[Gluster-devel] how to set the default read/write block size for all transactions for optimal performance (e.g. anything similar to rsize, wsize nfs options?)

Sabuj Pattanayek sabujp at gmail.com
Mon Jul 21 05:19:01 UTC 2008


On Sun, Jul 20, 2008 at 9:56 PM, Anand Babu Periasamy <ab at gnu.org.in> wrote:
> If you got some spare time, can you also benchmark this version..
> http://ftp.zresearch.com/pub/gluster/glusterfs/1.4-qa/glusterfs-1.4.0qa29.tar.gz

It's busted. Tried to do:

df -h
cd /export/glfs/tmp
ls -l
time dd if=/dev/zero of=testFile bs=4k count=20000
dd: writing `testFile': Software caused connection abort
dd: closing output file `testFile': Transport endpoint is not connected
0.001u 0.003s 0:00.12 0.0%      0+0k 0+0io 0pf+0w

It immediately causes an EOF from peer error and then socket read
failed (Transport endpoint is not connected) in state 1 and a crash in
the glusterfs client, You can find the client and server logs in
http://structbio.vanderbilt.edu/~pattans/glfs/ .

Sabuj Pattanayek

More information about the Gluster-devel mailing list