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
