Re: Adding getrusage profiling data to EXPLAIN output - Mailing list pgsql-hackers

From Itagaki Takahiro
Subject Re: Adding getrusage profiling data to EXPLAIN output
Date
Msg-id AANLkTin_Le9EoBVu-eJjvaMg_vcCJVAKcfnNMCuMB3Fj@mail.gmail.com
Whole thread Raw
In response to Adding getrusage profiling data to EXPLAIN output  (Greg Stark <stark@mit.edu>)
Responses Re: Adding getrusage profiling data to EXPLAIN output
List pgsql-hackers
On Fri, Oct 1, 2010 at 9:16 AM, Greg Stark <stark@mit.edu> wrote:
> Attached is a patch to display getrusage output to EXPLAIN output.
> This is the patch I mentioned previously in
> http://archives.postgresql.org/pgsql-hackers/2010-02/msg00684.php and
> it raises the same issues we were talking about then.

How much overhead do you have with "resource" option?
getrusage() calls for each tuple might have considerable overheads.
How much difference between (analyze) and (analyze, resource) options?

Auto_explain and pg_stat_statements will be also adjusted to the change
when the patch is acceptable, I was asked for "queries ordered by CPU times"
in pg_stat_statements several times. The getrusage infrastructure will
make it a real possibility.

--
Itagaki Takahiro


pgsql-hackers by date:

Previous
From: Greg Smith
Date:
Subject: Re: Postgres vs. intel ccNUMA on Linux
Next
From: Robert Haas
Date:
Subject: Re: I: About "Our CLUSTER implementation is pessimal" patch