Re: Poor RAC inter-instance performance

From: Ivan Vasquez <ivan_at_looker.itos.uga.edu>
Date: Tue, 30 Mar 2004 09:37:32 -0500
Message-ID: <c4c0nc$hrs$1@cronkite.cc.uga.edu>

Hans,

Yes, the GB links are dedicated to this and were set up according to the Metalink instructions. cmcfg.ora has:

HeartBeat=15000
ClusterName=Oracle Cluster Manager, version 9i PollInterval=1000
MissCount=20
PrivateNodeNames=int-node1 int-node2
PublicNodeNames=node1 node2
ServicePort=9998
KernelModuleName=hangcheck-timer
CmDiskFile=/dev/raw/raw30
HostName=int-node1

/etc/hosts:

10.0.0.1        int-node1
10.0.0.2        int-node2

I also make changes to /proc in /etc/sysctl.conf for network parameters:

#Network parameters for Oracle 9i

net.core.rmem_default=262144
net.core.rmem_max=262144
net.core.wmem_default=262144
net.core.wmem_max=262144

Ivan.

"Hans Forbrich" <forbrich_at_yahoo.net> wrote in message news:oz3ac.24071$wg1.16790_at_edtnps84...
> Ivan Vasquez wrote:
>
> > I'm testing a 2-node Linux RAC installation that's performing poorly
under
> > certain circumstances. The cluster is using 1G NICs as interconnect. I
> > already know I'm not supposed to ask for great performance out of it,
> > however the interconnect's capacity is far from reached whenever I
notice
> > bad performance.
>
> I'm not there yet, so this is pure curiosity:
>
> 1) Are the 1G NICs dedicated to this?
> 2) Are you using DNS or /etc/hosts? I'd expect DNS to be slow.
>
> /Hans
Received on Tue Mar 30 2004 - 08:37:32 CST