[PERFORM] Running PG on cluster files systems

[Hannes Dorbath]

GFS2, OFCS2, lustre, CXFS, GPFS, Veritas and what else there is..

..has someone experience with any of those? Is it bearable to run PG on 
them from a performance point of view? I guess not, but any positive 
reports?


Thanks

--
Regards,
Hannes Dorbath

---(end of broadcast)---
TIP 9: In versions below 8.0, the planner will ignore your desire to
  choose an index scan if your joining column's datatypes do not
  match

Re: [PERFORM] Running PG on cluster files systems

[Devrim GUNDUZ]

Hi,

On Tue, 2007-01-09 at 15:15 +0100, Hannes Dorbath wrote:
 GFS2, OFCS2, lustre, CXFS, GPFS, Veritas and what else there is..
 
 ..has someone experience with any of those? Is it bearable to run PG
 on them from a performance point of view? I guess not, but any
 positive  reports?

I have tested it on GFS (v1) and lustre. On Lustre, I saw a bit
performance problem, but I think we could bear it thinking the
advantages of Lustre.

OTOH, RHEL AS + RHEL Cluster Suite + LVM + GFS combination worked very
well, as compared to extX. I don't have benchmarks handy, BTW.

Regards,
-- 
The PostgreSQL Company - Command Prompt, Inc. 1.503.667.4564
PostgreSQL Replication, Consulting, Custom Development, 24x7 support
Managed Services, Shared and Dedicated Hosting
Co-Authors: plPHP, ODBCng - http://www.commandprompt.com/





signature.asc
Description: This is a digitally signed message part