xfs
[Top] [All Lists]

Re: [PATCH 3/4] writeback: pay attention to wbc->nr_to_write in write_ca

To: Dave Chinner <david@xxxxxxxxxxxxx>, linux-fsdevel@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx
Subject: Re: [PATCH 3/4] writeback: pay attention to wbc->nr_to_write in write_cache_pages
From: tytso@xxxxxxx
Date: Sun, 25 Apr 2010 22:45:27 -0400
In-reply-to: <20100426024302.GC13043@xxxxxxxxx>
Mail-followup-to: tytso@xxxxxxx, Dave Chinner <david@xxxxxxxxxxxxx>, linux-fsdevel@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx
References: <1271731314-5893-1-git-send-email-david@xxxxxxxxxxxxx> <1271731314-5893-4-git-send-email-david@xxxxxxxxxxxxx> <20100425033315.GC667@xxxxxxxxx> <20100426014908.GD11437@dastard> <20100426024302.GC13043@xxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Sun, Apr 25, 2010 at 10:43:02PM -0400, tytso@xxxxxxx wrote:
> Have you tested with multiple files that are subject to writeout at
> the same time?  After all, if your I/O allocator does a great job of
> keeping the files contiguous in chunks larger tham 4MB, then if you
> have two or more files that need to be written out, the page allocator
> will round robin between the two files in 4MB chunks, and that might
> not be considered an ideal I/O pattern.

Argh.  Sorry for not proof reading better before hitting the send
key....

s/tham/than/
s/page allocator/writeback code/

                                                - Ted

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