2005-04-16 22:20:36 +00:00
|
|
|
/*
|
2006-10-03 21:01:26 +00:00
|
|
|
* mm/page-writeback.c
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* Copyright (C) 2002, Linus Torvalds.
|
2007-10-17 06:25:50 +00:00
|
|
|
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* Contains functions related to writing back dirty pages at the
|
|
|
|
* address_space level.
|
|
|
|
*
|
2008-10-16 05:01:59 +00:00
|
|
|
* 10Apr2002 Andrew Morton
|
2005-04-16 22:20:36 +00:00
|
|
|
* Initial version
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
2011-10-16 06:01:52 +00:00
|
|
|
#include <linux/export.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/writeback.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/backing-dev.h>
|
2006-12-10 10:19:27 +00:00
|
|
|
#include <linux/task_io_accounting_ops.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/blkdev.h>
|
|
|
|
#include <linux/mpage.h>
|
2006-09-26 06:30:57 +00:00
|
|
|
#include <linux/rmap.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/sysctl.h>
|
|
|
|
#include <linux/cpu.h>
|
|
|
|
#include <linux/syscalls.h>
|
2006-08-29 18:05:54 +00:00
|
|
|
#include <linux/buffer_head.h>
|
2006-08-29 18:06:09 +00:00
|
|
|
#include <linux/pagevec.h>
|
2010-07-07 03:24:07 +00:00
|
|
|
#include <trace/events/writeback.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2011-06-20 04:18:42 +00:00
|
|
|
/*
|
|
|
|
* Sleep at most 200ms at a time in balance_dirty_pages().
|
|
|
|
*/
|
|
|
|
#define MAX_PAUSE max(HZ/5, 1)
|
|
|
|
|
2010-08-29 17:22:30 +00:00
|
|
|
/*
|
|
|
|
* Estimate write bandwidth at 200ms intervals.
|
|
|
|
*/
|
|
|
|
#define BANDWIDTH_INTERVAL max(HZ/5, 1)
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
|
|
|
|
* will look to see if it needs to force writeback or throttling.
|
|
|
|
*/
|
|
|
|
static long ratelimit_pages = 32;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When balance_dirty_pages decides that the caller needs to perform some
|
|
|
|
* non-background writeback, this is how many pages it will attempt to write.
|
2009-09-23 13:56:00 +00:00
|
|
|
* It should be somewhat larger than dirtied pages to ensure that reasonably
|
2005-04-16 22:20:36 +00:00
|
|
|
* large amounts of I/O are submitted.
|
|
|
|
*/
|
2009-09-23 13:56:00 +00:00
|
|
|
static inline long sync_writeback_pages(unsigned long dirtied)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-09-23 13:56:00 +00:00
|
|
|
if (dirtied < ratelimit_pages)
|
|
|
|
dirtied = ratelimit_pages;
|
|
|
|
|
|
|
|
return dirtied + dirtied / 2;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/* The following parameters are exported via /proc/sys/vm */
|
|
|
|
|
|
|
|
/*
|
2009-09-23 17:37:09 +00:00
|
|
|
* Start background writeback (via writeback threads) at this percentage
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2009-03-23 00:57:38 +00:00
|
|
|
int dirty_background_ratio = 10;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
/*
|
|
|
|
* dirty_background_bytes starts at 0 (disabled) so that it is a function of
|
|
|
|
* dirty_background_ratio * the amount of dirtyable memory
|
|
|
|
*/
|
|
|
|
unsigned long dirty_background_bytes;
|
|
|
|
|
2008-02-05 06:29:20 +00:00
|
|
|
/*
|
|
|
|
* free highmem will not be subtracted from the total free memory
|
|
|
|
* for calculating free ratios if vm_highmem_is_dirtyable is true
|
|
|
|
*/
|
|
|
|
int vm_highmem_is_dirtyable;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* The generator of dirty data starts writeback at this percentage
|
|
|
|
*/
|
2009-03-23 00:57:38 +00:00
|
|
|
int vm_dirty_ratio = 20;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
/*
|
|
|
|
* vm_dirty_bytes starts at 0 (disabled) so that it is a function of
|
|
|
|
* vm_dirty_ratio * the amount of dirtyable memory
|
|
|
|
*/
|
|
|
|
unsigned long vm_dirty_bytes;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
2009-03-31 22:23:18 +00:00
|
|
|
* The interval between `kupdate'-style writebacks
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2009-05-17 05:56:28 +00:00
|
|
|
unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
2009-03-31 22:23:18 +00:00
|
|
|
* The longest time for which data is allowed to remain dirty
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2009-05-17 05:56:28 +00:00
|
|
|
unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Flag that makes the machine dump writes/reads and block dirtyings.
|
|
|
|
*/
|
|
|
|
int block_dump;
|
|
|
|
|
|
|
|
/*
|
2006-03-24 11:15:49 +00:00
|
|
|
* Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
|
|
|
|
* a full sync is triggered after this time elapses without any disk activity.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
int laptop_mode;
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(laptop_mode);
|
|
|
|
|
|
|
|
/* End of sysctl-exported parameters */
|
|
|
|
|
2011-03-02 21:54:09 +00:00
|
|
|
unsigned long global_dirty_limit;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-10-17 06:25:50 +00:00
|
|
|
/*
|
|
|
|
* Scale the writeback cache size proportional to the relative writeout speeds.
|
|
|
|
*
|
|
|
|
* We do this by keeping a floating proportion between BDIs, based on page
|
|
|
|
* writeback completions [end_page_writeback()]. Those devices that write out
|
|
|
|
* pages fastest will get the larger share, while the slower will get a smaller
|
|
|
|
* share.
|
|
|
|
*
|
|
|
|
* We use page writeout completions because we are interested in getting rid of
|
|
|
|
* dirty pages. Having them written out is the primary goal.
|
|
|
|
*
|
|
|
|
* We introduce a concept of time, a period over which we measure these events,
|
|
|
|
* because demand can/will vary over time. The length of this period itself is
|
|
|
|
* measured in page writeback completions.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
static struct prop_descriptor vm_completions;
|
2007-10-17 06:25:50 +00:00
|
|
|
static struct prop_descriptor vm_dirties;
|
2007-10-17 06:25:50 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* couple the period to the dirty_ratio:
|
|
|
|
*
|
|
|
|
* period/2 ~ roundup_pow_of_two(dirty limit)
|
|
|
|
*/
|
|
|
|
static int calc_period_shift(void)
|
|
|
|
{
|
|
|
|
unsigned long dirty_total;
|
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (vm_dirty_bytes)
|
|
|
|
dirty_total = vm_dirty_bytes / PAGE_SIZE;
|
|
|
|
else
|
|
|
|
dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
|
|
|
|
100;
|
2007-10-17 06:25:50 +00:00
|
|
|
return 2 + ilog2(dirty_total - 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
* update the period when the dirty threshold changes.
|
2007-10-17 06:25:50 +00:00
|
|
|
*/
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
static void update_completion_period(void)
|
|
|
|
{
|
|
|
|
int shift = calc_period_shift();
|
|
|
|
prop_change_shift(&vm_completions, shift);
|
|
|
|
prop_change_shift(&vm_dirties, shift);
|
|
|
|
}
|
|
|
|
|
|
|
|
int dirty_background_ratio_handler(struct ctl_table *table, int write,
|
2009-09-23 22:57:19 +00:00
|
|
|
void __user *buffer, size_t *lenp,
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2009-09-23 22:57:19 +00:00
|
|
|
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (ret == 0 && write)
|
|
|
|
dirty_background_bytes = 0;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int dirty_background_bytes_handler(struct ctl_table *table, int write,
|
2009-09-23 22:57:19 +00:00
|
|
|
void __user *buffer, size_t *lenp,
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2009-09-23 22:57:19 +00:00
|
|
|
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (ret == 0 && write)
|
|
|
|
dirty_background_ratio = 0;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-10-17 06:25:50 +00:00
|
|
|
int dirty_ratio_handler(struct ctl_table *table, int write,
|
2009-09-23 22:57:19 +00:00
|
|
|
void __user *buffer, size_t *lenp,
|
2007-10-17 06:25:50 +00:00
|
|
|
loff_t *ppos)
|
|
|
|
{
|
|
|
|
int old_ratio = vm_dirty_ratio;
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
int ret;
|
|
|
|
|
2009-09-23 22:57:19 +00:00
|
|
|
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
|
2007-10-17 06:25:50 +00:00
|
|
|
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
update_completion_period();
|
|
|
|
vm_dirty_bytes = 0;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
int dirty_bytes_handler(struct ctl_table *table, int write,
|
2009-09-23 22:57:19 +00:00
|
|
|
void __user *buffer, size_t *lenp,
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
loff_t *ppos)
|
|
|
|
{
|
2009-02-11 21:04:23 +00:00
|
|
|
unsigned long old_bytes = vm_dirty_bytes;
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
int ret;
|
|
|
|
|
2009-09-23 22:57:19 +00:00
|
|
|
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
|
|
|
|
update_completion_period();
|
|
|
|
vm_dirty_ratio = 0;
|
2007-10-17 06:25:50 +00:00
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Increment the BDI's writeout completion count and the global writeout
|
|
|
|
* completion count. Called from test_clear_page_writeback().
|
|
|
|
*/
|
|
|
|
static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
|
|
|
|
{
|
2010-12-09 04:44:24 +00:00
|
|
|
__inc_bdi_stat(bdi, BDI_WRITTEN);
|
2008-04-30 07:54:36 +00:00
|
|
|
__prop_inc_percpu_max(&vm_completions, &bdi->completions,
|
|
|
|
bdi->max_prop_frac);
|
2007-10-17 06:25:50 +00:00
|
|
|
}
|
|
|
|
|
2008-04-30 07:54:37 +00:00
|
|
|
void bdi_writeout_inc(struct backing_dev_info *bdi)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
__bdi_writeout_inc(bdi);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(bdi_writeout_inc);
|
|
|
|
|
2009-02-18 22:48:18 +00:00
|
|
|
void task_dirty_inc(struct task_struct *tsk)
|
2007-10-17 06:25:50 +00:00
|
|
|
{
|
|
|
|
prop_inc_single(&vm_dirties, &tsk->dirties);
|
|
|
|
}
|
|
|
|
|
2007-10-17 06:25:50 +00:00
|
|
|
/*
|
|
|
|
* Obtain an accurate fraction of the BDI's portion.
|
|
|
|
*/
|
|
|
|
static void bdi_writeout_fraction(struct backing_dev_info *bdi,
|
|
|
|
long *numerator, long *denominator)
|
|
|
|
{
|
2010-12-17 04:22:00 +00:00
|
|
|
prop_fraction_percpu(&vm_completions, &bdi->completions,
|
2007-10-17 06:25:50 +00:00
|
|
|
numerator, denominator);
|
|
|
|
}
|
|
|
|
|
2007-10-17 06:25:50 +00:00
|
|
|
static inline void task_dirties_fraction(struct task_struct *tsk,
|
|
|
|
long *numerator, long *denominator)
|
|
|
|
{
|
|
|
|
prop_fraction_single(&vm_dirties, &tsk->dirties,
|
|
|
|
numerator, denominator);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-08-11 21:17:40 +00:00
|
|
|
* task_dirty_limit - scale down dirty throttling threshold for one task
|
2007-10-17 06:25:50 +00:00
|
|
|
*
|
|
|
|
* task specific dirty limit:
|
|
|
|
*
|
|
|
|
* dirty -= (dirty/8) * p_{t}
|
2010-08-11 21:17:40 +00:00
|
|
|
*
|
|
|
|
* To protect light/slow dirtying tasks from heavier/fast ones, we start
|
|
|
|
* throttling individual tasks before reaching the bdi dirty limit.
|
|
|
|
* Relatively low thresholds will be allocated to heavy dirtiers. So when
|
|
|
|
* dirty pages grow large, heavy dirtiers will be throttled first, which will
|
|
|
|
* effectively curb the growth of dirty pages. Light dirtiers with high enough
|
|
|
|
* dirty threshold may never get throttled.
|
2007-10-17 06:25:50 +00:00
|
|
|
*/
|
2011-07-01 19:31:25 +00:00
|
|
|
#define TASK_LIMIT_FRACTION 8
|
2010-08-11 21:17:39 +00:00
|
|
|
static unsigned long task_dirty_limit(struct task_struct *tsk,
|
|
|
|
unsigned long bdi_dirty)
|
2007-10-17 06:25:50 +00:00
|
|
|
{
|
|
|
|
long numerator, denominator;
|
2010-08-11 21:17:39 +00:00
|
|
|
unsigned long dirty = bdi_dirty;
|
2011-07-01 19:31:25 +00:00
|
|
|
u64 inv = dirty / TASK_LIMIT_FRACTION;
|
2007-10-17 06:25:50 +00:00
|
|
|
|
|
|
|
task_dirties_fraction(tsk, &numerator, &denominator);
|
|
|
|
inv *= numerator;
|
|
|
|
do_div(inv, denominator);
|
|
|
|
|
|
|
|
dirty -= inv;
|
|
|
|
|
2010-08-11 21:17:39 +00:00
|
|
|
return max(dirty, bdi_dirty/2);
|
2007-10-17 06:25:50 +00:00
|
|
|
}
|
|
|
|
|
2011-07-01 19:31:25 +00:00
|
|
|
/* Minimum limit for any task */
|
|
|
|
static unsigned long task_min_dirty_limit(unsigned long bdi_dirty)
|
|
|
|
{
|
|
|
|
return bdi_dirty - bdi_dirty / TASK_LIMIT_FRACTION;
|
|
|
|
}
|
|
|
|
|
2008-04-30 07:54:35 +00:00
|
|
|
/*
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
static unsigned int bdi_min_ratio;
|
|
|
|
|
|
|
|
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
2009-09-14 11:12:40 +00:00
|
|
|
spin_lock_bh(&bdi_lock);
|
2008-04-30 07:54:36 +00:00
|
|
|
if (min_ratio > bdi->max_ratio) {
|
2008-04-30 07:54:35 +00:00
|
|
|
ret = -EINVAL;
|
2008-04-30 07:54:36 +00:00
|
|
|
} else {
|
|
|
|
min_ratio -= bdi->min_ratio;
|
|
|
|
if (bdi_min_ratio + min_ratio < 100) {
|
|
|
|
bdi_min_ratio += min_ratio;
|
|
|
|
bdi->min_ratio += min_ratio;
|
|
|
|
} else {
|
|
|
|
ret = -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
2009-09-14 11:12:40 +00:00
|
|
|
spin_unlock_bh(&bdi_lock);
|
2008-04-30 07:54:36 +00:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (max_ratio > 100)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2009-09-14 11:12:40 +00:00
|
|
|
spin_lock_bh(&bdi_lock);
|
2008-04-30 07:54:36 +00:00
|
|
|
if (bdi->min_ratio > max_ratio) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
} else {
|
|
|
|
bdi->max_ratio = max_ratio;
|
|
|
|
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
|
|
|
|
}
|
2009-09-14 11:12:40 +00:00
|
|
|
spin_unlock_bh(&bdi_lock);
|
2008-04-30 07:54:35 +00:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
2008-04-30 07:54:36 +00:00
|
|
|
EXPORT_SYMBOL(bdi_set_max_ratio);
|
2008-04-30 07:54:35 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* Work out the current dirty-memory clamping and background writeout
|
|
|
|
* thresholds.
|
|
|
|
*
|
|
|
|
* The main aim here is to lower them aggressively if there is a lot of mapped
|
|
|
|
* memory around. To avoid stressing page reclaim with lots of unreclaimable
|
|
|
|
* pages. It is better to clamp down on writers than to start swapping, and
|
|
|
|
* performing lots of scanning.
|
|
|
|
*
|
|
|
|
* We only allow 1/2 of the currently-unmapped memory to be dirtied.
|
|
|
|
*
|
|
|
|
* We don't permit the clamping level to fall below 5% - that is getting rather
|
|
|
|
* excessive.
|
|
|
|
*
|
|
|
|
* We make sure that the background writeout level is below the adjusted
|
|
|
|
* clamping level.
|
|
|
|
*/
|
2007-05-06 21:48:59 +00:00
|
|
|
|
|
|
|
static unsigned long highmem_dirtyable_memory(unsigned long total)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
int node;
|
|
|
|
unsigned long x = 0;
|
|
|
|
|
2007-10-16 08:25:39 +00:00
|
|
|
for_each_node_state(node, N_HIGH_MEMORY) {
|
2007-05-06 21:48:59 +00:00
|
|
|
struct zone *z =
|
|
|
|
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
|
|
|
|
|
2009-09-22 00:01:42 +00:00
|
|
|
x += zone_page_state(z, NR_FREE_PAGES) +
|
|
|
|
zone_reclaimable_pages(z);
|
2007-05-06 21:48:59 +00:00
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Make sure that the number of highmem pages is never larger
|
|
|
|
* than the number of the total dirtyable memory. This can only
|
|
|
|
* occur in very strange VM situations but we want to make sure
|
|
|
|
* that this does not occur.
|
|
|
|
*/
|
|
|
|
return min(x, total);
|
|
|
|
#else
|
|
|
|
return 0;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2008-05-12 19:21:04 +00:00
|
|
|
/**
|
|
|
|
* determine_dirtyable_memory - amount of memory that may be used
|
|
|
|
*
|
|
|
|
* Returns the numebr of pages that can currently be freed and used
|
|
|
|
* by the kernel for direct mappings.
|
|
|
|
*/
|
|
|
|
unsigned long determine_dirtyable_memory(void)
|
2007-05-06 21:48:59 +00:00
|
|
|
{
|
|
|
|
unsigned long x;
|
|
|
|
|
2009-09-22 00:01:42 +00:00
|
|
|
x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
|
2008-02-05 06:29:20 +00:00
|
|
|
|
|
|
|
if (!vm_highmem_is_dirtyable)
|
|
|
|
x -= highmem_dirtyable_memory(x);
|
|
|
|
|
2007-05-06 21:48:59 +00:00
|
|
|
return x + 1; /* Ensure that we never return 0 */
|
|
|
|
}
|
|
|
|
|
2011-06-20 04:18:42 +00:00
|
|
|
static unsigned long hard_dirty_limit(unsigned long thresh)
|
|
|
|
{
|
|
|
|
return max(thresh, global_dirty_limit);
|
|
|
|
}
|
|
|
|
|
2010-08-14 20:05:17 +00:00
|
|
|
/*
|
2010-08-11 21:17:40 +00:00
|
|
|
* global_dirty_limits - background-writeback and dirty-throttling thresholds
|
|
|
|
*
|
|
|
|
* Calculate the dirty thresholds based on sysctl parameters
|
|
|
|
* - vm.dirty_background_ratio or vm.dirty_background_bytes
|
|
|
|
* - vm.dirty_ratio or vm.dirty_bytes
|
|
|
|
* The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
|
2011-01-03 16:36:48 +00:00
|
|
|
* real-time tasks.
|
2010-08-11 21:17:40 +00:00
|
|
|
*/
|
2010-08-11 21:17:39 +00:00
|
|
|
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-01-06 22:39:29 +00:00
|
|
|
unsigned long background;
|
|
|
|
unsigned long dirty;
|
2011-01-13 23:46:27 +00:00
|
|
|
unsigned long uninitialized_var(available_memory);
|
2005-04-16 22:20:36 +00:00
|
|
|
struct task_struct *tsk;
|
|
|
|
|
2011-01-13 23:46:27 +00:00
|
|
|
if (!vm_dirty_bytes || !dirty_background_bytes)
|
|
|
|
available_memory = determine_dirtyable_memory();
|
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (vm_dirty_bytes)
|
|
|
|
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
|
2010-10-26 21:21:45 +00:00
|
|
|
else
|
|
|
|
dirty = (vm_dirty_ratio * available_memory) / 100;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (dirty_background_bytes)
|
|
|
|
background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
|
|
|
|
else
|
|
|
|
background = (dirty_background_ratio * available_memory) / 100;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
mm: add dirty_background_bytes and dirty_bytes sysctls
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>
2009-01-06 22:39:31 +00:00
|
|
|
if (background >= dirty)
|
|
|
|
background = dirty / 2;
|
2005-04-16 22:20:36 +00:00
|
|
|
tsk = current;
|
|
|
|
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
|
|
|
|
background += background / 4;
|
|
|
|
dirty += dirty / 4;
|
|
|
|
}
|
|
|
|
*pbackground = background;
|
|
|
|
*pdirty = dirty;
|
2010-12-07 04:34:29 +00:00
|
|
|
trace_global_dirty_state(background, dirty);
|
2010-08-11 21:17:39 +00:00
|
|
|
}
|
2007-10-17 06:25:50 +00:00
|
|
|
|
2011-03-02 23:14:34 +00:00
|
|
|
/**
|
2010-08-11 21:17:40 +00:00
|
|
|
* bdi_dirty_limit - @bdi's share of dirty throttling threshold
|
2011-03-02 23:14:34 +00:00
|
|
|
* @bdi: the backing_dev_info to query
|
|
|
|
* @dirty: global dirty limit in pages
|
2010-08-11 21:17:40 +00:00
|
|
|
*
|
2011-03-02 23:14:34 +00:00
|
|
|
* Returns @bdi's dirty limit in pages. The term "dirty" in the context of
|
|
|
|
* dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
|
|
|
|
* And the "limit" in the name is not seriously taken as hard limit in
|
|
|
|
* balance_dirty_pages().
|
2010-08-11 21:17:40 +00:00
|
|
|
*
|
2011-03-02 23:14:34 +00:00
|
|
|
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
|
2010-08-11 21:17:40 +00:00
|
|
|
* - starving fast devices
|
|
|
|
* - piling up dirty pages (that will take long time to sync) on slow devices
|
|
|
|
*
|
|
|
|
* The bdi's share of dirty limit will be adapting to its throughput and
|
|
|
|
* bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
|
|
|
|
*/
|
|
|
|
unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
|
2010-08-11 21:17:39 +00:00
|
|
|
{
|
|
|
|
u64 bdi_dirty;
|
|
|
|
long numerator, denominator;
|
2007-10-17 06:25:50 +00:00
|
|
|
|
2010-08-11 21:17:39 +00:00
|
|
|
/*
|
|
|
|
* Calculate this BDI's share of the dirty ratio.
|
|
|
|
*/
|
|
|
|
bdi_writeout_fraction(bdi, &numerator, &denominator);
|
2007-10-17 06:25:50 +00:00
|
|
|
|
2010-08-11 21:17:39 +00:00
|
|
|
bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
|
|
|
|
bdi_dirty *= numerator;
|
|
|
|
do_div(bdi_dirty, denominator);
|
2007-10-17 06:25:50 +00:00
|
|
|
|
2010-08-11 21:17:39 +00:00
|
|
|
bdi_dirty += (dirty * bdi->min_ratio) / 100;
|
|
|
|
if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
|
|
|
|
bdi_dirty = dirty * bdi->max_ratio / 100;
|
|
|
|
|
|
|
|
return bdi_dirty;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2010-08-29 17:22:30 +00:00
|
|
|
static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
|
|
|
|
unsigned long elapsed,
|
|
|
|
unsigned long written)
|
|
|
|
{
|
|
|
|
const unsigned long period = roundup_pow_of_two(3 * HZ);
|
|
|
|
unsigned long avg = bdi->avg_write_bandwidth;
|
|
|
|
unsigned long old = bdi->write_bandwidth;
|
|
|
|
u64 bw;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bw = written * HZ / elapsed
|
|
|
|
*
|
|
|
|
* bw * elapsed + write_bandwidth * (period - elapsed)
|
|
|
|
* write_bandwidth = ---------------------------------------------------
|
|
|
|
* period
|
|
|
|
*/
|
|
|
|
bw = written - bdi->written_stamp;
|
|
|
|
bw *= HZ;
|
|
|
|
if (unlikely(elapsed > period)) {
|
|
|
|
do_div(bw, elapsed);
|
|
|
|
avg = bw;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
bw += (u64)bdi->write_bandwidth * (period - elapsed);
|
|
|
|
bw >>= ilog2(period);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* one more level of smoothing, for filtering out sudden spikes
|
|
|
|
*/
|
|
|
|
if (avg > old && old >= (unsigned long)bw)
|
|
|
|
avg -= (avg - old) >> 3;
|
|
|
|
|
|
|
|
if (avg < old && old <= (unsigned long)bw)
|
|
|
|
avg += (old - avg) >> 3;
|
|
|
|
|
|
|
|
out:
|
|
|
|
bdi->write_bandwidth = bw;
|
|
|
|
bdi->avg_write_bandwidth = avg;
|
|
|
|
}
|
|
|
|
|
2011-03-02 21:54:09 +00:00
|
|
|
/*
|
|
|
|
* The global dirtyable memory and dirty threshold could be suddenly knocked
|
|
|
|
* down by a large amount (eg. on the startup of KVM in a swapless system).
|
|
|
|
* This may throw the system into deep dirty exceeded state and throttle
|
|
|
|
* heavy/light dirtiers alike. To retain good responsiveness, maintain
|
|
|
|
* global_dirty_limit for tracking slowly down to the knocked down dirty
|
|
|
|
* threshold.
|
|
|
|
*/
|
|
|
|
static void update_dirty_limit(unsigned long thresh, unsigned long dirty)
|
|
|
|
{
|
|
|
|
unsigned long limit = global_dirty_limit;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Follow up in one step.
|
|
|
|
*/
|
|
|
|
if (limit < thresh) {
|
|
|
|
limit = thresh;
|
|
|
|
goto update;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Follow down slowly. Use the higher one as the target, because thresh
|
|
|
|
* may drop below dirty. This is exactly the reason to introduce
|
|
|
|
* global_dirty_limit which is guaranteed to lie above the dirty pages.
|
|
|
|
*/
|
|
|
|
thresh = max(thresh, dirty);
|
|
|
|
if (limit > thresh) {
|
|
|
|
limit -= (limit - thresh) >> 5;
|
|
|
|
goto update;
|
|
|
|
}
|
|
|
|
return;
|
|
|
|
update:
|
|
|
|
global_dirty_limit = limit;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void global_update_bandwidth(unsigned long thresh,
|
|
|
|
unsigned long dirty,
|
|
|
|
unsigned long now)
|
|
|
|
{
|
|
|
|
static DEFINE_SPINLOCK(dirty_lock);
|
|
|
|
static unsigned long update_time;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* check locklessly first to optimize away locking for the most time
|
|
|
|
*/
|
|
|
|
if (time_before(now, update_time + BANDWIDTH_INTERVAL))
|
|
|
|
return;
|
|
|
|
|
|
|
|
spin_lock(&dirty_lock);
|
|
|
|
if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) {
|
|
|
|
update_dirty_limit(thresh, dirty);
|
|
|
|
update_time = now;
|
|
|
|
}
|
|
|
|
spin_unlock(&dirty_lock);
|
|
|
|
}
|
|
|
|
|
2010-08-29 17:22:30 +00:00
|
|
|
void __bdi_update_bandwidth(struct backing_dev_info *bdi,
|
2011-03-02 21:54:09 +00:00
|
|
|
unsigned long thresh,
|
|
|
|
unsigned long dirty,
|
|
|
|
unsigned long bdi_thresh,
|
|
|
|
unsigned long bdi_dirty,
|
2010-08-29 17:22:30 +00:00
|
|
|
unsigned long start_time)
|
|
|
|
{
|
|
|
|
unsigned long now = jiffies;
|
|
|
|
unsigned long elapsed = now - bdi->bw_time_stamp;
|
|
|
|
unsigned long written;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* rate-limit, only update once every 200ms.
|
|
|
|
*/
|
|
|
|
if (elapsed < BANDWIDTH_INTERVAL)
|
|
|
|
return;
|
|
|
|
|
|
|
|
written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Skip quiet periods when disk bandwidth is under-utilized.
|
|
|
|
* (at least 1s idle time between two flusher runs)
|
|
|
|
*/
|
|
|
|
if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time))
|
|
|
|
goto snapshot;
|
|
|
|
|
2011-03-02 21:54:09 +00:00
|
|
|
if (thresh)
|
|
|
|
global_update_bandwidth(thresh, dirty, now);
|
|
|
|
|
2010-08-29 17:22:30 +00:00
|
|
|
bdi_update_write_bandwidth(bdi, elapsed, written);
|
|
|
|
|
|
|
|
snapshot:
|
|
|
|
bdi->written_stamp = written;
|
|
|
|
bdi->bw_time_stamp = now;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bdi_update_bandwidth(struct backing_dev_info *bdi,
|
2011-03-02 21:54:09 +00:00
|
|
|
unsigned long thresh,
|
|
|
|
unsigned long dirty,
|
|
|
|
unsigned long bdi_thresh,
|
|
|
|
unsigned long bdi_dirty,
|
2010-08-29 17:22:30 +00:00
|
|
|
unsigned long start_time)
|
|
|
|
{
|
|
|
|
if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
|
|
|
|
return;
|
|
|
|
spin_lock(&bdi->wb.list_lock);
|
2011-03-02 21:54:09 +00:00
|
|
|
__bdi_update_bandwidth(bdi, thresh, dirty, bdi_thresh, bdi_dirty,
|
|
|
|
start_time);
|
2010-08-29 17:22:30 +00:00
|
|
|
spin_unlock(&bdi->wb.list_lock);
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* balance_dirty_pages() must be called by processes which are generating dirty
|
|
|
|
* data. It looks at the number of dirty pages in the machine and will force
|
|
|
|
* the caller to perform writeback if the system is over `vm_dirty_ratio'.
|
2009-09-23 17:37:09 +00:00
|
|
|
* If we're over `background_thresh' then the writeback threads are woken to
|
|
|
|
* perform some writeout.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2009-09-23 13:56:00 +00:00
|
|
|
static void balance_dirty_pages(struct address_space *mapping,
|
|
|
|
unsigned long write_chunk)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2010-09-12 19:34:05 +00:00
|
|
|
unsigned long nr_reclaimable, bdi_nr_reclaimable;
|
|
|
|
unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */
|
|
|
|
unsigned long bdi_dirty;
|
2009-01-06 22:39:29 +00:00
|
|
|
unsigned long background_thresh;
|
|
|
|
unsigned long dirty_thresh;
|
|
|
|
unsigned long bdi_thresh;
|
2011-07-01 19:31:25 +00:00
|
|
|
unsigned long task_bdi_thresh;
|
|
|
|
unsigned long min_task_bdi_thresh;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned long pages_written = 0;
|
2009-09-17 17:59:14 +00:00
|
|
|
unsigned long pause = 1;
|
2010-08-11 21:17:37 +00:00
|
|
|
bool dirty_exceeded = false;
|
2011-07-01 19:31:25 +00:00
|
|
|
bool clear_dirty_exceeded = true;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct backing_dev_info *bdi = mapping->backing_dev_info;
|
2010-08-29 17:22:30 +00:00
|
|
|
unsigned long start_time = jiffies;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
for (;;) {
|
2007-11-15 00:59:15 +00:00
|
|
|
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
|
|
|
|
global_page_state(NR_UNSTABLE_NFS);
|
2010-09-12 19:34:05 +00:00
|
|
|
nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
|
2007-11-15 00:59:15 +00:00
|
|
|
|
2010-08-11 21:17:39 +00:00
|
|
|
global_dirty_limits(&background_thresh, &dirty_thresh);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Throttle it only when the background writeback cannot
|
|
|
|
* catch-up. This avoids (excessively) small writeouts
|
|
|
|
* when the bdi limits are ramping up.
|
|
|
|
*/
|
2010-09-12 19:34:05 +00:00
|
|
|
if (nr_dirty <= (background_thresh + dirty_thresh) / 2)
|
2010-08-11 21:17:39 +00:00
|
|
|
break;
|
|
|
|
|
|
|
|
bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
|
2011-07-01 19:31:25 +00:00
|
|
|
min_task_bdi_thresh = task_min_dirty_limit(bdi_thresh);
|
|
|
|
task_bdi_thresh = task_dirty_limit(current, bdi_thresh);
|
2010-08-11 21:17:39 +00:00
|
|
|
|
2010-08-11 21:17:37 +00:00
|
|
|
/*
|
|
|
|
* In order to avoid the stacked BDI deadlock we need
|
|
|
|
* to ensure we accurately count the 'dirty' pages when
|
|
|
|
* the threshold is low.
|
|
|
|
*
|
|
|
|
* Otherwise it would be possible to get thresh+n pages
|
|
|
|
* reported dirty, even though there are thresh-m pages
|
|
|
|
* actually dirty; with m+n sitting in the percpu
|
|
|
|
* deltas.
|
|
|
|
*/
|
2011-07-01 19:31:25 +00:00
|
|
|
if (task_bdi_thresh < 2 * bdi_stat_error(bdi)) {
|
2010-08-11 21:17:37 +00:00
|
|
|
bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
|
2010-09-12 19:34:05 +00:00
|
|
|
bdi_dirty = bdi_nr_reclaimable +
|
|
|
|
bdi_stat_sum(bdi, BDI_WRITEBACK);
|
2010-08-11 21:17:37 +00:00
|
|
|
} else {
|
|
|
|
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
|
2010-09-12 19:34:05 +00:00
|
|
|
bdi_dirty = bdi_nr_reclaimable +
|
|
|
|
bdi_stat(bdi, BDI_WRITEBACK);
|
2010-08-11 21:17:37 +00:00
|
|
|
}
|
2007-11-15 00:59:15 +00:00
|
|
|
|
2010-08-11 21:17:37 +00:00
|
|
|
/*
|
|
|
|
* The bdi thresh is somehow "soft" limit derived from the
|
|
|
|
* global "hard" limit. The former helps to prevent heavy IO
|
|
|
|
* bdi or process from holding back light ones; The latter is
|
|
|
|
* the last resort safeguard.
|
|
|
|
*/
|
2011-07-01 19:31:25 +00:00
|
|
|
dirty_exceeded = (bdi_dirty > task_bdi_thresh) ||
|
2010-09-12 19:34:05 +00:00
|
|
|
(nr_dirty > dirty_thresh);
|
2011-07-01 19:31:25 +00:00
|
|
|
clear_dirty_exceeded = (bdi_dirty <= min_task_bdi_thresh) &&
|
|
|
|
(nr_dirty <= dirty_thresh);
|
2010-08-11 21:17:37 +00:00
|
|
|
|
|
|
|
if (!dirty_exceeded)
|
2007-10-17 06:25:50 +00:00
|
|
|
break;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-10-17 06:25:50 +00:00
|
|
|
if (!bdi->dirty_exceeded)
|
|
|
|
bdi->dirty_exceeded = 1;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2011-03-02 21:54:09 +00:00
|
|
|
bdi_update_bandwidth(bdi, dirty_thresh, nr_dirty,
|
|
|
|
bdi_thresh, bdi_dirty, start_time);
|
2010-08-29 17:22:30 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
|
|
|
|
* Unstable writes are a feature of certain networked
|
|
|
|
* filesystems (i.e. NFS) in which data may have been
|
|
|
|
* written to the server's write cache, but has not yet
|
|
|
|
* been flushed to permanent storage.
|
2009-06-30 18:41:35 +00:00
|
|
|
* Only move pages to writeback if this bdi is over its
|
|
|
|
* threshold otherwise wait until the disk writes catch
|
|
|
|
* up.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2011-05-05 01:54:37 +00:00
|
|
|
trace_balance_dirty_start(bdi);
|
2011-07-01 19:31:25 +00:00
|
|
|
if (bdi_nr_reclaimable > task_bdi_thresh) {
|
2011-05-05 01:54:37 +00:00
|
|
|
pages_written += writeback_inodes_wb(&bdi->wb,
|
|
|
|
write_chunk);
|
|
|
|
trace_balance_dirty_written(bdi, pages_written);
|
2010-08-11 21:17:37 +00:00
|
|
|
if (pages_written >= write_chunk)
|
|
|
|
break; /* We've done our duty */
|
2007-10-17 06:25:50 +00:00
|
|
|
}
|
2010-12-22 01:24:21 +00:00
|
|
|
__set_current_state(TASK_UNINTERRUPTIBLE);
|
2009-10-09 10:40:42 +00:00
|
|
|
io_schedule_timeout(pause);
|
2011-05-05 01:54:37 +00:00
|
|
|
trace_balance_dirty_wait(bdi);
|
2009-09-17 17:59:14 +00:00
|
|
|
|
2011-06-20 04:18:42 +00:00
|
|
|
dirty_thresh = hard_dirty_limit(dirty_thresh);
|
|
|
|
/*
|
|
|
|
* max-pause area. If dirty exceeded but still within this
|
|
|
|
* area, no need to sleep for more than 200ms: (a) 8 pages per
|
|
|
|
* 200ms is typically more than enough to curb heavy dirtiers;
|
|
|
|
* (b) the pause time limit makes the dirtiers more responsive.
|
|
|
|
*/
|
2011-08-16 19:37:14 +00:00
|
|
|
if (nr_dirty < dirty_thresh &&
|
|
|
|
bdi_dirty < (task_bdi_thresh + bdi_thresh) / 2 &&
|
2011-06-20 04:18:42 +00:00
|
|
|
time_after(jiffies, start_time + MAX_PAUSE))
|
|
|
|
break;
|
2009-09-17 17:59:14 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Increase the delay for each loop, up to our previous
|
|
|
|
* default of taking a 100ms nap.
|
|
|
|
*/
|
|
|
|
pause <<= 1;
|
|
|
|
if (pause > HZ / 10)
|
|
|
|
pause = HZ / 10;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2011-07-01 19:31:25 +00:00
|
|
|
/* Clear dirty_exceeded flag only when no task can exceed the limit */
|
|
|
|
if (clear_dirty_exceeded && bdi->dirty_exceeded)
|
2007-10-17 06:25:50 +00:00
|
|
|
bdi->dirty_exceeded = 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
if (writeback_in_progress(bdi))
|
2009-09-23 17:37:09 +00:00
|
|
|
return;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* In laptop mode, we wait until hitting the higher threshold before
|
|
|
|
* starting background writeout, and then write out all the way down
|
|
|
|
* to the lower threshold. So slow writers cause minimal disk activity.
|
|
|
|
*
|
|
|
|
* In normal mode, we start background writeout at the lower
|
|
|
|
* background_thresh, to keep the amount of dirty memory low.
|
|
|
|
*/
|
|
|
|
if ((laptop_mode && pages_written) ||
|
2010-08-11 21:17:37 +00:00
|
|
|
(!laptop_mode && (nr_reclaimable > background_thresh)))
|
2010-06-08 16:15:15 +00:00
|
|
|
bdi_start_background_writeback(bdi);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2007-10-08 16:54:37 +00:00
|
|
|
void set_page_dirty_balance(struct page *page, int page_mkwrite)
|
2006-09-26 06:30:58 +00:00
|
|
|
{
|
2007-10-08 16:54:37 +00:00
|
|
|
if (set_page_dirty(page) || page_mkwrite) {
|
2006-09-26 06:30:58 +00:00
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
|
|
|
|
if (mapping)
|
|
|
|
balance_dirty_pages_ratelimited(mapping);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-06-24 06:13:48 +00:00
|
|
|
static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/**
|
2006-03-24 11:18:10 +00:00
|
|
|
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
|
2005-05-01 15:59:26 +00:00
|
|
|
* @mapping: address_space which was dirtied
|
2006-04-02 11:59:55 +00:00
|
|
|
* @nr_pages_dirtied: number of pages which the caller has just dirtied
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* Processes which are dirtying memory should call in here once for each page
|
|
|
|
* which was newly dirtied. The function will periodically check the system's
|
|
|
|
* dirty state and will initiate writeback if needed.
|
|
|
|
*
|
|
|
|
* On really big machines, get_writeback_state is expensive, so try to avoid
|
|
|
|
* calling it too often (ratelimiting). But once we're over the dirty memory
|
|
|
|
* limit we decrease the ratelimiting by a lot, to prevent individual processes
|
|
|
|
* from overshooting the limit by (ratelimit_pages) each.
|
|
|
|
*/
|
2006-03-24 11:18:10 +00:00
|
|
|
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
|
|
|
|
unsigned long nr_pages_dirtied)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2011-06-11 23:53:57 +00:00
|
|
|
struct backing_dev_info *bdi = mapping->backing_dev_info;
|
2006-03-24 11:18:10 +00:00
|
|
|
unsigned long ratelimit;
|
|
|
|
unsigned long *p;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2011-06-11 23:53:57 +00:00
|
|
|
if (!bdi_cap_account_dirty(bdi))
|
|
|
|
return;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
ratelimit = ratelimit_pages;
|
2007-10-17 06:25:50 +00:00
|
|
|
if (mapping->backing_dev_info->dirty_exceeded)
|
2005-04-16 22:20:36 +00:00
|
|
|
ratelimit = 8;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check the rate limiting. Also, we do not want to throttle real-time
|
|
|
|
* tasks in balance_dirty_pages(). Period.
|
|
|
|
*/
|
2006-03-24 11:18:10 +00:00
|
|
|
preempt_disable();
|
2009-06-24 06:13:48 +00:00
|
|
|
p = &__get_cpu_var(bdp_ratelimits);
|
2006-03-24 11:18:10 +00:00
|
|
|
*p += nr_pages_dirtied;
|
|
|
|
if (unlikely(*p >= ratelimit)) {
|
2009-09-23 13:56:00 +00:00
|
|
|
ratelimit = sync_writeback_pages(*p);
|
2006-03-24 11:18:10 +00:00
|
|
|
*p = 0;
|
|
|
|
preempt_enable();
|
2009-09-23 13:56:00 +00:00
|
|
|
balance_dirty_pages(mapping, ratelimit);
|
2005-04-16 22:20:36 +00:00
|
|
|
return;
|
|
|
|
}
|
2006-03-24 11:18:10 +00:00
|
|
|
preempt_enable();
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2006-03-24 11:18:10 +00:00
|
|
|
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2007-03-01 04:13:21 +00:00
|
|
|
void throttle_vm_writeout(gfp_t gfp_mask)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-01-06 22:39:29 +00:00
|
|
|
unsigned long background_thresh;
|
|
|
|
unsigned long dirty_thresh;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
for ( ; ; ) {
|
2010-08-11 21:17:39 +00:00
|
|
|
global_dirty_limits(&background_thresh, &dirty_thresh);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Boost the allowable dirty threshold a bit for page
|
|
|
|
* allocators so they don't get DoS'ed by heavy writers
|
|
|
|
*/
|
|
|
|
dirty_thresh += dirty_thresh / 10; /* wheeee... */
|
|
|
|
|
2006-06-30 08:55:42 +00:00
|
|
|
if (global_page_state(NR_UNSTABLE_NFS) +
|
|
|
|
global_page_state(NR_WRITEBACK) <= dirty_thresh)
|
|
|
|
break;
|
2009-07-09 12:52:32 +00:00
|
|
|
congestion_wait(BLK_RW_ASYNC, HZ/10);
|
2007-10-17 06:30:45 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The caller might hold locks which can prevent IO completion
|
|
|
|
* or progress in the filesystem. So we cannot just sit here
|
|
|
|
* waiting for IO to complete.
|
|
|
|
*/
|
|
|
|
if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO))
|
|
|
|
break;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
|
|
|
|
*/
|
|
|
|
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
|
2009-09-23 22:57:19 +00:00
|
|
|
void __user *buffer, size_t *length, loff_t *ppos)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-09-23 22:57:19 +00:00
|
|
|
proc_dointvec(table, write, buffer, length, ppos);
|
2010-05-21 18:00:35 +00:00
|
|
|
bdi_arm_supers_timer();
|
2005-04-16 22:20:36 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-05-20 07:18:47 +00:00
|
|
|
#ifdef CONFIG_BLOCK
|
2010-04-06 12:25:14 +00:00
|
|
|
void laptop_mode_timer_fn(unsigned long data)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2010-04-06 12:25:14 +00:00
|
|
|
struct request_queue *q = (struct request_queue *)data;
|
|
|
|
int nr_pages = global_page_state(NR_FILE_DIRTY) +
|
|
|
|
global_page_state(NR_UNSTABLE_NFS);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2010-04-06 12:25:14 +00:00
|
|
|
/*
|
|
|
|
* We want to write everything out, not just down to the dirty
|
|
|
|
* threshold
|
|
|
|
*/
|
|
|
|
if (bdi_has_dirty_io(&q->backing_dev_info))
|
2010-06-08 16:15:15 +00:00
|
|
|
bdi_start_writeback(&q->backing_dev_info, nr_pages);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We've spun up the disk and we're in laptop mode: schedule writeback
|
|
|
|
* of all dirty data a few seconds from now. If the flush is already scheduled
|
|
|
|
* then push it back - the user is still using the disk.
|
|
|
|
*/
|
2010-04-06 12:25:14 +00:00
|
|
|
void laptop_io_completion(struct backing_dev_info *info)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2010-04-06 12:25:14 +00:00
|
|
|
mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We're in laptop mode and we've just synced. The sync's writes will have
|
|
|
|
* caused another writeback to be scheduled by laptop_io_completion.
|
|
|
|
* Nothing needs to be written back anymore, so we unschedule the writeback.
|
|
|
|
*/
|
|
|
|
void laptop_sync_completion(void)
|
|
|
|
{
|
2010-04-06 12:25:14 +00:00
|
|
|
struct backing_dev_info *bdi;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
|
|
|
|
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
|
|
|
|
del_timer(&bdi->laptop_mode_wb_timer);
|
|
|
|
|
|
|
|
rcu_read_unlock();
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2010-05-20 07:18:47 +00:00
|
|
|
#endif
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If ratelimit_pages is too high then we can get into dirty-data overload
|
|
|
|
* if a large number of processes all perform writes at the same time.
|
|
|
|
* If it is too low then SMP machines will call the (expensive)
|
|
|
|
* get_writeback_state too often.
|
|
|
|
*
|
|
|
|
* Here we set ratelimit_pages to a level which ensures that when all CPUs are
|
|
|
|
* dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
|
|
|
|
* thresholds before writeback cuts in.
|
|
|
|
*
|
|
|
|
* But the limit should not be set too high. Because it also controls the
|
|
|
|
* amount of memory which the balance_dirty_pages() caller has to write back.
|
|
|
|
* If this is too large then the caller will block on the IO queue all the
|
|
|
|
* time. So limit it to four megabytes - the balance_dirty_pages() caller
|
|
|
|
* will write six megabyte chunks, max.
|
|
|
|
*/
|
|
|
|
|
2006-09-29 09:01:25 +00:00
|
|
|
void writeback_set_ratelimit(void)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2006-09-29 09:01:24 +00:00
|
|
|
ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
|
2005-04-16 22:20:36 +00:00
|
|
|
if (ratelimit_pages < 16)
|
|
|
|
ratelimit_pages = 16;
|
|
|
|
if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
|
|
|
|
ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
|
|
|
|
}
|
|
|
|
|
2006-06-27 09:54:10 +00:00
|
|
|
static int __cpuinit
|
2005-04-16 22:20:36 +00:00
|
|
|
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
|
|
|
|
{
|
2006-09-29 09:01:25 +00:00
|
|
|
writeback_set_ratelimit();
|
2007-02-10 09:46:37 +00:00
|
|
|
return NOTIFY_DONE;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2006-06-27 09:54:09 +00:00
|
|
|
static struct notifier_block __cpuinitdata ratelimit_nb = {
|
2005-04-16 22:20:36 +00:00
|
|
|
.notifier_call = ratelimit_handler,
|
|
|
|
.next = NULL,
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
2007-01-30 00:37:38 +00:00
|
|
|
* Called early on to tune the page writeback dirty limits.
|
|
|
|
*
|
|
|
|
* We used to scale dirty pages according to how total memory
|
|
|
|
* related to pages that could be allocated for buffers (by
|
|
|
|
* comparing nr_free_buffer_pages() to vm_total_pages.
|
|
|
|
*
|
|
|
|
* However, that was when we used "dirty_ratio" to scale with
|
|
|
|
* all memory, and we don't do that any more. "dirty_ratio"
|
|
|
|
* is now applied to total non-HIGHPAGE memory (by subtracting
|
|
|
|
* totalhigh_pages from vm_total_pages), and as such we can't
|
|
|
|
* get into the old insane situation any more where we had
|
|
|
|
* large amounts of dirty pages compared to a small amount of
|
|
|
|
* non-HIGHMEM memory.
|
|
|
|
*
|
|
|
|
* But we might still want to scale the dirty_ratio by how
|
|
|
|
* much memory the box has..
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
void __init page_writeback_init(void)
|
|
|
|
{
|
2007-10-17 06:25:50 +00:00
|
|
|
int shift;
|
|
|
|
|
2006-09-29 09:01:25 +00:00
|
|
|
writeback_set_ratelimit();
|
2005-04-16 22:20:36 +00:00
|
|
|
register_cpu_notifier(&ratelimit_nb);
|
2007-10-17 06:25:50 +00:00
|
|
|
|
|
|
|
shift = calc_period_shift();
|
|
|
|
prop_descriptor_init(&vm_completions, shift);
|
2007-10-17 06:25:50 +00:00
|
|
|
prop_descriptor_init(&vm_dirties, shift);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2010-08-10 00:19:12 +00:00
|
|
|
/**
|
|
|
|
* tag_pages_for_writeback - tag pages to be written by write_cache_pages
|
|
|
|
* @mapping: address space structure to write
|
|
|
|
* @start: starting page index
|
|
|
|
* @end: ending page index (inclusive)
|
|
|
|
*
|
|
|
|
* This function scans the page range from @start to @end (inclusive) and tags
|
|
|
|
* all pages that have DIRTY tag set with a special TOWRITE tag. The idea is
|
|
|
|
* that write_cache_pages (or whoever calls this function) will then use
|
|
|
|
* TOWRITE tag to identify pages eligible for writeback. This mechanism is
|
|
|
|
* used to avoid livelocking of writeback by a process steadily creating new
|
|
|
|
* dirty pages in the file (thus it is important for this function to be quick
|
|
|
|
* so that it can tag pages faster than a dirtying process can create them).
|
|
|
|
*/
|
|
|
|
/*
|
|
|
|
* We tag pages in batches of WRITEBACK_TAG_BATCH to reduce tree_lock latency.
|
|
|
|
*/
|
|
|
|
void tag_pages_for_writeback(struct address_space *mapping,
|
|
|
|
pgoff_t start, pgoff_t end)
|
|
|
|
{
|
2010-08-11 21:17:30 +00:00
|
|
|
#define WRITEBACK_TAG_BATCH 4096
|
2010-08-10 00:19:12 +00:00
|
|
|
unsigned long tagged;
|
|
|
|
|
|
|
|
do {
|
|
|
|
spin_lock_irq(&mapping->tree_lock);
|
|
|
|
tagged = radix_tree_range_tag_if_tagged(&mapping->page_tree,
|
|
|
|
&start, end, WRITEBACK_TAG_BATCH,
|
|
|
|
PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
|
|
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
|
|
WARN_ON_ONCE(tagged > WRITEBACK_TAG_BATCH);
|
|
|
|
cond_resched();
|
2010-08-19 21:13:33 +00:00
|
|
|
/* We check 'start' to handle wrapping when end == ~0UL */
|
|
|
|
} while (tagged >= WRITEBACK_TAG_BATCH && start);
|
2010-08-10 00:19:12 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tag_pages_for_writeback);
|
|
|
|
|
2006-08-29 18:06:09 +00:00
|
|
|
/**
|
2007-05-11 05:22:51 +00:00
|
|
|
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
|
2006-08-29 18:06:09 +00:00
|
|
|
* @mapping: address space structure to write
|
|
|
|
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
|
2007-05-11 05:22:51 +00:00
|
|
|
* @writepage: function called for each page
|
|
|
|
* @data: data passed to writepage function
|
2006-08-29 18:06:09 +00:00
|
|
|
*
|
2007-05-11 05:22:51 +00:00
|
|
|
* If a page is already under I/O, write_cache_pages() skips it, even
|
2006-08-29 18:06:09 +00:00
|
|
|
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
|
|
|
|
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
|
|
|
|
* and msync() need to guarantee that all the data which was dirty at the time
|
|
|
|
* the call was made get new I/O started against them. If wbc->sync_mode is
|
|
|
|
* WB_SYNC_ALL then we were called for data integrity and we must wait for
|
|
|
|
* existing IO to complete.
|
2010-08-10 00:19:12 +00:00
|
|
|
*
|
|
|
|
* To avoid livelocks (when other process dirties new pages), we first tag
|
|
|
|
* pages which should be written back with TOWRITE tag and only then start
|
|
|
|
* writing them. For data-integrity sync we have to be careful so that we do
|
|
|
|
* not miss some pages (e.g., because some other process has cleared TOWRITE
|
|
|
|
* tag we set). The rule we follow is that TOWRITE tag can be cleared only
|
|
|
|
* by the process clearing the DIRTY tag (and submitting the page for IO).
|
2006-08-29 18:06:09 +00:00
|
|
|
*/
|
2007-05-11 05:22:51 +00:00
|
|
|
int write_cache_pages(struct address_space *mapping,
|
|
|
|
struct writeback_control *wbc, writepage_t writepage,
|
|
|
|
void *data)
|
2006-08-29 18:06:09 +00:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
int done = 0;
|
|
|
|
struct pagevec pvec;
|
|
|
|
int nr_pages;
|
2009-01-06 22:39:04 +00:00
|
|
|
pgoff_t uninitialized_var(writeback_index);
|
2006-08-29 18:06:09 +00:00
|
|
|
pgoff_t index;
|
|
|
|
pgoff_t end; /* Inclusive */
|
2009-01-06 22:39:06 +00:00
|
|
|
pgoff_t done_index;
|
2009-01-06 22:39:04 +00:00
|
|
|
int cycled;
|
2006-08-29 18:06:09 +00:00
|
|
|
int range_whole = 0;
|
2010-08-10 00:19:12 +00:00
|
|
|
int tag;
|
2006-08-29 18:06:09 +00:00
|
|
|
|
|
|
|
pagevec_init(&pvec, 0);
|
|
|
|
if (wbc->range_cyclic) {
|
2009-01-06 22:39:04 +00:00
|
|
|
writeback_index = mapping->writeback_index; /* prev offset */
|
|
|
|
index = writeback_index;
|
|
|
|
if (index == 0)
|
|
|
|
cycled = 1;
|
|
|
|
else
|
|
|
|
cycled = 0;
|
2006-08-29 18:06:09 +00:00
|
|
|
end = -1;
|
|
|
|
} else {
|
|
|
|
index = wbc->range_start >> PAGE_CACHE_SHIFT;
|
|
|
|
end = wbc->range_end >> PAGE_CACHE_SHIFT;
|
|
|
|
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
|
|
|
|
range_whole = 1;
|
2009-01-06 22:39:04 +00:00
|
|
|
cycled = 1; /* ignore range_cyclic tests */
|
2006-08-29 18:06:09 +00:00
|
|
|
}
|
2010-06-06 16:38:15 +00:00
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
|
2010-08-10 00:19:12 +00:00
|
|
|
tag = PAGECACHE_TAG_TOWRITE;
|
|
|
|
else
|
|
|
|
tag = PAGECACHE_TAG_DIRTY;
|
2006-08-29 18:06:09 +00:00
|
|
|
retry:
|
2010-06-06 16:38:15 +00:00
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
|
2010-08-10 00:19:12 +00:00
|
|
|
tag_pages_for_writeback(mapping, index, end);
|
2009-01-06 22:39:06 +00:00
|
|
|
done_index = index;
|
2009-01-06 22:39:09 +00:00
|
|
|
while (!done && (index <= end)) {
|
|
|
|
int i;
|
|
|
|
|
2010-08-10 00:19:12 +00:00
|
|
|
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
|
2009-01-06 22:39:09 +00:00
|
|
|
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
|
|
|
|
if (nr_pages == 0)
|
|
|
|
break;
|
2006-08-29 18:06:09 +00:00
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
|
|
|
|
/*
|
2009-01-06 22:39:11 +00:00
|
|
|
* At this point, the page may be truncated or
|
|
|
|
* invalidated (changing page->mapping to NULL), or
|
|
|
|
* even swizzled back from swapper_space to tmpfs file
|
|
|
|
* mapping. However, page->index will not change
|
|
|
|
* because we have a reference on the page.
|
2006-08-29 18:06:09 +00:00
|
|
|
*/
|
2009-01-06 22:39:11 +00:00
|
|
|
if (page->index > end) {
|
|
|
|
/*
|
|
|
|
* can't be range_cyclic (1st pass) because
|
|
|
|
* end == -1 in that case.
|
|
|
|
*/
|
|
|
|
done = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
writeback: make mapping->writeback_index to point to the last written page
For range-cyclic writeback (e.g. kupdate), the writeback code sets a
continuation point of the next writeback to mapping->writeback_index which
is set the page after the last written page. This happens so that we
evenly write the whole file even if pages in it get continuously
redirtied.
However, in some cases, sequential writer is writing in the middle of the
page and it just redirties the last written page by continuing from that.
For example with an application which uses a file as a big ring buffer we
see:
[1st writeback session]
...
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898514 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898522 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898530 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898538 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898546 + 8
kworker/0:1-11 4571: block_rq_issue: 8,0 W 0 () 94898514 + 40
>> flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898554 + 8
>> flush-8:0-2743 4571: block_rq_issue: 8,0 W 0 () 94898554 + 8
[2nd writeback session after 35sec]
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898562 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898570 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898578 + 8
...
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94898562 + 640
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94899202 + 72
...
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899962 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899970 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899978 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899986 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899994 + 8
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94899962 + 40
>> flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898554 + 8
>> flush-8:0-2743 4606: block_rq_issue: 8,0 W 0 () 94898554 + 8
So we seeked back to 94898554 after we wrote all the pages at the end of
the file.
This extra seek seems unnecessary. If we continue writeback from the last
written page, we can avoid it and do not cause harm to other cases. The
original intent of even writeout over the whole file is preserved and if
the page does not get redirtied pagevec_lookup_tag() just skips it.
As an exceptional case, when I/O error happens, set done_index to the next
page as the comment in the code suggests.
Tested-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-22 23:33:40 +00:00
|
|
|
done_index = page->index;
|
2009-01-06 22:39:11 +00:00
|
|
|
|
2006-08-29 18:06:09 +00:00
|
|
|
lock_page(page);
|
|
|
|
|
2009-01-06 22:39:09 +00:00
|
|
|
/*
|
|
|
|
* Page truncated or invalidated. We can freely skip it
|
|
|
|
* then, even for data integrity operations: the page
|
|
|
|
* has disappeared concurrently, so there could be no
|
|
|
|
* real expectation of this data interity operation
|
|
|
|
* even if there is now a new, dirty page at the same
|
|
|
|
* pagecache address.
|
|
|
|
*/
|
2006-08-29 18:06:09 +00:00
|
|
|
if (unlikely(page->mapping != mapping)) {
|
2009-01-06 22:39:09 +00:00
|
|
|
continue_unlock:
|
2006-08-29 18:06:09 +00:00
|
|
|
unlock_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2009-01-06 22:39:10 +00:00
|
|
|
if (!PageDirty(page)) {
|
|
|
|
/* someone wrote it for us */
|
|
|
|
goto continue_unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (PageWriteback(page)) {
|
|
|
|
if (wbc->sync_mode != WB_SYNC_NONE)
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
else
|
|
|
|
goto continue_unlock;
|
|
|
|
}
|
2006-08-29 18:06:09 +00:00
|
|
|
|
2009-01-06 22:39:10 +00:00
|
|
|
BUG_ON(PageWriteback(page));
|
|
|
|
if (!clear_page_dirty_for_io(page))
|
2009-01-06 22:39:09 +00:00
|
|
|
goto continue_unlock;
|
2006-08-29 18:06:09 +00:00
|
|
|
|
2010-07-07 03:24:08 +00:00
|
|
|
trace_wbc_writepage(wbc, mapping->backing_dev_info);
|
2007-05-11 05:22:51 +00:00
|
|
|
ret = (*writepage)(page, wbc, data);
|
2009-01-06 22:39:06 +00:00
|
|
|
if (unlikely(ret)) {
|
|
|
|
if (ret == AOP_WRITEPAGE_ACTIVATE) {
|
|
|
|
unlock_page(page);
|
|
|
|
ret = 0;
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* done_index is set past this page,
|
|
|
|
* so media errors will not choke
|
|
|
|
* background writeout for the entire
|
|
|
|
* file. This has consequences for
|
|
|
|
* range_cyclic semantics (ie. it may
|
|
|
|
* not be suitable for data integrity
|
|
|
|
* writeout).
|
|
|
|
*/
|
writeback: make mapping->writeback_index to point to the last written page
For range-cyclic writeback (e.g. kupdate), the writeback code sets a
continuation point of the next writeback to mapping->writeback_index which
is set the page after the last written page. This happens so that we
evenly write the whole file even if pages in it get continuously
redirtied.
However, in some cases, sequential writer is writing in the middle of the
page and it just redirties the last written page by continuing from that.
For example with an application which uses a file as a big ring buffer we
see:
[1st writeback session]
...
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898514 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898522 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898530 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898538 + 8
flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898546 + 8
kworker/0:1-11 4571: block_rq_issue: 8,0 W 0 () 94898514 + 40
>> flush-8:0-2743 4571: block_bio_queue: 8,0 W 94898554 + 8
>> flush-8:0-2743 4571: block_rq_issue: 8,0 W 0 () 94898554 + 8
[2nd writeback session after 35sec]
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898562 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898570 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898578 + 8
...
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94898562 + 640
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94899202 + 72
...
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899962 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899970 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899978 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899986 + 8
flush-8:0-2743 4606: block_bio_queue: 8,0 W 94899994 + 8
kworker/0:1-11 4606: block_rq_issue: 8,0 W 0 () 94899962 + 40
>> flush-8:0-2743 4606: block_bio_queue: 8,0 W 94898554 + 8
>> flush-8:0-2743 4606: block_rq_issue: 8,0 W 0 () 94898554 + 8
So we seeked back to 94898554 after we wrote all the pages at the end of
the file.
This extra seek seems unnecessary. If we continue writeback from the last
written page, we can avoid it and do not cause harm to other cases. The
original intent of even writeout over the whole file is preserved and if
the page does not get redirtied pagevec_lookup_tag() just skips it.
As an exceptional case, when I/O error happens, set done_index to the next
page as the comment in the code suggests.
Tested-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-22 23:33:40 +00:00
|
|
|
done_index = page->index + 1;
|
2009-01-06 22:39:06 +00:00
|
|
|
done = 1;
|
|
|
|
break;
|
|
|
|
}
|
2010-06-09 00:37:18 +00:00
|
|
|
}
|
2009-01-06 22:39:06 +00:00
|
|
|
|
2010-08-24 01:44:34 +00:00
|
|
|
/*
|
|
|
|
* We stop writing back only if we are not doing
|
|
|
|
* integrity sync. In case of integrity sync we have to
|
|
|
|
* keep going until we have written all the pages
|
|
|
|
* we tagged for writeback prior to entering this loop.
|
|
|
|
*/
|
|
|
|
if (--wbc->nr_to_write <= 0 &&
|
|
|
|
wbc->sync_mode == WB_SYNC_NONE) {
|
|
|
|
done = 1;
|
|
|
|
break;
|
mm: write_cache_pages integrity fix
In write_cache_pages, nr_to_write is heeded even for data-integrity syncs,
so the function will return success after writing out nr_to_write pages,
even if that was not sufficient to guarantee data integrity.
The callers tend to set it to values that could break data interity
semantics easily in practice. For example, nr_to_write can be set to
mapping->nr_pages * 2, however if a file has a single, dirty page, then
fsync is called, subsequent pages might be concurrently added and dirtied,
then write_cache_pages might writeout two of these newly dirty pages,
while not writing out the old page that should have been written out.
Fix this by ignoring nr_to_write if it is a data integrity sync.
This is a data integrity bug.
The reason this has been done in the past is to avoid stalling sync
operations behind page dirtiers.
"If a file has one dirty page at offset 1000000000000000 then someone
does an fsync() and someone else gets in first and starts madly writing
pages at offset 0, we want to write that page at 1000000000000000.
Somehow."
What we do today is return success after an arbitrary amount of pages are
written, whether or not we have provided the data-integrity semantics that
the caller has asked for. Even this doesn't actually fix all stall cases
completely: in the above situation, if the file has a huge number of pages
in pagecache (but not dirty), then mapping->nrpages is going to be huge,
even if pages are being dirtied.
This change does indeed make the possibility of long stalls lager, and
that's not a good thing, but lying about data integrity is even worse. We
have to either perform the sync, or return -ELINUXISLAME so at least the
caller knows what has happened.
There are subsequent competing approaches in the works to solve the stall
problems properly, without compromising data integrity.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:08 +00:00
|
|
|
}
|
2006-08-29 18:06:09 +00:00
|
|
|
}
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
cond_resched();
|
|
|
|
}
|
2009-02-12 03:34:23 +00:00
|
|
|
if (!cycled && !done) {
|
2006-08-29 18:06:09 +00:00
|
|
|
/*
|
2009-01-06 22:39:04 +00:00
|
|
|
* range_cyclic:
|
2006-08-29 18:06:09 +00:00
|
|
|
* We hit the last page and there is more work to be done: wrap
|
|
|
|
* back to the start of the file
|
|
|
|
*/
|
2009-01-06 22:39:04 +00:00
|
|
|
cycled = 1;
|
2006-08-29 18:06:09 +00:00
|
|
|
index = 0;
|
2009-01-06 22:39:04 +00:00
|
|
|
end = writeback_index - 1;
|
2006-08-29 18:06:09 +00:00
|
|
|
goto retry;
|
|
|
|
}
|
2010-06-09 00:37:18 +00:00
|
|
|
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
|
|
|
|
mapping->writeback_index = done_index;
|
2008-07-11 23:27:31 +00:00
|
|
|
|
2006-08-29 18:06:09 +00:00
|
|
|
return ret;
|
|
|
|
}
|
2007-05-11 05:22:51 +00:00
|
|
|
EXPORT_SYMBOL(write_cache_pages);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Function used by generic_writepages to call the real writepage
|
|
|
|
* function and set the mapping flags on error
|
|
|
|
*/
|
|
|
|
static int __writepage(struct page *page, struct writeback_control *wbc,
|
|
|
|
void *data)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = data;
|
|
|
|
int ret = mapping->a_ops->writepage(page, wbc);
|
|
|
|
mapping_set_error(mapping, ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
|
|
|
|
* @mapping: address space structure to write
|
|
|
|
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
|
|
|
|
*
|
|
|
|
* This is a library function, which implements the writepages()
|
|
|
|
* address_space_operation.
|
|
|
|
*/
|
|
|
|
int generic_writepages(struct address_space *mapping,
|
|
|
|
struct writeback_control *wbc)
|
|
|
|
{
|
2011-03-17 09:47:06 +00:00
|
|
|
struct blk_plug plug;
|
|
|
|
int ret;
|
|
|
|
|
2007-05-11 05:22:51 +00:00
|
|
|
/* deal with chardevs and other special file */
|
|
|
|
if (!mapping->a_ops->writepage)
|
|
|
|
return 0;
|
|
|
|
|
2011-03-17 09:47:06 +00:00
|
|
|
blk_start_plug(&plug);
|
|
|
|
ret = write_cache_pages(mapping, wbc, __writepage, mapping);
|
|
|
|
blk_finish_plug(&plug);
|
|
|
|
return ret;
|
2007-05-11 05:22:51 +00:00
|
|
|
}
|
2006-08-29 18:06:09 +00:00
|
|
|
|
|
|
|
EXPORT_SYMBOL(generic_writepages);
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
|
|
|
|
{
|
2005-11-16 23:07:01 +00:00
|
|
|
int ret;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
if (wbc->nr_to_write <= 0)
|
|
|
|
return 0;
|
|
|
|
if (mapping->a_ops->writepages)
|
2006-09-26 06:30:57 +00:00
|
|
|
ret = mapping->a_ops->writepages(mapping, wbc);
|
2005-11-16 23:07:01 +00:00
|
|
|
else
|
|
|
|
ret = generic_writepages(mapping, wbc);
|
|
|
|
return ret;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* write_one_page - write out a single page and optionally wait on I/O
|
2005-05-01 15:59:26 +00:00
|
|
|
* @page: the page to write
|
|
|
|
* @wait: if true, wait on writeout
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* The page must be locked by the caller and will be unlocked upon return.
|
|
|
|
*
|
|
|
|
* write_one_page() returns a negative error code if I/O failed.
|
|
|
|
*/
|
|
|
|
int write_one_page(struct page *page, int wait)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = page->mapping;
|
|
|
|
int ret = 0;
|
|
|
|
struct writeback_control wbc = {
|
|
|
|
.sync_mode = WB_SYNC_ALL,
|
|
|
|
.nr_to_write = 1,
|
|
|
|
};
|
|
|
|
|
|
|
|
BUG_ON(!PageLocked(page));
|
|
|
|
|
|
|
|
if (wait)
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
|
|
|
|
if (clear_page_dirty_for_io(page)) {
|
|
|
|
page_cache_get(page);
|
|
|
|
ret = mapping->a_ops->writepage(page, &wbc);
|
|
|
|
if (ret == 0 && wait) {
|
|
|
|
wait_on_page_writeback(page);
|
|
|
|
if (PageError(page))
|
|
|
|
ret = -EIO;
|
|
|
|
}
|
|
|
|
page_cache_release(page);
|
|
|
|
} else {
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(write_one_page);
|
|
|
|
|
2007-02-10 09:43:15 +00:00
|
|
|
/*
|
|
|
|
* For address_spaces which do not use buffers nor write back.
|
|
|
|
*/
|
|
|
|
int __set_page_dirty_no_writeback(struct page *page)
|
|
|
|
{
|
|
|
|
if (!PageDirty(page))
|
2011-01-13 23:45:49 +00:00
|
|
|
return !TestSetPageDirty(page);
|
2007-02-10 09:43:15 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-03-31 22:19:39 +00:00
|
|
|
/*
|
|
|
|
* Helper function for set_page_dirty family.
|
|
|
|
* NOTE: This relies on being atomic wrt interrupts.
|
|
|
|
*/
|
|
|
|
void account_page_dirtied(struct page *page, struct address_space *mapping)
|
|
|
|
{
|
|
|
|
if (mapping_cap_account_dirty(mapping)) {
|
|
|
|
__inc_zone_page_state(page, NR_FILE_DIRTY);
|
2010-10-26 21:21:35 +00:00
|
|
|
__inc_zone_page_state(page, NR_DIRTIED);
|
2009-03-31 22:19:39 +00:00
|
|
|
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
|
|
|
|
task_dirty_inc(current);
|
|
|
|
task_io_account_write(PAGE_CACHE_SIZE);
|
|
|
|
}
|
|
|
|
}
|
2010-08-20 09:31:26 +00:00
|
|
|
EXPORT_SYMBOL(account_page_dirtied);
|
2009-03-31 22:19:39 +00:00
|
|
|
|
2010-10-26 21:21:33 +00:00
|
|
|
/*
|
|
|
|
* Helper function for set_page_writeback family.
|
|
|
|
* NOTE: Unlike account_page_dirtied this does not rely on being atomic
|
|
|
|
* wrt interrupts.
|
|
|
|
*/
|
|
|
|
void account_page_writeback(struct page *page)
|
|
|
|
{
|
|
|
|
inc_zone_page_state(page, NR_WRITEBACK);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(account_page_writeback);
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* For address_spaces which do not use buffers. Just tag the page as dirty in
|
|
|
|
* its radix tree.
|
|
|
|
*
|
|
|
|
* This is also used when a single buffer is being dirtied: we want to set the
|
|
|
|
* page dirty in that case, but not all the buffers. This is a "bottom-up"
|
|
|
|
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
|
|
|
|
*
|
|
|
|
* Most callers have locked the page, which pins the address_space in memory.
|
|
|
|
* But zap_pte_range() does not lock the page, however in that case the
|
|
|
|
* mapping is pinned by the vma's ->vm_file reference.
|
|
|
|
*
|
|
|
|
* We take care to handle the case where the page was truncated from the
|
2007-10-19 23:27:18 +00:00
|
|
|
* mapping by re-checking page_mapping() inside tree_lock.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
int __set_page_dirty_nobuffers(struct page *page)
|
|
|
|
{
|
|
|
|
if (!TestSetPageDirty(page)) {
|
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
struct address_space *mapping2;
|
|
|
|
|
2006-12-10 10:19:24 +00:00
|
|
|
if (!mapping)
|
|
|
|
return 1;
|
|
|
|
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_lock_irq(&mapping->tree_lock);
|
2006-12-10 10:19:24 +00:00
|
|
|
mapping2 = page_mapping(page);
|
|
|
|
if (mapping2) { /* Race with truncate? */
|
|
|
|
BUG_ON(mapping2 != mapping);
|
2007-07-17 11:03:34 +00:00
|
|
|
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
|
2009-03-31 22:19:39 +00:00
|
|
|
account_page_dirtied(page, mapping);
|
2006-12-10 10:19:24 +00:00
|
|
|
radix_tree_tag_set(&mapping->page_tree,
|
|
|
|
page_index(page), PAGECACHE_TAG_DIRTY);
|
|
|
|
}
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_unlock_irq(&mapping->tree_lock);
|
2006-12-10 10:19:24 +00:00
|
|
|
if (mapping->host) {
|
|
|
|
/* !PageAnon && !swapper_space */
|
|
|
|
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2006-03-24 11:18:11 +00:00
|
|
|
return 1;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2006-03-24 11:18:11 +00:00
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When a writepage implementation decides that it doesn't want to write this
|
|
|
|
* page for some reason, it should redirty the locked page via
|
|
|
|
* redirty_page_for_writepage() and it should then unlock the page and return 0
|
|
|
|
*/
|
|
|
|
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
|
|
|
|
{
|
|
|
|
wbc->pages_skipped++;
|
|
|
|
return __set_page_dirty_nobuffers(page);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(redirty_page_for_writepage);
|
|
|
|
|
|
|
|
/*
|
2009-09-16 09:50:14 +00:00
|
|
|
* Dirty a page.
|
|
|
|
*
|
|
|
|
* For pages with a mapping this should be done under the page lock
|
|
|
|
* for the benefit of asynchronous memory errors who prefer a consistent
|
|
|
|
* dirty state. This rule can be broken in some special cases,
|
|
|
|
* but should be better not to.
|
|
|
|
*
|
2005-04-16 22:20:36 +00:00
|
|
|
* If the mapping doesn't provide a set_page_dirty a_op, then
|
|
|
|
* just fall through and assume that it wants buffer_heads.
|
|
|
|
*/
|
2009-02-18 22:48:18 +00:00
|
|
|
int set_page_dirty(struct page *page)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
|
|
|
|
if (likely(mapping)) {
|
|
|
|
int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
|
mm: reclaim invalidated page ASAP
invalidate_mapping_pages is very big hint to reclaimer. It means user
doesn't want to use the page any more. So in order to prevent working set
page eviction, this patch move the page into tail of inactive list by
PG_reclaim.
Please, remember that pages in inactive list are working set as well as
active list. If we don't move pages into inactive list's tail, pages near
by tail of inactive list can be evicted although we have a big clue about
useless pages. It's totally bad.
Now PG_readahead/PG_reclaim is shared. fe3cba17 added ClearPageReclaim
into clear_page_dirty_for_io for preventing fast reclaiming readahead
marker page.
In this series, PG_reclaim is used by invalidated page, too. If VM find
the page is invalidated and it's dirty, it sets PG_reclaim to reclaim
asap. Then, when the dirty page will be writeback,
clear_page_dirty_for_io will clear PG_reclaim unconditionally. It
disturbs this serie's goal.
I think it's okay to clear PG_readahead when the page is dirty, not
writeback time. So this patch moves ClearPageReadahead. In v4,
ClearPageReadahead in set_page_dirty has a problem which is reported by
Steven Barrett. It's due to compound page. Some driver(ex, audio) calls
set_page_dirty with compound page which isn't on LRU. but my patch does
ClearPageRelcaim on compound page. In non-CONFIG_PAGEFLAGS_EXTENDED, it
breaks PageTail flag.
I think it doesn't affect THP and pass my test with THP enabling but Cced
Andrea for double check.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Reported-by: Steven Barrett <damentz@liquorix.net>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-22 23:32:54 +00:00
|
|
|
/*
|
|
|
|
* readahead/lru_deactivate_page could remain
|
|
|
|
* PG_readahead/PG_reclaim due to race with end_page_writeback
|
|
|
|
* About readahead, if the page is written, the flags would be
|
|
|
|
* reset. So no problem.
|
|
|
|
* About lru_deactivate_page, if the page is redirty, the flag
|
|
|
|
* will be reset. So no problem. but if the page is used by readahead
|
|
|
|
* it will confuse readahead and make it restart the size rampup
|
|
|
|
* process. But it's a trivial problem.
|
|
|
|
*/
|
|
|
|
ClearPageReclaim(page);
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
|
|
|
#ifdef CONFIG_BLOCK
|
|
|
|
if (!spd)
|
|
|
|
spd = __set_page_dirty_buffers;
|
|
|
|
#endif
|
|
|
|
return (*spd)(page);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2006-03-24 11:18:11 +00:00
|
|
|
if (!PageDirty(page)) {
|
|
|
|
if (!TestSetPageDirty(page))
|
|
|
|
return 1;
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(set_page_dirty);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* set_page_dirty() is racy if the caller has no reference against
|
|
|
|
* page->mapping->host, and if the page is unlocked. This is because another
|
|
|
|
* CPU could truncate the page off the mapping and then free the mapping.
|
|
|
|
*
|
|
|
|
* Usually, the page _is_ locked, or the caller is a user-space process which
|
|
|
|
* holds a reference on the inode by having an open file.
|
|
|
|
*
|
|
|
|
* In other cases, the page should be locked before running set_page_dirty().
|
|
|
|
*/
|
|
|
|
int set_page_dirty_lock(struct page *page)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2011-03-10 07:52:07 +00:00
|
|
|
lock_page(page);
|
2005-04-16 22:20:36 +00:00
|
|
|
ret = set_page_dirty(page);
|
|
|
|
unlock_page(page);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(set_page_dirty_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Clear a page's dirty flag, while caring for dirty memory accounting.
|
|
|
|
* Returns true if the page was previously dirty.
|
|
|
|
*
|
|
|
|
* This is for preparing to put the page under writeout. We leave the page
|
|
|
|
* tagged as dirty in the radix tree so that a concurrent write-for-sync
|
|
|
|
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
|
|
|
|
* implementation will run either set_page_writeback() or set_page_dirty(),
|
|
|
|
* at which stage we bring the page's dirty flag and radix-tree dirty tag
|
|
|
|
* back into sync.
|
|
|
|
*
|
|
|
|
* This incoherency between the page's dirty flag and radix-tree tag is
|
|
|
|
* unfortunate, but it only exists while the page is locked.
|
|
|
|
*/
|
|
|
|
int clear_page_dirty_for_io(struct page *page)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
|
2007-07-19 08:47:22 +00:00
|
|
|
BUG_ON(!PageLocked(page));
|
|
|
|
|
VM: Fix nasty and subtle race in shared mmap'ed page writeback
The VM layer (on the face of it, fairly reasonably) expected that when
it does a ->writepage() call to the filesystem, it would write out the
full page at that point in time. Especially since it had earlier marked
the whole page dirty with "set_page_dirty()".
But that isn't actually the case: ->writepage() does not actually write
a page, it writes the parts of the page that have been explicitly marked
dirty before, *and* that had not got written out for other reasons since
the last time we told it they were dirty.
That last caveat is the important one.
Which _most_ of the time ends up being the whole page (since we had
called "set_page_dirty()" on the page earlier), but if the filesystem
had done any dirty flushing of its own (for example, to honor some
internal write ordering guarantees), it might end up doing only a
partial page IO (or none at all) when ->writepage() is actually called.
That is the correct thing in general (since we actually often _want_
only the known-dirty parts of the page to be written out), but the
shared dirty page handling had implicitly forgotten about these details,
and had a number of cases where it was doing just the "->writepage()"
part, without telling the low-level filesystem that the whole page might
have been re-dirtied as part of being mapped writably into user space.
Since most of the time the FS did actually write out the full page, we
didn't notice this for a loong time, and this needed some really odd
patterns to trigger. But it caused occasional corruption with rtorrent
and with the Debian "apt" database, because both use shared mmaps to
update the end result.
This fixes it. Finally. After way too much hair-pulling.
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Martin J. Bligh <mbligh@google.com>
Acked-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Martin Johansson <martin@fatbob.nu>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Andrei Popa <andrei.popa@i-neo.ro>
Cc: High Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Guillaume Chazarain <guichaz@yahoo.fr>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Kenneth Cheng <kenneth.w.chen@intel.com>
Cc: Tobias Diedrich <ranma@tdiedrich.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
|
|
|
if (mapping && mapping_cap_account_dirty(mapping)) {
|
|
|
|
/*
|
|
|
|
* Yes, Virginia, this is indeed insane.
|
|
|
|
*
|
|
|
|
* We use this sequence to make sure that
|
|
|
|
* (a) we account for dirty stats properly
|
|
|
|
* (b) we tell the low-level filesystem to
|
|
|
|
* mark the whole page dirty if it was
|
|
|
|
* dirty in a pagetable. Only to then
|
|
|
|
* (c) clean the page again and return 1 to
|
|
|
|
* cause the writeback.
|
|
|
|
*
|
|
|
|
* This way we avoid all nasty races with the
|
|
|
|
* dirty bit in multiple places and clearing
|
|
|
|
* them concurrently from different threads.
|
|
|
|
*
|
|
|
|
* Note! Normally the "set_page_dirty(page)"
|
|
|
|
* has no effect on the actual dirty bit - since
|
|
|
|
* that will already usually be set. But we
|
|
|
|
* need the side effects, and it can help us
|
|
|
|
* avoid races.
|
|
|
|
*
|
|
|
|
* We basically use the page "master dirty bit"
|
|
|
|
* as a serialization point for all the different
|
|
|
|
* threads doing their things.
|
|
|
|
*/
|
|
|
|
if (page_mkclean(page))
|
|
|
|
set_page_dirty(page);
|
2007-07-19 08:47:22 +00:00
|
|
|
/*
|
|
|
|
* We carefully synchronise fault handlers against
|
|
|
|
* installing a dirty pte and marking the page dirty
|
|
|
|
* at this point. We do this by having them hold the
|
|
|
|
* page lock at some point after installing their
|
|
|
|
* pte, but before marking the page dirty.
|
|
|
|
* Pages are always locked coming in here, so we get
|
|
|
|
* the desired exclusion. See mm/memory.c:do_wp_page()
|
|
|
|
* for more comments.
|
|
|
|
*/
|
VM: Fix nasty and subtle race in shared mmap'ed page writeback
The VM layer (on the face of it, fairly reasonably) expected that when
it does a ->writepage() call to the filesystem, it would write out the
full page at that point in time. Especially since it had earlier marked
the whole page dirty with "set_page_dirty()".
But that isn't actually the case: ->writepage() does not actually write
a page, it writes the parts of the page that have been explicitly marked
dirty before, *and* that had not got written out for other reasons since
the last time we told it they were dirty.
That last caveat is the important one.
Which _most_ of the time ends up being the whole page (since we had
called "set_page_dirty()" on the page earlier), but if the filesystem
had done any dirty flushing of its own (for example, to honor some
internal write ordering guarantees), it might end up doing only a
partial page IO (or none at all) when ->writepage() is actually called.
That is the correct thing in general (since we actually often _want_
only the known-dirty parts of the page to be written out), but the
shared dirty page handling had implicitly forgotten about these details,
and had a number of cases where it was doing just the "->writepage()"
part, without telling the low-level filesystem that the whole page might
have been re-dirtied as part of being mapped writably into user space.
Since most of the time the FS did actually write out the full page, we
didn't notice this for a loong time, and this needed some really odd
patterns to trigger. But it caused occasional corruption with rtorrent
and with the Debian "apt" database, because both use shared mmaps to
update the end result.
This fixes it. Finally. After way too much hair-pulling.
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Martin J. Bligh <mbligh@google.com>
Acked-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Martin Johansson <martin@fatbob.nu>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Andrei Popa <andrei.popa@i-neo.ro>
Cc: High Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Guillaume Chazarain <guichaz@yahoo.fr>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Kenneth Cheng <kenneth.w.chen@intel.com>
Cc: Tobias Diedrich <ranma@tdiedrich.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
|
|
|
if (TestClearPageDirty(page)) {
|
2006-12-10 10:19:24 +00:00
|
|
|
dec_zone_page_state(page, NR_FILE_DIRTY);
|
2007-10-17 06:25:47 +00:00
|
|
|
dec_bdi_stat(mapping->backing_dev_info,
|
|
|
|
BDI_RECLAIMABLE);
|
VM: Fix nasty and subtle race in shared mmap'ed page writeback
The VM layer (on the face of it, fairly reasonably) expected that when
it does a ->writepage() call to the filesystem, it would write out the
full page at that point in time. Especially since it had earlier marked
the whole page dirty with "set_page_dirty()".
But that isn't actually the case: ->writepage() does not actually write
a page, it writes the parts of the page that have been explicitly marked
dirty before, *and* that had not got written out for other reasons since
the last time we told it they were dirty.
That last caveat is the important one.
Which _most_ of the time ends up being the whole page (since we had
called "set_page_dirty()" on the page earlier), but if the filesystem
had done any dirty flushing of its own (for example, to honor some
internal write ordering guarantees), it might end up doing only a
partial page IO (or none at all) when ->writepage() is actually called.
That is the correct thing in general (since we actually often _want_
only the known-dirty parts of the page to be written out), but the
shared dirty page handling had implicitly forgotten about these details,
and had a number of cases where it was doing just the "->writepage()"
part, without telling the low-level filesystem that the whole page might
have been re-dirtied as part of being mapped writably into user space.
Since most of the time the FS did actually write out the full page, we
didn't notice this for a loong time, and this needed some really odd
patterns to trigger. But it caused occasional corruption with rtorrent
and with the Debian "apt" database, because both use shared mmaps to
update the end result.
This fixes it. Finally. After way too much hair-pulling.
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Martin J. Bligh <mbligh@google.com>
Acked-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Martin Johansson <martin@fatbob.nu>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Andrei Popa <andrei.popa@i-neo.ro>
Cc: High Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Guillaume Chazarain <guichaz@yahoo.fr>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Kenneth Cheng <kenneth.w.chen@intel.com>
Cc: Tobias Diedrich <ranma@tdiedrich.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
|
|
|
return 1;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
VM: Fix nasty and subtle race in shared mmap'ed page writeback
The VM layer (on the face of it, fairly reasonably) expected that when
it does a ->writepage() call to the filesystem, it would write out the
full page at that point in time. Especially since it had earlier marked
the whole page dirty with "set_page_dirty()".
But that isn't actually the case: ->writepage() does not actually write
a page, it writes the parts of the page that have been explicitly marked
dirty before, *and* that had not got written out for other reasons since
the last time we told it they were dirty.
That last caveat is the important one.
Which _most_ of the time ends up being the whole page (since we had
called "set_page_dirty()" on the page earlier), but if the filesystem
had done any dirty flushing of its own (for example, to honor some
internal write ordering guarantees), it might end up doing only a
partial page IO (or none at all) when ->writepage() is actually called.
That is the correct thing in general (since we actually often _want_
only the known-dirty parts of the page to be written out), but the
shared dirty page handling had implicitly forgotten about these details,
and had a number of cases where it was doing just the "->writepage()"
part, without telling the low-level filesystem that the whole page might
have been re-dirtied as part of being mapped writably into user space.
Since most of the time the FS did actually write out the full page, we
didn't notice this for a loong time, and this needed some really odd
patterns to trigger. But it caused occasional corruption with rtorrent
and with the Debian "apt" database, because both use shared mmaps to
update the end result.
This fixes it. Finally. After way too much hair-pulling.
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Martin J. Bligh <mbligh@google.com>
Acked-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Martin Johansson <martin@fatbob.nu>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Andrei Popa <andrei.popa@i-neo.ro>
Cc: High Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Guillaume Chazarain <guichaz@yahoo.fr>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Kenneth Cheng <kenneth.w.chen@intel.com>
Cc: Tobias Diedrich <ranma@tdiedrich.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
|
|
|
return 0;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
VM: Fix nasty and subtle race in shared mmap'ed page writeback
The VM layer (on the face of it, fairly reasonably) expected that when
it does a ->writepage() call to the filesystem, it would write out the
full page at that point in time. Especially since it had earlier marked
the whole page dirty with "set_page_dirty()".
But that isn't actually the case: ->writepage() does not actually write
a page, it writes the parts of the page that have been explicitly marked
dirty before, *and* that had not got written out for other reasons since
the last time we told it they were dirty.
That last caveat is the important one.
Which _most_ of the time ends up being the whole page (since we had
called "set_page_dirty()" on the page earlier), but if the filesystem
had done any dirty flushing of its own (for example, to honor some
internal write ordering guarantees), it might end up doing only a
partial page IO (or none at all) when ->writepage() is actually called.
That is the correct thing in general (since we actually often _want_
only the known-dirty parts of the page to be written out), but the
shared dirty page handling had implicitly forgotten about these details,
and had a number of cases where it was doing just the "->writepage()"
part, without telling the low-level filesystem that the whole page might
have been re-dirtied as part of being mapped writably into user space.
Since most of the time the FS did actually write out the full page, we
didn't notice this for a loong time, and this needed some really odd
patterns to trigger. But it caused occasional corruption with rtorrent
and with the Debian "apt" database, because both use shared mmaps to
update the end result.
This fixes it. Finally. After way too much hair-pulling.
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Martin J. Bligh <mbligh@google.com>
Acked-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Martin Johansson <martin@fatbob.nu>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Andrei Popa <andrei.popa@i-neo.ro>
Cc: High Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Gordon Farquharson <gordonfarquharson@gmail.com>
Cc: Guillaume Chazarain <guichaz@yahoo.fr>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Kenneth Cheng <kenneth.w.chen@intel.com>
Cc: Tobias Diedrich <ranma@tdiedrich.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
|
|
|
return TestClearPageDirty(page);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
2005-11-18 09:10:53 +00:00
|
|
|
EXPORT_SYMBOL(clear_page_dirty_for_io);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
int test_clear_page_writeback(struct page *page)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (mapping) {
|
2007-10-17 06:25:48 +00:00
|
|
|
struct backing_dev_info *bdi = mapping->backing_dev_info;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned long flags;
|
|
|
|
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_lock_irqsave(&mapping->tree_lock, flags);
|
2005-04-16 22:20:36 +00:00
|
|
|
ret = TestClearPageWriteback(page);
|
2007-10-17 06:25:48 +00:00
|
|
|
if (ret) {
|
2005-04-16 22:20:36 +00:00
|
|
|
radix_tree_tag_clear(&mapping->page_tree,
|
|
|
|
page_index(page),
|
|
|
|
PAGECACHE_TAG_WRITEBACK);
|
2008-04-30 07:54:37 +00:00
|
|
|
if (bdi_cap_account_writeback(bdi)) {
|
2007-10-17 06:25:48 +00:00
|
|
|
__dec_bdi_stat(bdi, BDI_WRITEBACK);
|
2007-10-17 06:25:50 +00:00
|
|
|
__bdi_writeout_inc(bdi);
|
|
|
|
}
|
2007-10-17 06:25:48 +00:00
|
|
|
}
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_unlock_irqrestore(&mapping->tree_lock, flags);
|
2005-04-16 22:20:36 +00:00
|
|
|
} else {
|
|
|
|
ret = TestClearPageWriteback(page);
|
|
|
|
}
|
2011-07-26 00:12:37 +00:00
|
|
|
if (ret) {
|
2007-07-19 08:49:17 +00:00
|
|
|
dec_zone_page_state(page, NR_WRITEBACK);
|
2011-07-26 00:12:37 +00:00
|
|
|
inc_zone_page_state(page, NR_WRITTEN);
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int test_set_page_writeback(struct page *page)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = page_mapping(page);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (mapping) {
|
2007-10-17 06:25:48 +00:00
|
|
|
struct backing_dev_info *bdi = mapping->backing_dev_info;
|
2005-04-16 22:20:36 +00:00
|
|
|
unsigned long flags;
|
|
|
|
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_lock_irqsave(&mapping->tree_lock, flags);
|
2005-04-16 22:20:36 +00:00
|
|
|
ret = TestSetPageWriteback(page);
|
2007-10-17 06:25:48 +00:00
|
|
|
if (!ret) {
|
2005-04-16 22:20:36 +00:00
|
|
|
radix_tree_tag_set(&mapping->page_tree,
|
|
|
|
page_index(page),
|
|
|
|
PAGECACHE_TAG_WRITEBACK);
|
2008-04-30 07:54:37 +00:00
|
|
|
if (bdi_cap_account_writeback(bdi))
|
2007-10-17 06:25:48 +00:00
|
|
|
__inc_bdi_stat(bdi, BDI_WRITEBACK);
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
if (!PageDirty(page))
|
|
|
|
radix_tree_tag_clear(&mapping->page_tree,
|
|
|
|
page_index(page),
|
|
|
|
PAGECACHE_TAG_DIRTY);
|
2010-08-10 00:19:12 +00:00
|
|
|
radix_tree_tag_clear(&mapping->page_tree,
|
|
|
|
page_index(page),
|
|
|
|
PAGECACHE_TAG_TOWRITE);
|
2008-07-26 02:45:32 +00:00
|
|
|
spin_unlock_irqrestore(&mapping->tree_lock, flags);
|
2005-04-16 22:20:36 +00:00
|
|
|
} else {
|
|
|
|
ret = TestSetPageWriteback(page);
|
|
|
|
}
|
2007-07-19 08:49:17 +00:00
|
|
|
if (!ret)
|
2010-10-26 21:21:33 +00:00
|
|
|
account_page_writeback(page);
|
2005-04-16 22:20:36 +00:00
|
|
|
return ret;
|
|
|
|
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(test_set_page_writeback);
|
|
|
|
|
|
|
|
/*
|
2007-10-16 08:24:40 +00:00
|
|
|
* Return true if any of the pages in the mapping are marked with the
|
2005-04-16 22:20:36 +00:00
|
|
|
* passed tag.
|
|
|
|
*/
|
|
|
|
int mapping_tagged(struct address_space *mapping, int tag)
|
|
|
|
{
|
2011-07-26 00:12:31 +00:00
|
|
|
return radix_tree_tagged(&mapping->page_tree, tag);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(mapping_tagged);
|