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 D79ABD1CAB1 for ; Fri, 30 Apr 2004 03:34:45 -0300 (ADT) 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 55501-06 for ; Fri, 30 Apr 2004 03:34:26 -0300 (ADT) Received: from gpdnet.co.uk (gpdnet.plus.com [212.56.100.243]) by svr1.postgresql.org (Postfix) with ESMTP id EBC7DD1CA4F for ; Fri, 30 Apr 2004 03:34:23 -0300 (ADT) Received: from gary (unverified [192.168.1.2]) by gpdnet.co.uk (SurgeMail 1.8g3) with ESMTP id 326 for ; Fri, 30 Apr 2004 07:33:52 +0100 From: "Gary Doades" To: pgsql-performance@postgresql.org Date: Fri, 30 Apr 2004 07:33:11 +0100 MIME-Version: 1.0 Subject: Re: planner/optimizer question Message-ID: <40920137.13806.16F37CC5@localhost> In-reply-to: <17898.1083280669@sss.pgh.pa.us> References: <200404291354.33304.josh@agliodbs.com> X-mailer: Pegasus Mail for Windows (v4.12a) Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT Content-description: Mail message body X-Server: High Performance Mail Server - http://surgemail.com X-Virus-Scanned: by amavisd-new at postgresql.org X-Spam-Status: No, hits=0.0 tagged_above=0.0 required=5.0 tests= X-Spam-Level: X-Archive-Number: 200404/522 X-Sequence-Number: 6822 On 29 Apr 2004 at 19:17, Tom Lane wrote: > Josh Berkus writes: > > Certainly the fact that MSSQL is essentially a single-user database makes > > things easier for them. > > Our recent testing (cf the "Xeon" thread) says that the interlocking we > do to make the world safe for multiple backends has a fairly high cost > (at least on some hardware) compared to the rest of the work in > scenarios where you are doing zero-I/O scans of data already in memory. > Especially so for index scans. I'm not sure this completely explains > the differential that Gary is complaining about, but it could be part of > it. Is it really true that MSSQL doesn't support concurrent operations? > > regards, tom lane As far as I am aware SQLSever supports concurrent operations. It certainly creates more threads for each connection. None of my observations of the system under load (50 ish concurrent users, 150 ish connections) suggest that it is serializing queries. These tests are currentl on single processor Athlon XP 2000+ systems. Regards, Gary.