Re: Optimizer improvements: to do or not to do? - Mailing list pgsql-hackers

From Tom Lane
Subject Re: Optimizer improvements: to do or not to do?
Date
Msg-id 17246.1158183513@sss.pgh.pa.us
Whole thread Raw
In response to Re: Optimizer improvements: to do or not to do?  (Ron Mayer <rm_pg@cheapcomplexdevices.com>)
List pgsql-hackers
Ron Mayer <rm_pg@cheapcomplexdevices.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


pgsql-hackers by date:

Previous
From: Ron Mayer
Date:
Subject: Re: Optimizer improvements: to do or not to do?
Next
From: "Marshall, Steve"
Date:
Subject: Re: - Proposal for repreparing prepared statements