linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [patch] mm: task dirty accounting fix
@ 2009-02-10  4:39 Nick Piggin
  2009-02-10  9:12 ` Peter Zijlstra
  0 siblings, 1 reply; 3+ messages in thread
From: Nick Piggin @ 2009-02-10  4:39 UTC (permalink / raw)
  To: Linux Kernel Mailing List, Peter Zijlstra, YAMAMOTO Takashi,
	Andrew Morton

Hi,

This is based from an earlier patch from YAMAMOTO-san which I have
somewhat simplified. What do you think?

Thanks,
Nick

--
YAMAMOTO-san noticed that task_dirty_inc doesn't seem to be called properly for
cases where set_page_dirty is not used to dirty a page (eg. mark_buffer_dirty).

Additionally, there is some inconsistency about when task_dirty_inc is
called. It is used for dirty balancing, however it even gets called for
__set_page_dirty_no_writeback.

So rather than increment it in a set_page_dirty wrapper, move it down to
exactly where the dirty page accounting stats are incremented.

Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Signed-off-by: Nick Piggin <npiggin@suse.de>
---
 fs/buffer.c         |    1 +
 include/linux/mm.h  |    1 +
 mm/page-writeback.c |   13 +++----------
 3 files changed, 5 insertions(+), 10 deletions(-)

Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -1162,6 +1162,7 @@ extern int filemap_fault(struct vm_area_
 
 /* mm/page-writeback.c */
 int write_one_page(struct page *page, int wait);
+void task_dirty_inc(struct task_struct *tsk);
 
 /* readahead.c */
 #define VM_MAX_READAHEAD	128	/* kbytes */
Index: linux-2.6/mm/page-writeback.c
===================================================================
--- linux-2.6.orig/mm/page-writeback.c
+++ linux-2.6/mm/page-writeback.c
@@ -241,7 +241,7 @@ void bdi_writeout_inc(struct backing_dev
 }
 EXPORT_SYMBOL_GPL(bdi_writeout_inc);
 
-static inline void task_dirty_inc(struct task_struct *tsk)
+void task_dirty_inc(struct task_struct *tsk)
 {
 	prop_inc_single(&vm_dirties, &tsk->dirties);
 }
@@ -1228,6 +1228,7 @@ int __set_page_dirty_nobuffers(struct pa
 				__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);
 			}
 			radix_tree_tag_set(&mapping->page_tree,
@@ -1263,7 +1264,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage
  * If the mapping doesn't provide a set_page_dirty a_op, then
  * just fall through and assume that it wants buffer_heads.
  */
-static int __set_page_dirty(struct page *page)
+int set_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
@@ -1281,14 +1282,6 @@ static int __set_page_dirty(struct page
 	}
 	return 0;
 }
-
-int set_page_dirty(struct page *page)
-{
-	int ret = __set_page_dirty(page);
-	if (ret)
-		task_dirty_inc(current);
-	return ret;
-}
 EXPORT_SYMBOL(set_page_dirty);
 
 /*
Index: linux-2.6/fs/buffer.c
===================================================================
--- linux-2.6.orig/fs/buffer.c
+++ linux-2.6/fs/buffer.c
@@ -628,6 +628,7 @@ static int __set_page_dirty(struct page
 			__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);
 		}
 		radix_tree_tag_set(&mapping->page_tree,

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [patch] mm: task dirty accounting fix
  2009-02-10  4:39 [patch] mm: task dirty accounting fix Nick Piggin
@ 2009-02-10  9:12 ` Peter Zijlstra
  2009-02-12  1:43   ` Nick Piggin
  0 siblings, 1 reply; 3+ messages in thread
From: Peter Zijlstra @ 2009-02-10  9:12 UTC (permalink / raw)
  To: Nick Piggin; +Cc: Linux Kernel Mailing List, YAMAMOTO Takashi, Andrew Morton

On Tue, 2009-02-10 at 05:39 +0100, Nick Piggin wrote:
> Hi,
> 
> This is based from an earlier patch from YAMAMOTO-san which I have
> somewhat simplified. What do you think?

Looks nice. Was a bit surprised we never actually merged the previous
one though..

> Thanks,
> Nick
> 
> --
> YAMAMOTO-san noticed that task_dirty_inc doesn't seem to be called properly for
> cases where set_page_dirty is not used to dirty a page (eg. mark_buffer_dirty).
> 
> Additionally, there is some inconsistency about when task_dirty_inc is
> called. It is used for dirty balancing, however it even gets called for
> __set_page_dirty_no_writeback.
> 
> So rather than increment it in a set_page_dirty wrapper, move it down to
> exactly where the dirty page accounting stats are incremented.
> 
> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
> Signed-off-by: Nick Piggin <npiggin@suse.de>

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

> ---
>  fs/buffer.c         |    1 +
>  include/linux/mm.h  |    1 +
>  mm/page-writeback.c |   13 +++----------
>  3 files changed, 5 insertions(+), 10 deletions(-)
> 
> Index: linux-2.6/include/linux/mm.h
> ===================================================================
> --- linux-2.6.orig/include/linux/mm.h
> +++ linux-2.6/include/linux/mm.h
> @@ -1162,6 +1162,7 @@ extern int filemap_fault(struct vm_area_
>  
>  /* mm/page-writeback.c */
>  int write_one_page(struct page *page, int wait);
> +void task_dirty_inc(struct task_struct *tsk);
>  
>  /* readahead.c */
>  #define VM_MAX_READAHEAD	128	/* kbytes */
> Index: linux-2.6/mm/page-writeback.c
> ===================================================================
> --- linux-2.6.orig/mm/page-writeback.c
> +++ linux-2.6/mm/page-writeback.c
> @@ -241,7 +241,7 @@ void bdi_writeout_inc(struct backing_dev
>  }
>  EXPORT_SYMBOL_GPL(bdi_writeout_inc);
>  
> -static inline void task_dirty_inc(struct task_struct *tsk)
> +void task_dirty_inc(struct task_struct *tsk)
>  {
>  	prop_inc_single(&vm_dirties, &tsk->dirties);
>  }
> @@ -1228,6 +1228,7 @@ int __set_page_dirty_nobuffers(struct pa
>  				__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);
>  			}
>  			radix_tree_tag_set(&mapping->page_tree,
> @@ -1263,7 +1264,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage
>   * If the mapping doesn't provide a set_page_dirty a_op, then
>   * just fall through and assume that it wants buffer_heads.
>   */
> -static int __set_page_dirty(struct page *page)
> +int set_page_dirty(struct page *page)
>  {
>  	struct address_space *mapping = page_mapping(page);
>  
> @@ -1281,14 +1282,6 @@ static int __set_page_dirty(struct page
>  	}
>  	return 0;
>  }
> -
> -int set_page_dirty(struct page *page)
> -{
> -	int ret = __set_page_dirty(page);
> -	if (ret)
> -		task_dirty_inc(current);
> -	return ret;
> -}
>  EXPORT_SYMBOL(set_page_dirty);
>  
>  /*
> Index: linux-2.6/fs/buffer.c
> ===================================================================
> --- linux-2.6.orig/fs/buffer.c
> +++ linux-2.6/fs/buffer.c
> @@ -628,6 +628,7 @@ static int __set_page_dirty(struct page
>  			__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);
>  		}
>  		radix_tree_tag_set(&mapping->page_tree,


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [patch] mm: task dirty accounting fix
  2009-02-10  9:12 ` Peter Zijlstra
@ 2009-02-12  1:43   ` Nick Piggin
  0 siblings, 0 replies; 3+ messages in thread
From: Nick Piggin @ 2009-02-12  1:43 UTC (permalink / raw)
  To: Peter Zijlstra; +Cc: Linux Kernel Mailing List, YAMAMOTO Takashi, Andrew Morton

On Tue, Feb 10, 2009 at 10:12:51AM +0100, Peter Zijlstra wrote:
> On Tue, 2009-02-10 at 05:39 +0100, Nick Piggin wrote:
> > Hi,
> > 
> > This is based from an earlier patch from YAMAMOTO-san which I have
> > somewhat simplified. What do you think?
> 
> Looks nice. Was a bit surprised we never actually merged the previous
> one though..

So was I, it was always in the back of my mind because I didn't
want to lose a good fix. I was going to just resend it, but I
decided it should actually be more consistent to do this accounting
with the other ones, and the patch ended up being much smaller as
a result too.

But credit to YAMAMOTO san for the core fix.

> 
> > Thanks,
> > Nick
> > 
> > --
> > YAMAMOTO-san noticed that task_dirty_inc doesn't seem to be called properly for
> > cases where set_page_dirty is not used to dirty a page (eg. mark_buffer_dirty).
> > 
> > Additionally, there is some inconsistency about when task_dirty_inc is
> > called. It is used for dirty balancing, however it even gets called for
> > __set_page_dirty_no_writeback.
> > 
> > So rather than increment it in a set_page_dirty wrapper, move it down to
> > exactly where the dirty page accounting stats are incremented.
> > 
> > Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
> > Signed-off-by: Nick Piggin <npiggin@suse.de>
> 
> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> 
> > ---
> >  fs/buffer.c         |    1 +
> >  include/linux/mm.h  |    1 +
> >  mm/page-writeback.c |   13 +++----------
> >  3 files changed, 5 insertions(+), 10 deletions(-)
> > 
> > Index: linux-2.6/include/linux/mm.h
> > ===================================================================
> > --- linux-2.6.orig/include/linux/mm.h
> > +++ linux-2.6/include/linux/mm.h
> > @@ -1162,6 +1162,7 @@ extern int filemap_fault(struct vm_area_
> >  
> >  /* mm/page-writeback.c */
> >  int write_one_page(struct page *page, int wait);
> > +void task_dirty_inc(struct task_struct *tsk);
> >  
> >  /* readahead.c */
> >  #define VM_MAX_READAHEAD	128	/* kbytes */
> > Index: linux-2.6/mm/page-writeback.c
> > ===================================================================
> > --- linux-2.6.orig/mm/page-writeback.c
> > +++ linux-2.6/mm/page-writeback.c
> > @@ -241,7 +241,7 @@ void bdi_writeout_inc(struct backing_dev
> >  }
> >  EXPORT_SYMBOL_GPL(bdi_writeout_inc);
> >  
> > -static inline void task_dirty_inc(struct task_struct *tsk)
> > +void task_dirty_inc(struct task_struct *tsk)
> >  {
> >  	prop_inc_single(&vm_dirties, &tsk->dirties);
> >  }
> > @@ -1228,6 +1228,7 @@ int __set_page_dirty_nobuffers(struct pa
> >  				__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);
> >  			}
> >  			radix_tree_tag_set(&mapping->page_tree,
> > @@ -1263,7 +1264,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage
> >   * If the mapping doesn't provide a set_page_dirty a_op, then
> >   * just fall through and assume that it wants buffer_heads.
> >   */
> > -static int __set_page_dirty(struct page *page)
> > +int set_page_dirty(struct page *page)
> >  {
> >  	struct address_space *mapping = page_mapping(page);
> >  
> > @@ -1281,14 +1282,6 @@ static int __set_page_dirty(struct page
> >  	}
> >  	return 0;
> >  }
> > -
> > -int set_page_dirty(struct page *page)
> > -{
> > -	int ret = __set_page_dirty(page);
> > -	if (ret)
> > -		task_dirty_inc(current);
> > -	return ret;
> > -}
> >  EXPORT_SYMBOL(set_page_dirty);
> >  
> >  /*
> > Index: linux-2.6/fs/buffer.c
> > ===================================================================
> > --- linux-2.6.orig/fs/buffer.c
> > +++ linux-2.6/fs/buffer.c
> > @@ -628,6 +628,7 @@ static int __set_page_dirty(struct page
> >  			__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);
> >  		}
> >  		radix_tree_tag_set(&mapping->page_tree,

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2009-02-12  1:44 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2009-02-10  4:39 [patch] mm: task dirty accounting fix Nick Piggin
2009-02-10  9:12 ` Peter Zijlstra
2009-02-12  1:43   ` Nick Piggin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).