Thanks for the response Hannes. The db will be read only. Still looking for a response as to why cpu is so high when computations are performed on the fs. Even when single node where traffic is sent back via loopback. Can anyone answer this? Provide a solution to excessively high cpu usage? Will have to try lustre next, but would prefer to stick with gluster if this problem can be solved. Thanks. On Fri, Feb 29, 2008 at 1:47 PM, Hannes Dorbath <light@xxxxxxxxxxxxxxxxxxxx> wrote: > billy cokalopolous wrote: > > Just like mysql server causing glusterfs & glusterfsd high cpu load when > > mounted on glusterfs, 5 concurrent md5sum operations on a 300MB file > cause > > the same high cpu usage for glusterfs and glusterfsd (see below) > > Not an answer to your question, but running a database on a network file > systems is in general considered a very bad idea. Look into block level > based replication for a DBMS (DRBD, ENBD, iSCSI, AoE, FC, etc). > > > -- > Best regards, > Hannes Dorbath >
