8bc3be2751
After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s: ~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispatch queues goes like this: s_io s_more_io ------------------------- 1) 100M,1K 0 2) 1K 96M 3) 0 96M 1) initial state with a 100M file and a 1K file 2) 4M written, nr_to_write <= 0, so write more 3) 1K written, nr_to_write > 0, no more writes(BUG) nr_to_write > 0 in (3) fools the upper layer to think that data have all been written out. The big dirty file is actually still sitting in s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and let the loop in generic_sync_sb_inodes() continue: this may starve newly expired inodes in s_dirty. It is also not an option to draw inodes from both s_more_io and s_dirty, an let the loop go on: this might lead to live locks, and might also starve other superblocks in sync time(well kupdate may still starve some superblocks, that's another bug). We have to return when a full scan of s_io completes. So nr_to_write > 0 does not necessarily mean that "all data are written". This patch introduces a flag writeback_control.more_io to indicate that more io should be done. With it the big dirty file no longer has to wait for the next kupdate invokation 5s later. In sync_sb_inodes() we only set more_io on super_blocks we actually visited. This avoids the interaction between two pdflush deamons. Also in __sync_single_inode() we don't blindly keep requeuing the io if the filesystem cannot progress. Failing to do so may lead to 100% iowait. Tested-by: Mike Snitzer <snitzer@gmail.com> Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Michael Rubin <mrubin@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
150 lines
4.4 KiB
C
150 lines
4.4 KiB
C
/*
|
|
* include/linux/writeback.h
|
|
*/
|
|
#ifndef WRITEBACK_H
|
|
#define WRITEBACK_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/fs.h>
|
|
|
|
struct backing_dev_info;
|
|
|
|
extern spinlock_t inode_lock;
|
|
extern struct list_head inode_in_use;
|
|
extern struct list_head inode_unused;
|
|
|
|
/*
|
|
* Yes, writeback.h requires sched.h
|
|
* No, sched.h is not included from here.
|
|
*/
|
|
static inline int task_is_pdflush(struct task_struct *task)
|
|
{
|
|
return task->flags & PF_FLUSHER;
|
|
}
|
|
|
|
#define current_is_pdflush() task_is_pdflush(current)
|
|
|
|
/*
|
|
* fs/fs-writeback.c
|
|
*/
|
|
enum writeback_sync_modes {
|
|
WB_SYNC_NONE, /* Don't wait on anything */
|
|
WB_SYNC_ALL, /* Wait on every mapping */
|
|
WB_SYNC_HOLD, /* Hold the inode on sb_dirty for sys_sync() */
|
|
};
|
|
|
|
/*
|
|
* 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 {
|
|
struct backing_dev_info *bdi; /* If !NULL, only write back this
|
|
queue */
|
|
enum writeback_sync_modes sync_mode;
|
|
unsigned long *older_than_this; /* If !NULL, only write back inodes
|
|
older than this */
|
|
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 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_reclaim:1; /* Invoked from the page allocator */
|
|
unsigned for_writepages:1; /* This is a writepages() call */
|
|
unsigned range_cyclic:1; /* range_start is cyclic */
|
|
unsigned more_io:1; /* more io to be dispatched */
|
|
};
|
|
|
|
/*
|
|
* fs/fs-writeback.c
|
|
*/
|
|
void writeback_inodes(struct writeback_control *wbc);
|
|
int inode_wait(void *);
|
|
void sync_inodes_sb(struct super_block *, int wait);
|
|
void sync_inodes(int wait);
|
|
|
|
/* 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_LOCK, 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
|
|
*/
|
|
int wakeup_pdflush(long nr_pages);
|
|
void laptop_io_completion(void);
|
|
void laptop_sync_completion(void);
|
|
void throttle_vm_writeout(gfp_t gfp_mask);
|
|
|
|
/* These are exported to sysctl. */
|
|
extern int dirty_background_ratio;
|
|
extern int vm_dirty_ratio;
|
|
extern int dirty_writeback_interval;
|
|
extern int dirty_expire_interval;
|
|
extern int vm_highmem_is_dirtyable;
|
|
extern int block_dump;
|
|
extern int laptop_mode;
|
|
|
|
extern int dirty_ratio_handler(struct ctl_table *table, int write,
|
|
struct file *filp, void __user *buffer, size_t *lenp,
|
|
loff_t *ppos);
|
|
|
|
struct ctl_table;
|
|
struct file;
|
|
int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *,
|
|
void __user *, size_t *, loff_t *);
|
|
|
|
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 pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
|
|
int generic_writepages(struct address_space *mapping,
|
|
struct writeback_control *wbc);
|
|
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);
|
|
int sync_page_range(struct inode *inode, struct address_space *mapping,
|
|
loff_t pos, loff_t count);
|
|
int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
|
|
loff_t pos, loff_t count);
|
|
void set_page_dirty_balance(struct page *page, int page_mkwrite);
|
|
void writeback_set_ratelimit(void);
|
|
|
|
/* pdflush.c */
|
|
extern int nr_pdflush_threads; /* Global so it can be exported to sysctl
|
|
read-only. */
|
|
|
|
|
|
#endif /* WRITEBACK_H */
|