| From: | John A Meinel <john(at)arbash-meinel(dot)com> |
|---|---|
| To: | Anjan Dave <adave(at)vantage(dot)com> |
| Cc: | Geoffrey <esoteric(at)3times25(dot)net>, Mischa Sandberg <mischa(dot)sandberg(at)telus(dot)net>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: Whence the Opterons? |
| Date: | 2005-05-09 15:40:07 |
| Message-ID: | 427F8457.6000001@arbash-meinel.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Anjan Dave wrote:
> Wasn't the context switching issue occurring in specific cases only?
>
> I haven't seen any benchmarks for a 50% performance difference. Neither
> have I seen any benchmarks of pure disk IO performance of specific
> models of Dell vs HP or Sun Opterons.
>
> Thanks,
> Anjan
>
Well, I'm speaking more from what I remember reading, than personal
testing. Probably 50% is too high, but I thought I remembered it being
more general than just specific cases.
I agree, though, that disk bandwidth is probably more important than CPU
issues, though. And the extra 15k might get you a lot of disk performance.
John
=:->
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Jim C. Nasby | 2005-05-09 16:34:23 | Re: [PERFORM] "Hash index" vs. "b-tree index" (PostgreSQL |
| Previous Message | Neil Conway | 2005-05-09 15:34:57 | Re: [PERFORM] "Hash index" vs. "b-tree index" (PostgreSQL |