linux_dsm_epyc7002/include/linux/writeback.h
Wu Fengguang 1a12d8bd7b writeback: scale IO chunk size up to half device bandwidth
Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
concern of not holding I_SYNC for too long.  (At least, that was the
comment previously.)  This doesn't make sense now because the only
time we wait for I_SYNC is if we are calling sync or fsync, and in
that case we need to write out all of the data anyway.  Previously
there may have been other code paths that waited on I_SYNC, but not
any more.					    -- Theodore Ts'o

So remove the MAX_WRITEBACK_PAGES constraint. The writeback pages
will adapt to as large as the storage device can write within 500ms.

XFS is observed to do IO completions in a batch, and the batch size is
equal to the write chunk size. To avoid dirty pages to suddenly drop
out of balance_dirty_pages()'s dirty control scope and create large
fluctuations, the chunk size is also limited to half the control scope.

The balance_dirty_pages() control scrope is

	[(background_thresh + dirty_thresh) / 2, dirty_thresh]

which is by default [15%, 20%] of global dirty pages, whose range size
is dirty_thresh / DIRTY_FULL_SCOPE.

The adpative write chunk size will be rounded to the nearest 4MB
boundary.

http://bugzilla.kernel.org/show_bug.cgi?id=13930

CC: Theodore Ts'o <tytso@mit.edu>
CC: Dave Chinner <david@fromorbit.com>
CC: Chris Mason <chris.mason@oracle.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-07-09 22:09:03 -07:00

194 lines
6.2 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)
*
* 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_SCOPE 8
#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2)
#define DIRTY_MAXPAUSE_AREA 16
#define DIRTY_PASSGOOD_AREA 8
/*
* 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 */