From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 11:28:30 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D4F791065670 for ; Wed, 27 Feb 2008 11:28:30 +0000 (UTC) (envelope-from pmurray@nevada.net.nz) Received: from bellagio.open2view.net (bellagio.open2view.net [210.48.79.75]) by mx1.freebsd.org (Postfix) with ESMTP id A298C8FC1F for ; Wed, 27 Feb 2008 11:28:30 +0000 (UTC) (envelope-from pmurray@nevada.net.nz) Received: from [10.1.1.9] (219-89-71-208.ipnets.xtra.co.nz [219.89.71.208]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) by bellagio.open2view.net (Postfix) with ESMTP id E68707F074B for ; Thu, 28 Feb 2008 00:09:12 +1300 (NZDT) Message-Id: From: Philip Murray To: freebsd-performance@freebsd.org Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (Apple Message framework v919.2) Date: Thu, 28 Feb 2008 00:09:04 +1300 X-Mailer: Apple Mail (2.919.2) Subject: Slow iSCSI performance X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 27 Feb 2008 11:28:30 -0000 Hi, I'm trying to use the new iSCSI initiator (thanks!) with 7, but I'm getting dismal performance. A simple dd will will max out at about 2MB/ sec, and untarring the likes of the ports tree is a painful task. The target is another FreeBSD 7 machine running the NetBSD target daemon from ports exporting a ZVOL from ZFS (also tried with a file on UFS). It'll start off relatively fast and then suddenly dies after a few seconds, and then eventually will start again: tty da0 da1 pass0 cpu tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy in id 0 78 63.90 494 30.80 0.00 0 0.00 0.00 0 0.00 0 0 5 2 93 0 77 63.89 575 35.90 0.00 0 0.00 0.00 0 0.00 0 0 8 3 89 0 77 63.86 581 36.26 0.00 0 0.00 0.00 0 0.00 0 0 5 4 91 0 77 63.64 268 16.64 0.00 0 0.00 0.00 0 0.00 0 0 3 2 95 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 0 100 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 0 100 The two hosts are connected with GbE, and iperf can saturate it without trouble (~987Mb/sec in both directions). Any ideas where to start looking for the culprit? Cheers Phil