From owner-freebsd-geom@FreeBSD.ORG Sun Dec 2 07:38:34 2012 Return-Path: Delivered-To: freebsd-geom@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 6439FED2 for ; Sun, 2 Dec 2012 07:38:34 +0000 (UTC) (envelope-from mgrooms@shrew.net) Received: from mx2.shrew.net (mx2.shrew.net [38.97.5.132]) by mx1.freebsd.org (Postfix) with ESMTP id 2D24A8FC0C for ; Sun, 2 Dec 2012 07:38:33 +0000 (UTC) Received: from mail.shrew.net (mail1.shrew.prv [10.22.203.23]) by mx2.shrew.net (8.14.5/8.14.5) with ESMTP id qB27JTR7052408 for ; Sun, 2 Dec 2012 01:19:29 -0600 (CST) (envelope-from mgrooms@shrew.net) Received: from [10.22.200.30] (cpe-70-113-194-94.austin.res.rr.com [70.113.194.94]) by mail.shrew.net (Postfix) with ESMTPSA id 6D0CE181C1 for ; Sun, 2 Dec 2012 01:19:31 -0600 (CST) Message-ID: <50BB010A.5070306@shrew.net> Date: Sun, 02 Dec 2012 01:19:38 -0600 From: Matthew Grooms User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:16.0) Gecko/20121026 Thunderbird/16.0.2 MIME-Version: 1.0 To: freebsd-geom@FreeBSD.org Subject: 9.1-RC3 GEOM gate stalls ... Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.7 (mx2.shrew.net [10.22.203.22]); Sun, 02 Dec 2012 01:19:29 -0600 (CST) X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 02 Dec 2012 07:38:34 -0000 All, I was attempting to run some performance tests against a block device exported from one host to another using ggated/ggatec. After starting bonnie++ on a ufs formatted mount, the process appears to stall at the 'Reading intelligently' stage. The ggated process appears to respond to requests quickly enough ( from looking at the network traffic between ggatec ggated ), so I suspect ggatec is causing the delay. The issue appears to be simple to re-produce: 1) Export a block device using ggated 2) Import the device using ggatec 3) Format the device using newfs 4) Mount the formatted filesystem 5) Run bonnie++ on the mounted filesystem Is this a known issue? Thanks, -Matthew