[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.DEB.2.00.1002270550330.17433@p34.internal.lan>
Date: Sat, 27 Feb 2010 05:51:15 -0500 (EST)
From: Justin Piszcz <jpiszcz@...idpixels.com>
To: Eric Sandeen <sandeen@...hat.com>
cc: linux-ext4@...r.kernel.org, linux-kernel@...r.kernel.org,
Alan Piszcz <ap@...arrain.com>
Subject: Re: EXT4 is ~2X as slow as XFS (593MB/s vs 304MB/s) for writes?
On Sat, 27 Feb 2010, Justin Piszcz wrote:
>
>
> On Fri, 26 Feb 2010, Eric Sandeen wrote:
>
> > Eric Sandeen wrote:
> >
> > Oh, you need very recent util-linux-ng as well, and use libblkid from there
> > with:
> >
> > [e2fsprogs] # ./configure --disable-libblkid
> >
> > Otherwise you can just feed mkfs.ext4 stripe & stride manually.
> >
> > -Eric
> >
I also tried with the default chunk size (64KiB) incase ext4 had a problem
with chunk sizes > 64KiB, the results were the same for ext4, I also tried
ext2 & ext3 as well just to see what their performance would be:
p63:~# mkfs.ext2 -b 4096 -E stride=16,stripe-width=176 /dev/md0
p63:~# mount /dev/md0 /r1
p63:/r1# dd if=/dev/zero of=file bs=1M count=10240
10737418240 bytes (11 GB) copied, 19.9434 s, 538 MB/s
p63:/r1#
p63:~# mkfs.ext3 -b 4096 -E stride=16,stripe-width=176 /dev/md0
p63:~# mount /dev/md0 /r1
p63:/r1# dd if=/dev/zero of=file bs=1M count=10240
10737418240 bytes (11 GB) copied, 31.0195 s, 346 MB/s
p63:~# mkfs.ext4 -b 4096 -E stride=16,stripe-width=176 /dev/md0
p63:~# mount /dev/md0 /r1
p63:/r1# dd if=/dev/zero of=file bs=1M count=10240
10737418240 bytes (11 GB) copied, 35.3866 s, 303 MB/s
And, for comparison, XFS:
p63:~# mkfs.xfs -f /dev/md0 > /dev/null 2>&1
p63:~# mount /dev/md0 /r1
p63:~# cd /r1
p63:/r1# dd if=/dev/zero of=file bs=1M count=10240
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 18.1527 s, 592 MB/s
p63:/r1#
--
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