Re: I/O on select count(*) - Mailing list pgsql-performance

From Tom Lane
Subject Re: I/O on select count(*)
Date
Msg-id 5697.1211211478@sss.pgh.pa.us
Whole thread Raw
In response to Re: I/O on select count(*)  (Bruce Momjian <bruce@momjian.us>)
List pgsql-performance
Bruce Momjian <bruce@momjian.us> writes:
> Matthew Wakeling wrote:
>> Does it really take that long to zero out 8kB of RAM? I thought CPUs were
>> really quick at doing that!

> Yea, that was my assumption too.

You have to write the page (to be sure there is space for it on disk)
not only zero it.

This design is kind of a holdover, though, from back when we had one
ever-growing clog file.  Today I'd be inclined to think about managing
it more like pg_xlog, ie, have some background process pre-create a
whole segment file at a time.

            regards, tom lane

pgsql-performance by date:

Previous
From: Bruce Momjian
Date:
Subject: Re: I/O on select count(*)
Next
From: Greg Smith
Date:
Subject: Re: I/O on select count(*)