[Linux-cluster] GFS on 2.6.8.1
David Teigland
teigland at redhat.com
Mon Oct 4 04:28:30 UTC 2004
On Fri, Oct 01, 2004 at 04:12:23PM -0700, Daniel McNeil wrote:
> I am just starting to test and did a quick untar test to
> see approximate performance of gfs compared to ext3.
> I only have gfs mounted on 1 node for this test.
> Here are the results:
>
> The command run was 'time tar xf /Views/linux-2.6.8.1.tar'
> where /Views is an NFS mounted file system and the current
> working directory is in a clean file system on a single
> disk drive.
>
> real user sys
> ext3 data=ordered 0m16.962s 0m0.552s 0m6.529s
> ext3 data=journal 0m39.599s 0m0.501s 0m5.856s
> gfs 1-node mounted 1m23.849s 0m0.890s 0m17.991s
For me, gfs is about 3 times slower than ext3-ordered here (FWIW I'm not
reading from NFS). GFS with dlm and nolock were about the same.
> The 2nd test was removing the files (time rm -rf linux-2.6.8.1/)
>
> real user sys
> ext3 data=ordered 0m1.225s 0m0.021s 0m1.048s
> ext3 data=journal 0m1.286s 0m0.024s 0m1.038s
> gfs 1-node mounted 0m49.565s 0m0.094s 0m8.191s
GFS is 5 to 6 times slower than ext3 for me on this one.
I'll let someone else give a more expert answer to your questions. I
think you'll find, though, that in the absence of contention, locking
isn't a very significant part of the fs performance. You can see this in
your test by trying both lock_dlm and lock_nolock modules.
> 1. Is GFS doing the equivalent of data=journal?
no, not by default
--
Dave Teigland <teigland at redhat.com>
More information about the Linux-cluster
mailing list