linux_dsm_epyc7002/include/linux/writeback.h
Wu Fengguang bb0822954a squeeze max-pause area and drop pass-good area
Revert the pass-good area introduced in ffd1f609ab ("writeback:
introduce max-pause and pass-good dirty limits") and make the max-pause
area smaller and safe.

This fixes ~30% performance regression in the ext3 data=writeback
fio_mmap_randwrite_64k/fio_mmap_randrw_64k test cases, where there are
12 JBOD disks, on each disk runs 8 concurrent tasks doing reads+writes.

Using deadline scheduler also has a regression, but not that big as CFQ,
so this suggests we have some write starvation.

The test logs show that

- the disks are sometimes under utilized

- global dirty pages sometimes rush high to the pass-good area for
  several hundred seconds, while in the mean time some bdi dirty pages
  drop to very low value (bdi_dirty << bdi_thresh).  Then suddenly the
  global dirty pages dropped under global dirty threshold and bdi_dirty
  rush very high (for example, 2 times higher than bdi_thresh). During
  which time balance_dirty_pages() is not called at all.

So the problems are

1) The random writes progress so slow that they break the assumption of
   the max-pause logic that "8 pages per 200ms is typically more than
   enough to curb heavy dirtiers".

2) The max-pause logic ignored task_bdi_thresh and thus opens the possibility
   for some bdi's to over dirty pages, leading to (bdi_dirty >> bdi_thresh)
   and then (bdi_thresh >> bdi_dirty) for others.

3) The higher max-pause/pass-good thresholds somehow leads to the bad
   swing of dirty pages.

The fix is to allow the task to slightly dirty over task_bdi_thresh, but
no way to exceed bdi_dirty and/or global dirty_thresh.

Tests show that it fixed the JBOD regression completely (both behavior
and performance), while still being able to cut down large pause times
in balance_dirty_pages() for single-disk cases.

Reported-by: Li Shaohua <shaohua.li@intel.com>
Tested-by: Li Shaohua <shaohua.li@intel.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-08-19 22:42:07 +08:00

183 lines
5.8 KiB
C

/*
* include/linux/writeback.h
*/
#ifndef WRITEBACK_H
#define WRITEBACK_H
#include <linux/sched.h>
#include <linux/fs.h>
/*
* 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)
/*
* 4MB minimal write chunk size
*/
#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10))
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 */