Re: Scalability fo Batch Operations in RAC

So the overhead associated with communication between two nodes is 50%? Sounds like bad scaling, but we've seen it worse :) We need the wait-profile, not the blocking and interconnect information.

Best regards,

Mogens

Ravi_Kulkarni_at_Dell.com wrote:

> Sriram,
>
> Are you using Parallelism (are you seeing parallel slaves being
> spawned on node 2 as seen in gv$px_session when batch job is
> running) ? DB /Table/index level ?
> Try rerunning load by turning off Parallelism at each level.
>
> Remember, default DOP (degree of parallelism) is a function of #
> instances, cpu_count and few parallel% parameters.
>
>
> Thanks,
> Ravi.
>
> ------------------------------------------------------------------------
> *From:* oracle-l-bounce_at_freelists.org
> [mailto:oracle-l-bounce_at_freelists.org] *On Behalf Of *Sriram Kumar
> *Sent:* Monday, December 26, 2005 9:50 AM
> *To:* ORACLE-L
> *Subject:* Scalability fo Batch Operations in RAC
>
> Hi Gurus,
>
> We are running a heavy batch operation of a banking application on
> RAC. Say the configuration is a 2 node 4 CPU Itanium2 box running
> 9.2.0.4 .

--
http://www.freelists.org/webpage/oracle-l