From owner-freebsd-database@FreeBSD.ORG Sat Jan 14 14:42:03 2006 Return-Path: X-Original-To: freebsd-database@freebsd.org Delivered-To: freebsd-database@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8935516A420 for ; Sat, 14 Jan 2006 14:42:03 +0000 (GMT) (envelope-from arne_woerner@yahoo.com) Received: from web30315.mail.mud.yahoo.com (web30315.mail.mud.yahoo.com [68.142.201.233]) by mx1.FreeBSD.org (Postfix) with SMTP id CDE9443D46 for ; Sat, 14 Jan 2006 14:42:02 +0000 (GMT) (envelope-from arne_woerner@yahoo.com) Received: (qmail 6201 invoked by uid 60001); 14 Jan 2006 14:42:02 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=Sk4zUBB5SVYo5NWxEIU788OQQyI+d+jCtnRxF6//QNNQpRWQ5ugzsm/MCPvnR00bJ+zVbBV72yVYctZYTYUG39NmVwjPF06H9rzPhkHlEpKDqiWkw2S3ZX0PMOoRPuObx4T4gFf17zVF60DcJrDrxrFQu+iWK2EodJ8p+st+G4A= ; Message-ID: <20060114144202.6199.qmail@web30315.mail.mud.yahoo.com> Received: from [213.54.74.99] by web30315.mail.mud.yahoo.com via HTTP; Sat, 14 Jan 2006 06:42:02 PST Date: Sat, 14 Jan 2006 06:42:02 -0800 (PST) From: Arne Woerner To: Slawek Zak , freebsd-performance@freebsd.org, freebsd-database@freebsd.org In-Reply-To: <787bbe1c0601140457y6de99891n86b49a728eedac94@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: Subject: Re: Horrible PostgreSQL performance with NFS X-BeenThere: freebsd-database@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Database use and development under FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 14 Jan 2006 14:42:03 -0000 --- Slawek Zak wrote: > On 1/13/06, Arne Woerner wrote: > 40MB/s. CPU load negligible. I don't have > an exact number, as this machine has other > processes running. But overall, the system > load didn't exceed 5%. > Looks good... > I saturated fast ethernet on the host > with this test. Filer is connected with > Gb and can spew around 70MB/s easily. > CPU load on the host didn't exceed 4%. > Looks even better... :-) > > 3. test the NIC performance with > Filer doesn't respond to large icmp packets. > Ok... This isn't so important, since NFS speed is higher than local disc speed. > > My theory would be, that your NICs need a > > lot of CPU time, while your local discs > > dont need so much CPU time. :-) > > I don't think so. Drivers account for system > time. It doesn't exceed 20% of overall load. > The postgres processes are very busy doing > almost nothing. Semops is most of the work > they seem to do. > Hmm... But why does switching from local disc to NFS makes the PostgreSQL performance so bad? The semops of postgres are most likely the same, since postgres would not check if it runs on NFS or local filesystems, would it? Were there any other changes? Did you do those "dd" tests with small block sizes (like 1byte: bs=1), like somebody on one of those lists suggests, too? Then we could see, if there is a high latency that ruins everything... -Arne __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com