[Linux-cluster] GFS on 2.6.8.1 more simple performance numbers

[Daniel Phillips]

Hi Daniel,

On Friday 15 October 2004 20:15, Daniel McNeil wrote:
> rm is 6 times slower on gfs than ext3.  Reverse scaling
> on removes happening on 2 nodes in parallel.  These are
> in separate directories, so one would not expect DLM
> conflicts.
>
> Thoughts?

With two nodes, GFS is running two journals, that's gotta hurt.  On the 
single-node tar test, GFS's monster inodes probably take a toll, but 
I'm sure it's not the whole story.

Regards,

Daniel