2da02997e0
This change introduces two new sysctls to /proc/sys/vm: dirty_background_bytes and dirty_bytes. dirty_background_bytes is the counterpart to dirty_background_ratio and dirty_bytes is the counterpart to dirty_ratio. With growing memory capacities of individual machines, it's no longer sufficient to specify dirty thresholds as a percentage of the amount of dirtyable memory over the entire system. dirty_background_bytes and dirty_bytes specify quantities of memory, in bytes, that represent the dirty limits for the entire system. If either of these values is set, its value represents the amount of dirty memory that is needed to commence either background or direct writeback. When a `bytes' or `ratio' file is written, its counterpart becomes a function of the written value. For example, if dirty_bytes is written to be 8096, 8K of memory is required to commence direct writeback. dirty_ratio is then functionally equivalent to 8K / the amount of dirtyable memory: dirtyable_memory = free pages + mapped pages + file cache dirty_background_bytes = dirty_background_ratio * dirtyable_memory -or- dirty_background_ratio = dirty_background_bytes / dirtyable_memory AND dirty_bytes = dirty_ratio * dirtyable_memory -or- dirty_ratio = dirty_bytes / dirtyable_memory Only one of dirty_background_bytes and dirty_background_ratio may be specified at a time, and only one of dirty_bytes and dirty_ratio may be specified. When one sysctl is written, the other appears as 0 when read. The `bytes' files operate on a page size granularity since dirty limits are compared with ZVC values, which are in page units. Prior to this change, the minimum dirty_ratio was 5 as implemented by get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user written value between 0 and 100. This restriction is maintained, but dirty_bytes has a lower limit of only one page. Also prior to this change, the dirty_background_ratio could not equal or exceed dirty_ratio. This restriction is maintained in addition to restricting dirty_background_bytes. If either background threshold equals or exceeds that of the dirty threshold, it is implicitly set to half the dirty threshold. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Andrea Righi <righi.andrea@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
175 lines
5.5 KiB
C
175 lines
5.5 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 */
|
|
/*
|
|
* 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 unsigned long dirty_background_bytes;
|
|
extern int vm_dirty_ratio;
|
|
extern unsigned long vm_dirty_bytes;
|
|
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);
|
|
|
|
extern int dirty_background_ratio_handler(struct ctl_table *table, int write,
|
|
struct file *filp, void __user *buffer, size_t *lenp,
|
|
loff_t *ppos);
|
|
extern int dirty_background_bytes_handler(struct ctl_table *table, int write,
|
|
struct file *filp, void __user *buffer, size_t *lenp,
|
|
loff_t *ppos);
|
|
extern int dirty_ratio_handler(struct ctl_table *table, int write,
|
|
struct file *filp, void __user *buffer, size_t *lenp,
|
|
loff_t *ppos);
|
|
extern int dirty_bytes_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(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 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 */
|