mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-16 01:04:08 +08:00
e98be2d599
The estimation value will start from 100MB/s and adapt to the real bandwidth in seconds. It tries to update the bandwidth only when disk is fully utilized. Any inactive period of more than one second will be skipped. The estimated bandwidth will be reflecting how fast the device can writeout when _fully utilized_, and won't drop to 0 when it goes idle. The value will remain constant at disk idle time. At busy write time, if not considering fluctuations, it will also remain high unless be knocked down by possible concurrent reads that compete for the disk time and bandwidth with async writes. The estimation is not done purely in the flusher because there is no guarantee for write_cache_pages() to return timely to update bandwidth. The bdi->avg_write_bandwidth smoothing is very effective for filtering out sudden spikes, however may be a little biased in long term. The overheads are low because the bdi bandwidth update only occurs at 200ms intervals. The 200ms update interval is suitable, because it's not possible to get the real bandwidth for the instance at all, due to large fluctuations. The NFS commits can be as large as seconds worth of data. One XFS completion may be as large as half second worth of data if we are going to increase the write chunk to half second worth of data. In ext4, fluctuations with time period of around 5 seconds is observed. And there is another pattern of irregular periods of up to 20 seconds on SSD tests. That's why we are not only doing the estimation at 200ms intervals, but also averaging them over a period of 3 seconds and then go further to do another level of smoothing in avg_write_bandwidth. CC: Li Shaohua <shaohua.li@intel.com> CC: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
156 lines
4.9 KiB
C
156 lines
4.9 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;
|
|
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);
|
|
|
|
/* 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 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 */
|