X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id 1E7A6D1B55E for ; Wed, 17 Mar 2004 17:58:14 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 07620-06 for ; Wed, 17 Mar 2004 13:58:12 -0400 (AST) Received: from sss.pgh.pa.us (unknown [192.204.191.242]) by svr1.postgresql.org (Postfix) with ESMTP id C82B7D1B4D3 for ; Wed, 17 Mar 2004 13:58:09 -0400 (AST) Received: from sss2.sss.pgh.pa.us (tgl@localhost [127.0.0.1]) by sss.pgh.pa.us (8.12.11/8.12.11) with ESMTP id i2HHw9aq026452; Wed, 17 Mar 2004 12:58:09 -0500 (EST) To: "Rosser Schwarz" Cc: pgsql-performance@postgresql.org Subject: Re: atrocious update performance In-reply-to: <002a01c40c45$f736d8a0$2500fa0a@CardServices.TCI.com> References: <002a01c40c45$f736d8a0$2500fa0a@CardServices.TCI.com> Comments: In-reply-to "Rosser Schwarz" message dated "Wed, 17 Mar 2004 11:33:31 -0600" Date: Wed, 17 Mar 2004 12:58:09 -0500 Message-ID: <26451.1079546289@sss.pgh.pa.us> From: Tom Lane X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200403/240 X-Sequence-Number: 6096 "Rosser Schwarz" writes: >> Could you retry the strace with -r and -T options > Unlike the previous run (this is a trace of the explain), this one went > immediately. No delay. Hm. It looks like you mistakenly traced psql rather than the backend, but since the delay went away we wouldn't have learned anything anyhow. Have you got any idea what conditions may have changed between seeing delay and not seeing delay? > I also have, per Aaron's request, a trace -ct against the backend running > the explain analyze. I killed it well before "a few minutes"; it's just > shy of 900K. I don't think I'll be forwarding that on to the list, though > I can put it up on a web server somewhere easily enough. > Try . This is pretty odd too. It looks like it's doing checkpoints every so often (look for the writes to pg_control), which a backend engaged in a long-running query surely ought not be doing. Need to think about why that might be... regards, tom lane