xfs
[Top] [All Lists]

Re: [PATCH 06/34] xfs: dynamic speculative EOF preallocation

To: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Subject: Re: [PATCH 06/34] xfs: dynamic speculative EOF preallocation
From: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Wed, 22 Dec 2010 08:42:40 +1100
Cc: xfs@xxxxxxxxxxx
In-reply-to: <20101221151511.GA26127@xxxxxxxxxxxxx>
References: <1292916570-25015-1-git-send-email-david@xxxxxxxxxxxxx> <1292916570-25015-7-git-send-email-david@xxxxxxxxxxxxx> <20101221151511.GA26127@xxxxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Tue, Dec 21, 2010 at 10:15:11AM -0500, Christoph Hellwig wrote:
> This patch causes tesr 014 to take ~ 870 seconds instead of 6, thus
> beeing almost 150 times slower on mt 32-bit test VM, so I'll have to NAK
> it for now.

It's not the speculative preallocation changes - ithey are just
exposing some other regression. That is, using MOUNT_OPTIONS="-o
allocsize=4k" gives the previous behaviour, while allocsize=512m
gives the same behaviour as the dynamic preallocation.

The dynamic behaviour is resulting in megabyte sized IOs being
issued for random 512 byte writes (which is wrong), so I'm tending
towards it being a regression caused by the reecent writeback path
changes. I'll dig deeper today.

Cheers,

Dave.
-- 
Dave Chinner
david@xxxxxxxxxxxxx

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