Re: How much expensive are row level statistics?

From: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
To: Michael Fuhr <mike(at)fuhr(dot)org>
Cc: Merlin Moncure <merlin(dot)moncure(at)rcsonline(dot)com>, pgsql-performance(at)postgresql(dot)org, Carlos Benkendorf <carlosbenkendorf(at)yahoo(dot)com(dot)br>
Subject: Re: How much expensive are row level statistics?
Date: 2005-12-13 03:20:45
Message-ID: 1667.1134444045@sss.pgh.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers pgsql-patches pgsql-performance

Michael Fuhr <mike(at)fuhr(dot)org> writes:
> Further tests show that for this application
> the killer is stats_command_string, not stats_block_level or
> stats_row_level.

I tried it with pgbench -c 10, and got these results:
41% reduction in TPS rate for stats_command_string
9% reduction in TPS rate for stats_block/row_level (any combination)

strace'ing a backend confirms my belief that stats_block/row_level send
just one stats message per transaction (at least for the relatively
small number of tables touched per transaction by pgbench). However
stats_command_string sends 14(!) --- there are seven commands per
pgbench transaction and each results in sending a <command> message and
later an <IDLE> message.

Given the rather lackadaisical way in which the stats collector makes
the data available, it seems like the backends are being much too
enthusiastic about posting their stats_command_string status
immediately. Might be worth thinking about how to cut back the
overhead by suppressing some of these messages.

regards, tom lane

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Jim C. Nasby 2005-12-13 03:39:46 Re: [GENERAL] missing something obvious about intervals?
Previous Message Andrew Dunstan 2005-12-13 03:12:41 Re: 7.3 failure on platypus

Browse pgsql-patches by date

  From Date Subject
Next Message Simon Riggs 2005-12-13 22:31:29 Re: Inherited Constraints
Previous Message Michael Fuhr 2005-12-13 01:07:51 Re: How much expensive are row level statistics?

Browse pgsql-performance by date

  From Date Subject
Next Message Tom Lane 2005-12-13 04:17:51 Re: Memory Leakage Problem
Previous Message Michael Fuhr 2005-12-13 01:07:51 Re: How much expensive are row level statistics?