table
handling so there is no reason to use rw_semaphore between read and
write path so this patch removes the lock from read path totally and
changes rw_semaphore with mutex.  So, we could do

old:

  read-read: OK
  read-write: NO
  write-write: NO

Now:

  read-read: OK
  read-write: OK
  write-write: NO

The below data proves mixed workload performs well 11 times and there is
also enhance on write-write path because current rw-semaphore doesn't
support SPIN_ON_OWNER.  It's side effect but anyway good thing for us.

Write-related tests perform better (from 61% to 1058%) but read path has
good/bad(from -2.22% to 1.45%) but they are all marginal within stddev.

  CPU 12
  iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0

  ==Initial write                ==Initial write
  records: 10                    records: 10
  avg:  516189.16                avg:  839907.96
  std:   22486.53 (4.36%)        std:   47902.17 (5.70%)
  max:  546970.60                max:  909910.35
  min:  481131.54                min:  751148.38
  ==Rewrite                      ==Rewrite
  records: 10                    records: 10
  avg:  509527.98                avg: 1050156.37
  std:   45799.94 (8.99%)        std:   40695.44 (3.88%)
  max:  611574.27                max: 1111929.26
  min:  443679.95                min:  980409.62
  ==Read                         ==Read
  records: 10                    records: 10
  avg: 4408624.17                avg: 4472546.76
  std:  281152.61 (6.38%)        std:  163662.78 (3.66%)
  max: 4867888.66                max: 4727351.03
  min: 4058347.69                min: 4126520.88
  ==Re-read                      ==Re-read
  records: 10                    records: 10
  avg: 4462147.53                avg: 4363257.75
  std:  283546.11 (6.35%)        std:  247292.63 (5.67%)
  max: 4912894.44                max: 4677241.75
  min: 4131386.50                min: 4035235.84
  ==Reverse Read                 ==Reverse Read
  records: 10                    records: 10
  avg: 4565865.97                avg: 4485818.08
  std:  313395.63 (6.86%)        std:  248470.10 (5.54%)
  max: 5232749.16                max: 4789749.94
  min: 4185809.62                min: 3963081.34
  ==Stride read                  ==Stride read
  records: 10                    records: 10
  avg: 4515981.80                avg: 4418806.01
  std:  211192.32 (4.68%)        std:  212837.97 (4.82%)
  max: 4889287.28                max: 4686967.22
  min: 4210362.00                min: 4083041.84
  ==Random read                  ==Random read
  records: 10                    records: 10
  avg: 4410525.23                avg: 4387093.18
  std:  236693.22 (5.37%)        std:  235285.23 (5.36%)
  max: 4713698.47                max: 4669760.62
  min: 4057163.62                min: 3952002.16
  ==Mixed workload               ==Mixed workload
  records: 10                    records: 10
  avg:  243234.25                avg: 2818677.27
  std:   28505.07 (11.72%)       std:  195569.70 (6.94%)
  max:  288905.23                max: 3126478.11
  min:  212473.16                min: 2484150.69
  ==Random write                 ==Random write
  records: 10                    records: 10
  avg:  555887.07                avg: 1053057.79
  std:   70841.98 (12.74%)       std:   35195.36 (3.34%)
  max:  683188.28                max: 1096125.73
  min:  437299.57                min:  992481.93
  ==Pwrite                       ==Pwrite
  records: 10                    records: 10
  avg:  501745.93                avg:  810363.09
  std:   16373.54 (3.26%)        std:   19245.01 (2.37%)
  max:  518724.52                max:  833359.70
  min:  464208.73                min:  765501.87
  ==Pread                        ==Pread
  records: 10                    records: 10
  avg: 4539894.60                avg: 4457680.58
  std:  197094.66 (4.34%)        std:  188965.60 (4.24%)
  max: 4877170.38                max: 4689905.53
  min: 4226326.03                min: 4095739.72

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>
2014-01-30 16:56:56 -08:00

110 lines
3.0 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 {
rwlock_t tb_lock; /* protect table */
void *compress_workmem;
void *compress_buffer;
struct table *table;
struct zs_pool *mem_pool;
struct mutex buffer_lock; /* protect compress buffers */
};
struct zram {
struct zram_meta *meta;
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 */
struct zram_stats stats;
};
#endif