Re: regression in page writeback

[Wu Fengguang <fengguang.wu@intel.com>]

On Wed, Sep 30, 2009 at 07:39:36AM +0800, Dave Chinner wrote:
> On Mon, Sep 28, 2009 at 10:25:24AM -0400, Chris Mason wrote:
> > On Mon, Sep 28, 2009 at 11:07:00AM +1000, Dave Chinner wrote:
> > > In the context of the setup I was talking about, I meant is that sync
> > > IO _should_ be unthrottled because it is self-throttling by it's
> > > very nature. The current code makes no differentiation between the
> > > two.
> > 
> > This isn't entirely true anymore.  WB_SYNC_ALL is turned into a sync
> > bio, which is sent down with higher priority.  There may be a few spots
> > that still need to be changed for it, but it is much better than it was.
> 
> Oh, I didn't realise that had changed - when did WRITE_SYNC_PLUG get
> introduced?

About 5 months before, when Linus complained something similar :)

        http://lkml.org/lkml/2009/4/6/114

Thanks,
Fengguang

> FWIW, I notice that __block_write_full_page(), gfs2, btrfs
> and jdb use WRITE_SYNC_PLUG to implement this, but it appears that
> filesystems that have their own writeback code (e.g. XFS) have not
> been converted (gfs2 and btrfs being the exceptions).
> 
> Oh well, something else that needs tweaking in XFS...
> 
> Cheers,
> 
> Dave.
> -- 
> Dave Chinner
> david@fromorbit.com