xfs
[Top] [All Lists]

Re: [PATCH 26/27] xfs: cleanup I/O-related buffer flags

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: [PATCH 26/27] xfs: cleanup I/O-related buffer flags
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Wed, 6 Jul 2011 05:11:18 -0400
Cc: xfs@xxxxxxxxxxx
In-reply-to: <20110706035411.GU1026@dastard>
References: <20110701094321.936534538@xxxxxxxxxxxxxxxxxxxxxx> <20110701094607.536262104@xxxxxxxxxxxxxxxxxxxxxx> <20110706035411.GU1026@dastard>
User-agent: Mutt/1.5.21 (2010-09-15)
On Wed, Jul 06, 2011 at 01:54:11PM +1000, Dave Chinner wrote:
> Is it worthwhile tagging all these as READ_META and WRITE_META?
> Though that probably needs to be done as a separate commit...

Right now they preempt synchronous writes, which is not something we
want.  There is a patch out on lkml removing that hack, at which point
we should tag them as _META to make blktrace output more useful.

> >  /* flags used only internally */
> > -#define _XBF_PAGES (1 << 18)/* backed by refcounted pages */
> > -#define    _XBF_RUN_QUEUES (1 << 19)/* run block device task queue */
> > -#define    _XBF_KMEM       (1 << 20)/* backed by heap memory */
> > -#define _XBF_DELWRI_Q      (1 << 21)/* buffer on delwri queue */
> > +#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */
> > +#define    _XBF_KMEM       (1 << 21)/* backed by heap memory */
> > +#define _XBF_DELWRI_Q      (1 << 22)/* buffer on delwri queue */
> 
> Might be worthwhile cleaning up the stray tab before _XBF_KMEM
> there.

done.

<Prev in Thread] Current Thread [Next in Thread>