On Mon, 2013-04-08 at 20:34 +0800, Fengguang Wu wrote:
> Hi Ben,
>
> On Sun, Apr 07, 2013 at 08:01:38PM +0100, Ben Hutchings wrote:
> > This is missing from 3.0.y and 3.2.y; should we have it?
>
> It would help 3.2.y, however not as much for 3.0.y.
>
> The background is, when the IO-less dirty throttling patches
> go upstream, there were concerns that the change set is too complex.
> So it end up being merged in two stages: v3.2 includes the core bits
> and v3.3 includes the improvement/optimization bits.
>
> This patch falls into the latter category.
It looked like a bug fix to me. The reason I ask is because commit
4adaa611020f 'Btrfs: fix race between mmap writes and compression' adds
a call to account_page_redirty() which doesn't exist in 3.2.y. I've
added these both to the patch queue now.
Ben.
> As for pre-3.2 kernels, they run the old threshold based
> balance_dirty_pages() and are not sensible to dirty accounting errors.
>
> Thanks,
> Fengguang
>
> > ---
> > From: Wu Fengguang <fengguang.wu@xxxxxxxxx>
> > Date: Mon, 8 Aug 2011 15:22:00 -0600
> > Subject: writeback: fix dirtied pages accounting on redirty
> >
> > commit 2f800fbd777b792de54187088df19a7df0251254 upstream.
> >
> > De-account the accumulative dirty counters on page redirty.
> >
> > Page redirties (very common in ext4) will introduce mismatch between
> > counters (a) and (b)
> >
> > a) NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied
> > b) NR_WRITTEN, BDI_WRITTEN
> >
> > This will introduce systematic errors in balanced_rate and result in
> > dirty page position errors (ie. the dirty pages are no longer balanced
> > around the global/bdi setpoints).
> >
> > Acked-by: Jan Kara <jack@xxxxxxx>
> > Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> > Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
> > ---
> > include/linux/writeback.h | 2 ++
> > mm/page-writeback.c | 19 +++++++++++++++++++
> > 2 files changed, 21 insertions(+)
> >
> > diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> > index 05eaf5e..b30419c 100644
> > --- a/include/linux/writeback.h
> > +++ b/include/linux/writeback.h
> > @@ -197,6 +197,8 @@ void writeback_set_ratelimit(void);
> > void tag_pages_for_writeback(struct address_space *mapping,
> > pgoff_t start, pgoff_t end);
> >
> > +void account_page_redirty(struct page *page);
> > +
> > /* pdflush.c */
> > extern int nr_pdflush_threads; /* Global so it can be exported to sysctl
> > read-only. */
> > diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> > index 5d1ef5d..96b3e7a 100644
> > --- a/mm/page-writeback.c
> > +++ b/mm/page-writeback.c
> > @@ -1825,6 +1825,24 @@ int __set_page_dirty_nobuffers(struct page *page)
> > EXPORT_SYMBOL(__set_page_dirty_nobuffers);
> >
> > /*
> > + * Call this whenever redirtying a page, to de-account the dirty counters
> > + * (NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied), so that they match the written
> > + * counters (NR_WRITTEN, BDI_WRITTEN) in long term. The mismatches will lead to
> > + * systematic errors in balanced_dirty_ratelimit and the dirty pages position
> > + * control.
> > + */
> > +void account_page_redirty(struct page *page)
> > +{
> > + struct address_space *mapping = page->mapping;
> > + if (mapping && mapping_cap_account_dirty(mapping)) {
> > + current->nr_dirtied--;
> > + dec_zone_page_state(page, NR_DIRTIED);
> > + dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
> > + }
> > +}
> > +EXPORT_SYMBOL(account_page_redirty);
> > +
> > +/*
> > * 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
> > @@ -1832,6 +1850,7 @@ EXPORT_SYMBOL(__set_page_dirty_nobuffers);
> > int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
> > {
> > wbc->pages_skipped++;
> > + account_page_redirty(page);
> > return __set_page_dirty_nobuffers(page);
> > }
> > EXPORT_SYMBOL(redirty_page_for_writepage);
> >
> >
> > --
> > Ben Hutchings
> > I'm not a reverse psychological virus. Please don't copy me into your sig.
>
>
>
--
Ben Hutchings
Klipstein's 4th Law of Prototyping and Production:
A fail-safe circuit will destroy others.
Attachment:
signature.asc
Description: This is a digitally signed message part