From: | Greg Smith <greg(at)2ndquadrant(dot)com> |
---|---|
To: | Viji V Nair <viji(at)fedoraproject(dot)org> |
Cc: | nair rajiv <nair331(at)gmail(dot)com>, Andres Freund <andres(at)anarazel(dot)de>, pgsql-performance(at)postgresql(dot)org |
Subject: | Re: splitting data into multiple tables |
Date: | 2010-01-26 20:32:34 |
Message-ID: | 4B5F5162.8010607@2ndquadrant.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
Viji V Nair wrote:
> There are catches in the SAN controllers also. SAN vendors wont give
> that much information regarding their internal controller design. They
> will say they have 4 external 4G ports, you should also check how many
> internal ports they have and the how the controllers are operating,
> in Active-Active or Active- Standby mode.
Right, the SAN cache serves the same purpose as the controller cache on
direct-attached storage. I've never seen a Fiber Channel card that had
its own local cache too; doubt that's even possible. So I think of them
as basically being the same type of cache, with the primary difference
being that the transfers between the host and the cache has some latency
on it with FC compared to direct storage.
You're right that people should question the internal design too of
course. Some days I wonder if I'm in the wrong business--the people who
do SAN tuning seem to have no idea what they're doing and yet are still
expensive to hire. But this is off-topic for the question being asked here.
--
Greg Smith 2ndQuadrant Baltimore, MD
PostgreSQL Training, Services and Support
greg(at)2ndQuadrant(dot)com www.2ndQuadrant.com
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2010-01-26 20:48:28 | Re: Poor query plan across OR operator |
Previous Message | Robert Haas | 2010-01-26 19:35:07 | Re: Poor query plan across OR operator |