OpenCloudOS-Kernel/include/linux/writeback.h

164 lines
4.9 KiB
C
Raw Normal View History

/*
* 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.
*/
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
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 */
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
unsigned range_cyclic:1; /* range_start is cyclic */
writeback: speed up writeback of big dirty files 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>
2008-02-05 14:29:36 +08:00
unsigned more_io:1; /* more io to be dispatched */
/*
* write_cache_pages() won't update wbc->nr_to_write and
* mapping->writeback_index if no_nrwrite_index_update
* is set. write_cache_pages() may write more than we
* requested and we want to make sure nr_to_write and
* writeback_index are updated in a consistent manner
* so we use a single control to update them
*/
unsigned no_nrwrite_index_update:1;
};
/*
* 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 unsigned long determine_dirtyable_memory(void);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 14:25:50 +08:00
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 get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
struct backing_dev_info *bdi);
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 */