From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 00:14:07 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 92F8C37B401 for ; Sun, 29 Jun 2003 00:14:07 -0700 (PDT) Received: from craig.afraid.org (h24-69-213-234.cc.shawcable.net [24.69.213.234]) by mx1.FreeBSD.org (Postfix) with ESMTP id EB37F43F93 for ; Sun, 29 Jun 2003 00:14:06 -0700 (PDT) (envelope-from craig@craig.afraid.org) Received: from fireball.internal.lan ([10.0.0.2] helo=fireball) by craig.afraid.org with smtp (Exim 4.20) id 19WWNx-0001V9-UV; Sun, 29 Jun 2003 00:14:05 -0700 Message-ID: <000901c33e0e$09266000$0200000a@fireball> From: "Craig Reyenga" To: "David Gilbert" References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <20030629003134.GV71533@klapaucius.zer0.org> <16126.18820.474512.227009@canoe.velocet.net> Date: Sun, 29 Jun 2003 00:14:09 -0700 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 6.00.2600.0000 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000 cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: Craig Reyenga List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 29 Jun 2003 07:14:07 -0000 From: "David Gilbert" > >>>>> "Gregory" == Gregory Sutter writes: > > Gregory> Will you please summarize the motherboard performance data so > Gregory> we know which boards to buy and which to skip? Thanks. > > I've been working on such a summary. So far, the 'nvidia' chipset > boards have all tested badly. They couldn't be coaxed to pass more > than 100meg of traffic by any means we could discern. It's kind of funny that my FIC VA-503+ from 1997 washes the Nvidia aside. > > The K7S5A has been our mainstay. Many of them are DOA, but the ones > that pass a couple weeks of cpuburn (see port) ... both on cpu and > memory tests ... work amazingly well. These boards are limited to 300 > megabit total thruput by being a 33Mhz 32bit PCI bus. > What tools in FreeBSD could you use to see that the PCI bus is the limiting factor? Or is it simply done with a calculator? [snip] -Craig From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 00:21:53 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 E646C37B405 for ; Sun, 29 Jun 2003 00:21:53 -0700 (PDT) Received: from craig.afraid.org (h24-69-213-234.cc.shawcable.net [24.69.213.234]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0A20D43FFB for ; Sun, 29 Jun 2003 00:21:53 -0700 (PDT) (envelope-from craig@craig.afraid.org) Received: from fireball.internal.lan ([10.0.0.2] helo=fireball) by craig.afraid.org with smtp (Exim 4.20) id 19WWVU-0001Vz-I4; Sun, 29 Jun 2003 00:21:52 -0700 Message-ID: <001f01c33e0f$1f4716d0$0200000a@fireball> From: "Craig Reyenga" To: "David Gilbert" References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> Date: Sun, 29 Jun 2003 00:21:56 -0700 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 6.00.2600.0000 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000 cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: Craig Reyenga List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 29 Jun 2003 07:21:54 -0000 From: "David Gilbert" > >>>>> "Craig" == Craig Reyenga writes: > > >> 300 megabit is about where 32bit 33Mhz PCI maxes out. > > Craig> Could you tell me a little more about your tests? What boards, > Craig> and what configuration? > > Well... first of all, a 33Mhz 32-bit PCI bus can transfer 33M * 32 > bits ... which is just about 1 gigabit of _total_ PCI bus bandwidth. > Consider that you're likely testing disk->RAM->NIC and you end up with > 1/3 of that as throughput (minus bus overhead) so 300 megabit is a > good number. I should have mentioned that Iperf tests only linespeed with the options I fed it. My 5400rpm disks can't even saturate a 100mbit line :( [snip] > Now some boards I've tested (like the nvidia chipset) are strangely > limited to 100megabit. I can't explain this. It seems low no matter > how you cut it. As I mentioned in a previous email, this is horrible. Does this manifest itself with disk controllers and other high-bandwidth devices? > > Our testing has been threefold: > > 1) Generating packets. We test the machines ability to generate both > large (1500, 3000 and 9000 byte) and small (64 byte) packets. The > large scale generation of packets is necessary for the other > tests. So far, some packet flood utilities from the linux hacker > camp are our most efficient small packet generators. netcat on > memory cached objects or on /dev/zero generate our big packets. > > 2) Passing packets. Primarily, we're interested in routing. Passing > packets, passing packets with 100k routes and passing packets with > 100's of ipf accounting rules are our benchmarks. We look at both > small and large packet performance. Packet passing machines have > at least two interfaces ... but sometimes 3 or 4 are tested. > Polling is a major win in the small packet passing race. > > 3) Receiving packets. netcat is our friend again here. Receiving > packets doesn't appear to be the same level of challenge as > generating or passing them. > > At any rate, we're clearly not testing file delivery. We sometimes > play with file delivery as a first test ... or for other testing > reasons. We've found several boards that corrupt packets when they > pass more than 100megabit of packets. We havn't explained that one > yet. Our tests centre on routing packets (because that's what we do > with our high performance FreeBSD boxes. All our other FreeBSD boxes > "just work" at the level of performance they have). > I look forward to seeing a paper on this; it would certainly assist people in hardware purchase decisions. [snip] -Craig From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 04:58:39 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 A39F937B401 for ; Sun, 29 Jun 2003 04:58:39 -0700 (PDT) Received: from ms-dienst.rz.rwth-aachen.de (ms-1.rz.RWTH-Aachen.DE [134.130.3.130]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7979543F75 for ; Sun, 29 Jun 2003 04:58:38 -0700 (PDT) (envelope-from chris@unixpages.org) Received: from ms-1 (ms-dienst.rz.RWTH-Aachen.DE [134.130.3.132]) by ms-dienst.rz.rwth-aachen.de (iPlanet Messaging Server 5.2 HotFix 1.12 (built Feb 13 2003)) with ESMTP id <0HH80072IRXLLU@ms-dienst.rz.rwth-aachen.de> for freebsd-performance@freebsd.org; Sun, 29 Jun 2003 13:58:34 +0200 (MEST) Received: from relay.RWTH-Aachen.DE ([134.130.3.1]) by ms-1 (MailMonitor for SMTP v1.2.2 ) ; Sun, 29 Jun 2003 13:58:33 +0200 (MEST) Received: from haakonia.hitnet.rwth-aachen.de (daemon@haakonia.hitnet.RWTH-Aachen.DE [137.226.181.92]) h5TBwWNY028926; Sun, 29 Jun 2003 13:58:32 +0200 (MEST) Received: from gondor.middleearth (gondor.middleearth [192.168.1.42]) by haakonia.hitnet.rwth-aachen.de (Postfix) with ESMTP id 78FC51B; Sun, 29 Jun 2003 11:58:32 +0000 (GMT) Received: by gondor.middleearth (Postfix, from userid 1001) id C8A5F474A; Sun, 29 Jun 2003 13:58:27 +0200 (CEST) Date: Sun, 29 Jun 2003 13:58:27 +0200 From: Christian Brueffer In-reply-to: <16126.18820.474512.227009@canoe.velocet.net> To: David Gilbert Message-id: <20030629115827.GA637@unixpages.org> MIME-version: 1.0 Content-type: multipart/signed; boundary=6c2NcOVqGQ03X4Wi; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-disposition: inline User-Agent: Mutt/1.4.1i X-Operating-System: FreeBSD 5.1-CURRENT X-PGP-Key: http://people.freebsd.org/~brueffer/brueffer.key.asc X-PGP-Fingerprint: A5C8 2099 19FF AACA F41B B29B 6C76 178C A0ED 982D References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <20030629003134.GV71533@klapaucius.zer0.org> <16126.18820.474512.227009@canoe.velocet.net> cc: freebsd-performance@freebsd.org cc: Gregory Sutter Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 11:58:40 -0000 --6c2NcOVqGQ03X4Wi Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Jun 28, 2003 at 10:05:56PM -0400, David Gilbert wrote: > >>>>> "Gregory" =3D=3D Gregory Sutter writes: >=20 > Gregory> Will you please summarize the motherboard performance data so > Gregory> we know which boards to buy and which to skip? Thanks. >=20 > I've been working on such a summary. So far, the 'nvidia' chipset > boards have all tested badly. They couldn't be coaxed to pass more > than 100meg of traffic by any means we could discern. >=20 > The K7S5A has been our mainstay. Many of them are DOA, but the ones > that pass a couple weeks of cpuburn (see port) ... both on cpu and > memory tests ... work amazingly well. These boards are limited to 300 > megabit total thruput by being a 33Mhz 32bit PCI bus. >=20 > We've been testing mainly Athlon boards ... we havn't seen good P4 > boards ... but most of the boards we've had through for the P4 have > been workstation and not server boards. >=20 > The tiger tyan MPX is a dual board with 64 bit slots. I havn't had > time to fully benchmark it becuase we use it as a fairly primary > database server ... but it has generally been able to perform at or > near the top of the class. >=20 > There is an ASUS dusl board with 32-bit only slots and the AMD 76x > chipset (unfortunately it's far away and I can't look at it). it's > 32-bit slots run at 66Mhz and have extrodinarily good thruput. > AFAICT, it's currently out of production ... but the dual board on the > ASUS site looks very good. >=20 If you're talking about the ASUS A7M266-D, it actually has two 64bit PCI slots (powering a SCSI controller and a NIC here). It runs extremely well so far. - Christian --=20 Christian Brueffer chris@unixpages.org brueffer@FreeBSD.org GPG Key: http://people.freebsd.org/~brueffer/brueffer.key.asc GPG Fingerprint: A5C8 2099 19FF AACA F41B B29B 6C76 178C A0ED 982D --6c2NcOVqGQ03X4Wi Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (FreeBSD) iD8DBQE+/tRjbHYXjKDtmC0RApEaAKCPSYu3YiDvY4Q2eo/oYXh+VsbjwQCdFWCm 6jHcWxK5U5KJ4D2KVn8IjMI= =/U/f -----END PGP SIGNATURE----- --6c2NcOVqGQ03X4Wi-- From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 08:51:53 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 0BACC37B435 for ; Sun, 29 Jun 2003 08:51:53 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 126C343FDD for ; Sun, 29 Jun 2003 08:51:51 -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 AFC5F138945; Sun, 29 Jun 2003 11:51:42 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id 1214874DC4; Sun, 29 Jun 2003 11:51:42 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id 60F3E4AD1; Sun, 29 Jun 2003 11:51:38 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16127.2826.306427.946086@canoe.velocet.net> Date: Sun, 29 Jun 2003 11:51:38 -0400 To: Craig Reyenga In-Reply-To: <001f01c33e0f$1f4716d0$0200000a@fireball> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: David Gilbert cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 15:51:53 -0000 >>>>> "Craig" == Craig Reyenga writes: >> Now some boards I've tested (like the nvidia chipset) are strangely >> limited to 100megabit. I can't explain this. It seems low no >> matter how you cut it. Craig> As I mentioned in a previous email, this is horrible. Does this Craig> manifest itself with disk controllers and other high-bandwidth Craig> devices? Well... I don't have any disk controllers to test, but I've verified this behaviour with em, bge, sk, and nge chipsets. Of these, as I've said before, the em shines. The bge has good performance, too ... but we've seen a lot of corrupted routed packets ... it has some interaction with some motherboard chipsets. Craig> I look forward to seeing a paper on this; it would certainly Craig> assist people in hardware purchase decisions. It's in the back of my mind. I don't think I'll have time for this BSDCon, but maybe soon thereafter. It's getting to the point where we should have a BSD Journal. 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 Sun Jun 29 08:55:06 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 BE25F37B401 for ; Sun, 29 Jun 2003 08:55:06 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id C88BE43FDF for ; Sun, 29 Jun 2003 08:55:05 -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 59A88138282 for ; Sun, 29 Jun 2003 11:55:05 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id 5196B74C27; Sun, 29 Jun 2003 11:55:05 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id B60974AD1; Sun, 29 Jun 2003 11:55:01 -0400 (EDT) Resent-Message-ID: <16127.3026.897967.804387@canoe.velocet.net> Resent-Date: Sun, 29 Jun 2003 11:54:58 -0400 Resent-To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16127.3008.179405.697453@canoe.velocet.net> In-Reply-To: <000901c33e0e$09266000$0200000a@fireball> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <20030629003134.GV71533@klapaucius.zer0.org> <16126.18820.474512.227009@canoe.velocet.net> <000901c33e0e$09266000$0200000a@fireball> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid From: David Gilbert To: Craig Reyenga Date: Sun, 29 Jun 2003 11:54:40 -0400 Resent-From: dgilbert@velocet.ca (David Gilbert) Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 15:55:07 -0000 >>>>> "Craig" == Craig Reyenga writes: Craig> From: "David Gilbert" >> >>>>> "Gregory" == Gregory Sutter writes: >> Gregory> Will you please summarize the motherboard performance data so Gregory> we know which boards to buy and which to skip? Thanks. >> I've been working on such a summary. So far, the 'nvidia' chipset >> boards have all tested badly. They couldn't be coaxed to pass more >> than 100meg of traffic by any means we could discern. Craig> It's kind of funny that my FIC VA-503+ from 1997 washes the Craig> Nvidia aside. Memories. The FIC-503+ was a real trooper. Craig> What tools in FreeBSD could you use to see that the PCI bus is Craig> the limiting factor? Or is it simply done with a calculator? In hindsight, I forgot to mention that my 300 megabit figure is based on bidirectional routing tests :). Our theory that the PCI bus is at fault is largely due to the number of tests we've run ... where the OS is identical and we vary the hardware. We also use the calculator to think about bus maximums. 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 Sun Jun 29 12:28:37 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 54C0B37B401 for ; Sun, 29 Jun 2003 12:28:37 -0700 (PDT) Received: from mail1.zer0.org (klapaucius.zer0.org [204.152.186.45]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9C3E743F85 for ; Sun, 29 Jun 2003 12:28:36 -0700 (PDT) (envelope-from gsutter@zer0.org) Received: by mail1.zer0.org (Postfix, from userid 1001) id 60891239A14; Sun, 29 Jun 2003 12:28:36 -0700 (PDT) Date: Sun, 29 Jun 2003 12:28:36 -0700 From: Gregory Sutter To: David Gilbert Message-ID: <20030629192836.GW71533@klapaucius.zer0.org> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="gpOboRovIPmaBszt" Content-Disposition: inline In-Reply-To: <16127.2826.306427.946086@canoe.velocet.net> Organization: Zer0 X-Purpose: For great justice! Mail-Copies-To: poster X-Message-Flag: Ditch this virus-ridden Outlook crap and get a real mailer! X-Habeas-SWE-1: winter into spring X-Habeas-SWE-2: brightly anticipated X-Habeas-SWE-3: like Habeas SWE (tm) X-Habeas-SWE-4: Copyright 2002 Habeas (tm) X-Habeas-SWE-5: Sender Warranted Email (SWE) (tm). The sender of this X-Habeas-SWE-6: email in exchange for a license for this Habeas X-Habeas-SWE-7: warrant mark warrants that this is a Habeas Compliant X-Habeas-SWE-8: Message (HCM) and not spam. Please report use of this X-Habeas-SWE-9: mark in spam to . User-Agent: Mutt/1.5.4i cc: freebsd-performance@freebsd.org cc: Craig Reyenga Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 19:28:37 -0000 --gpOboRovIPmaBszt Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 2003-06-29 11:51 -0400, David Gilbert wrote: > >>>>> "Craig" =3D=3D Craig Reyenga writes: >=20 > Craig> I look forward to seeing a paper on this; it would certainly > Craig> assist people in hardware purchase decisions. >=20 > It's in the back of my mind. I don't think I'll have time for this > BSDCon, but maybe soon thereafter. It's getting to the point where we > should have a BSD Journal. Dave, The submission deadline for this year's BSDcon is long past, but you can always finish it up for next year's USENIX or BSDcon. Alternatively, you could write up your results for publication in the Daemon News ezine (), a monthly publication since 1998. We accept all types of BSD and Unix-related articles from short newbie articles to journal-quality pieces. To submit work or ask questions, email . Regards, Greg --=20 Gregory S. Sutter The whole problem with the world is that mailto:gsutter@zer0.org fools and fanatics are always so certain http://zer0.org/~gsutter/ of themselves, and wiser people so full hkp://wwwkeys.pgp.net/0x845DFEDD of doubts. --Bertrand Russell --gpOboRovIPmaBszt Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- iD8DBQE+/z3kIBUx1YRd/t0RAodzAJ9r99yLl2jwvRdQeTTdEjtEO8e+pACffInr dK0j9KvvKmWW6l1llRW9Fdo= =yDq4 -----END PGP SIGNATURE----- --gpOboRovIPmaBszt-- From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 13:38:08 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 82B2137B401 for ; Sun, 29 Jun 2003 13:38:08 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id B435B43FE5 for ; Sun, 29 Jun 2003 13:38:07 -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 632D0138193; Sun, 29 Jun 2003 16:38:06 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id B1FCD74DBE; Sun, 29 Jun 2003 16:38:05 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id 546E64AD1; Sun, 29 Jun 2003 16:38:01 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16127.20008.573475.411172@canoe.velocet.net> Date: Sun, 29 Jun 2003 16:38:00 -0400 To: Gregory Sutter In-Reply-To: <20030629192836.GW71533@klapaucius.zer0.org> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <20030629192836.GW71533@klapaucius.zer0.org> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: David Gilbert cc: freebsd-performance@freebsd.org cc: Craig Reyenga Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 20:38:09 -0000 >>>>> "Gregory" == Gregory Sutter writes: Gregory> The submission deadline for this year's BSDcon is long past, Gregory> but you can always finish it up for next year's USENIX or Gregory> BSDcon. Alternatively, you could write up your results for Gregory> publication in the Daemon News ezine Gregory> (), a monthly publication since Gregory> 1998. We accept all types of BSD and Unix-related articles Gregory> from short newbie articles to journal-quality pieces. To Gregory> submit work or ask questions, email Gregory> . All worth mentioning, I admit ... which is to say I would consider it... but from a purely academic point of view, having a properly accredited journal (with an appropriate editorial board and a proper peer review process) would do more for both *BSD and the individual. Certainly, I keep abrest of developments in our little world... and I respect some of the work that is published in various places for FreeBSD, but in the end, my goal is to have FreeBSD stack up against the Cisco and Juniper routers ... and that requires a broader audience ... both for criticism and for exposure. My basic argument on generic OS routing is this: If you never do anything unexpected, a closed system router (not even just closed source) will do you fine. They're generally reliable beasts and the facts about them are known to thier own liberate. If you need something to pass 1 gigabit of traffic with a maximum of 600 kpps, a CCNE should be able to tell you which Cisco to select ... and you shouldn't have any problems until your needs substantially change. No such advice exists for FreeBSD or Linux ... or indeed Win-XP. While the latter two don't interest me, it should be no less possible. Can FreeBSD pass 600 kpps? Can FreeBSD pass 1 gigabit? It's taken months, but I can say yes ... with the right hardware. Now... we have an uphill battle. Common knowledge is that the only way to massivly route packets are custom ASIC's. Little mention is made of route clustering and other technologies that would scale generic system routing. Even though it's reasonably well known that the modern desktop processor has become rediculously powerful. 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 Sun Jun 29 15:54:59 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 D171D37B401 for ; Sun, 29 Jun 2003 15:54:59 -0700 (PDT) Received: from silver.he.iki.fi (silver.he.iki.fi [193.64.42.241]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9EEA844015 for ; Sun, 29 Jun 2003 15:54:58 -0700 (PDT) (envelope-from pete@he.iki.fi) Received: from PETEX31 (gprs-prointernet-3e47d544.mobile.inet.fi [62.71.213.68]) by silver.he.iki.fi (8.12.9/8.11.4) with SMTP id h5TMsgsL031824; Mon, 30 Jun 2003 01:54:46 +0300 (EEST) (envelope-from pete@he.iki.fi) Message-ID: <008c01c33e91$730d7e30$44d5473e@PETEX31> From: "Petri Helenius" To: "David Gilbert" , "Gregory Sutter" References: <20030628190036.0E06B37B405@hub.freebsd.org><000f01c33dad$1595a0f0$e602a8c0@flatline><16126.9805.829406.368426@canoe.velocet.net><20030629003134.GV71533@klapaucius.zer0.org> <16126.18820.474512.227009@canoe.velocet.net> Date: Mon, 30 Jun 2003 00:54:34 +0200 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 8bit 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: David Gilbert cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 22:55:00 -0000 Related to this subject, it would help if one of the tools, or dmesg would give PCI clock, width and possible waitstates configured for the slot. I couldnīt figure out how to make pciconf or similar to display them... Pete ----- Original Message ----- From: "David Gilbert" To: "Gregory Sutter" Cc: "David Gilbert" ; Sent: Sunday, June 29, 2003 4:05 AM Subject: Re: Tuning Gigabit > >>>>> "Gregory" == Gregory Sutter writes: > > Gregory> Will you please summarize the motherboard performance data so > Gregory> we know which boards to buy and which to skip? Thanks. > > I've been working on such a summary. So far, the 'nvidia' chipset > boards have all tested badly. They couldn't be coaxed to pass more > than 100meg of traffic by any means we could discern. > > The K7S5A has been our mainstay. Many of them are DOA, but the ones > that pass a couple weeks of cpuburn (see port) ... both on cpu and > memory tests ... work amazingly well. These boards are limited to 300 > megabit total thruput by being a 33Mhz 32bit PCI bus. > > We've been testing mainly Athlon boards ... we havn't seen good P4 > boards ... but most of the boards we've had through for the P4 have > been workstation and not server boards. > > The tiger tyan MPX is a dual board with 64 bit slots. I havn't had > time to fully benchmark it becuase we use it as a fairly primary > database server ... but it has generally been able to perform at or > near the top of the class. > > There is an ASUS dusl board with 32-bit only slots and the AMD 76x > chipset (unfortunately it's far away and I can't look at it). it's > 32-bit slots run at 66Mhz and have extrodinarily good thruput. > AFAICT, it's currently out of production ... but the dual board on the > ASUS site looks very good. > > 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================ > _______________________________________________ > 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 Sun Jun 29 20:12:23 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 D0D3037B401 for ; Sun, 29 Jun 2003 20:12:23 -0700 (PDT) Received: from mail1.zer0.org (klapaucius.zer0.org [204.152.186.45]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0D0CC44013 for ; Sun, 29 Jun 2003 20:12:23 -0700 (PDT) (envelope-from gsutter@zer0.org) Received: by mail1.zer0.org (Postfix, from userid 1001) id A2AE5239A14; Sun, 29 Jun 2003 20:12:22 -0700 (PDT) Date: Sun, 29 Jun 2003 20:12:22 -0700 From: Gregory Sutter To: David Gilbert Message-ID: <20030630031222.GE10726@klapaucius.zer0.org> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <20030629192836.GW71533@klapaucius.zer0.org> <16127.20008.573475.411172@canoe.velocet.net> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="MGdfKiBebYi9ts3p" Content-Disposition: inline In-Reply-To: <16127.20008.573475.411172@canoe.velocet.net> Organization: Zer0 X-Purpose: For great justice! Mail-Copies-To: poster X-PGP-Fingerprint: D161 E4EA 4BFA 2427 F3F9 5B1F 2015 31D5 845D FEDD X-PGP-Key: http://zer0.org/~gsutter/gsutter.pgp X-Habeas-SWE-1: winter into spring X-Habeas-SWE-2: brightly anticipated X-Habeas-SWE-3: like Habeas SWE (tm) X-Habeas-SWE-4: Copyright 2002 Habeas (tm) X-Habeas-SWE-5: Sender Warranted Email (SWE) (tm). The sender of this X-Habeas-SWE-6: email in exchange for a license for this Habeas X-Habeas-SWE-7: warrant mark warrants that this is a Habeas Compliant X-Habeas-SWE-8: Message (HCM) and not spam. Please report use of this X-Habeas-SWE-9: mark in spam to . User-Agent: Mutt/1.5.4i cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 30 Jun 2003 03:12:24 -0000 --MGdfKiBebYi9ts3p Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 2003-06-29 16:38 -0400, David Gilbert wrote: > >>>>> "Gregory" =3D=3D Gregory Sutter writes: >=20 > Gregory> The submission deadline for this year's BSDcon is long past, > Gregory> but you can always finish it up for next year's USENIX or > Gregory> BSDcon. Alternatively, you could write up your results for > Gregory> publication in the Daemon News ezine > Gregory> (), a monthly publication since > Gregory> 1998. We accept all types of BSD and Unix-related articles > Gregory> from short newbie articles to journal-quality pieces. To > Gregory> submit work or ask questions, email > Gregory> . >=20 > All worth mentioning, I admit ... which is to say I would consider > it... but from a purely academic point of view, having a properly > accredited journal (with an appropriate editorial board and a proper > peer review process) would do more for both *BSD and the individual. The current situation is pretty good, with relevant papers being published by USENIX. Do you think a specific BSD academic journal would be a significant improvement? Greg --=20 Gregory S. Sutter I believe there are more instances of the mailto:gsutter@zer0.org abridgment of the freedom of the people by http://zer0.org/~gsutter/ gradual and silent encroachments of those in power than by violent and sudden usurpations. --James Madison --MGdfKiBebYi9ts3p Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- iD8DBQE+/6qWIBUx1YRd/t0RAn7XAJ9cl491ywK2ALlT4TDt3pQmwufwTACeMunU k+uOZ4sZCkFFjr8H3087rk8= =Hhlj -----END PGP SIGNATURE----- --MGdfKiBebYi9ts3p-- From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 22:00:11 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 3327537B401 for ; Sun, 29 Jun 2003 22:00:11 -0700 (PDT) Received: from platon.gneto.com (as6-1-5.kr.m.bonet.se [217.215.84.52]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3604843FE5 for ; Sun, 29 Jun 2003 22:00:09 -0700 (PDT) (envelope-from martin@mullet.se) Received: from mullet.se (unknown [192.168.2.127]) by platon.gneto.com (Postfix) with ESMTP id EDCA24AB3; Mon, 30 Jun 2003 07:00:06 +0200 (CEST) Message-ID: <3EFFC3D5.7070605@mullet.se> Date: Mon, 30 Jun 2003 07:00:05 +0200 From: Martin Nilsson User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.4b) Gecko/20030507 X-Accept-Language: sv, en-us, en MIME-Version: 1.0 To: David Gilbert References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> In-Reply-To: <16127.2826.306427.946086@canoe.velocet.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 30 Jun 2003 05:00:11 -0000 David Gilbert wrote: > Well... I don't have any disk controllers to test, but I've verified > this behaviour with em, bge, sk, and nge chipsets. Of these, as I've > said before, the em shines. =20 I have made some simple speed testing of gigabit NICs too. My results=20 are that Linux 2.4.18+ is usually faster and have much lower CPU load=20 than FreeBSD 4.8. I have tested the following NIC:s em (1000/XT,Anvik),=20 nge(32/33), bge (Altima 1002), ti (Netgear GA620T). For FreeBSD I've found that use nothing beats the ti with its special=20 firmware. > The bge has good performance, too ... but > we've seen a lot of corrupted routed packets ... it has some > interaction with some motherboard chipsets. The VIA chipsets often have very poor PCI bus performance if you don't=20 load the 4 in 1 drivers (windows only). The max PCI speed I've been able = to get with (semi old ~1.5years) VIA chipsets are about 70MB/s measured=20 with a SCSI disk array on a 32/33 bus. The intel, SiS and serverworks=20 chipsets perform as expected, I haven't tested any Nvida boards. > It's in the back of my mind. I don't think I'll have time for this > BSDCon, but maybe soon thereafter. It's getting to the point where we > should have a BSD Journal. I would be interested in helping to test this, I have a bunch of lab=20 boxes with 64/66PCI or PCI-X slots and NICs to work with. I'm able to=20 get access to most new motherboards and chipsets to test chipset=20 specific performance. What I need is someone to help me develop useful=20 things to test, validate results and to check testing methodology. /Martin --=20 Martin Nilsson M.Sc CS&E, CTO Mullet Scandinavia AB, Malm=F6, SWEDEN E-mail: martin@mullet.se, Phone: +46-(0)708-606170, Web: www.mullet.se Our business is well enigineered servers optimised for FreeBSD & Linux From owner-freebsd-performance@FreeBSD.ORG Mon Jun 30 05:44:29 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 9ECE737B401 for ; Mon, 30 Jun 2003 05:44:29 -0700 (PDT) Received: from otter3.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 76A3843FE5 for ; Mon, 30 Jun 2003 05:44:28 -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 h5UCiR56035771 for ; Mon, 30 Jun 2003 07:44:27 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <3F003092.30405@centtech.com> Date: Mon, 30 Jun 2003 07:44:02 -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: freebsd-performance@freebsd.org References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <3EFFC3D5.7070605@mullet.se> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: Tuning Gigabit 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, 30 Jun 2003 12:44:29 -0000 Martin Nilsson wrote: > > I would be interested in helping to test this, I have a bunch of lab > boxes with 64/66PCI or PCI-X slots and NICs to work with. I'm able to > get access to most new motherboards and chipsets to test chipset > specific performance. What I need is someone to help me develop useful > things to test, validate results and to check testing methodology. I'm interested in helping with this too.. I have access to hundreds of boards, test equipment, processors, nics, you name it. I just need to be led in the right direction with this. Anyone want to lead some minions in finding out some of this info? Eric -- ------------------------------------------------------------------ Eric Anderson Systems Administrator Centaur Technology Attitudes are contagious, is yours worth catching? ------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Mon Jun 30 13:57:01 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 885FE37B401 for ; Mon, 30 Jun 2003 13:57:01 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8AB5344001 for ; Mon, 30 Jun 2003 13:57:00 -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 8EFAC138805; Mon, 30 Jun 2003 16:56:59 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id D5D1A74D7D; Mon, 30 Jun 2003 16:56:58 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id 1F5504AD2; Mon, 30 Jun 2003 16:56:55 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16128.42007.75314.462685@canoe.velocet.net> Date: Mon, 30 Jun 2003 16:56:55 -0400 To: Eric Anderson In-Reply-To: <3F003092.30405@centtech.com> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <3EFFC3D5.7070605@mullet.se> <3F003092.30405@centtech.com> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 30 Jun 2003 20:57:01 -0000 >>>>> "Eric" == Eric Anderson writes: Eric> Martin Nilsson wrote: >> I would be interested in helping to test this, I have a bunch of >> lab boxes with 64/66PCI or PCI-X slots and NICs to work with. I'm >> able to get access to most new motherboards and chipsets to test >> chipset specific performance. What I need is someone to help me >> develop useful things to test, validate results and to check >> testing methodology. Eric> I'm interested in helping with this too.. I have access to Eric> hundreds of boards, test equipment, processors, nics, you name Eric> it. I just need to be led in the right direction with this. Eric> Anyone want to lead some minions in finding out some of this Eric> info? We have a fairly well developed testing methodogy here ... with a couple of people I can lend to the task. To be useful, they'll need both root and console access to boxes (serial cross connects are fine) ... along with somone who can play with BIOS settings on request. We'd be very willing to donate the hands and eyes to do much of the volume testing. ... our only problem is buying enough new hardware. 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 Mon Jun 30 14:24:58 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 4C11237B401 for ; Mon, 30 Jun 2003 14:24:58 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 63E4543FE5 for ; Mon, 30 Jun 2003 14:24:57 -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 65B8F1383B5; Mon, 30 Jun 2003 17:24:56 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id 1973474C27; Mon, 30 Jun 2003 17:24:56 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id 689714AD2; Mon, 30 Jun 2003 17:24:52 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16128.43684.374770.746318@canoe.velocet.net> Date: Mon, 30 Jun 2003 17:24:52 -0400 To: Martin Nilsson In-Reply-To: <3EFFC3D5.7070605@mullet.se> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <3EFFC3D5.7070605@mullet.se> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: David Gilbert cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 30 Jun 2003 21:24:58 -0000 >>>>> "Martin" == Martin Nilsson writes: Martin> David Gilbert wrote: >> Well... I don't have any disk controllers to test, but I've >> verified this behaviour with em, bge, sk, and nge chipsets. Of >> these, as I've said before, the em shines. Martin> I have made some simple speed testing of gigabit NICs too. My Martin> results are that Linux 2.4.18+ is usually faster and have much Martin> lower CPU load than FreeBSD 4.8. I have tested the following Martin> NIC:s em (1000/XT,Anvik), nge(32/33), bge (Altima 1002), ti Martin> (Netgear GA620T). For FreeBSD I've found that use nothing Martin> beats the ti with its special firmware. I don't think I've had a 'ti' in the shop, but I did find that 5.x is substantially better than 4.8... 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 Mon Jun 30 14:36:10 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 2286737B404 for ; Mon, 30 Jun 2003 14:36:10 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1D04844013 for ; Mon, 30 Jun 2003 14:33:07 -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 275D81384A7; Mon, 30 Jun 2003 17:32:43 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id E679074D80; Mon, 30 Jun 2003 17:32:42 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id D9FF14AD2; Mon, 30 Jun 2003 17:32:38 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16128.44150.843061.276466@canoe.velocet.net> Date: Mon, 30 Jun 2003 17:32:38 -0400 To: Gregory Sutter In-Reply-To: <20030630031222.GE10726@klapaucius.zer0.org> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <20030629192836.GW71533@klapaucius.zer0.org> <16127.20008.573475.411172@canoe.velocet.net> <20030630031222.GE10726@klapaucius.zer0.org> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: David Gilbert cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 30 Jun 2003 21:36:10 -0000 >>>>> "Gregory" == Gregory Sutter writes: Gregory> The current situation is pretty good, with relevant papers Gregory> being published by USENIX. Do you think a specific BSD Gregory> academic journal would be a significant improvement? I suppose I could be lookint to publish with USENIX. I've thought of it, of course... but from the other side, I might be more interested in subscribing to a *BSD journal. Sigh... or I could just keep my head down and work on what we need here ... sigh. 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 Mon Jun 30 16:33:54 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 63E2037B401 for ; Mon, 30 Jun 2003 16:33:54 -0700 (PDT) Received: from perrin.int.nxad.com (internal.ext.nxad.com [69.1.70.251]) by mx1.FreeBSD.org (Postfix) with ESMTP id E861943F93 for ; Mon, 30 Jun 2003 16:33:53 -0700 (PDT) (envelope-from sean@nxad.com) Received: by perrin.int.nxad.com (Postfix, from userid 1001) id 6BE8521058; Mon, 30 Jun 2003 16:33:53 -0700 (PDT) Date: Mon, 30 Jun 2003 16:33:53 -0700 From: Sean Chittenden To: "D. J. Bernstein" Message-ID: <20030630233353.GG96753@perrin.int.nxad.com> References: <20030626025029.71392.qmail@cr.yp.to> <200306260515.h5Q5FhPF020045@bitblocks.com> <20030626212659.51367.qmail@cr.yp.to> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20030626212659.51367.qmail@cr.yp.to> X-PGP-Key: finger seanc@FreeBSD.org X-PGP-Fingerprint: 3849 3760 1AFE 7B17 11A0 83A6 DD99 E31F BC84 B341 X-Web-Homepage: http://sean.chittenden.org/ User-Agent: Mutt/1.5.4i cc: freebsd-performance@freebsd.org Subject: Re: ten thousand small processes 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, 30 Jun 2003 23:33:54 -0000 > > Instead of complaining about wasting 78 megabytes and arguing > > about why various proposed solutions fall short and why your way > > is the best, why don't you come up with a patch that saves space > > for small programs? > > Funny. Seems to me that I keep making concrete > suggestions---including a detailed proposal for giving more space to > malloc()---and the answer is consistently ``We really don't care > about per-process overhead.'' What's the benefit of a patch for > people who don't even see the problem? It'd be slick if malloc(3) had a mallopt(3) call that'd make it easier to monkey with the _malloc_options, but, until such time as phk is on this list or decides to add such an interface, why not just set: _malloc_options = "<<<<<<<<<<<<<<<"; /* '<' * 15 */ to reduce the malloc cache to 0? From malloc(3): TUNING Once, when the first call is made to one of these memory allocation rou- tines, various flags will be set or reset, which affect the workings of this allocation implementation. The ``name'' of the file referenced by the symbolic link named /etc/malloc.conf, the value of the environment variable MALLOC_OPTIONS, and the string pointed to by the global variable _malloc_options will be interpreted, in that order, character by character as flags. Most flags are single letters, where uppercase indicates that the behav- ior is set, or on, and lowercase means that the behavior is not set, or off. [snip] < Reduce the size of the cache by a factor of two. The default cache size is 16 pages. This option can be specified multiple times. -sc -- Sean Chittenden From owner-freebsd-performance@FreeBSD.ORG Sun Jun 29 08:36:48 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 6209337B401 for ; Sun, 29 Jun 2003 08:36:48 -0700 (PDT) Received: from smtp-out.comcast.net (smtp-out.comcast.net [24.153.64.113]) by mx1.FreeBSD.org (Postfix) with ESMTP id 764AD4401F for ; Sun, 29 Jun 2003 08:36:45 -0700 (PDT) (envelope-from nevans@talkpoint.com) Received: from paladin.nextvenue.com (pcp03126014pcs.avenel01.nj.comcast.net [68.38.172.93]) by mtaout03.icomcast.net (iPlanet Messaging Server 5.2 HotFix 1.16 (built May 14 2003)) with SMTP id <0HH9006UT20EYI@mtaout03.icomcast.net> for freebsd-performance@freebsd.org; Sun, 29 Jun 2003 11:36:15 -0400 (EDT) Date: Sun, 29 Jun 2003 11:36:22 -0400 From: Nick Evans In-reply-to: <20030629115827.GA637@unixpages.org> To: freebsd-performance@freebsd.org Message-id: <20030629113622.74655443.nevans@talkpoint.com> Organization: Talkpoint Communications MIME-version: 1.0 X-Mailer: Sylpheed version 0.8.10claws (GTK+ 1.2.10; i386-portbld-freebsd5.1) Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT References: <20030629115827.GA637@unixpages.org> X-Mailman-Approved-At: Mon, 30 Jun 2003 16:50:25 -0700 Subject: Re: Tuning Gigabit 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: Sun, 29 Jun 2003 15:36:48 -0000 On Sun, 29 Jun 2003 07:58:27 -0400 Christian Brueffer wrote: > On Sat, Jun 28, 2003 at 10:05:56PM -0400, David Gilbert wrote: > > >>>>> "Gregory" == Gregory Sutter writes: > > > > Gregory> Will you please summarize the motherboard performance data so > > Gregory> we know which boards to buy and which to skip? Thanks. > > > > I've been working on such a summary. So far, the 'nvidia' chipset > > boards have all tested badly. They couldn't be coaxed to pass more > > than 100meg of traffic by any means we could discern. > > > > The K7S5A has been our mainstay. Many of them are DOA, but the ones > > that pass a couple weeks of cpuburn (see port) ... both on cpu and > > memory tests ... work amazingly well. These boards are limited to 300 > > megabit total thruput by being a 33Mhz 32bit PCI bus. > > > > We've been testing mainly Athlon boards ... we havn't seen good P4 > > boards ... but most of the boards we've had through for the P4 have > > been workstation and not server boards. > > > > The tiger tyan MPX is a dual board with 64 bit slots. I havn't had > > time to fully benchmark it becuase we use it as a fairly primary > > database server ... but it has generally been able to perform at or > > near the top of the class. > > > > There is an ASUS dusl board with 32-bit only slots and the AMD 76x > > chipset (unfortunately it's far away and I can't look at it). it's > > 32-bit slots run at 66Mhz and have extrodinarily good thruput. > > AFAICT, it's currently out of production ... but the dual board on the > > ASUS site looks very good. > > > > If you're talking about the ASUS A7M266-D, it actually has two 64bit > PCI slots (powering a SCSI controller and a NIC here). > It runs extremely well so far. > > - Christian > > -- > Christian Brueffer chris@unixpages.org brueffer@FreeBSD.org > GPG Key: http://people.freebsd.org/~brueffer/brueffer.key.asc > GPG Fingerprint: A5C8 2099 19FF AACA F41B B29B 6C76 178C A0ED 982D I recently tested a Compaq DL380, 733Mhz processor, 512meg ram with two fiber 64-bit Intel Pro 1000's. The system (4.8-R) forwarded 500 megabits at about 20% idle with IPFilter loaded but with no rules. The system uses a ServerWorks chipset and has several 64-bit pci slots. I used netperf on several systems on either side of the firewall. In the next week or so I'll be testing two Pentium 4 2.4 gig systems with ServerWorks chipsets using a much larger cluster of load applying systems. I'll post those results. When I tested the same configuration on a Compaq 1850R (450Mhz, i440BX, 32-bit PCI) I could only muster about 250-270 megabits of traffic. I figured the PCI bus was the limiting factor and stepped up to the DL380. Previously I've forwarded 50,000 packets per second on a Celeron 900Mhz, Intel 810 chipset, 32-bit PCI (4.4-R) system with IPFilter loaded and IIRC 150 rules in effect. The system used Intel PRO/100S dual port server adapters. I used ping -f for those tests. I have access to about 25-30 systems to apply load with so if anyone wants something specific tested I might be able to work it into my schedule. Nick ------------------------------- nick.evans network.engineering talkpoint communications, inc. land 212.909.2967 cell From owner-freebsd-performance@FreeBSD.ORG Mon Jun 30 20:15:38 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 24D8237B401 for ; Mon, 30 Jun 2003 20:15:38 -0700 (PDT) Received: from stoneport.math.uic.edu (stoneport.math.uic.edu [131.193.178.160]) by mx1.FreeBSD.org (Postfix) with SMTP id 857A943FCB for ; Mon, 30 Jun 2003 20:15:37 -0700 (PDT) (envelope-from djb-dsn-1057029368.11066@cr.yp.to) Received: (qmail 11067 invoked by uid 1017); 1 Jul 2003 03:16:08 -0000 Date: 1 Jul 2003 03:16:08 -0000 Message-ID: <20030701031608.11066.qmail@cr.yp.to> Automatic-Legal-Notices: See http://cr.yp.to/mailcopyright.html. From: "D. J. Bernstein" To: freebsd-performance@freebsd.org References: <20030626025029.71392.qmail@cr.yp.to> <200306260515.h5Q5FhPF020045@bitblocks.com> <20030626212659.51367.qmail@cr.yp.to> <20030630233353.GG96753@perrin.int.nxad.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Subject: Re: ten thousand small processes 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, 01 Jul 2003 03:15:38 -0000 Sean Chittenden writes: > reduce the malloc cache to 0 Measure. Don't speculate. Other people's proposals were inadequate (alloca, threads) or dangerous (sbrk), but at least they were related to the problem. ---D. J. Bernstein, Associate Professor, Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago From owner-freebsd-performance@FreeBSD.ORG Tue Jul 1 00:32:11 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 7CA7337B401 for ; Tue, 1 Jul 2003 00:32:11 -0700 (PDT) Received: from l07.oase.research.kpn.com (l07.oase.research.kpn.com [139.63.192.207]) by mx1.FreeBSD.org (Postfix) with ESMTP id E2F9644008 for ; Tue, 1 Jul 2003 00:32:09 -0700 (PDT) (envelope-from k.j.koster@telecom.tno.nl) content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable X-MimeOLE: Produced By Microsoft Exchange V6.0.6375.0 Date: Tue, 1 Jul 2003 09:32:07 +0200 Message-ID: <0DD8055E0FECF744B5FF8053F80C4A2D011F4018@l07.oase.research.kpn.com> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: ten thousand small processes Thread-Index: AcM/fxE1gfSsTbZrQWCpUQyRtTVMjwAI04nw From: To: cc: freebsd-performance@freebsd.org Subject: RE: ten thousand small processes 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, 01 Jul 2003 07:32:11 -0000 Dear mr. Bernstein, >=20 > > reduce the malloc cache to 0 >=20 > Measure. Don't speculate. > Ehrm... No, sorry. He can speculate if he likes, and you can measure. = You have the problem and therefore a context to measure in, and he does = not. Kees Jan =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D You can't have everything. Where would you put it? [Steven Wright] From owner-freebsd-performance@FreeBSD.ORG Thu Jul 3 07:36:11 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 ACA6237B401 for ; Thu, 3 Jul 2003 07:36:11 -0700 (PDT) Received: from otter3.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 965DB43FDF for ; Thu, 3 Jul 2003 07:36:10 -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 h63Ea456037107; Thu, 3 Jul 2003 09:36:09 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <3F043F3A.1030907@centtech.com> Date: Thu, 03 Jul 2003 09:35:38 -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: David Gilbert References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <3EFFC3D5.7070605@mullet.se> <3F003092.30405@centtech.com> <16128.42007.75314.462685@canoe.velocet.net> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 03 Jul 2003 14:36:12 -0000 David Gilbert wrote: >>>>>>"Eric" == Eric Anderson writes: >>>>> > > Eric> Martin Nilsson wrote: > >>> I would be interested in helping to test this, I have a bunch of >>>lab boxes with 64/66PCI or PCI-X slots and NICs to work with. I'm >>>able to get access to most new motherboards and chipsets to test >>>chipset specific performance. What I need is someone to help me >>>develop useful things to test, validate results and to check >>>testing methodology. >> > > Eric> I'm interested in helping with this too.. I have access to > Eric> hundreds of boards, test equipment, processors, nics, you name > Eric> it. I just need to be led in the right direction with this. > > Eric> Anyone want to lead some minions in finding out some of this > Eric> info? > > We have a fairly well developed testing methodogy here ... with a > couple of people I can lend to the task. To be useful, they'll need > both root and console access to boxes (serial cross connects are fine) > ... along with somone who can play with BIOS settings on request. > We'd be very willing to donate the hands and eyes to do much of the > volume testing. > > ... our only problem is buying enough new hardware. What would be a good initial start hardware-wise? Eric -- ------------------------------------------------------------------ Eric Anderson Systems Administrator Centaur Technology Attitudes are contagious, is yours worth catching? ------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Thu Jul 3 13:09:55 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 9ADE937B401 for ; Thu, 3 Jul 2003 13:09:55 -0700 (PDT) Received: from sabre.velocet.net (sabre.velocet.net [216.138.209.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8D45C43FBD for ; Thu, 3 Jul 2003 13:09:54 -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 58B181391E6; Thu, 3 Jul 2003 16:09:38 -0400 (EDT) Received: by trooper.velocet.ca (Postfix, from userid 66) id 9E5A474DBE; Thu, 3 Jul 2003 16:09:37 -0400 (EDT) Received: by canoe.velocet.net (Postfix, from userid 101) id 345F547A4; Thu, 3 Jul 2003 16:09:35 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <16132.36223.175148.275860@canoe.velocet.net> Date: Thu, 3 Jul 2003 16:09:35 -0400 To: Eric Anderson In-Reply-To: <3F043F3A.1030907@centtech.com> References: <20030628190036.0E06B37B405@hub.freebsd.org> <000f01c33dad$1595a0f0$e602a8c0@flatline> <16126.9805.829406.368426@canoe.velocet.net> <000901c33dd1$12268780$0200000a@fireball> <16126.19861.842507.318997@canoe.velocet.net> <001f01c33e0f$1f4716d0$0200000a@fireball> <16127.2826.306427.946086@canoe.velocet.net> <3EFFC3D5.7070605@mullet.se> <3F003092.30405@centtech.com> <16128.42007.75314.462685@canoe.velocet.net> <3F043F3A.1030907@centtech.com> X-Mailer: VM 7.14 under 21.4 (patch 12) "Portable Code" XEmacs Lucid cc: David Gilbert cc: freebsd-performance@freebsd.org Subject: Re: Tuning Gigabit 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, 03 Jul 2003 20:09:55 -0000 >>>>> "Eric" == Eric Anderson writes: Eric> What would be a good initial start hardware-wise? To start testing this type of setup (gigabit routing), you'd need a vlan'able switch with many gigabit ports, and then for each test you need: 1 or more packet generators (one interface each) 1 router (two interfaces) 1 or more victims (one interface each) For bidirectional packet passing tests, it's best to have two (or more) generators and 2 or more victims. The victims generally have the least load and are good places to measure actual traffic passed. It's a good idea to have serial (or other) console on each of these machines as livelock is not uncommon. There are also useful statistics you can collect from the console that you can't always get from the network login ... because the near-livelock conditions may not give you enough updates. It is also sometimes a good idea to have a 100meg card in the boxes for OOB management. Multiply this times the number of tests you want to do. We find that you get about one test every two hours total work (much tearing down and building up of machines inbetween included in that estimate). 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 Fri Jul 4 14:25:53 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 C932A37B401 for ; Fri, 4 Jul 2003 14:25:53 -0700 (PDT) Received: from mta2.adelphia.net (mta2.adelphia.net [64.8.50.178]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1A2E844008 for ; Fri, 4 Jul 2003 14:25:53 -0700 (PDT) (envelope-from Support@Netflag.Net) Received: from nfn2.Netflag.Net ([68.69.240.35]) by mta2.adelphia.net (InterMail vM.5.01.05.32 201-253-122-126-132-20030307) with ESMTP id <20030704212552.JCJE1359.mta2.adelphia.net@nfn2.Netflag.Net> for ; Fri, 4 Jul 2003 17:25:52 -0400 Message-Id: <5.2.0.9.2.20030704142253.026801a0@pop.dc3.adelphia.net> X-Sender: pedramn@pop.dc3.adelphia.net X-Mailer: QUALCOMM Windows Eudora Version 5.2.0.9 Date: Fri, 04 Jul 2003 14:25:08 -0700 To: freebsd-performance@freebsd.org From: Pedram Nimreezi In-Reply-To: <20030701031608.11066.qmail@cr.yp.to> References: <20030626025029.71392.qmail@cr.yp.to> <200306260515.h5Q5FhPF020045@bitblocks.com> <20030626212659.51367.qmail@cr.yp.to> <20030630233353.GG96753@perrin.int.nxad.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Subject: linux-HA 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, 04 Jul 2003 21:25:54 -0000 I've been hearing a lot about Linux-HA (High Availability) as an avid Linux? not interested person I was wondering if there was any such construction available to freebsd... as opposed to like an taking over an IP when a specific server no longer pings... I say that since mysql replication doesn't work too well when you're load balancing using round robin A records. Forums lose data, stuff like that. From owner-freebsd-performance@FreeBSD.ORG Fri Jul 4 23:34:06 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 A0C3237B401 for ; Fri, 4 Jul 2003 23:34:06 -0700 (PDT) Received: from mail.webjockey.net (mail.webjockey.net [208.141.46.3]) by mx1.FreeBSD.org (Postfix) with ESMTP id 85CA443FAF for ; Fri, 4 Jul 2003 23:34:05 -0700 (PDT) (envelope-from gary@outloud.org) Received: from cheeta-vmcymvfy.outloud.org (wv-mrtnbrg-cmts1a-a-168.shphwv.adelphia.net [68.67.224.168]) by mail.webjockey.net (8.12.9/8.12.8) with ESMTP id h656YbQT043968 for ; Sat, 5 Jul 2003 02:34:38 -0400 (EDT) (envelope-from gary@outloud.org) Message-Id: <6.0.0.10.0.20030705022833.025a2c88@localhost> X-Sender: ancient/208.141.46.3@localhost X-Mailer: QUALCOMM Windows Eudora Version 6.0.0.10 (Beta) Date: Sat, 05 Jul 2003 02:34:05 -0400 To: freebsd-performance@freebsd.org From: Gary Stanley Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Subject: SCSI Bus 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: Sat, 05 Jul 2003 06:34:06 -0000 Hiya. With Adaptec 2120S Raid Controllers (PCI-X 66mhz) and 5 or 6 Ultra320 RAID5 drives, what's the maximum data rate I could achieve on the array? It currently seems to max out around 30mbyte/s with a small amount of burst. procs memory page disks faults cpu r b w avm fre flt re pi po fr sr aa0 md0 in sy cs us sy id 0 8 0 264040 75156 83 3 0 0 8321 8310 0 0 8251 23037 2613 14 58 28 6 2 0 265680 85652 80 0 0 0 8375 10985 651 0 8477 177349 3938 14 62 24 6 2 0 265780 95692 20 0 0 2 8419 11011 651 0 8426 201621 3493 12 62 26 tty aacd0 acd0 fd0 cpu tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy in id 0 2 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 14 0 33 25 28 0 77 51.71 637 32.18 0.00 0 0.00 0.00 0 0.00 7 0 26 24 43 0 76 51.38 656 32.94 0.00 0 0.00 0.00 0 0.00 9 0 27 25 39 0 76 51.85 616 31.18 0.00 0 0.00 0.00 0 0.00 8 0 26 26 39 0 76 51.56 636 32.01 0.00 0 0.00 0.00 0 0.00 6 0 22 24 47 ITEM SIZE LIMIT USED FREE REQUESTS PIPE: 160, 0, 4, 98, 20542 SWAPMETA: 160, 233016, 19, 57, 12493 unpcb: 160, 0, 46, 54, 21349 ripcb: 192, 131070, 0, 42, 5 syncache: 160, 15359, 8, 273, 2099188 tcpcb: 576, 131070, 3956, 2664, 1970515 udpcb: 192, 131070, 6, 36, 243 socket: 192, 131070, 4008, 2690, 1992113 DIRHASH: 1024, 0, 471, 377, 3917 KNOTE: 64, 0, 6882, 2782, 3950885 NFSNODE: 352, 0, 647, 849, 2379 NFSMOUNT: 544, 0, 2, 12, 2 VNODE: 192, 0, 34216, 22, 34216 NAMEI: 1024, 0, 0, 32, 22168837 VMSPACE: 192, 0, 45, 83, 38265 PROC: 416, 0, 51, 47, 38271 DP fakepg: 64, 0, 0, 0, 0 PV ENTRY: 28, 2690702, 140870, 383281, 23461659 MAP ENTRY: 48, 0, 3633, 5760, 3394017 KMAP ENTRY: 48, 64455, 233, 151, 83750 MAP: 108, 0, 7, 3, 7 VM OBJECT: 92, 0, 32805, 99, 595113 If it helps any, Dual Xeon 2.0ghz procs, 2 gigs of ram, supermicro board, etc. From owner-freebsd-performance@FreeBSD.ORG Sat Jul 5 04:47:04 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 A699337B401 for ; Sat, 5 Jul 2003 04:47:04 -0700 (PDT) Received: from mailout05.sul.t-online.com (mailout05.sul.t-online.com [194.25.134.82]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8D1CA44015 for ; Sat, 5 Jul 2003 04:47:03 -0700 (PDT) (envelope-from Alexander@Leidinger.net) Received: from fwd06.aul.t-online.de by mailout05.sul.t-online.com with smtp id 19YlVO-0004s4-03; Sat, 05 Jul 2003 13:47:02 +0200 Received: from Andro-Beta.Leidinger.net (r1Ou26ZcgeQpqdJpp7LcHJVdOsfaBskJuVHyRPHVyiT7PKy48Xy38K@[80.131.125.196]) by fmrl06.sul.t-online.com with esmtp id 19YlVD-25IYnQ0; Sat, 5 Jul 2003 13:46:51 +0200 Received: from Magelan.Leidinger.net (Magelan [192.168.1.1]) h65BknK4044349 for ; Sat, 5 Jul 2003 13:46:50 +0200 (CEST) (envelope-from Alexander@Leidinger.net) Received: from Magelan.Leidinger.net (netchild@localhost [127.0.0.1]) by Magelan.Leidinger.net (8.12.9/8.12.9) with SMTP id h65BknfJ000816 for ; Sat, 5 Jul 2003 13:46:49 +0200 (CEST) (envelope-from Alexander@Leidinger.net) Date: Sat, 5 Jul 2003 13:46:49 +0200 From: Alexander Leidinger To: freebsd-performance@freebsd.org Message-Id: <20030705134649.5f4f7945.Alexander@Leidinger.net> In-Reply-To: <5.2.0.9.2.20030704142253.026801a0@pop.dc3.adelphia.net> References: <20030626025029.71392.qmail@cr.yp.to> <200306260515.h5Q5FhPF020045@bitblocks.com> <20030626212659.51367.qmail@cr.yp.to> <20030630233353.GG96753@perrin.int.nxad.com> <5.2.0.9.2.20030704142253.026801a0@pop.dc3.adelphia.net> X-Mailer: Sylpheed version 0.8.10claws (GTK+ 1.2.10; i386-portbld-freebsd5.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Seen: false X-ID: r1Ou26ZcgeQpqdJpp7LcHJVdOsfaBskJuVHyRPHVyiT7PKy48Xy38K@t-dialin.net Subject: Re: linux-HA 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: Sat, 05 Jul 2003 11:47:04 -0000 On Fri, 04 Jul 2003 14:25:08 -0700 Pedram Nimreezi wrote: > I've been hearing a lot about Linux-HA (High Availability) as an avid > Linux? not interested person > I was wondering if there was any such construction available to freebsd... http://www.leidinger.net/cgi-bin/search.pl?q=cluster&num=10 > as opposed to like an > taking over an IP when a specific server no longer pings... I say that > since mysql replication doesn't > work too well when you're load balancing using round robin A records. > Forums lose data, stuff like that. I don't have hard data for load balancing, but at least for failover situations 2 MySQL (3.23.x) servers replicate without problems here. For more than 2 systems it is a little bit tricky. Bye, Alexander. -- "One world, one web, one program" -- Microsoft promotional ad "Ein Volk, ein Reich, ein Fuehrer" -- Adolf Hitler http://www.Leidinger.net Alexander @ Leidinger.net GPG fingerprint = C518 BC70 E67F 143F BE91 3365 79E2 9C60 B006 3FE7 From owner-freebsd-performance@FreeBSD.ORG Sat Jul 5 12:56:44 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 C14D337B401 for ; Sat, 5 Jul 2003 12:56:44 -0700 (PDT) Received: from mta1.adelphia.net (mta1.adelphia.net [64.8.50.175]) by mx1.FreeBSD.org (Postfix) with ESMTP id E87AD43F93 for ; Sat, 5 Jul 2003 12:56:43 -0700 (PDT) (envelope-from Support@Netflag.Net) Received: from nfn2.Netflag.Net ([68.69.240.35]) by mta1.adelphia.net (InterMail vM.5.01.05.32 201-253-122-126-132-20030307) with ESMTP id <20030705200100.DZHF25556.mta1.adelphia.net@nfn2.Netflag.Net>; Sat, 5 Jul 2003 16:01:00 -0400 Message-Id: <5.2.0.9.2.20030705120909.026a7df8@pop.dc3.adelphia.net> X-Sender: pedramn@pop.dc3.adelphia.net X-Mailer: QUALCOMM Windows Eudora Version 5.2.0.9 Date: Sat, 05 Jul 2003 12:19:49 -0700 To: Alexander Leidinger , freebsd-performance@freebsd.org From: Pedram Nimreezi In-Reply-To: <20030705134649.5f4f7945.Alexander@Leidinger.net> References: <5.2.0.9.2.20030704142253.026801a0@pop.dc3.adelphia.net> <20030626025029.71392.qmail@cr.yp.to> <200306260515.h5Q5FhPF020045@bitblocks.com> <20030626212659.51367.qmail@cr.yp.to> <20030630233353.GG96753@perrin.int.nxad.com> <5.2.0.9.2.20030704142253.026801a0@pop.dc3.adelphia.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Content-Filtered-By: Mailman/MimeDel 2.1.1 Subject: Re: linux-HA 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: Sat, 05 Jul 2003 19:56:45 -0000 isn't it more like Eine Welt, ein Netz, ein Programm anyway.. I lose forum data, maybe it was a 4.x thing? At 01:46 PM 7/5/2003 +0200, Alexander Leidinger wrote: >On Fri, 04 Jul 2003 14:25:08 -0700 >Pedram Nimreezi wrote: > > > I've been hearing a lot about Linux-HA (High Availability) as an avid > > Linux? not interested person > > I was wondering if there was any such construction available to freebsd... > >http://www.leidinger.net/cgi-bin/search.pl?q=cluster&num=10 > > > as opposed to like an > > taking over an IP when a specific server no longer pings... I say that > > since mysql replication doesn't > > work too well when you're load balancing using round robin A records. > > Forums lose data, stuff like that. > >I don't have hard data for load balancing, but at least for failover >situations 2 MySQL (3.23.x) servers replicate without problems here. For >more than 2 systems it is a little bit tricky. > >Bye, >Alexander. > >-- > "One world, one web, one program" -- Microsoft promotional ad > "Ein Volk, ein Reich, ein Fuehrer" -- Adolf Hitler > >http://www.Leidinger.net Alexander @ Leidinger.net > GPG fingerprint = C518 BC70 E67F 143F BE91 3365 79E2 9C60 B006 3FE7 >_______________________________________________ >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"