From owner-svn-src-head@FreeBSD.ORG Wed Jun 10 13:57:00 2009 Return-Path: Delivered-To: svn-src-head@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 379DE106567F; Wed, 10 Jun 2009 13:57:00 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42]) by mx1.freebsd.org (Postfix) with ESMTP id 03F0D8FC19; Wed, 10 Jun 2009 13:57:00 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from bigwig.baldwin.cx (66.111.2.69.static.nyinternet.net [66.111.2.69]) by cyrus.watson.org (Postfix) with ESMTPSA id A5FCB46B37; Wed, 10 Jun 2009 09:56:59 -0400 (EDT) Received: from jhbbsd.hudson-trading.com (unknown [209.249.190.8]) by bigwig.baldwin.cx (Postfix) with ESMTPA id 84E3A8A06A; Wed, 10 Jun 2009 09:56:58 -0400 (EDT) From: John Baldwin To: Dag-Erling =?utf-8?q?Sm=C3=B8rgrav?= Date: Wed, 10 Jun 2009 09:23:41 -0400 User-Agent: KMail/1.9.7 References: <200906100121.n5A1LWVO089719@svn.freebsd.org> <3c1674c90906100008i4c632312j32f223b8aca14934@mail.gmail.com> <86ljo0wgnv.fsf@ds4.des.no> In-Reply-To: <86ljo0wgnv.fsf@ds4.des.no> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Message-Id: <200906100923.42093.jhb@freebsd.org> X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.0.1 (bigwig.baldwin.cx); Wed, 10 Jun 2009 09:56:58 -0400 (EDT) X-Virus-Scanned: clamav-milter 0.95.1 at bigwig.baldwin.cx X-Virus-Status: Clean X-Spam-Status: No, score=-2.5 required=4.2 tests=AWL,BAYES_00,RDNS_NONE autolearn=no version=3.2.5 X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on bigwig.baldwin.cx Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org, Kip Macy , Dmitry Morozovsky Subject: Re: svn commit: r193878 - head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs X-BeenThere: svn-src-head@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SVN commit messages for the src tree for head/-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Jun 2009 13:57:00 -0000 On Wednesday 10 June 2009 6:02:12 am Dag-Erling Sm=C3=B8rgrav wrote: > Kip Macy writes: > > Dmitry Morozovsky writes: > > > Hmm, I failed to see how boolean prevent the usage: > > > > > > if arch=3D=3Di386 || memsize < 4G > > > =C2=A0 =C2=A0 =C2=A0 =C2=A0zfs_prefetch=3D0 > > > else > > > =C2=A0 =C2=A0 =C2=A0 =C2=A0zfs_prefetch=3D1 > > > > > > and admin can flip the switch to non-default position. > > > > > Right, what you're advocating is zfs_prefetch_non_default. Which is > > simpler, but still rather weird. >=20 > No, he's advocating zfs_prefetch_enable which is initialized to either 0 > or 1 at boot time and can be administratively set to either 0 and 1 > regardless of its initial value. I don't see the problem... Yes, you can simply do a TUNABLE_INT_FETCH() after the initial calculation = to=20 honor any user override. Many existing settings already work this way wher= e=20 the user can override the auto-tuned value (e.g. all the buffer-cache tunin= g=20 settings). =2D-=20 John Baldwin