linux/include/linux/writeback.h
Dave Chinner 7747bd4bce sync: don't block the flusher thread waiting on IO
When sync does it's WB_SYNC_ALL writeback, it issues data Io and
then immediately waits for IO completion. This is done in the
context of the flusher thread, and hence completely ties up the
flusher thread for the backing device until all the dirty inodes
have been synced. On filesystems that are dirtying inodes constantly
and quickly, this means the flusher thread can be tied up for
minutes per sync call and hence badly affect system level write IO
performance as the page cache cannot be cleaned quickly.

We already have a wait loop for IO completion for sync(2), so cut
this out of the flusher thread and delegate it to wait_sb_inodes().
Hence we can do rapid IO submission, and then wait for it all to
complete.

Effect of sync on fsmark before the patch:

FSUse%        Count         Size    Files/sec     App Overhead
.....
     0       640000         4096      35154.6          1026984
     0       720000         4096      36740.3          1023844
     0       800000         4096      36184.6           916599
     0       880000         4096       1282.7          1054367
     0       960000         4096       3951.3           918773
     0      1040000         4096      40646.2           996448
     0      1120000         4096      43610.1           895647
     0      1200000         4096      40333.1           921048

And a single sync pass took:

  real    0m52.407s
  user    0m0.000s
  sys     0m0.090s

After the patch, there is no impact on fsmark results, and each
individual sync(2) operation run concurrently with the same fsmark
workload takes roughly 7s:

  real    0m6.930s
  user    0m0.000s
  sys     0m0.039s

IOWs, sync is 7-8x faster on a busy filesystem and does not have an
adverse impact on ongoing async data write operations.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-02 09:16:42 -07:00

187 lines
6.0 KiB
C

/*
* include/linux/writeback.h
*/
#ifndef WRITEBACK_H
#define WRITEBACK_H
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
DECLARE_PER_CPU(int, dirty_throttle_leaks);
/*
* The 1/4 region under the global dirty thresh is for smooth dirty throttling:
*
* (thresh - thresh/DIRTY_FULL_SCOPE, thresh)
*
* Further beyond, all dirtier tasks will enter a loop waiting (possibly long
* time) for the dirty pages to drop, unless written enough pages.
*
* The global dirty threshold is normally equal to the global dirty limit,
* except when the system suddenly allocates a lot of anonymous memory and
* knocks down the global dirty threshold quickly, in which case the global
* dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
*/
#define DIRTY_SCOPE 8
#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2)
struct backing_dev_info;
/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
WB_SYNC_NONE, /* Don't wait on anything */
WB_SYNC_ALL, /* Wait on every mapping */
};
/*
* why some writeback work was initiated
*/
enum wb_reason {
WB_REASON_BACKGROUND,
WB_REASON_TRY_TO_FREE_PAGES,
WB_REASON_SYNC,
WB_REASON_PERIODIC,
WB_REASON_LAPTOP_TIMER,
WB_REASON_FREE_MORE_MEM,
WB_REASON_FS_FREE_SPACE,
WB_REASON_FORKER_THREAD,
WB_REASON_MAX,
};
extern const char *wb_reason_name[];
/*
* A control structure which tells the writeback code what to do. These are
* always on the stack, and hence need no locking. They are always initialised
* in a manner such that unspecified fields are set to zero.
*/
struct writeback_control {
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
/*
* For a_ops->writepages(): if start or end are non-zero then this is
* a hint that the filesystem need only write out the pages inside that
* byterange. The byte at `end' is included in the writeout request.
*/
loff_t range_start;
loff_t range_end;
enum writeback_sync_modes sync_mode;
unsigned for_kupdate:1; /* A kupdate writeback */
unsigned for_background:1; /* A background writeback */
unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
};
/*
* fs/fs-writeback.c
*/
struct bdi_writeback;
int inode_wait(void *);
void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
void sync_inodes_sb(struct super_block *);
long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
enum wb_reason reason);
long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
might_sleep();
wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE);
}
/*
* mm/page-writeback.c
*/
#ifdef CONFIG_BLOCK
void laptop_io_completion(struct backing_dev_info *info);
void laptop_sync_completion(void);
void laptop_mode_sync(struct work_struct *work);
void laptop_mode_timer_fn(unsigned long data);
#else
static inline void laptop_sync_completion(void) { }
#endif
void throttle_vm_writeout(gfp_t gfp_mask);
bool zone_dirty_ok(struct zone *zone);
extern unsigned long global_dirty_limit;
/* These are exported to sysctl. */
extern int dirty_background_ratio;
extern unsigned long dirty_background_bytes;
extern int vm_dirty_ratio;
extern unsigned long vm_dirty_bytes;
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
extern int vm_highmem_is_dirtyable;
extern int block_dump;
extern int laptop_mode;
extern int dirty_background_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_background_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
struct ctl_table;
int dirty_writeback_centisecs_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
unsigned long dirty);
void __bdi_update_bandwidth(struct backing_dev_info *bdi,
unsigned long thresh,
unsigned long bg_thresh,
unsigned long dirty,
unsigned long bdi_thresh,
unsigned long bdi_dirty,
unsigned long start_time);
void page_writeback_init(void);
void balance_dirty_pages_ratelimited(struct address_space *mapping);
typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
void *data);
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
void set_page_dirty_balance(struct page *page, int page_mkwrite);
void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
void account_page_redirty(struct page *page);
#endif /* WRITEBACK_H */