Received: from magus.postgresql.org (magus.postgresql.org [87.238.57.229]) by mail.postgresql.org (Postfix) with ESMTP id C219C1648186 for ; Fri, 30 Mar 2012 22:11:23 -0300 (ADT) Received: from [2001:1528:137::f1] (helo=mail.gransy.com) by magus.postgresql.org with esmtp (Exim 4.72) (envelope-from ) id 1SDmqg-0005P7-Mo for pgsql-performance@postgresql.org; Sat, 31 Mar 2012 01:11:23 +0000 Received: from antispam.gransy.com (antispam.gransy.com [77.78.104.124]) by mail.gransy.com (Postfix) with ESMTP id AB47B508652 for ; Sat, 31 Mar 2012 03:11:08 +0200 (CEST) Received: from mail.gransy.com ([82.208.29.194]) by antispam.gransy.com (antispam.gransy.com [77.78.104.124]) (amavisd-new, port 10024) with ESMTP id dymKcKOt95hB for ; Sat, 31 Mar 2012 03:11:08 +0200 (CEST) Received: by mail.gransy.com (Postfix, from userid 5000) id 9A6FB508675; Sat, 31 Mar 2012 03:11:08 +0200 (CEST) Received: from [192.168.1.237] (ip-78-45-133-255.net.upcbroadband.cz [78.45.133.255]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.gransy.com (Postfix) with ESMTPSA id 68297508652 for ; Sat, 31 Mar 2012 03:11:08 +0200 (CEST) Message-ID: <4F7659AC.1000507@fuzzy.cz> Date: Sat, 31 Mar 2012 03:11:08 +0200 From: Tomas Vondra User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:11.0) Gecko/20120312 Thunderbird/11.0 MIME-Version: 1.0 To: pgsql-performance@postgresql.org Subject: Re: database slowdown while a lot of inserts occur References: <1333049228.99470.YahooMailNeo@web162801.mail.bf1.yahoo.com> In-Reply-To: <1333049228.99470.YahooMailNeo@web162801.mail.bf1.yahoo.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Host-Lookup-Failed: Reverse DNS lookup failed for 2001:1528:137::f1 (failed) X-Pg-Spam-Score: 0.3 (/) X-Archive-Number: 201203/192 X-Sequence-Number: 46642 On 29.3.2012 21:27, Bob Lunney wrote: > Lance, > > May small inserts cause frequent fsyncs. Is there any way those small > inserts can be batched into some larger sets of inserts that use copy to > perform the load? Not necessarily - fsync happens at COMMIT time, not when the INSERT is performed (unless each INSERT stands on it's own). Tomas