[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20120704132519.GA4301@gmail.com>
Date: Wed, 4 Jul 2012 21:25:20 +0800
From: Zheng Liu <gnehzuil.liu@...il.com>
To: Ric Wheeler <rwheeler@...hat.com>
Cc: Phillip Susi <psusi@...ntu.com>, Jan Kara <jack@...e.cz>,
Eric Sandeen <sandeen@...hat.com>,
Theodore Ts'o <tytso@....edu>, Fredrick <fjohnber@...o.com>,
linux-ext4@...r.kernel.org, Andreas Dilger <adilger@...ger.ca>,
wenqing.lz@...bao.com
Subject: Re: ext4_fallocate
On Wed, Jul 04, 2012 at 08:20:07AM -0400, Ric Wheeler wrote:
> On 07/03/2012 11:06 PM, Phillip Susi wrote:
> For reasonably sized files, you might just as well really write out
> the full file with "write" (do pre-allocation the old fashioned
> way).
>
> Performance of course depends on the size of the file, but for a 1GB
> file you can do this in a few seconds and prevent fragmentation and
> totally eliminate the performance of flipping extents.
>
> How large is the file you need to pre-allocate? How long does the
> job typically run (minutes? hours? days?) :)
We have over one thousand servers with ten or more 2T SATA disks, and we
need to pre-allocate a lot of files with fixed size until the space of
every disks is occupied when the application starts up on first time.
Meanwhile this number is increasing every months. It will be absolutely
a nightmare for SA if we use the old fashioned way to do pre-allocation.
Regards,
Zheng
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists