From owner-freebsd-performance@FreeBSD.ORG Mon Apr 28 01:54:57 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DA8E737B405 for ; Mon, 28 Apr 2003 01:54:57 -0700 (PDT) Received: from limes.kompakt.com.pl (limes.kompakt.com.pl [195.164.48.229]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0051243FD7 for ; Mon, 28 Apr 2003 01:54:53 -0700 (PDT) (envelope-from ryba@kompakt.pl) Received: (from root@localhost) by limes.kompakt.com.pl (8.11.6/8.11.2) id h3S89Ws09431 for freebsd-performance@freebsd.org.AVP; Mon, 28 Apr 2003 10:09:32 +0200 Received: from ryba.kompakt.pl (finis.kompakt.com.pl [195.164.48.227]) by limes.kompakt.com.pl (8.11.6/8.11.2) with ESMTP id h3S89VA09427 for ; Mon, 28 Apr 2003 10:09:31 +0200 From: Piotr Rybicki Organization: Kompakt To: freebsd-performance@freebsd.org Date: Mon, 28 Apr 2003 10:54:48 +0200 User-Agent: KMail/1.5.1 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-2" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200304281054.48976.ryba@kompakt.pl> Subject: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 28 Apr 2003 08:54:58 -0000 Hi everyone. In man tuning(7) we read, that swap size should be about 2x main memmory size. Why swap size should be so big? Isn't swap size equal to main memmory size enough? Ok, if we have a very large amount (and total size) of processes, then larger swap could be desired. But i'm afraid we would end-up having swap-machine not a server. Also swap size has no impact on system tables sizes. Assuming we have MAXUSERS set to 0 (auto-scale), the value is calculated only by ammount of physical memmory size (and of course page size, but i assume it's constant). Shouldn't the section in man tuning(7) about swap size be changed, or am i missing something? Regards Piotr Rybicki From owner-freebsd-performance@FreeBSD.ORG Mon Apr 28 14:14:24 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 58A9137B404 for ; Mon, 28 Apr 2003 14:14:24 -0700 (PDT) Received: from mail.gmx.net (pop.gmx.net [213.165.65.60]) by mx1.FreeBSD.org (Postfix) with SMTP id 24CF943FBD for ; Mon, 28 Apr 2003 14:14:23 -0700 (PDT) (envelope-from michaelnottebrock@gmx.net) Received: (qmail 750 invoked by uid 65534); 28 Apr 2003 21:14:20 -0000 Received: from pD90032F7.dip.t-dialin.net (EHLO kiste.my.domain) (217.0.50.247) by mail.gmx.net (mp010-rz3) with SMTP; 28 Apr 2003 23:14:20 +0200 From: Michael Nottebrock To: freebsd-performance@freebsd.org Date: Mon, 28 Apr 2003 23:14:21 +0200 User-Agent: KMail/1.5.1 References: <200304281054.48976.ryba@kompakt.pl> In-Reply-To: <200304281054.48976.ryba@kompakt.pl> MIME-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg=pgp-sha1; boundary="Boundary-02=_umZr+BxWq6mXRZU"; charset="iso-8859-2" Content-Transfer-Encoding: 7bit Message-Id: <200304282314.22236.michaelnottebrock@gmx.net> Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 28 Apr 2003 21:14:24 -0000 --Boundary-02=_umZr+BxWq6mXRZU Content-Type: text/plain; charset="iso-8859-2" Content-Transfer-Encoding: quoted-printable Content-Description: signed data Content-Disposition: inline On Monday 28 April 2003 10:54, Piotr Rybicki wrote: > Hi everyone. > > In man tuning(7) we read, that swap size should be about 2x main memmory > size. Why swap size should be so big? Isn't swap size equal to main memmo= ry > size enough? IMHO the swapsize=3D2x phys. mem size has always been just a rule of thumb.= You=20 need as much swap as you need (doh). But so far, the memory requirements of= =20 software have pretty much grown proportionally with the availibility /=20 affordability of bigger sticks of memory and thus the rule of thumb still=20 makes sense. YMMV. =2D-=20 Regards, Michael Nottebrock --Boundary-02=_umZr+BxWq6mXRZU Content-Type: application/pgp-signature Content-Description: signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (FreeBSD) iD8DBQA+rZmuXhc68WspdLARAhjFAKCmnenqs1EQgJRujtsw0buvBcuy+gCeIX3c AderGVxnKPgED8qCyVRkKRU= =xscJ -----END PGP SIGNATURE----- --Boundary-02=_umZr+BxWq6mXRZU-- From owner-freebsd-performance@FreeBSD.ORG Tue Apr 29 00:29:12 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D7A4337B401 for ; Tue, 29 Apr 2003 00:29:12 -0700 (PDT) Received: from trinity.webmatic.de (trinity.webmatic.de [212.78.99.4]) by mx1.FreeBSD.org (Postfix) with ESMTP id CBF1A43F85 for ; Tue, 29 Apr 2003 00:29:11 -0700 (PDT) (envelope-from tk@webmatic.de) Received: from tarpit.webmatic.de (tarpit.webmatic.de [212.78.101.46]) by trinity.webmatic.de (Postfix) with ESMTP id 4CB8BF7AD for ; Tue, 29 Apr 2003 09:29:10 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by localhost.webmatic.de (Postfix) with ESMTP id 56B681526F for ; Tue, 29 Apr 2003 09:29:09 +0200 (CEST) Received: from tarpit.webmatic.de ([127.0.0.1]) by localhost (tarpit.webmatic.de [127.0.0.1:10024]) (amavisd-new) with ESMTP id 82402-08 for ; Tue, 29 Apr 2003 09:28:57 +0200 (CEST) Message-ID: <3EAE2AB9.4030408@webmatic.de> Date: Tue, 29 Apr 2003 09:33:13 +0200 From: "Thomas Krause (Webmatic)" User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.3) Gecko/20030312 X-Accept-Language: de-de, en-us, en MIME-Version: 1.0 To: freebsd-performance@freebsd.org Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new Subject: apache2 tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 29 Apr 2003 07:29:13 -0000 Hello, I want to build a new webserver (dual xeon with 4 GB RAM). The server provides mostly dynamic php-pages. In the ports Makefile there are compile option like WITH_THREADS and WITH_MPM (which includes WITH_THREADS). These are useful options for a production machine? Also, is it useful to compile the kernel with ACCEPT_FILTER_DATA and ACCEPT_FILTER_HTTP? And if yes, is apache compiled with accept filter by default? Kind regards, Thomas. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 05:44:02 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4448737B401 for ; Wed, 30 Apr 2003 05:44:02 -0700 (PDT) Received: from bluhayz.homeunix.org (ip68-106-103-50.nv.nv.cox.net [68.106.103.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5CA2E43FE3 for ; Wed, 30 Apr 2003 05:44:01 -0700 (PDT) (envelope-from dero@bluhayz.homeunix.org) Received: (from nobody@localhost) by bluhayz.homeunix.org (8.11.3/8.11.3) id h3UCjaT06061; Wed, 30 Apr 2003 08:45:36 -0400 (EDT) (envelope-from dero@bluhayz.homeunix.org) From: agent dero X-Authentication-Warning: bluhayz.homeunix.org: nobody set sender to dero@bluhayz.homeunix.org using -f Received: from 172.178.229.216 (SquirrelMail authenticated user dero) by bluhayz.homeunix.org with HTTP; Wed, 30 Apr 2003 08:45:35 -0400 (EDT) Message-ID: <3045.172.178.229.216.1051706735.squirrel@bluhayz.homeunix.org> Date: Wed, 30 Apr 2003 08:45:35 -0400 (EDT) To: freebsd-performance@freebsd.org User-Agent: SquirrelMail/1.4.0 MIME-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 X-Priority: 3 Importance: Normal Subject: FBSD 5 & SMP X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 12:44:02 -0000 I was reading the FBSD 5.0 release notes, and how the new version has better support for multiple processors. I haven't been able to find any a 4.x-STABLE SMP support docs. Does this mean that 4.7, my current release, doesn't support the multiple processors well. I am rebuilding my small business' server, and trying to decide if a dual processor will be the better way to go, but not sure if the advantages are going to be huge with the. I read the previous message about WITH_THREADS as a ports option, but the ports maximizing the dual CPUs isn't my greatest, I need the kernel itself to maximize the CPUs. Is this possible under any of the stable releases, before 5.0 ?? prost, agent dero From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 05:57:14 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9649C37B401 for ; Wed, 30 Apr 2003 05:57:14 -0700 (PDT) Received: from otter3.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id B071B43FCB for ; Wed, 30 Apr 2003 05:57:13 -0700 (PDT) (envelope-from anderson@centtech.com) Received: from centtech.com (electron.centtech.com [204.177.173.173]) by otter3.centtech.com (8.12.3/8.12.3) with ESMTP id h3UCvB56078882; Wed, 30 Apr 2003 07:57:11 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <3EAFC81D.4070808@centtech.com> Date: Wed, 30 Apr 2003 07:57:01 -0500 From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; Linux i386; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: agent dero References: <3045.172.178.229.216.1051706735.squirrel@bluhayz.homeunix.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org Subject: Re: FBSD 5 & SMP X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 12:57:15 -0000 agent dero wrote: > I was reading the FBSD 5.0 release notes, and how the new version has > better support for multiple processors. I haven't been able to find any a > 4.x-STABLE SMP support docs. Does this mean that 4.7, my current release, > doesn't support the multiple processors well. I am rebuilding my small > business' server, and trying to decide if a dual processor will be the > better way to go, but not sure if the advantages are going to be huge with > the. I read the previous message about WITH_THREADS as a ports option, but > the ports maximizing the dual CPUs isn't my greatest, I need the kernel > itself to maximize the CPUs. Is this possible under any of the stable > releases, before 5.0 ?? Yes, FreeBSD versions prior to 5.0 have SMP support, however 5.0's support is more "finely tuned" and will give you better results. However, since this sounds like a production server, you may want to stick with 4.8-RELEASE, and built a new kernel with SMP support. Depending on what you are using the machine for, you may or may not see a performance benefit of a dual processor machine. What's the machine's primary function? Eric -- ------------------------------------------------------------------ Eric Anderson Systems Administrator Centaur Technology Attitudes are contagious, is yours worth catching? ------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 06:06:00 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 84EE737B401 for ; Wed, 30 Apr 2003 06:06:00 -0700 (PDT) Received: from smtp-relay2.barrysworld.com (smtp-relay2.barrysworld.com [213.221.172.236]) by mx1.FreeBSD.org (Postfix) with ESMTP id 723B943FE5 for ; Wed, 30 Apr 2003 06:05:59 -0700 (PDT) (envelope-from killing@barrysworld.com) Received: from [213.221.181.50] (helo=barrysworld.com) by smtp-relay2.barrysworld.com with esmtp (Exim 4.12) id 19ArGw-00072P-00; Wed, 30 Apr 2003 14:05:18 +0100 Received: from vader [212.135.219.179] by barrysworld.com with ESMTP (SMTPD32-7.15) id AAB0145E026C; Wed, 30 Apr 2003 14:08:00 +0100 Message-ID: <017101c30f19$2414fc60$b3db87d4@vader> From: "Steven Hartland" To: "Eric Anderson" , "agent dero" References: <3045.172.178.229.216.1051706735.squirrel@bluhayz.homeunix.org> <3EAFC81D.4070808@centtech.com> Date: Wed, 30 Apr 2003 14:05:14 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1158 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1165 cc: freebsd-performance@freebsd.org Subject: Re: FBSD 5 & SMP X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: Steven Hartland List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 13:06:01 -0000 Im not sure it depends on the machine and the apps being run. We have been running 5.0-RELEASE on all or production machines after we did a soke test and found no issues at all in our environment. What would be interesting to know though is if 4.8 + Hyperthreading + SMP out performed 5.0 SMP as it doesn't have Hyperthreading support. Any one know if 5.0 has Hyperthreading in CURRENT? Steve ----- Original Message ----- From: "Eric Anderson" To: "agent dero" Cc: Sent: Wednesday, April 30, 2003 1:57 PM Subject: Re: FBSD 5 & SMP > agent dero wrote: > > I was reading the FBSD 5.0 release notes, and how the new version has > > better support for multiple processors. I haven't been able to find any a > > 4.x-STABLE SMP support docs. Does this mean that 4.7, my current release, > > doesn't support the multiple processors well. I am rebuilding my small > > business' server, and trying to decide if a dual processor will be the > > better way to go, but not sure if the advantages are going to be huge with > > the. I read the previous message about WITH_THREADS as a ports option, but > > the ports maximizing the dual CPUs isn't my greatest, I need the kernel > > itself to maximize the CPUs. Is this possible under any of the stable > > releases, before 5.0 ?? > > Yes, FreeBSD versions prior to 5.0 have SMP support, however 5.0's > support is more "finely tuned" and will give you better results. > However, since this sounds like a production server, you may want to > stick with 4.8-RELEASE, and built a new kernel with SMP support. > Depending on what you are using the machine for, you may or may not see > a performance benefit of a dual processor machine. > > What's the machine's primary function? > > Eric > > > -- > ------------------------------------------------------------------ > Eric Anderson Systems Administrator Centaur Technology > Attitudes are contagious, is yours worth catching? > ------------------------------------------------------------------ > > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" > From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 06:16:25 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2717F37B401 for ; Wed, 30 Apr 2003 06:16:25 -0700 (PDT) Received: from otter3.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5091543FEA for ; Wed, 30 Apr 2003 06:16:24 -0700 (PDT) (envelope-from anderson@centtech.com) Received: from centtech.com (electron.centtech.com [204.177.173.173]) by otter3.centtech.com (8.12.3/8.12.3) with ESMTP id h3UDGK56080076; Wed, 30 Apr 2003 08:16:20 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <3EAFCC9A.1080003@centtech.com> Date: Wed, 30 Apr 2003 08:16:10 -0500 From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; Linux i386; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Steven Hartland References: <3045.172.178.229.216.1051706735.squirrel@bluhayz.homeunix.org> <3EAFC81D.4070808@centtech.com> <017101c30f19$2414fc60$b3db87d4@vader> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org cc: agent dero Subject: Re: FBSD 5 & SMP X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 13:16:25 -0000 I would be using 5.0 on my newest production machine if the NFS serving worked.. :( Steven Hartland wrote: > Im not sure it depends on the machine and the apps being run. > We have been running 5.0-RELEASE on all or production > machines after we did a soke test and found no issues at all > in our environment. What would be interesting to know though > is if 4.8 + Hyperthreading + SMP out performed 5.0 SMP > as it doesn't have Hyperthreading support. Any one know if > 5.0 has Hyperthreading in CURRENT? > > Steve > ----- Original Message ----- > From: "Eric Anderson" > To: "agent dero" > Cc: > Sent: Wednesday, April 30, 2003 1:57 PM > Subject: Re: FBSD 5 & SMP > > > >>agent dero wrote: >> >>>I was reading the FBSD 5.0 release notes, and how the new version has >>>better support for multiple processors. I haven't been able to find any a >>>4.x-STABLE SMP support docs. Does this mean that 4.7, my current release, >>>doesn't support the multiple processors well. I am rebuilding my small >>>business' server, and trying to decide if a dual processor will be the >>>better way to go, but not sure if the advantages are going to be huge with >>>the. I read the previous message about WITH_THREADS as a ports option, but >>>the ports maximizing the dual CPUs isn't my greatest, I need the kernel >>>itself to maximize the CPUs. Is this possible under any of the stable >>>releases, before 5.0 ?? >> >>Yes, FreeBSD versions prior to 5.0 have SMP support, however 5.0's >>support is more "finely tuned" and will give you better results. >>However, since this sounds like a production server, you may want to >>stick with 4.8-RELEASE, and built a new kernel with SMP support. >>Depending on what you are using the machine for, you may or may not see >>a performance benefit of a dual processor machine. >> >>What's the machine's primary function? >> >>Eric >> >> >>-- >>------------------------------------------------------------------ >>Eric Anderson Systems Administrator Centaur Technology >>Attitudes are contagious, is yours worth catching? >>------------------------------------------------------------------ >> >>_______________________________________________ >>freebsd-performance@freebsd.org mailing list >>http://lists.freebsd.org/mailman/listinfo/freebsd-performance >>To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" >> > > > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" -- ------------------------------------------------------------------ Eric Anderson Systems Administrator Centaur Technology Attitudes are contagious, is yours worth catching? ------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 14:50:47 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D849437B401 for ; Wed, 30 Apr 2003 14:50:47 -0700 (PDT) Received: from mail.ubergeeks.com (lorax.ubergeeks.com [209.145.65.55]) by mx1.FreeBSD.org (Postfix) with ESMTP id CEDC943F85 for ; Wed, 30 Apr 2003 14:50:44 -0700 (PDT) (envelope-from adrian+freebsd-perf@ubergeeks.com) Received: from mail.ubergeeks.com (localhost [127.0.0.1]) by mail.ubergeeks.com (8.12.8p1/8.12.8) with ESMTP id h3ULoh0D060249; Wed, 30 Apr 2003 17:50:43 -0400 (EDT) (envelope-from adrian+freebsd-perf@ubergeeks.com) Received: from localhost (adrian@localhost)h3ULohoW060246; Wed, 30 Apr 2003 17:50:43 -0400 (EDT) (envelope-from adrian+freebsd-perf@ubergeeks.com) X-Authentication-Warning: lorax.ubergeeks.com: adrian owned process doing -bs Date: Wed, 30 Apr 2003 17:50:43 -0400 (EDT) From: Adrian Filipi-Martin Sender: adrian@ubergeeks.com To: Michael Nottebrock In-Reply-To: <200304282314.22236.michaelnottebrock@gmx.net> Message-ID: <20030430174616.E59039@lorax.ubergeeks.com> References: <200304281054.48976.ryba@kompakt.pl> <200304282314.22236.michaelnottebrock@gmx.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: freebsd-performance@freebsd.org Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 21:50:48 -0000 On Mon, 28 Apr 2003, Michael Nottebrock wrote: > On Monday 28 April 2003 10:54, Piotr Rybicki wrote: > > Hi everyone. > > > > In man tuning(7) we read, that swap size should be about 2x main memmory > > size. Why swap size should be so big? Isn't swap size equal to main memmory > > size enough? > > IMHO the swapsize=2x phys. mem size has always been just a rule of thumb. You > need as much swap as you need (doh). But so far, the memory requirements of > software have pretty much grown proportionally with the availibility / > affordability of bigger sticks of memory and thus the rule of thumb still > makes sense. YMMV. > > -- > Regards, > Michael Nottebrock It used to mean something. 1x for swapping (whole processes) and 1x for paging (just pages of a process). Each portion was used for exactly one purpose. This is no longer a valid reason though. IIRC, it is because FreeBSD has a unified buffer cache. I don't know if there are any other reasons for 2x. I don't bothe with more than 1x personally, if that much. Swap space is really there for emergencies only IMHO. Adrian -- [ adrian@ubergeeks.com ] From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 16:00:23 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DD27937B420 for ; Wed, 30 Apr 2003 16:00:23 -0700 (PDT) Received: from postal2.lbl.gov (postal2.lbl.gov [131.243.248.26]) by mx1.FreeBSD.org (Postfix) with ESMTP id 08A2543FA3 for ; Wed, 30 Apr 2003 16:00:22 -0700 (PDT) (envelope-from j_guojun@lbl.gov) Received: from postal2.lbl.gov (localhost [127.0.0.1]) by postal2.lbl.gov (8.12.9/8.12.9) with ESMTP id h3UN0LCW007426 for ; Wed, 30 Apr 2003 16:00:21 -0700 (PDT) Received: from lbl.gov (gracie.lbl.gov [131.243.2.175]) by postal2.lbl.gov (8.12.9/8.12.9) with ESMTP id h3UN0L1b007423; Wed, 30 Apr 2003 16:00:21 -0700 (PDT) Sender: jin@lbl.gov Message-ID: <3EB05582.297F50AE@lbl.gov> Date: Wed, 30 Apr 2003 16:00:18 -0700 From: "Jin Guojun [DSD]" X-Mailer: Mozilla 4.76 [en] (X11; U; FreeBSD 4.7-RELEASE i386) X-Accept-Language: zh, zh-CN, en MIME-Version: 1.0 To: Adrian Filipi-Martin References: <200304281054.48976.ryba@kompakt.pl> <20030430174616.E59039@lorax.ubergeeks.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Content-Filtered-By: Mailman/MimeDel 2.1.1 cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 23:00:24 -0000 Adrian Filipi-Martin wrote: > On Mon, 28 Apr 2003, Michael Nottebrock wrote: > > > On Monday 28 April 2003 10:54, Piotr Rybicki wrote: > > > Hi everyone. > > > > > > In man tuning(7) we read, that swap size should be about 2x main memmory > > > size. Why swap size should be so big? Isn't swap size equal to main memmory > > > size enough? > > > > IMHO the swapsize=2x phys. mem size has always been just a rule of thumb. You > > need as much swap as you need (doh). But so far, the memory requirements of > > software have pretty much grown proportionally with the availibility / > > affordability of bigger sticks of memory and thus the rule of thumb still > > makes sense. YMMV. > > > > -- > > Regards, > > Michael Nottebrock > > It used to mean something. 1x for swapping (whole processes) and > 1x for paging (just pages of a process). Each portion was used for exactly > one purpose. This is no longer a valid reason though. IIRC, it is because > FreeBSD has a unified buffer cache. > > I don't know if there are any other reasons for 2x. I don't bothe > with more than 1x personally, if that much. Swap space is really there for > emergencies only IMHO. > > Adrian This was a simple math for large process swap. If you have big processes that take the all available memory (95%), how do you swap them? You need to swap out one to a disk space that has 95% memory size, where there other one must reside on another disk space having the same size. 95% x 2 = 190% --> 200% That is the only reason for 2X, so two big process can be swapped. The original SWAP space was 2.5x, because the 0.5x was for backing up other small processes in case there are two big processes running. What is the best size? It really depends on the maximum total memory needed for all possible applications the machine will run. Theoretically, it can be zero if it is your desktop machine that never runs out of memory. This is the best performance you can get. Or, it can be as big as you need (tuning says "If you do not have a lot of RAM, though ...") if (1) no money to buy more RAM, (2) no slot to put more RAM or (3) it is a server just favor by every user to run their programs. Swap space is prepared for too many processes outrunning the RAM. It is not for improving performance, but exchange cost of disk for RAM. More swap space required means that more swap time means slow. Compare 256MB RAM + 512MB SWAP with 512 MB RAM + 0 SWAP, I think the later works better because if two processes cannot coexist in 512 MB RAM, they will not run on a 256MB system simultaneously any way. Summary: If you have a lot of memory and you are able to control all processes not to overrun the system memory, 0.5 - 1x swap is OK; you need some swap space to back up yourself in case something happens. That is why 2x is recommended; but not required if this is not a server. For server, 2x may be required, and typically 2.5x is needed. -- ------------ Jin Guojun ----------- v --- j_guojun@lbl.gov --- Distributed Systems Department http://www.itg.lbl.gov/~jin M/S 50B-2239 Ph#:(510) 486-7531 Fax: 486-6363 Lawrence Berkeley National Laboratory, Berkeley, CA 94720 From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 16:19:07 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 71FD337B404 for ; Wed, 30 Apr 2003 16:19:07 -0700 (PDT) Received: from stork.mail.pas.earthlink.net (stork.mail.pas.earthlink.net [207.217.120.188]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8177F43FBF for ; Wed, 30 Apr 2003 16:19:06 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0429.cvx40-bradley.dialup.earthlink.net ([216.244.43.174] helo=mindspring.com) by stork.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19B0qm-0007er-00; Wed, 30 Apr 2003 16:18:57 -0700 Message-ID: <3EB05944.B66F13D@mindspring.com> Date: Wed, 30 Apr 2003 16:16:20 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Adrian Filipi-Martin References: <200304281054.48976.ryba@kompakt.pl> <20030430174616.E59039@lorax.ubergeeks.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a420d75dc81dcda64c9ebf8e47e13f47b33ca473d225a0f487350badd9bab72f9c350badd9bab72f9c cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 23:19:07 -0000 Adrian Filipi-Martin wrote: > On Mon, 28 Apr 2003, Michael Nottebrock wrote: > > On Monday 28 April 2003 10:54, Piotr Rybicki wrote: > > > In man tuning(7) we read, that swap size should be about 2x main memmory > > > size. Why swap size should be so big? Isn't swap size equal to main memmory > > > size enough? > > > > IMHO the swapsize=2x phys. mem size has always been just a rule of thumb. You > > need as much swap as you need (doh). But so far, the memory requirements of > > software have pretty much grown proportionally with the availibility / > > affordability of bigger sticks of memory and thus the rule of thumb still > > makes sense. YMMV. > > It used to mean something. 1x for swapping (whole processes) and > 1x for paging (just pages of a process). Each portion was used for exactly > one purpose. This is no longer a valid reason though. IIRC, it is because > FreeBSD has a unified buffer cache. > > I don't know if there are any other reasons for 2x. I don't bothe > with more than 1x personally, if that much. Swap space is really there for > emergencies only IMHO. 1) Memory overcommit Because memory can be overcommitted, as of BSD's adoption of the Mach VM, the amount of swap that's recommended has grown. 2) Aggressive caching Because FreeBSD aggressively caches data, it would prefer to swap out dirty pages which have not been used for a long time, than to throw away clean pages that have been used recenty. Historical implementations would throw away clean pages to avoid swapping, and only when they were out of them, would they actually start swapping (or when a clean page was faulted in very recently). The amount of recommended swap is higher because of this, as the more swap you have, the better your cache locality, and the better this policy operates. So it's grown from "as much swap as you feel you need" to "as much swap as you have RAM" to "1.5 times RAM" to "2x RAM". All in all, it's just a rule of thumb; however, there are some consequences to not following it, for each time things have changed, the consequences get more and more dire. 8-). This is why people don't give much creedence to the people who are trying to run without swap; we're willing to help them track down things that make it impossible, but we recognize that just because something's possible doesn't mean it's a good idea. -- Terry From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 16:21:44 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2B97137B401 for ; Wed, 30 Apr 2003 16:21:44 -0700 (PDT) Received: from seattlefenix.net (seattlefenix.net [216.231.34.252]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8BAC143F3F for ; Wed, 30 Apr 2003 16:21:43 -0700 (PDT) (envelope-from roo@seattlefenix.net) Received: by seattlefenix.net (Postfix, from userid 1001) id 965D3B25C; Wed, 30 Apr 2003 16:15:22 -0700 (PDT) Date: Wed, 30 Apr 2003 16:15:22 -0700 From: Benjamin Krueger To: "Jin Guojun [DSD]" Message-ID: <20030430231522.GO11702@surreal.seattlefenix.net> References: <200304281054.48976.ryba@kompakt.pl> <20030430174616.E59039@lorax.ubergeeks.com> <3EB05582.297F50AE@lbl.gov> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3EB05582.297F50AE@lbl.gov> User-Agent: Mutt/1.4i cc: Adrian Filipi-Martin cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: Benjamin Krueger List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 23:21:44 -0000 * Jin Guojun [DSD] (j_guojun@lbl.gov) [030430 15:54]: > > Summary: > If you have a lot of memory and you are able to control all processes > not to overrun the system memory, 0.5 - 1x swap is OK; you need some > swap space to back up yourself in case something happens. > That is why 2x is recommended; but not required if this is not a server. > > For server, 2x may be required, and typically 2.5x is needed. In what instance can you expect to have server processes that are ok to page to disk? Maybe I'm wrong, but I've always considered a server that is paging my important processes to disk a broken server in need of ram. -- Benjamin Krueger From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 16:32:14 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B93AD37B401 for ; Wed, 30 Apr 2003 16:32:14 -0700 (PDT) Received: from walter.dfmm.org (walter.dfmm.org [209.151.233.240]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3DBD343F85 for ; Wed, 30 Apr 2003 16:32:14 -0700 (PDT) (envelope-from jason@shalott.net) Received: (qmail 24497 invoked by uid 1000); 30 Apr 2003 23:32:10 -0000 Received: from localhost (sendmail-bs@127.0.0.1) by localhost with SMTP; 30 Apr 2003 23:32:10 -0000 Date: Wed, 30 Apr 2003 16:32:09 -0700 (PDT) From: Jason Stone X-X-Sender: To: In-Reply-To: <3EB05582.297F50AE@lbl.gov> Message-ID: <20030430162823.I4074-100000@walter> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 23:32:15 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 > If you have a lot of memory and you are able to control all processes > not to overrun the system memory, 0.5 - 1x swap is OK; you need some > swap space to back up yourself in case something happens. That is why > 2x is recommended; but not required if this is not a server. > > For server, 2x may be required, and typically 2.5x is needed. Also remember that crash-dumps get written to swap, so if you want to be able to take a dump in the event of a panic, you need at least as much swap as physical ram. Since crash-dumps are usually a good idea (or at least the ability to take a dump if your system starts acting strangely), I think you should never have less than 1x ram on a production system. -Jason -------------------------------------------------------------------------- Freud himself was a bit of a cold fish, and one cannot avoid the suspicion that he was insufficiently fondled when he was an infant. -- Ashley Montagu -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (FreeBSD) Comment: See https://private.idealab.com/public/jason/jason.gpg iD8DBQE+sFz6swXMWWtptckRAsFIAJ47vP344lTYuN4fP5w0/kosWbEz1wCdG1i6 NprsPd0En9cOzYjOL3scKXE= =Zxe3 -----END PGP SIGNATURE----- From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 16:52:34 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2A29E37B401 for ; Wed, 30 Apr 2003 16:52:34 -0700 (PDT) Received: from meitner.wh.uni-dortmund.de (meitner.wh.Uni-Dortmund.DE [129.217.129.133]) by mx1.FreeBSD.org (Postfix) with ESMTP id 69BC443F75 for ; Wed, 30 Apr 2003 16:52:33 -0700 (PDT) (envelope-from michaelnottebrock@gmx.net) Received: from lofi.dyndns.org (pc2-105.intern.meitner [10.3.12.105]) by meitner.wh.uni-dortmund.de (Postfix) with ESMTP id C3C0B167788 for ; Thu, 1 May 2003 01:47:44 +0200 (CEST) Received: from kiste.my.domain (kiste.my.domain [192.168.8.4]) (authenticated bits=0) by lofi.dyndns.org (8.12.6p2/8.12.6) with ESMTP id h3UNqU4X043899 (version=TLSv1/SSLv3 cipher=RC4-MD5 bits=128 verify=NO) for ; Thu, 1 May 2003 01:52:31 +0200 (CEST) (envelope-from michaelnottebrock@gmx.net) From: Michael Nottebrock To: freebsd-performance@freebsd.org Date: Thu, 1 May 2003 01:52:29 +0200 User-Agent: KMail/1.5.1 References: <200304281054.48976.ryba@kompakt.pl> <3EB05582.297F50AE@lbl.gov> <20030430231522.GO11702@surreal.seattlefenix.net> In-Reply-To: <20030430231522.GO11702@surreal.seattlefenix.net> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200305010152.30062.michaelnottebrock@gmx.net> X-Virus-Scanned: by amavisd-new Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2003 23:52:34 -0000 On Thursday 01 May 2003 01:15, Benjamin Krueger wrote: > In what instance can you expect to have server processes that are ok to > page to disk? Almost every machine has some mostly dormant server processes which can be paged out (for example sshd's on web-servers). Sticking so much memory into a machine that nothing at all will be paged out although there are lots of processes which are idle for long amounts of time is really a waste of money. Paging is a good thing. :) -- Regards, Michael Nottebrock From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 17:04:13 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 522A237B405 for ; Wed, 30 Apr 2003 17:04:13 -0700 (PDT) Received: from 66-162-33-178.gen.twtelecom.net (66-162-33-181.gen.twtelecom.net [66.162.33.181]) by mx1.FreeBSD.org (Postfix) with ESMTP id 842D043FBD for ; Wed, 30 Apr 2003 17:04:12 -0700 (PDT) (envelope-from steve@expertcity.com) Received: from [10.4.2.41] (helo=expertcity.com) by 66-162-33-178.gen.twtelecom.net with esmtp (Exim 3.22 #4) id 19B1Ya-000756-00; Wed, 30 Apr 2003 17:04:12 -0700 Message-ID: <3EB0647B.3040506@expertcity.com> Date: Wed, 30 Apr 2003 17:04:11 -0700 From: Steve Francis User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.4a) Gecko/20030401 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Jason Stone References: <20030430162823.I4074-100000@walter> In-Reply-To: <20030430162823.I4074-100000@walter> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 00:04:13 -0000 Actually, from man dumpon: The size of the specified dump device must be at least 64 KB greater than the size of physical memory. We just got bit by this - 1G of ram, and we had 1 G of swap. Just a bit shy... Jason Stone wrote: >Also remember that crash-dumps get written to swap, so if you want to be >able to take a dump in the event of a panic, you need at least as much >swap as physical ram. > >Since crash-dumps are usually a good idea (or at least the ability to take >a dump if your system starts acting strangely), I think you should never >have less than 1x ram on a production system. > > > -Jason > > -------------------------------------------------------------------------- > Freud himself was a bit of a cold fish, and one cannot avoid the suspicion > that he was insufficiently fondled when he was an infant. > -- Ashley Montagu >-----BEGIN PGP SIGNATURE----- >Version: GnuPG v1.2.1 (FreeBSD) >Comment: See https://private.idealab.com/public/jason/jason.gpg > >iD8DBQE+sFz6swXMWWtptckRAsFIAJ47vP344lTYuN4fP5w0/kosWbEz1wCdG1i6 >NprsPd0En9cOzYjOL3scKXE= >=Zxe3 >-----END PGP SIGNATURE----- > >_______________________________________________ >freebsd-performance@freebsd.org mailing list >http://lists.freebsd.org/mailman/listinfo/freebsd-performance >To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" > > From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 17:24:39 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 28C2637B401 for ; Wed, 30 Apr 2003 17:24:39 -0700 (PDT) Received: from heron.mail.pas.earthlink.net (heron.mail.pas.earthlink.net [207.217.120.189]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8B44B43FBF for ; Wed, 30 Apr 2003 17:24:38 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0055.cvx22-bradley.dialup.earthlink.net ([209.179.198.55] helo=mindspring.com) by heron.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19B1sF-0005Pz-00; Wed, 30 Apr 2003 17:24:32 -0700 Message-ID: <3EB0685D.B88C7D3C@mindspring.com> Date: Wed, 30 Apr 2003 17:20:45 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Benjamin Krueger References: <200304281054.48976.ryba@kompakt.pl> <3EB05582.297F50AE@lbl.gov> <20030430231522.GO11702@surreal.seattlefenix.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a46442b4a032ab4b4ebc99b4a4fc62c29ca2d4e88014a4647c350badd9bab72f9c350badd9bab72f9c cc: Adrian Filipi-Martin cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 00:24:39 -0000 Benjamin Krueger wrote: > * Jin Guojun [DSD] (j_guojun@lbl.gov) [030430 15:54]: > > For server, 2x may be required, and typically 2.5x is needed. > > In what instance can you expect to have server processes that are ok to > page to disk? Maybe I'm wrong, but I've always considered a server that > is paging my important processes to disk a broken server in need of ram. When your boss won't buy you more hardware, and expects you to do your job anyway, and your job involves deploying services on the available machinery. As long as the processing load, when swap is included, doesn't impact user-visible performance, it probably doesn't matter if you are swapping or not. So I'm going to say there's a fair bit of distance between "user experience broken", "organization broken", and "server broken", with "server broken" being last in line... 8-). -- Terry From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 17:36:13 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F299237B404 for ; Wed, 30 Apr 2003 17:36:12 -0700 (PDT) Received: from postal2.lbl.gov (postal2.lbl.gov [131.243.248.26]) by mx1.FreeBSD.org (Postfix) with ESMTP id 43BFA43F85 for ; Wed, 30 Apr 2003 17:36:12 -0700 (PDT) (envelope-from j_guojun@lbl.gov) Received: from postal2.lbl.gov (localhost [127.0.0.1]) by postal2.lbl.gov (8.12.9/8.12.9) with ESMTP id h410aACY011694 for ; Wed, 30 Apr 2003 17:36:11 -0700 (PDT) Received: from lbl.gov (gracie.lbl.gov [131.243.2.175]) by postal2.lbl.gov (8.12.9/8.12.9) with ESMTP id h410a81b011685; Wed, 30 Apr 2003 17:36:08 -0700 (PDT) Sender: jin@lbl.gov Message-ID: <3EB06BF6.CD475@lbl.gov> Date: Wed, 30 Apr 2003 17:36:06 -0700 From: "Jin Guojun [DSD]" X-Mailer: Mozilla 4.76 [en] (X11; U; FreeBSD 4.7-RELEASE i386) X-Accept-Language: zh, zh-CN, en MIME-Version: 1.0 To: Jason Stone References: <20030430162823.I4074-100000@walter> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 00:36:13 -0000 Jason Stone wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > > If you have a lot of memory and you are able to control all processes > > not to overrun the system memory, 0.5 - 1x swap is OK; you need some > > swap space to back up yourself in case something happens. That is why > > 2x is recommended; but not required if this is not a server. > > > > For server, 2x may be required, and typically 2.5x is needed. > > Also remember that crash-dumps get written to swap, so if you want to be > able to take a dump in the event of a panic, you need at least as much > swap as physical ram. > > Since crash-dumps are usually a good idea (or at least the ability to take > a dump if your system starts acting strangely), I think you should never > have less than 1x ram on a production system. > > -Jason In fact, becareful when enabling crash dump on a large RAM system, which is very bad idea, in recent practice. I used a 1GB RAM system to do kernel development, when panic, each KB takes 1-2 second to dump, and it also takes similar amout of time to do the savecore when system is up. crash dump on 1 GB memory system takes average 2000 second to complete :-( Recently, we upgraded all major systems to 4 GB RAM since RAM is cheap, the crash dump will take 8000 second to complete according to 1GB dump rate. So, this is the lesson we learnt to use only 64-128 MB RAM system to do kernel development due to crash dump issue, since developing kernel does not need a lot of memory. In this case, you do need a lot of swap since RAM is small. -Jin From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 18:45:12 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1285637B404 for ; Wed, 30 Apr 2003 18:45:12 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id F3C0743FCB for ; Wed, 30 Apr 2003 18:45:09 -0700 (PDT) (envelope-from dgilbert@velocet.ca) Received: from trooper.velocet.ca (trooper.velocet.net [216.138.242.2]) by sabre.velocet.net (Postfix) with ESMTP id E920C13824A; Wed, 30 Apr 2003 21:45:07 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id 992817478C; Wed, 30 Apr 2003 21:45:07 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id AC3CF567609; Wed, 30 Apr 2003 21:45:03 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16048.31775.642709.140262@canoe.velocet.net> Date: Wed, 30 Apr 2003 21:45:03 -0400 To: "Jin Guojun [DSD]" In-Reply-To: <3EB05582.297F50AE@lbl.gov> References: <200304281054.48976.ryba@kompakt.pl> <20030430174616.E59039@lorax.ubergeeks.com> <3EB05582.297F50AE@lbl.gov> X-Mailer: VM 7.07 under 21.1 (patch 14) "Cuyahoga Valley" XEmacs Lucid cc: Adrian Filipi-Martin cc: freebsd-performance@freebsd.org cc: Michael Nottebrock Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 01:45:12 -0000 >>>>> "Jin" == Jin Guojun <[DSD]" > writes: Jin> not have a lot of RAM, though ...") if (1) no money to buy more Jin> RAM, (2) no slot to put more RAM or (3) it is a server just favor Jin> by every user to run their programs. Jin> Swap space is prepared for too many processes outrunning the RAM. Jin> It is not for improving performance, but exchange cost of disk Jin> for RAM. More swap space required means that more swap time Jin> means slow. Another thing working in favour of 2x swap is that disk has been becoming that much cheaper. With 1G and 2G disks, I was carefully considering the 256M of swap (2x 128M of memory) that I configured. With disks of 80G and more, I have been putting 1G of swap on every spindle I install because it really doesn't make a difference and I'd rather have 4x 1G swap partitions spread across spindles than only one 4G partition. That's not to claim that I have 2G of RAM (I actually have 1G), but disk space in general has become amazingly cheap. Dave. -- ============================================================================ |David Gilbert, Velocet Communications. | Two things can only be | |Mail: dgilbert@velocet.net | equal if and only if they | |http://daveg.ca | are precisely opposite. | =========================================================GLO================ From owner-freebsd-performance@FreeBSD.ORG Wed Apr 30 23:25:45 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C44EC37B401 for ; Wed, 30 Apr 2003 23:25:45 -0700 (PDT) Received: from hotmail.com (bay1-f75.bay1.hotmail.com [65.54.245.75]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5881D43F75 for ; Wed, 30 Apr 2003 23:25:45 -0700 (PDT) (envelope-from rob_macgregor@hotmail.com) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Wed, 30 Apr 2003 23:25:45 -0700 Received: from 80.192.46.45 by by1fd.bay1.hotmail.msn.com with HTTP; Thu, 01 May 2003 06:25:44 GMT X-Originating-IP: [80.192.46.45] X-Originating-Email: [rob_macgregor@hotmail.com] From: "Rob MacGregor" To: freebsd-performance@freebsd.org Date: Thu, 01 May 2003 06:25:44 +0000 Mime-Version: 1.0 Content-Type: text/plain; format=flowed Message-ID: X-OriginalArrivalTime: 01 May 2003 06:25:45.0253 (UTC) FILETIME=[7F629550:01C30FAA] Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: KEEP_TRAFFIC_ON_THE_LIST@dev.null List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 06:25:46 -0000 >From: Terry Lambert > >So it's grown from "as much swap as you feel you need" to "as much >swap as you have RAM" to "1.5 times RAM" to "2x RAM". > >All in all, it's just a rule of thumb; however, there are some >consequences to not following it, for each time things have >changed, the consequences get more and more dire. 8-). > >This is why people don't give much creedence to the people who >are trying to run without swap; we're willing to help them track >down things that make it impossible, but we recognize that just >because something's possible doesn't mean it's a good idea. So you're suggesting that if I've got 16 GB of RAM I should have 32 GB of swap? That's an entire hard disk *just* for swap (though from a performance viewpoint, that's not bad). What about systems with even more RAM? I agree that having nowhere to store crash dumps is a Bad Thing. However there will be cases where that tradeoff is worth not having a swap device. In my own case at home I have a FreeBSD (4.8) system without any swap. I run without swap because the "disk" is a CompactFlash device - using that for swap wouldn't be smart. Then there's the issue of diskless systems where it's not possible to have swap. Please DO NOT send me ANY email directly unless it's a privacy issue. Reply-to mangled to assist those who don't read the above. -- Rob | What part of "no" was it you didn't understand? _________________________________________________________________ Overloaded with spam? With MSN 8, you can filter it out http://join.msn.com/?page=features/junkmail&pgmarket=en-gb&XAPID=32&DI=1059 From owner-freebsd-performance@FreeBSD.ORG Thu May 1 02:35:05 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 03BAB37B401 for ; Thu, 1 May 2003 02:35:05 -0700 (PDT) Received: from arthur.nitro.dk (port324.ds1-khk.adsl.cybercity.dk [212.242.113.79]) by mx1.FreeBSD.org (Postfix) with ESMTP id 52B3843FB1 for ; Thu, 1 May 2003 02:35:04 -0700 (PDT) (envelope-from simon@arthur.nitro.dk) Received: by arthur.nitro.dk (Postfix, from userid 1000) id DEEFE10BF86; Thu, 1 May 2003 11:35:02 +0200 (CEST) Date: Thu, 1 May 2003 11:35:02 +0200 From: "Simon L. Nielsen" To: freebsd-performance@freebsd.org Message-ID: <20030501093501.GA393@nitro.dk> References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="/9DWx/yDrRhgMJTb" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.4i Subject: Re: SWAP size X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 01 May 2003 09:35:05 -0000 --/9DWx/yDrRhgMJTb Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 2003.05.01 06:25:44 +0000, Rob MacGregor wrote: > Then there's the issue of diskless systems where it's not possible to hav= e=20 > swap. Actually it is with swap over NFS, but that's another story :) --=20 Simon L. Nielsen --/9DWx/yDrRhgMJTb Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (FreeBSD) iD8DBQE+sOpF8kocFXgPTRwRAvsTAKDDm9gZVU4OVbHVZ9OTYa3p7LFH7ACeN3y2 7w/2FJNwckq+PElwxRC4TuI= =Mg8c -----END PGP SIGNATURE----- --/9DWx/yDrRhgMJTb-- From owner-freebsd-performance@FreeBSD.ORG Thu May 1 17:29:26 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 408C937B401 for ; Thu, 1 May 2003 17:29:26 -0700 (PDT) Received: from bluhayz.homeunix.org (ip68-106-103-50.nv.nv.cox.net [68.106.103.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 60D2E43F3F for ; Thu, 1 May 2003 17:29:25 -0700 (PDT) (envelope-from dero@bluhayz.homeunix.org) Received: from bluhayz.homeunix.org (localhost [127.0.0.1]) h420UjiD000365 for ; Thu, 1 May 2003 20:30:45 -0400 (EDT) (envelope-from dero@bluhayz.homeunix.org) Received: from localhost (dero@localhost)h420UjQX000362 for ; Thu, 1 May 2003 20:30:45 -0400 (EDT) Date: Thu, 1 May 2003 20:30:44 -0400 (EDT) From: User DERO To: freebsd-performance@freebsd.org In-Reply-To: <20030501190036.1111A37B401@hub.freebsd.org> Message-ID: <20030501202719.W356@bluhayz.homeunix.org> References: <20030501190036.1111A37B401@hub.freebsd.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: Re: freebsd-performance Digest, Vol 3, Issue 1 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 00:29:26 -0000 Ok, a whole lot of talk about swapping and all, but any of you who have seen a new computer magazine knows that even common desktop PCs are capable of a couple GB of RAM. SO, if I am building a high powered desktop, or a medium sized server. With between 2-4GB of RAM, should I be partitioning my precious server space with a 4-10GB partition of SWAP? Since it is a large load LAN server, with about 2GB of RAM, should I have a good 5GB SWAP partition. And another question, since buying a couple gigs of RAM upfront isn't an option, but adding on later is, can FreeBSD handle a multiple GB SwapFile? prost, agent dero From owner-freebsd-performance@FreeBSD.ORG Thu May 1 18:00:58 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9206637B401 for ; Thu, 1 May 2003 18:00:58 -0700 (PDT) Received: from pintail.mail.pas.earthlink.net (pintail.mail.pas.earthlink.net [207.217.120.122]) by mx1.FreeBSD.org (Postfix) with ESMTP id DFEE943FAF for ; Thu, 1 May 2003 18:00:57 -0700 (PDT) (envelope-from doveclaw@earthlink.net) Received: from user-1120ir3.dsl.mindspring.com ([66.32.75.99] helo=[192.168.0.100]) by pintail.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 19BOv3-0003m2-00 for freebsd-performance@freebsd.org; Thu, 01 May 2003 18:00:57 -0700 From: Doveclaw To: freebsd-performance@freebsd.org Content-Type: text/plain Organization: Message-Id: <1051822879.5947.3.camel@amdbox.horizon2.net> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.2.4 Date: 01 May 2003 21:01:19 +0000 Content-Transfer-Encoding: 7bit Subject: Re: freebsd-performance Digest, Vol 3, Issue X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 01:00:58 -0000 I'm not really sure why the idea of having so much swap is taken to be so absurd or even expensive. I would think, if you could afford 2-4gb of ram you could afford buying a few extra gigs or an extra hd for swap. I'm not saying I would do this myself, it just seems like theres been a whole lot of strange reactions to the practice. 4GB of some kind of DDR SDRAM costs somewhere around a grand.. 8GB of hard drive space is nothing in comparison. On Fri, 2003-05-02 at 00:30, User DERO wrote: > Ok, a whole lot of talk about swapping and all, but any of you who have > seen a new computer magazine knows that even common desktop PCs are > capable of a couple GB of RAM. SO, if I am building a high powered > desktop, or a medium sized server. With between 2-4GB of RAM, should I be > partitioning my precious server space with a 4-10GB partition of SWAP? > Since it is a large load LAN server, with about 2GB of RAM, should I have > a good 5GB SWAP partition. > And another question, since buying a couple gigs of RAM upfront isn't an > option, but adding on later is, can FreeBSD handle a multiple GB SwapFile? > > prost, > agent dero > > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Thu May 1 18:01:28 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 90D0837B401 for ; Thu, 1 May 2003 18:01:28 -0700 (PDT) Received: from puffin.mail.pas.earthlink.net (puffin.mail.pas.earthlink.net [207.217.120.139]) by mx1.FreeBSD.org (Postfix) with ESMTP id 10C9743F85 for ; Thu, 1 May 2003 18:01:28 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0223.cvx40-bradley.dialup.earthlink.net ([216.244.42.223] helo=mindspring.com) by puffin.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19BOvV-0006qp-00; Thu, 01 May 2003 18:01:26 -0700 Message-ID: <3EB1C059.2BF994B7@mindspring.com> Date: Thu, 01 May 2003 17:48:25 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: User DERO References: <20030501190036.1111A37B401@hub.freebsd.org> <20030501202719.W356@bluhayz.homeunix.org> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a471bbe19c0c546b4a2f85523bb5f8e5a62601a10902912494350badd9bab72f9c350badd9bab72f9c cc: freebsd-performance@freebsd.org Subject: Re: freebsd-performance Digest, Vol 3, Issue 1 X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 01:01:28 -0000 User DERO wrote: > Ok, a whole lot of talk about swapping and all, but any of you who have > seen a new computer magazine knows that even common desktop PCs are > capable of a couple GB of RAM. SO, if I am building a high powered > desktop, or a medium sized server. With between 2-4GB of RAM, should I be > partitioning my precious server space with a 4-10GB partition of SWAP? No,you shopuld be swapping to a fileint FS that gets expanded automatically, as needed, just like Windows and MacOS X. Too bad it's not supported, and too bad that, if it was, the overhead would be too high because there's not VOP to get the FS block offsets, so you would have to go trouh the FS code to swap, and it would be much, much slower. > Since it is a large load LAN server, with about 2GB of RAM, should I have > a good 5GB SWAP partition. > And another question, since buying a couple gigs of RAM upfront isn't an > option, but adding on later is, can FreeBSD handle a multiple GB SwapFile? Yes, sort of. Swap gets page mappings, and the total of all page mappings is 4G on Intel (32 bit) architectures. -- Terry From owner-freebsd-performance@FreeBSD.ORG Thu May 1 18:04:59 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 71F8037B401 for ; Thu, 1 May 2003 18:04:59 -0700 (PDT) Received: from puffin.mail.pas.earthlink.net (puffin.mail.pas.earthlink.net [207.217.120.139]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0956143F93 for ; Thu, 1 May 2003 18:04:59 -0700 (PDT) (envelope-from tlambert2@mindspring.com) Received: from pool0223.cvx40-bradley.dialup.earthlink.net ([216.244.42.223] helo=mindspring.com) by puffin.mail.pas.earthlink.net with asmtp (SSLv3:RC4-MD5:128) (Exim 3.33 #1) id 19BOyq-0007Jt-00; Thu, 01 May 2003 18:04:53 -0700 Message-ID: <3EB1C112.DB934186@mindspring.com> Date: Thu, 01 May 2003 17:51:30 -0700 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Doveclaw References: <1051822879.5947.3.camel@amdbox.horizon2.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-ELNK-Trace: b1a02af9316fbb217a47c185c03b154d40683398e744b8a471bbe19c0c546b4a941ab26813d6dc952601a10902912494350badd9bab72f9c350badd9bab72f9c cc: freebsd-performance@freebsd.org Subject: Re: freebsd-performance Digest, Vol 3, Issue X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 01:04:59 -0000 Doveclaw wrote: > I'm not really sure why the idea of having so much swap is taken to be > so absurd or even expensive. I would think, if you could afford 2-4gb of > ram you could afford buying a few extra gigs or an extra hd for swap. > I'm not saying I would do this myself, it just seems like theres been a > whole lot of strange reactions to the practice. 4GB of some kind of DDR > SDRAM costs somewhere around a grand.. 8GB of hard drive space is > nothing in comparison. Old People. It's the same reason that people think 8% of a 120GB hard drive is "a lot of space" and refuse to set their free reserve on their FS's high enough to avoid fragmentation. -- Terry From owner-freebsd-performance@FreeBSD.ORG Thu May 1 18:17:28 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 303A137B401 for ; Thu, 1 May 2003 18:17:28 -0700 (PDT) Received: from isber.ucsb.edu (research.isber.ucsb.edu [128.111.147.5]) by mx1.FreeBSD.org (Postfix) with ESMTP id A86C343FBF for ; Thu, 1 May 2003 18:17:27 -0700 (PDT) (envelope-from randall@isber.ucsb.edu) Received: from research.isber.ucsb.edu ([128.111.147.5]) by isber.ucsb.edu with esmtp (Exim 3.36 #2) id 19BPAw-000LP7-00; Thu, 01 May 2003 18:17:22 -0700 Date: Thu, 1 May 2003 18:17:22 -0700 (PDT) From: randall ehren To: Terry Lambert In-Reply-To: <3EB1C112.DB934186@mindspring.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Scanner: exiscan *19BPAw-000LP7-00*KkHN1FmbyoI* (ISBER - Institute for Social, Behavioral, and Economic Research) cc: Doveclaw cc: freebsd-performance@freebsd.org Subject: Re: freebsd-performance Digest, Vol 3, Issue X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 01:17:28 -0000 > It's the same reason that people think 8% of a 120GB hard drive > is "a lot of space" and refuse to set their free reserve on their > FS's high enough to avoid fragmentation. what do you mean by "set their free reserve"? i've picked up on not letting filesystems get beyond 90% full but have not heard about setting a free reserve. -randall -- :// randall s. ehren :// voice 805.893.5632 :// systems administrator :// isber|survey|avss.ucsb.edu :// institute for social, behavioral, and economic research From owner-freebsd-performance@FreeBSD.ORG Thu May 1 19:08:44 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0DDC837B401 for ; Thu, 1 May 2003 19:08:44 -0700 (PDT) Received: from meitner.wh.uni-dortmund.de (meitner.wh.Uni-Dortmund.DE [129.217.129.133]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1F3C843FBD for ; Thu, 1 May 2003 19:08:43 -0700 (PDT) (envelope-from michaelnottebrock@gmx.net) Received: from lofi.dyndns.org (pc2-105.intern.meitner [10.3.12.105]) by meitner.wh.uni-dortmund.de (Postfix) with ESMTP id 4408A167594 for ; Fri, 2 May 2003 04:08:42 +0200 (CEST) Received: from kiste.my.domain (kiste.my.domain [192.168.8.4]) (authenticated bits=0) by lofi.dyndns.org (8.12.6p2/8.12.6) with ESMTP id h4228fbt057265 (version=TLSv1/SSLv3 cipher=RC4-MD5 bits=128 verify=NO) for ; Fri, 2 May 2003 04:08:41 +0200 (CEST) (envelope-from michaelnottebrock@gmx.net) From: Michael Nottebrock To: freebsd-performance@freebsd.org Date: Fri, 2 May 2003 04:08:36 +0200 User-Agent: KMail/1.5.1 References: In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg=pgp-sha1; boundary="Boundary-02=_oMds+Bke8AmOLxT"; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200305020408.41152.michaelnottebrock@gmx.net> X-Virus-Scanned: by amavisd-new Subject: Re: freebsd-performance Digest, Vol 3, Issue X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 May 2003 02:08:44 -0000 --Boundary-02=_oMds+Bke8AmOLxT Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Description: signed data Content-Disposition: inline On Friday 02 May 2003 03:17, randall ehren wrote: > what do you mean by "set their free reserve"? A lot of FreeBSD users only realize the existance of this when they are fac= ed=20 with a situation described in the FreeBSD FAQ: =2D--snip 9.25. How is it possible for a partition to be more than 100% full? A portion of each UFS partition (8%, by default) is reserved for use by the= =20 operating system and the root user. df(1) does not count that space when=20 calculating the Capacity column, so it can exceed 100%. Also, you'll notice= =20 that the Blocks column is always greater than the sum of the Used and Avail= =20 columns, usually by a factor of 8%. =46or more details, look up the -m option in tunefs(8). =2D--snip=20 =2E.. which says: =2D--snip =46rom the tunefs(8) manpage: -m minfree Specify the percentage of space held back from normal users; t= he minimum free space threshold. The default value used is 8%. This value can be set to zero, however up to a factor of three= in throughput will be lost over the performance obtained at a 10% threshold. Settings of 5% and less force space optimization to always be used which will greatly increase the overhead for fi= le writes. Note that if the value is raised above the current us= age level, users will be unable to allocate files until enough fil= es have been deleted to get under the higher threshold. =2D--snip =2D-=20 Regards, Michael Nottebrock --Boundary-02=_oMds+Bke8AmOLxT Content-Type: application/pgp-signature Content-Description: signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (FreeBSD) iD8DBQA+sdMoXhc68WspdLARAk5eAKCXk1J8pZZKUvZqu/a77V6jrywtZQCeIdvO xwrAM6O1VrsVIPYxv5MFh7I= =bU1t -----END PGP SIGNATURE----- --Boundary-02=_oMds+Bke8AmOLxT-- From owner-freebsd-performance@FreeBSD.ORG Sun Apr 13 11:28:11 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 57E3D37B417; Sun, 13 Apr 2003 11:28:11 -0700 (PDT) Received: from samson.dc.luth.se (samson.dc.luth.se [130.240.112.30]) by mx1.FreeBSD.org (Postfix) with ESMTP id C109D43F75; Sun, 13 Apr 2003 11:28:09 -0700 (PDT) (envelope-from bj@dc.luth.se) Received: from dc.luth.se (root@bompe.dc.luth.se [130.240.60.42]) by samson.dc.luth.se (8.12.5/8.12.5) with ESMTP id h3DIRxLG014071; Sun, 13 Apr 2003 20:27:59 +0200 (MET DST) Received: from bompe.dc.luth.se (bj@localhost.dc.luth.se [127.0.0.1]) by dc.luth.se (8.12.6/8.11.3) with ESMTP id h3DIRv2F004468; Sun, 13 Apr 2003 20:27:57 +0200 (CEST) (envelope-from bj@bompe.dc.luth.se) Message-Id: <200304131827.h3DIRv2F004468@dc.luth.se> X-Mailer: exmh version 2.5 07/13/2001 with nmh-1.0.4 To: Terry Lambert In-reply-to: Your message of Fri, 11 Apr 2003 09:32:51 PDT. <3E96EE33.FAF4FABB@mindspring.com> Dcc: X-Disposition-notification-to: Borje.Josefsson@dc.luth.se X-uri: http://www.dc.luth.se/~bj/index.html Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable From: Borje Josefsson cc: Mattias Pantzare cc: freebsd-hackers@freebsd.org cc: freebsd-performance@freebsd.org cc: Eric Anderson cc: David Gilbert Subject: Re: tcp_output starving -- is due to mbuf get delay? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: bj@dc.luth.se List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 13 Apr 2003 18:28:11 -0000 Date: Sun, 13 Apr 2003 18:28:11 -0000 X-Original-Date: Sun, 13 Apr 2003 20:27:57 +0200 X-List-Received-Date: Sun, 13 Apr 2003 18:28:11 -0000 On Fri, 11 Apr 2003 09:32:51 PDT Terry Lambert wrote: > See other posting; I listed a bunch of OIDs to play with. > = > One other, if you are running -CURRENT, would be: > = > net.isr.netisr_enable -> 1 I found "net.isr.enable", I hope that is what You mean. > This basically implements part 1 of 3 of LRP, which should > reduce your per packet latency by about 50ms +/- 50ms. > = > Note: The logic here is inverted; you'd expect "0=3DNo NETISR", > but it's just the opposite. I tried to install -current on a third system (just a PIII-933, with 33MH= z = bus) today: root@stinky 4# ttcp -s -t -f m -l 61440 -n 20345 dino ttcp-t: buflen=3D61440, nbuf=3D20345, align=3D16384/0, port=3D5001 tcp -= > dino ttcp-t: socket ttcp-t: connect ttcp-t: 1249996800 bytes in 27.04 real seconds =3D 352.65 Mbit/sec +++ ttcp-t: 20345 I/O calls, msec/call =3D 1.36, calls/sec =3D 752.31 ttcp-t: 0.0user 15.6sys 0:27real 57% 15i+359d 420maxrss 0+0pf 16+44950csw= root@stinky 5# = root@stinky 5# sysctl net.isr.enable=3D1 net.isr.enable: 0 -> 1 root@stinky 6# ttcp -s -t -f m -l 61440 -n 20345 dino ttcp-t: buflen=3D61440, nbuf=3D20345, align=3D16384/0, port=3D5001 tcp -= > dino ttcp-t: socket ttcp-t: connect ttcp-t: 1249996800 bytes in 27.27 real seconds =3D 349.70 Mbit/sec +++ ttcp-t: 20345 I/O calls, msec/call =3D 1.37, calls/sec =3D 746.03 ttcp-t: 0.0user 16.4sys 0:27real 60% 15i+355d 420maxrss 0+0pf 15+70547csw= I.e. no change. The same host with NetBSD gives me at least 525 Mbit/sec.= The symptoms with -current are the same as before. 100% CPU load. Note the strange behaviour on netstat below. I start at 50kpps (output), = and then fall back to 27,5k (steady). input (Total) output packets errs bytes packets errs bytes colls 16177 0 1067840 28767 0 43555599 0 28563 0 1885158 50583 0 76573756 0 28566 0 1885356 50582 0 76575270 0 28492 0 1880472 50451 0 76381478 0 28538 0 1883508 50534 0 76511682 0 27723 0 1829718 49096 0 74325466 0 15173 0 1001418 27498 0 41628940 0 15268 0 1007688 27581 0 41755578 0 15230 0 1005180 27498 0 41628732 0 15280 0 1008480 27498 0 41627892 0 15290 0 1009140 27624 0 41820384 0 15244 0 1006104 27498 0 41628172 0 15229 0 1005114 27498 0 41628108 0 15287 0 1008942 27540 0 41692056 0 15200 0 1003194 27413 0 41500866 0 15292 0 1009272 27625 0 41820522 0 15221 0 1004586 27411 0 41498918 0 15239 0 1005774 27540 0 41692552 0 15206 0 1003596 27540 0 41692752 0 15265 0 1007490 27584 0 41756928 0 15222 0 1004652 27539 0 41691102 0 15209 0 1003794 27540 0 41692944 0 15185 0 1002210 27496 0 41627448 0 15253 0 1006698 27540 0 41693344 0 15191 0 1002606 27496 0 41626656 0 15176 0 1001616 27540 0 41692880 0 15232 0 1005312 27627 0 41821342 0 2876 0 189816 5183 0 7838606 0 stinky# netstat -ss tcp: 863330 packets sent 863320 data packets (1250011712 bytes) 1 data packet (1448 bytes) retransmitted 9 ack-only packets (0 delayed) 1 control packet 483425 packets received 446021 acks (for 1250011665 bytes) 29 packets (1344 bytes) received in-sequence 37376 window update packets 1 connection request 1 connection established (including accepts) 1 connection updated cached RTT on close 1 connection updated cached RTT variance on close 446021 segments updated rtt (of 21215 attempts) 11864 correct ACK header predictions 26 correct data packet header predictions If time permits tomorrow, I'll install -current on one of the faster = hosts, but I don't think it will make any significant difference. --B=F6rje From owner-freebsd-performance@FreeBSD.ORG Sun Apr 13 12:38:04 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AF5FA37B401; Sun, 13 Apr 2003 12:38:04 -0700 (PDT) Received: from lrz.is-a-geek.org (217-117-54-155.teledisnet.be [217.117.54.155]) by mx1.FreeBSD.org (Postfix) with ESMTP id E86C343F75; Sun, 13 Apr 2003 12:38:02 -0700 (PDT) (envelope-from pinux@teledisnet.be) Received: from pinux by lrz.is-a-geek.org with local (Exim 3.33 #1) id 194oaF-0000DV-00; Sun, 13 Apr 2003 21:00:15 +0000 Received: from mail.teledisnet.be [217.117.32.52] by localhost with POP3 (fetchmail-5.9.11) for pinux@localhost (single-drop); Sun, 13 Apr 2003 21:00:15 +0000 (GMT) Received: from mx2.freebsd.org ([216.136.204.119]) byid HDAOOC00.AFP for ; Sun, 13 Apr 2003 20:29:00 +0200 Received: from hub.freebsd.org (hub.freebsd.org [216.136.204.18]) by mx2.freebsd.org (Postfix) with ESMTP id 358A7571FA; Sun, 13 Apr 2003 11:28:47 -0700 (PDT) (envelope-from owner-freebsd-hackers@freebsd.org) Received: from hub.freebsd.org (localhost [127.0.0.1]) by hub.freebsd.org (Postfix) with ESMTP id 016EA37B40A; Sun, 13 Apr 2003 11:28:47 -0700 (PDT) Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 57E3D37B417; Sun, 13 Apr 2003 11:28:11 -0700 (PDT) Received: from samson.dc.luth.se (samson.dc.luth.se [130.240.112.30]) by mx1.FreeBSD.org (Postfix) with ESMTP id C109D43F75; Sun, 13 Apr 2003 11:28:09 -0700 (PDT) (envelope-from bj@dc.luth.se) Received: from dc.luth.se (root@bompe.dc.luth.se [130.240.60.42]) by samson.dc.luth.se (8.12.5/8.12.5) with ESMTP id h3DIRxLG014071; Sun, 13 Apr 2003 20:27:59 +0200 (MET DST) Received: from bompe.dc.luth.se (bj@localhost.dc.luth.se [127.0.0.1]) by dc.luth.se (8.12.6/8.11.3) with ESMTP id h3DIRv2F004468; Sun, 13 Apr 2003 20:27:57 +0200 (CEST) (envelope-from bj@bompe.dc.luth.se) Message-Id: <200304131827.h3DIRv2F004468@dc.luth.se> X-Mailer: exmh version 2.5 07/13/2001 with nmh-1.0.4 To: Terry Lambert In-reply-to: Your message of Fri, 11 Apr 2003 09:32:51 PDT. <3E96EE33.FAF4FABB@mindspring.com> Dcc: X-Disposition-notification-to: Borje.Josefsson@dc.luth.se X-uri: http://www.dc.luth.se/~bj/index.html Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable From: Borje Josefsson X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Errors-To: owner-freebsd-hackers@freebsd.org Sender: "pinux@arrakis" cc: freebsd-hackers@freebsd.org cc: freebsd-performance@freebsd.org cc: Eric Anderson cc: David Gilbert Subject: Re: tcp_output starving -- is due to mbuf get delay? X-BeenThere: freebsd-performance@freebsd.org Reply-To: bj@dc.luth.se List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 13 Apr 2003 19:38:05 -0000 Date: Sun, 13 Apr 2003 19:38:05 -0000 X-Original-Date: Sun, 13 Apr 2003 20:27:57 +0200 X-List-Received-Date: Sun, 13 Apr 2003 19:38:05 -0000 On Fri, 11 Apr 2003 09:32:51 PDT Terry Lambert wrote: > See other posting; I listed a bunch of OIDs to play with. > = > One other, if you are running -CURRENT, would be: > = > net.isr.netisr_enable -> 1 I found "net.isr.enable", I hope that is what You mean. > This basically implements part 1 of 3 of LRP, which should > reduce your per packet latency by about 50ms +/- 50ms. > = > Note: The logic here is inverted; you'd expect "0=3DNo NETISR", > but it's just the opposite. I tried to install -current on a third system (just a PIII-933, with 33MH= z = bus) today: root@stinky 4# ttcp -s -t -f m -l 61440 -n 20345 dino ttcp-t: buflen=3D61440, nbuf=3D20345, align=3D16384/0, port=3D5001 tcp -= > dino ttcp-t: socket ttcp-t: connect ttcp-t: 1249996800 bytes in 27.04 real seconds =3D 352.65 Mbit/sec +++ ttcp-t: 20345 I/O calls, msec/call =3D 1.36, calls/sec =3D 752.31 ttcp-t: 0.0user 15.6sys 0:27real 57% 15i+359d 420maxrss 0+0pf 16+44950csw= root@stinky 5# = root@stinky 5# sysctl net.isr.enable=3D1 net.isr.enable: 0 -> 1 root@stinky 6# ttcp -s -t -f m -l 61440 -n 20345 dino ttcp-t: buflen=3D61440, nbuf=3D20345, align=3D16384/0, port=3D5001 tcp -= > dino ttcp-t: socket ttcp-t: connect ttcp-t: 1249996800 bytes in 27.27 real seconds =3D 349.70 Mbit/sec +++ ttcp-t: 20345 I/O calls, msec/call =3D 1.37, calls/sec =3D 746.03 ttcp-t: 0.0user 16.4sys 0:27real 60% 15i+355d 420maxrss 0+0pf 15+70547csw= I.e. no change. The same host with NetBSD gives me at least 525 Mbit/sec.= The symptoms with -current are the same as before. 100% CPU load. Note the strange behaviour on netstat below. I start at 50kpps (output), = and then fall back to 27,5k (steady). input (Total) output packets errs bytes packets errs bytes colls 16177 0 1067840 28767 0 43555599 0 28563 0 1885158 50583 0 76573756 0 28566 0 1885356 50582 0 76575270 0 28492 0 1880472 50451 0 76381478 0 28538 0 1883508 50534 0 76511682 0 27723 0 1829718 49096 0 74325466 0 15173 0 1001418 27498 0 41628940 0 15268 0 1007688 27581 0 41755578 0 15230 0 1005180 27498 0 41628732 0 15280 0 1008480 27498 0 41627892 0 15290 0 1009140 27624 0 41820384 0 15244 0 1006104 27498 0 41628172 0 15229 0 1005114 27498 0 41628108 0 15287 0 1008942 27540 0 41692056 0 15200 0 1003194 27413 0 41500866 0 15292 0 1009272 27625 0 41820522 0 15221 0 1004586 27411 0 41498918 0 15239 0 1005774 27540 0 41692552 0 15206 0 1003596 27540 0 41692752 0 15265 0 1007490 27584 0 41756928 0 15222 0 1004652 27539 0 41691102 0 15209 0 1003794 27540 0 41692944 0 15185 0 1002210 27496 0 41627448 0 15253 0 1006698 27540 0 41693344 0 15191 0 1002606 27496 0 41626656 0 15176 0 1001616 27540 0 41692880 0 15232 0 1005312 27627 0 41821342 0 2876 0 189816 5183 0 7838606 0 stinky# netstat -ss tcp: 863330 packets sent 863320 data packets (1250011712 bytes) 1 data packet (1448 bytes) retransmitted 9 ack-only packets (0 delayed) 1 control packet 483425 packets received 446021 acks (for 1250011665 bytes) 29 packets (1344 bytes) received in-sequence 37376 window update packets 1 connection request 1 connection established (including accepts) 1 connection updated cached RTT on close 1 connection updated cached RTT variance on close 446021 segments updated rtt (of 21215 attempts) 11864 correct ACK header predictions 26 correct data packet header predictions If time permits tomorrow, I'll install -current on one of the faster = hosts, but I don't think it will make any significant difference. --B=F6rje _______________________________________________ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Sun Apr 13 23:55:12 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 855E037B401 for ; Sun, 13 Apr 2003 23:55:12 -0700 (PDT) Received: from relay.pair.com (relay.pair.com [209.68.1.20]) by mx1.FreeBSD.org (Postfix) with SMTP id 4D55943FF2 for ; Sun, 13 Apr 2003 23:55:11 -0700 (PDT) (envelope-from silby@silby.com) Received: (qmail 31351 invoked from network); 14 Apr 2003 06:55:09 -0000 Received: from niwun.pair.com (HELO localhost) (209.68.2.70) by relay.pair.com with SMTP; 14 Apr 2003 06:55:09 -0000 X-pair-Authenticated: 209.68.2.70 From: Mike Silbersack To: Hiten Pandya In-Reply-To: <20030412195711.GA30459@unixdaemons.com> Message-ID: <20030413204451.V93049@odysseus.silby.com> References: <200304101311.h3ADBgjY022790@samson.dc.luth.se> <20030412195711.GA30459@unixdaemons.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: Borje Josefsson cc: freebsd-performance@freebsd.org cc: Eric Anderson cc: David Gilbert cc: freebsd-hackers@freebsd.org Subject: Re: tcp_output starving -- is due to mbuf get delay? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 14 Apr 2003 06:55:12 -0000 Date: Mon, 14 Apr 2003 06:55:12 -0000 X-Original-Date: Sun, 13 Apr 2003 20:51:20 -0500 (CDT) X-List-Received-Date: Mon, 14 Apr 2003 06:55:12 -0000 On Sat, 12 Apr 2003, Hiten Pandya wrote: > > That tcp_quench knocks the window size back to one packet, if I'm not > > mistaken. You might want to put a counter there and see if that's > > happening frequently to you; if so, it might explain some loss of > > performance. > > Maybe something like this: > > Cheers. > > -- Hiten As Jayanth pointed out, ip_output already keeps statistics on when it returns ENOBUFS, so adding this additional variable wouldn't be of much benefit. For reference (from netstat -s): 0 output packets dropped due to no bufs, etc. Although, I think ip_output could be improved. It precalculates the expected # of packets to be sent, and returns ENOBUFS early if its estimate looks bad. However, if it gets to the point where if_output is called, and if_output then fails, no statistic is kept. So, it does look like Hiten's patch could be useful, as well as another counter tracking if_output failures. But I'm too busy to worry about them for now. :) Mike "Silby" Silbersack From owner-freebsd-performance@FreeBSD.ORG Mon Apr 14 03:28:26 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D6B9037B40A for ; Mon, 14 Apr 2003 03:28:25 -0700 (PDT) Received: from linopryne.com (adslh185.cofs.net [207.87.240.185]) by mx1.FreeBSD.org (Postfix) with SMTP id B768543F3F for ; Mon, 14 Apr 2003 03:28:24 -0700 (PDT) (envelope-from jorge@linopryne.com) Received: (qmail 70570 invoked from network); 14 Apr 2003 10:29:23 -0000 Received: from localhost (HELO linopryne.com) (127.0.0.1) by 0 with SMTP; 14 Apr 2003 10:29:23 -0000 Received: from 192.168.0.4 (SquirrelMail authenticated user jorge@linopryne.com) by mail.linopryne.com with HTTP; Mon, 14 Apr 2003 06:29:23 -0400 (EDT) Message-ID: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> From: "Jorge Mario G." To: X-Priority: 3 Importance: Normal X-Mailer: SquirrelMail (version 1.2.10) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Subject: docs??? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 14 Apr 2003 10:28:26 -0000 Date: Mon, 14 Apr 2003 10:28:26 -0000 X-Original-Date: Mon, 14 Apr 2003 06:29:23 -0400 (EDT) X-List-Received-Date: Mon, 14 Apr 2003 10:28:26 -0000 Hi I'm trying to find documentation to configure a FreeBSD server for a high perfomance task. I've seen a couple of docs in the freebsd.org site and I also saw this book 4.4BSD desing and implementation. Is the information in that book still relevant and is it useful?? the problem is, I'm deep in south america and S&H costs are hand and leg. Recommended readings are appreciated thanks Jorge From owner-freebsd-performance@FreeBSD.ORG Mon Apr 14 03:34:47 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B79D737B401 for ; Mon, 14 Apr 2003 03:34:47 -0700 (PDT) Received: from mailbox.univie.ac.at (mail.univie.ac.at [131.130.1.27]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5F27343F3F for ; Mon, 14 Apr 2003 03:34:46 -0700 (PDT) (envelope-from l.ertl@univie.ac.at) Received: from pcle2.cc.univie.ac.at (pcle2.cc.univie.ac.at [131.130.2.177]) by mailbox.univie.ac.at (8.12.2/8.12.2) with ESMTP id h3EAYYIu016514; Mon, 14 Apr 2003 12:34:39 +0200 From: Lukas Ertl To: "Jorge Mario G." In-Reply-To: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> Message-ID: <20030414123359.M220@pcle2.cc.univie.ac.at> References: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE X-DCC-ZID-Univie-Metrics: unet 4261; Body=2 Fuz1=2 Fuz2=2 cc: freebsd-performance@freebsd.org Subject: Re: docs??? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 14 Apr 2003 10:34:48 -0000 Date: Mon, 14 Apr 2003 10:34:48 -0000 X-Original-Date: Mon, 14 Apr 2003 12:34:34 +0200 (CEST) X-List-Received-Date: Mon, 14 Apr 2003 10:34:48 -0000 On Mon, 14 Apr 2003, Jorge Mario G. wrote: > I'm trying to find documentation to configure a FreeBSD server for a high > perfomance task. > I've seen a couple of docs in the freebsd.org site and I also saw this bo= ok > 4.4BSD desing and implementation. Is the information in that book still > relevant and is it useful?? the problem is, I'm deep in south america and > S&H costs are hand and leg. Recommended readings are appreciated Have you read tuning(7)? regards, le --=20 Lukas Ertl eMail: l.ertl@univie.ac.at UNIX-Systemadministrator Tel.: (+43 1) 4277-14073 Zentraler Informatikdienst (ZID) Fax.: (+43 1) 4277-9140 der Universit=E4t Wien http://mailbox.univie.ac.at/~le/ From owner-freebsd-performance@FreeBSD.ORG Mon Apr 14 03:39:20 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8923937B401 for ; Mon, 14 Apr 2003 03:39:19 -0700 (PDT) Received: from mail.ngdc.net (mail.ngdc.net [195.190.153.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id CBD8543F75 for ; Mon, 14 Apr 2003 03:39:18 -0700 (PDT) (envelope-from hroi@ngdc.net) Message-ID: <3E9A9045.6010904@ngdc.net> From: Hroi Sigurdsson Organization: Netgroup A/S User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.4a) Gecko/20030303 X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> In-Reply-To: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: docs??? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 14 Apr 2003 10:39:20 -0000 Date: Mon, 14 Apr 2003 10:39:20 -0000 X-Original-Date: Mon, 14 Apr 2003 12:41:09 +0200 X-List-Received-Date: Mon, 14 Apr 2003 10:39:20 -0000 Jorge Mario G. wrote: > Hi > I'm trying to find documentation to configure a FreeBSD server for a high > perfomance task. > I've seen a couple of docs in the freebsd.org site and I also saw this book > 4.4BSD desing and implementation. Is the information in that book still > relevant and is it useful?? the problem is, I'm deep in south america and > S&H costs are hand and leg. Recommended readings are appreciated The tuning(7) manual page is a very good start. Design and Implementation is still relevant and useful, though FreeBSD has diverged considerably in many critical parts. I wouldn't recommend reading it for the purpose of performance tweaking. -- Hroi Sigurdsson hroi@ngdc.net NetGroup A/S http://www.ngdc.net From owner-freebsd-performance@FreeBSD.ORG Mon Apr 14 05:34:18 2003 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CD76737B401 for ; Mon, 14 Apr 2003 05:34:18 -0700 (PDT) Received: from otter3.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1A2A043FCB for ; Mon, 14 Apr 2003 05:34:18 -0700 (PDT) (envelope-from anderson@centtech.com) Received: from centtech.com (electron.centtech.com [204.177.173.173]) by otter3.centtech.com (8.12.3/8.12.3) with ESMTP id h3ECYH56012921; Mon, 14 Apr 2003 07:34:17 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <3E9AAABF.1060008@centtech.com> From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; Linux i386; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0 X-Accept-Language: en-us, en MIME-Version: 1.0 To: "Jorge Mario G." References: <1400.192.168.0.4.1050316163.squirrel@mail.linopryne.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org Subject: Re: docs??? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 14 Apr 2003 12:34:19 -0000 Date: Mon, 14 Apr 2003 12:34:19 -0000 X-Original-Date: Mon, 14 Apr 2003 07:34:07 -0500 X-List-Received-Date: Mon, 14 Apr 2003 12:34:19 -0000 Jorge Mario G. wrote: > Hi > I'm trying to find documentation to configure a FreeBSD server for a high > perfomance task. > I've seen a couple of docs in the freebsd.org site and I also saw this book > 4.4BSD desing and implementation. Is the information in that book still > relevant and is it useful?? the problem is, I'm deep in south america and > S&H costs are hand and leg. Recommended readings are appreciated > thanks Jorge, thanks for the interest. We've just begun this list, and I'm working on writing up some more detailed documentation on what we come up with here in this list, so stay tuned. In the mean time, ask questions (as specific as possible), and post anything you find that helps with what you are working on. Eric -- ------------------------------------------------------------------ Eric Anderson Systems Administrator Centaur Technology Attitudes are contagious, is yours worth catching? ------------------------------------------------------------------