From owner-freebsd-questions@freebsd.org Thu Jan 21 23:55:52 2016 Return-Path: Delivered-To: freebsd-questions@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 63FEEA8A7E5 for ; Thu, 21 Jan 2016 23:55:52 +0000 (UTC) (envelope-from mason@blisses.org) Received: from phlegethon.blisses.org (phlegethon.blisses.org [50.56.97.101]) (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 4E1C01F47 for ; Thu, 21 Jan 2016 23:55:51 +0000 (UTC) (envelope-from mason@blisses.org) Received: from blisses.org (cocytus.blisses.org [23.25.209.73]) by phlegethon.blisses.org (Postfix) with ESMTPSA id 909741493BE; Thu, 21 Jan 2016 18:55:47 -0500 (EST) Date: Thu, 21 Jan 2016 18:55:45 -0500 From: Mason Loring Bliss To: dweimer Cc: freebsd-questions@freebsd.org Subject: Re: ZFS performance help sought Message-ID: <20160121235545.GK4538@blisses.org> References: <20160121205139.GG4538@blisses.org> <20160121232810.GJ4538@blisses.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160121232810.GJ4538@blisses.org> User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 21 Jan 2016 23:55:52 -0000 On Thu, Jan 21, 2016 at 06:28:10PM -0500, Mason Loring Bliss wrote: > All that said, I wasn't setting write_limit_override, so I'm trying that, and > I'm cutting the txg.timeout back a couple seconds more. Well, that didn't help. System's still really choppy. last pid: 1707; load averages: 9.20, 4.75, 2.14 up 0+00:09:35 18:53:03 55 processes: 1 running, 54 sleeping CPU: 2.1% user, 0.0% nice, 62.6% system, 0.5% interrupt, 34.8% idle Mem: 323M Active, 331M Inact, 4589M Wired, 8928K Cache, 2677M Free ARC: 4096M Total, 916M MFU, 2303M MRU, 845M Anon, 17M Header, 15M Other Swap: 8192M Total, 8192M Free PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND 1501 root 1 33 0 42248K 3616K dmu_tx 1 0:10 5.76% zfs 1500 root 1 24 0 42248K 3768K pipewr 0 0:08 5.18% zfs Here's what I set: vfs.zfs.arc_max="4096M" vfs.zfs.arc_min="1024M" vfs.zfs.txg.timeout="3" vfs.zfs.write_limit_override="512M" I'm not seeing any obvious way to verify the write_limit_override setting - it appears not to show up in sysctl output. I'll wait for the current big transfer to finish and then I'll try it with prefetch disabled too. -- Mason Loring Bliss mason@blisses.org Ewige Blumenkraft! awake ? sleep : random() & 2 ? dream : sleep; -- Hamlet, Act III, Scene I