[Linux-cluster] GFS on 2.6.8.1

[Cahill, Ben M]

> -----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	
>