[Linux-cluster] GFS on 2.6.8.1
Cahill, Ben M
ben.m.cahill at intel.com
Tue Oct 5 15:49:09 UTC 2004
> -----Original Message-----
> From: linux-cluster-bounces at redhat.com
> [mailto:linux-cluster-bounces at redhat.com] On Behalf Of Daniel McNeil
> Sent: Friday, October 01, 2004 7:12 PM
> To: linux-cluster
> Subject: [Linux-cluster] GFS on 2.6.8.1
>
> 2. What is going on in the remove that is taking so long?
>
> With only 1 node mounting a gfs file system (3 node cluster)
> I should master all the locks.
>
> 3. If I re-ran the tar test after the remove (without umount/mount),
> the tar times were basically the same. I would have expected
> GFS to cache the free inodes and have a faster 2nd tar time.
> When does GFS stop caching the inode (and the dlm locks on the
> inodes?)
FYI, I did some experiments with OpenGFS almost a year ago, using a
similar tar/rm exercise ... I removed the journaling (retained locking),
and that improved performance significantly, especially in the case of
the rm!
I never got to the bottom of why journaling would be such a bottleneck
... Maybe Ken has some insight.
-- Ben --
Opinions are mine, not Intel's
>
> Now, on to more testing!
>
> Thanks,
>
> Daniel
>
More information about the Linux-cluster
mailing list