mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-16 01:04:08 +08:00
ffd1f609ab
The max-pause limit helps to keep the sleep time inside balance_dirty_pages() within MAX_PAUSE=200ms. The 200ms max sleep means per task rate limit of 8pages/200ms=160KB/s when dirty exceeded, which normally is enough to stop dirtiers from continue pushing the dirty pages high, unless there are a sufficient large number of slow dirtiers (eg. 500 tasks doing 160KB/s will still sum up to 80MB/s, exceeding the write bandwidth of a slow disk and hence accumulating more and more dirty pages). The pass-good limit helps to let go of the good bdi's in the presence of a blocked bdi (ie. NFS server not responding) or slow USB disk which for some reason build up a large number of initial dirty pages that refuse to go away anytime soon. For example, given two bdi's A and B and the initial state bdi_thresh_A = dirty_thresh / 2 bdi_thresh_B = dirty_thresh / 2 bdi_dirty_A = dirty_thresh / 2 bdi_dirty_B = dirty_thresh / 2 Then A get blocked, after a dozen seconds bdi_thresh_A = 0 bdi_thresh_B = dirty_thresh bdi_dirty_A = dirty_thresh / 2 bdi_dirty_B = dirty_thresh / 2 The (bdi_dirty_B < bdi_thresh_B) test is now useless and the dirty pages will be effectively throttled by condition (nr_dirty < dirty_thresh). This has two problems: (1) we lose the protections for light dirtiers (2) balance_dirty_pages() effectively becomes IO-less because the (bdi_nr_reclaimable > bdi_thresh) test won't be true. This is good for IO, but balance_dirty_pages() loses an important way to break out of the loop which leads to more spread out throttle delays. DIRTY_PASSGOOD_AREA can eliminate the above issues. The only problem is, DIRTY_PASSGOOD_AREA needs to be defined as 2 to fully cover the above example while this patch uses the more conservative value 8 so as not to surprise people with too many dirty pages than expected. The max-pause limit won't noticeably impact the speed dirty pages are knocked down when there is a sudden drop of global/bdi dirty thresholds. Because the heavy dirties will be throttled below 160KB/s which is slow enough. It does help to avoid long dirty throttle delays and especially will make light dirtiers more responsive. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
183 lines
5.9 KiB
C
183 lines
5.9 KiB
C
/*
|
|
* include/linux/writeback.h
|
|
*/
|
|
#ifndef WRITEBACK_H
|
|
#define WRITEBACK_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/fs.h>
|
|
|
|
/*
|
|
* The 1/16 region above the global dirty limit will be put to maximum pauses:
|
|
*
|
|
* (limit, limit + limit/DIRTY_MAXPAUSE_AREA)
|
|
*
|
|
* The 1/16 region above the max-pause region, dirty exceeded bdi's will be put
|
|
* to loops:
|
|
*
|
|
* (limit + limit/DIRTY_MAXPAUSE_AREA, limit + limit/DIRTY_PASSGOOD_AREA)
|
|
*
|
|
* 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_MAXPAUSE_AREA 16
|
|
#define DIRTY_PASSGOOD_AREA 8
|
|
|
|
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;
|
|
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(): 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 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 */
|
|
};
|
|
|
|
/*
|
|
* 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 *);
|
|
long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages);
|
|
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);
|
|
|
|
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 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 __bdi_update_bandwidth(struct backing_dev_info *bdi,
|
|
unsigned long 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_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 */
|