linux_dsm_epyc7002/include/linux/writeback.h
Dave Chinner 0b5649278e writeback: pay attention to wbc->nr_to_write in write_cache_pages
If a filesystem writes more than one page in ->writepage, write_cache_pages
fails to notice this and continues to attempt writeback when wbc->nr_to_write
has gone negative - this trace was captured from XFS:

    wbc_writeback_start: towrt=1024
    wbc_writepage: towrt=1024
    wbc_writepage: towrt=0
    wbc_writepage: towrt=-1
    wbc_writepage: towrt=-5
    wbc_writepage: towrt=-21
    wbc_writepage: towrt=-85

This has adverse effects on filesystem writeback behaviour. write_cache_pages()
needs to terminate after a certain number of pages are written, not after a
certain number of calls to ->writepage are made.  This is a regression
introduced by 17bc6c30cf ("vfs: Add
no_nrwrite_index_update writeback control flag"), but cannot be reverted
directly due to subsequent bug fixes that have gone in on top of it.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-08 18:12:44 -07:00

161 lines
5.0 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;
/*
* 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 {
struct backing_dev_info *bdi; /* If !NULL, only write back this
queue */
struct super_block *sb; /* if !NULL, only write inodes from
this super_block */
enum writeback_sync_modes sync_mode;
unsigned long *older_than_this; /* If !NULL, only write back inodes
older than this */
unsigned long wb_start; /* Time writeback_inodes_wb was
called. This is needed to avoid
extra jobs and livelock */
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_background:1; /* A background writeback */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned more_io:1; /* more io to be dispatched */
};
/*
* fs/fs-writeback.c
*/
struct bdi_writeback;
int inode_wait(void *);
void writeback_inodes_sb(struct super_block *);
int writeback_inodes_sb_if_idle(struct super_block *);
void sync_inodes_sb(struct super_block *);
void writeback_inodes_wbc(struct writeback_control *wbc);
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 get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
unsigned 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 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);
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 */