WSL2-Linux-Kernel/mm/page-writeback.c

1342 строки
36 KiB
C
Исходник Обычный вид История

/*
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* Contains functions related to writing back dirty pages at the
* address_space level.
*
* 10Apr2002 Andrew Morton
* Initial version
*/
#include <linux/kernel.h>
#include <linux/module.h>
#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>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 10:30:57 +04:00
#include <linux/rmap.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>
/*
* 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.
* It should be somewhat larger than dirtied pages to ensure that reasonably
* large amounts of I/O are submitted.
*/
static inline long sync_writeback_pages(unsigned long dirtied)
{
if (dirtied < ratelimit_pages)
dirtied = ratelimit_pages;
return dirtied + dirtied / 2;
}
/* The following parameters are exported via /proc/sys/vm */
/*
* Start background writeback (via writeback threads) at this percentage
*/
int dirty_background_ratio = 10;
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>
2009-01-07 01:39:31 +03:00
/*
* 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;
/*
* 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;
/*
* The generator of dirty data starts writeback at this percentage
*/
int vm_dirty_ratio = 20;
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>
2009-01-07 01:39:31 +03:00
/*
* 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;
/*
* The interval between `kupdate'-style writebacks
*/
unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
/*
* The longest time for which data is allowed to remain dirty
*/
unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */
/*
* Flag that makes the machine dump writes/reads and block dirtyings.
*/
int block_dump;
/*
* 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.
*/
int laptop_mode;
EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
/*
* 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;
static struct prop_descriptor vm_dirties;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
/*
* 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>
2009-01-07 01:39:31 +03:00
if (vm_dirty_bytes)
dirty_total = vm_dirty_bytes / PAGE_SIZE;
else
dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
100;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
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>
2009-01-07 01:39:31 +03:00
* update the period when the dirty threshold changes.
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
*/
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>
2009-01-07 01:39:31 +03:00
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,
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>
2009-01-07 01:39:31 +03:00
loff_t *ppos)
{
int ret;
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>
2009-01-07 01:39:31 +03:00
if (ret == 0 && write)
dirty_background_bytes = 0;
return ret;
}
int dirty_background_bytes_handler(struct ctl_table *table, int write,
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>
2009-01-07 01:39:31 +03:00
loff_t *ppos)
{
int ret;
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>
2009-01-07 01:39:31 +03:00
if (ret == 0 && write)
dirty_background_ratio = 0;
return ret;
}
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
int dirty_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
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>
2009-01-07 01:39:31 +03:00
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
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>
2009-01-07 01:39:31 +03:00
update_completion_period();
vm_dirty_bytes = 0;
}
return ret;
}
int dirty_bytes_handler(struct ctl_table *table, int write,
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>
2009-01-07 01:39:31 +03:00
loff_t *ppos)
{
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>
2009-01-07 01:39:31 +03:00
int ret;
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>
2009-01-07 01:39:31 +03:00
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
update_completion_period();
vm_dirty_ratio = 0;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
}
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)
{
__prop_inc_percpu_max(&vm_completions, &bdi->completions,
bdi->max_prop_frac);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
}
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);
void task_dirty_inc(struct task_struct *tsk)
{
prop_inc_single(&vm_dirties, &tsk->dirties);
}
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
/*
* Obtain an accurate fraction of the BDI's portion.
*/
static void bdi_writeout_fraction(struct backing_dev_info *bdi,
long *numerator, long *denominator)
{
if (bdi_cap_writeback_dirty(bdi)) {
prop_fraction_percpu(&vm_completions, &bdi->completions,
numerator, denominator);
} else {
*numerator = 0;
*denominator = 1;
}
}
/*
* Clip the earned share of dirty pages to that which is actually available.
* This avoids exceeding the total dirty_limit when the floating averages
* fluctuate too quickly.
*/
static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
unsigned long dirty, unsigned long *pbdi_dirty)
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
{
unsigned long avail_dirty;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
avail_dirty = global_page_state(NR_FILE_DIRTY) +
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
global_page_state(NR_WRITEBACK) +
global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK_TEMP);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (avail_dirty < dirty)
avail_dirty = dirty - avail_dirty;
else
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
avail_dirty = 0;
avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
bdi_stat(bdi, BDI_WRITEBACK);
*pbdi_dirty = min(*pbdi_dirty, avail_dirty);
}
static inline void task_dirties_fraction(struct task_struct *tsk,
long *numerator, long *denominator)
{
prop_fraction_single(&vm_dirties, &tsk->dirties,
numerator, denominator);
}
/*
* scale the dirty limit
*
* task specific dirty limit:
*
* dirty -= (dirty/8) * p_{t}
*/
static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
{
long numerator, denominator;
unsigned long dirty = *pdirty;
u64 inv = dirty >> 3;
task_dirties_fraction(tsk, &numerator, &denominator);
inv *= numerator;
do_div(inv, denominator);
dirty -= inv;
if (dirty < *pdirty/2)
dirty = *pdirty/2;
*pdirty = dirty;
}
/*
*
*/
static unsigned int bdi_min_ratio;
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
spin_lock_bh(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} 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;
}
}
spin_unlock_bh(&bdi_lock);
return ret;
}
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
{
int ret = 0;
if (max_ratio > 100)
return -EINVAL;
spin_lock_bh(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
spin_unlock_bh(&bdi_lock);
return ret;
}
EXPORT_SYMBOL(bdi_set_max_ratio);
/*
* 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.
*/
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
int node;
unsigned long x = 0;
memoryless nodes: fixup uses of node_online_map in generic code Here's a cut at fixing up uses of the online node map in generic code. mm/shmem.c:shmem_parse_mpol() Ensure nodelist is subset of nodes with memory. Use node_states[N_HIGH_MEMORY] as default for missing nodelist for interleave policy. mm/shmem.c:shmem_fill_super() initialize policy_nodes to node_states[N_HIGH_MEMORY] mm/page-writeback.c:highmem_dirtyable_memory() sum over nodes with memory mm/page_alloc.c:zlc_setup() allowednodes - use nodes with memory. mm/page_alloc.c:default_zonelist_order() average over nodes with memory. mm/page_alloc.c:find_next_best_node() skip nodes w/o memory. N_HIGH_MEMORY state mask may not be initialized at this time, unless we want to depend on early_calculate_totalpages() [see below]. Will ZONE_MOVABLE ever be configurable? mm/page_alloc.c:find_zone_movable_pfns_for_nodes() spread kernelcore over nodes with memory. This required calling early_calculate_totalpages() unconditionally, and populating N_HIGH_MEMORY node state therein from nodes in the early_node_map[]. If we can depend on this, we can eliminate the population of N_HIGH_MEMORY mask from __build_all_zonelists() and use the N_HIGH_MEMORY mask in find_next_best_node(). mm/mempolicy.c:mpol_check_policy() Ensure nodes specified for policy are subset of nodes with memory. [akpm@linux-foundation.org: fix warnings] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 12:25:39 +04:00
for_each_node_state(node, N_HIGH_MEMORY) {
struct zone *z =
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
x += zone_page_state(z, NR_FREE_PAGES) +
zone_reclaimable_pages(z);
}
/*
* 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
}
/**
* 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)
{
unsigned long x;
x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
return x + 1; /* Ensure that we never return 0 */
}
void
get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
{
unsigned long background;
unsigned long dirty;
unsigned long available_memory = determine_dirtyable_memory();
struct task_struct *tsk;
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>
2009-01-07 01:39:31 +03:00
if (vm_dirty_bytes)
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
else {
int dirty_ratio;
dirty_ratio = vm_dirty_ratio;
if (dirty_ratio < 5)
dirty_ratio = 5;
dirty = (dirty_ratio * available_memory) / 100;
}
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>
2009-01-07 01:39:31 +03:00
if (dirty_background_bytes)
background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
else
background = (dirty_background_ratio * available_memory) / 100;
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>
2009-01-07 01:39:31 +03:00
if (background >= dirty)
background = dirty / 2;
tsk = current;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
background += background / 4;
dirty += dirty / 4;
}
*pbackground = background;
*pdirty = dirty;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (bdi) {
u64 bdi_dirty;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
long numerator, denominator;
/*
* Calculate this BDI's share of the dirty ratio.
*/
bdi_writeout_fraction(bdi, &numerator, &denominator);
bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
bdi_dirty *= numerator;
do_div(bdi_dirty, denominator);
bdi_dirty += (dirty * bdi->min_ratio) / 100;
if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
bdi_dirty = dirty * bdi->max_ratio / 100;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
*pbdi_dirty = bdi_dirty;
clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
task_dirty_limit(current, pbdi_dirty);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
}
}
/*
* 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'.
* If we're over `background_thresh' then the writeback threads are woken to
* perform some writeout.
*/
static void balance_dirty_pages(struct address_space *mapping,
unsigned long write_chunk)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long pause = 1;
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.bdi = bdi,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = write_chunk,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
.range_cyclic = 1,
};
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
nr_writeback = global_page_state(NR_WRITEBACK);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
break;
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the bdi limits are ramping up.
*/
if (nr_reclaimable + nr_writeback <
(background_thresh + dirty_thresh) / 2)
break;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (!bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
/* 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.
* Only move pages to writeback if this bdi is over its
* threshold otherwise wait until the disk writes catch
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-09 11:08:54 +04:00
writeback_inodes_wbc(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
}
/*
* 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.
*/
if (bdi_thresh < 2*bdi_stat_error(bdi)) {
bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
} else if (bdi_nr_reclaimable) {
bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
}
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
break;
if (pages_written >= write_chunk)
break; /* We've done our duty */
__set_current_state(TASK_INTERRUPTIBLE);
io_schedule_timeout(pause);
/*
* 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;
}
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
bdi->dirty_exceeded)
bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return;
/*
* 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) ||
(!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS))
> background_thresh)))
bdi_start_writeback(bdi, NULL, 0);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
if (set_page_dirty(page) || page_mkwrite) {
struct address_space *mapping = page_mapping(page);
if (mapping)
balance_dirty_pages_ratelimited(mapping);
}
}
static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
/**
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
* @mapping: address_space which was dirtied
* @nr_pages_dirtied: number of pages which the caller has just dirtied
*
* 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.
*/
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
unsigned long ratelimit;
unsigned long *p;
ratelimit = ratelimit_pages;
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (mapping->backing_dev_info->dirty_exceeded)
ratelimit = 8;
/*
* Check the rate limiting. Also, we do not want to throttle real-time
* tasks in balance_dirty_pages(). Period.
*/
preempt_disable();
p = &__get_cpu_var(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
ratelimit = sync_writeback_pages(*p);
*p = 0;
preempt_enable();
balance_dirty_pages(mapping, ratelimit);
return;
}
preempt_enable();
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
void throttle_vm_writeout(gfp_t gfp_mask)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
for ( ; ; ) {
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
/*
* 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... */
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
* 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;
}
}
static void laptop_timer_fn(unsigned long unused);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
return 0;
}
writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-09 11:08:54 +04:00
static void do_laptop_sync(struct work_struct *work)
{
writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-09 11:08:54 +04:00
wakeup_flusher_threads(0);
kfree(work);
}
static void laptop_timer_fn(unsigned long unused)
{
writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-09 11:08:54 +04:00
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_laptop_sync);
schedule_work(work);
}
}
/*
* 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.
*/
void laptop_io_completion(void)
{
mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
}
/*
* 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)
{
del_timer(&laptop_mode_wb_timer);
}
/*
* 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.
*/
void writeback_set_ratelimit(void)
{
ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
ratelimit_pages = 16;
if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
}
static int __cpuinit
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
writeback_set_ratelimit();
return NOTIFY_DONE;
}
static struct notifier_block __cpuinitdata ratelimit_nb = {
.notifier_call = ratelimit_handler,
.next = NULL,
};
/*
* 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..
*/
void __init page_writeback_init(void)
{
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
int shift;
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
shift = calc_period_shift();
prop_descriptor_init(&vm_completions, shift);
prop_descriptor_init(&vm_dirties, shift);
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* 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.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
int cycled;
int range_whole = 0;
long nr_to_write = wbc->nr_to_write;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
if (index == 0)
cycled = 1;
else
cycled = 0;
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;
cycled = 1; /* ignore range_cyclic tests */
}
retry:
done_index = index;
while (!done && (index <= end)) {
int i;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* 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.
*/
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
break;
}
done_index = page->index + 1;
lock_page(page);
/*
* 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.
*/
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
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;
}
BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
ret = (*writepage)(page, wbc, data);
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).
*/
done = 1;
break;
}
}
if (nr_to_write > 0) {
nr_to_write--;
if (nr_to_write == 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
/*
* We stop writing back only if we are
* not doing integrity sync. In case of
* integrity sync we have to keep going
* because someone may be concurrently
* dirtying pages, and we might have
* synced a lot of newly appeared dirty
* pages, but have not synced all of the
* old dirty pages.
*/
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>
2009-01-07 01:39:08 +03:00
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
cycled = 1;
index = 0;
end = writeback_index - 1;
goto retry;
}
if (!wbc->no_nrwrite_index_update) {
if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
mapping->writeback_index = done_index;
wbc->nr_to_write = nr_to_write;
}
return ret;
}
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)
{
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
return write_cache_pages(mapping, wbc, __writepage, mapping);
}
EXPORT_SYMBOL(generic_writepages);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int ret;
if (wbc->nr_to_write <= 0)
return 0;
if (mapping->a_ops->writepages)
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 10:30:57 +04:00
ret = mapping->a_ops->writepages(mapping, wbc);
else
ret = generic_writepages(mapping, wbc);
return ret;
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* 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);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* 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);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
/*
* 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
* mapping by re-checking page_mapping() inside tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
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);
/*
* 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.
*
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/
int set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
if (likely(mapping)) {
int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
[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 22:45:40 +04:00
#ifdef CONFIG_BLOCK
if (!spd)
spd = __set_page_dirty_buffers;
#endif
return (*spd)(page);
}
if (!PageDirty(page)) {
if (!TestSetPageDirty(page))
return 1;
}
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;
lock_page_nosync(page);
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);
BUG_ON(!PageLocked(page));
mm: share PG_readahead and PG_reclaim Share the same page flag bit for PG_readahead and PG_reclaim. One is used only on file reads, another is only for emergency writes. One is used mostly for fresh/young pages, another is for old pages. Combinations of possible interactions are: a) clear PG_reclaim => implicit clear of PG_readahead it will delay an asynchronous readahead into a synchronous one it actually does _good_ for readahead: the pages will be reclaimed soon, it's readahead thrashing! in this case, synchronous readahead makes more sense. b) clear PG_readahead => implicit clear of PG_reclaim one(and only one) page will not be reclaimed in time it can be avoided by checking PageWriteback(page) in readahead first c) set PG_reclaim => implicit set of PG_readahead will confuse readahead and make it restart the size rampup process it's a trivial problem, and can mostly be avoided by checking PageWriteback(page) first in readahead d) set PG_readahead => implicit set of PG_reclaim PG_readahead will never be set on already cached pages. PG_reclaim will always be cleared on dirtying a page. so not a problem. In summary, a) we get better behavior b,d) possible interactions can be avoided c) racy condition exists that might affect readahead, but the chance is _really_ low, and the hurt on readahead is trivial. Compound pages also use PG_reclaim, but for now they do not interact with reclaim/readahead code. Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:48:07 +04:00
ClearPageReclaim(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 21:00:58 +03:00
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);
/*
* 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 21:00:58 +03:00
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
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 21:00:58 +03:00
return 1;
}
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 21:00:58 +03:00
return 0;
}
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 21:00:58 +03:00
return TestClearPageDirty(page);
}
EXPORT_SYMBOL(clear_page_dirty_for_io);
int test_clear_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int ret;
if (mapping) {
struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
ret = TestClearPageWriteback(page);
if (ret) {
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
if (bdi_cap_account_writeback(bdi)) {
__dec_bdi_stat(bdi, BDI_WRITEBACK);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
__bdi_writeout_inc(bdi);
}
}
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestClearPageWriteback(page);
}
if (ret)
dec_zone_page_state(page, NR_WRITEBACK);
return ret;
}
int test_set_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int ret;
if (mapping) {
struct backing_dev_info *bdi = mapping->backing_dev_info;
unsigned long flags;
spin_lock_irqsave(&mapping->tree_lock, flags);
ret = TestSetPageWriteback(page);
if (!ret) {
radix_tree_tag_set(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
if (bdi_cap_account_writeback(bdi))
__inc_bdi_stat(bdi, BDI_WRITEBACK);
}
if (!PageDirty(page))
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);
}
if (!ret)
inc_zone_page_state(page, NR_WRITEBACK);
return ret;
}
EXPORT_SYMBOL(test_set_page_writeback);
/*
* Return true if any of the pages in the mapping are marked with the
* passed tag.
*/
int mapping_tagged(struct address_space *mapping, int tag)
{
int ret;
rcu_read_lock();
ret = radix_tree_tagged(&mapping->page_tree, tag);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(mapping_tagged);