mirror of
https://github.com/followmsi/android_kernel_google_msm.git
synced 2024-11-06 23:17:41 +00:00
f758eeabeb
Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
162 lines
5.3 KiB
C
162 lines
5.3 KiB
C
/*
|
|
* include/linux/writeback.h
|
|
*/
|
|
#ifndef WRITEBACK_H
|
|
#define WRITEBACK_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/fs.h>
|
|
|
|
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 */
|
|
};
|
|
|
|
/*
|
|
* 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 {
|
|
enum writeback_sync_modes sync_mode;
|
|
unsigned long *older_than_this; /* If !NULL, only write back inodes
|
|
older than this */
|
|
unsigned long wb_start; /* Time writeback_inodes_wb was
|
|
called. This is needed to avoid
|
|
extra jobs and livelock */
|
|
long nr_to_write; /* Write this many pages, and decrement
|
|
this for each page written */
|
|
long pages_skipped; /* Pages which were not written */
|
|
long inodes_written; /* # of inodes written (at least) */
|
|
|
|
/*
|
|
* For a_ops->writepages(): is 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;
|
|
|
|
unsigned nonblocking:1; /* Don't get stuck on request queues */
|
|
unsigned encountered_congestion:1; /* An output: a queue is full */
|
|
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 more_io:1; /* more io to be dispatched */
|
|
};
|
|
|
|
/*
|
|
* fs/fs-writeback.c
|
|
*/
|
|
struct bdi_writeback;
|
|
int inode_wait(void *);
|
|
void writeback_inodes_sb(struct super_block *);
|
|
void writeback_inodes_sb_nr(struct super_block *, unsigned long nr);
|
|
int writeback_inodes_sb_if_idle(struct super_block *);
|
|
int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr);
|
|
void sync_inodes_sb(struct super_block *);
|
|
void writeback_inodes_wb(struct bdi_writeback *wb,
|
|
struct writeback_control *wbc);
|
|
long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
|
|
void wakeup_flusher_threads(long nr_pages);
|
|
|
|
/* 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);
|
|
}
|
|
static inline void inode_sync_wait(struct inode *inode)
|
|
{
|
|
might_sleep();
|
|
wait_on_bit(&inode->i_state, __I_SYNC, 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);
|
|
|
|
/* 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 unsigned long determine_dirtyable_memory(void);
|
|
|
|
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 page_writeback_init(void);
|
|
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
|
|
unsigned long nr_pages_dirtied);
|
|
|
|
static inline void
|
|
balance_dirty_pages_ratelimited(struct address_space *mapping)
|
|
{
|
|
balance_dirty_pages_ratelimited_nr(mapping, 1);
|
|
}
|
|
|
|
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);
|
|
|
|
/* pdflush.c */
|
|
extern int nr_pdflush_threads; /* Global so it can be exported to sysctl
|
|
read-only. */
|
|
|
|
|
|
#endif /* WRITEBACK_H */
|