Re: Optimizer improvements: to do or not to do?

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: Ron Mayer <rm_pg(at)cheapcomplexdevices(dot)com>
Cc: Gregory Stark <stark(at)enterprisedb(dot)com>, pgsql-hackers(at)postgresql(dot)org
Subject: Re: Optimizer improvements: to do or not to do?
Date: 2006-09-13 21:38:33
Message-ID: 17246.1158183513@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

Ron Mayer <rm_pg(at)cheapcomplexdevices(dot)com> writes:
> I'm wildly guessing that, the # of pages itself seems to be
> a bigger factor than the sequential/random nature.

No, they're both important: fetching N pages in sequence is way cheaper
than fetching the same number of pages scattered all over. This is
partly because you reduce seeking at the hardware level, and partly
because sequential reads cue the kernel to do read-ahead, allowing
overlap of I/O and computation.

regards, tom lane

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Marshall, Steve 2006-09-13 21:40:51 Re: - Proposal for repreparing prepared statements
Previous Message Ron Mayer 2006-09-13 21:24:24 Re: Optimizer improvements: to do or not to do?