From owner-freebsd-fs@freebsd.org Wed Mar 2 02:51:03 2016 Return-Path: Delivered-To: freebsd-fs@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id E9D16AC00A8 for ; Wed, 2 Mar 2016 02:51:03 +0000 (UTC) (envelope-from bfriesen@simple.dallas.tx.us) Received: from smtp.simplesystems.org (smtp.simplesystems.org [65.66.246.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8DB201C71 for ; Wed, 2 Mar 2016 02:51:03 +0000 (UTC) (envelope-from bfriesen@simple.dallas.tx.us) Received: from freddy.simplesystems.org (freddy.simplesystems.org [65.66.246.65]) by smtp.simplesystems.org (8.14.4+Sun/8.14.4) with ESMTP id u222obpA020688; Tue, 1 Mar 2016 20:50:37 -0600 (CST) Date: Tue, 1 Mar 2016 20:50:37 -0600 (CST) From: Bob Friesenhahn X-X-Sender: bfriesen@freddy.simplesystems.org To: Miroslav Lachman <000.fbsd@quip.cz> cc: Steven Hartland , freebsd-fs@freebsd.org Subject: Re: abnormally high CPU load after zfs destroy In-Reply-To: <56D5CEC1.2070000@quip.cz> Message-ID: References: <56D4964D.3010604@quip.cz> <56D4B66D.4070007@multiplay.co.uk> <56D5CEC1.2070000@quip.cz> User-Agent: Alpine 2.01 (GSO 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (smtp.simplesystems.org [65.66.246.90]); Tue, 01 Mar 2016 20:50:37 -0600 (CST) X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 02 Mar 2016 02:51:04 -0000 On Tue, 1 Mar 2016, Miroslav Lachman wrote: > Steven Hartland wrote on 02/29/2016 22:21: >> Its likely churning through the actual delete, show system processes in >> top and you'll see it. > > Yes, there are about 300 kernel thread doing ZFS work, but should it really > bomb the system that way? The system is heavilly lagging for about 10 > minutes. Are there any sysctl to control this behavior? Is it possible that you enabled the dedup feature? Bob -- Bob Friesenhahn bfriesen@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/