From owner-freebsd-hackers@FreeBSD.ORG Wed Nov 7 01:51:38 2012 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 921A41C9 for ; Wed, 7 Nov 2012 01:51:38 +0000 (UTC) (envelope-from sjg@evilcode.net) Received: from mail-ia0-f182.google.com (mail-ia0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 4C2B68FC0A for ; Wed, 7 Nov 2012 01:51:37 +0000 (UTC) Received: by mail-ia0-f182.google.com with SMTP id k10so999587iag.13 for ; Tue, 06 Nov 2012 17:51:37 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:x-gm-message-state; bh=uV/z6mSftyXZloCTXx5kfXXsn2ttzEjpZA23ClDuiiE=; b=aDg7Y/SYiFIN+6EaiRmmH7pNSEODNIpT9wns8oVaWcc9qcfzDxXNZNmKGk3YtqBt7Z +Ukoof7wnDD8GesctkiBK3MDsJ4q4zM8psHRASJeAM0/+VCDPayp2CdDeHTCbxTgTZ7a Z4/gnhLqsHzmrPCxLkwD+hqChgmzqlxSSmFEDVIWqstktcq8FUzwxW2b/MffrQa8EU7D 7S4Ji5PNM8zgDBDG6IWsVhAc7je9v00XjdhTFbJc3K2OWF4BQdbAGFDaO7Yj77NYe4I4 donw7i7+B4R6LeFjtuSkiAr9MZHYeaf0bbLfv4YRY7tF7RZmtU29mkn7P7KPT5pdZZqT N23A== MIME-Version: 1.0 Received: by 10.50.213.34 with SMTP id np2mr3148621igc.57.1352253097368; Tue, 06 Nov 2012 17:51:37 -0800 (PST) Received: by 10.64.29.3 with HTTP; Tue, 6 Nov 2012 17:51:37 -0800 (PST) In-Reply-To: <50997AB8.40607@rawbw.com> References: <50980ADD.4010402@rawbw.com> <50994FE0.2070205@rawbw.com> <50997AB8.40607@rawbw.com> Date: Tue, 6 Nov 2012 18:51:37 -0700 Message-ID: Subject: Re: pgbench performance is lagging compared to Linux and DragonflyBSD? From: "Samuel J. Greear" To: Yuri Content-Type: text/plain; charset=ISO-8859-1 X-Gm-Message-State: ALoCoQk0ZLZDowU1Gk5kgw4vSDOxTMDq1zSf7Q0wTEtw22/wrRQzxYlFctnUwKER1HhWlFxEGBON X-Mailman-Approved-At: Wed, 07 Nov 2012 04:32:23 +0000 Cc: freebsd-hackers@freebsd.org X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 07 Nov 2012 01:51:38 -0000 On Tue, Nov 6, 2012 at 2:01 PM, Yuri wrote: > On 11/06/2012 11:10, Samuel J. Greear wrote: >> >> Single and multi-socket hardware are not really directly comparable in >> PostgreSQL tests. > > > So if the CPUs are split between sockets, would such system generally > perform better or worse with PostgeSQL vs. non-split situation? > > Yuri Unless the algorithms you are testing are able to operate entirely out of the processors caches (and PostgreSQL does not fall into that category) performance will be generally lower as you add sockets. FreeBSD's ULE scheduler is aware of this and takes it into account, but the performance ULE is able to maintain across sockets (this applies to other OS's schedulers too) is more damage control than anything else. Sam