X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (mx1.hub.org [200.46.208.251]) by postgresql.org (Postfix) with ESMTP id 3A92111F6240 for ; Wed, 26 Apr 2006 19:17:06 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.208.251]) (amavisd-new, port 10024) with ESMTP id 40655-03 for ; Wed, 26 Apr 2006 19:16:50 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey- Received: from candle.pha.pa.us (candle.pha.pa.us [70.90.9.53]) by postgresql.org (Postfix) with ESMTP id 4E5CA11F6228 for ; Wed, 26 Apr 2006 19:16:47 -0300 (ADT) Received: (from pgman@localhost) by candle.pha.pa.us (8.11.6/8.11.6) id k3QMGkk15952; Wed, 26 Apr 2006 18:16:46 -0400 (EDT) From: Bruce Momjian Message-Id: <200604262216.k3QMGkk15952@candle.pha.pa.us> Subject: Re: Large (8M) cache vs. dual-core CPUs In-Reply-To: <20060426220929.GY97354@pervasive.com> To: "Jim C. Nasby" Date: Wed, 26 Apr 2006 18:16:46 -0400 (EDT) CC: Scott Marlowe , mark@mark.mielke.cc, Bill Moran , pgsql-performance@postgresql.org X-Mailer: ELM [version 2.4ME+ PL121 (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200604/613 X-Sequence-Number: 18697 Jim C. Nasby wrote: > On Wed, Apr 26, 2006 at 10:27:18AM -0500, Scott Marlowe wrote: > > If you haven't actually run a heavy benchmark of postgresql on the two > > architectures, please don't make your decision based on other > > benchmarks. Since you've got both a D920 and an X2 3800, that'd be a > > great place to start. Mock up some benchmark with a couple dozen > > threads hitting the server at once and see if the Intel can keep up. It > > Or better yet, use dbt* or even pgbench so others can reproduce... For why Opterons are superior to Intel for PostgreSQL, see: http://techreport.com/reviews/2005q2/opteron-x75/index.x?pg=2 Section "MESI-MESI-MOESI Banana-fana...". Specifically, this part about the Intel implementation: The processor with the Invalid data in its cache (CPU 0, let's say) might then wish to modify that chunk of data, but it could not do so while the only valid copy of the data is in the cache of the other processor (CPU 1). Instead, CPU 0 would have to wait until CPU 1 wrote the modified data back to main memory before proceeding.and that takes time, bus bandwidth, and memory bandwidth. This is the great drawback of MESI. AMD transfers the dirty cache line directly from cpu to cpu. I can imaging that helping our test-and-set shared memory usage quite a bit. -- Bruce Momjian http://candle.pha.pa.us EnterpriseDB http://www.enterprisedb.com + If your life is a hard drive, Christ can be your backup. +