From owner-freebsd-performance@FreeBSD.ORG Sat Nov 11 18:37:08 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 226FE16A407 for ; Sat, 11 Nov 2006 18:37:08 +0000 (UTC) (envelope-from amarat@ksu.ru) Received: from zealot.ksu.ru (zealot.ksu.ru [194.85.245.161]) by mx1.FreeBSD.org (Postfix) with ESMTP id 318B443D5A for ; Sat, 11 Nov 2006 18:37:05 +0000 (GMT) (envelope-from amarat@ksu.ru) Received: from [127.0.0.1] (localhost.lnet [127.0.0.1]) by zealot.ksu.ru (8.13.8/8.13.8) with ESMTP id kABIax82034579 for ; Sat, 11 Nov 2006 21:36:59 +0300 (MSK) (envelope-from amarat@ksu.ru) Message-ID: <4556184B.3090604@ksu.ru> Date: Sat, 11 Nov 2006 21:36:59 +0300 From: "Marat N.Afanasyev" User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.7.13) Gecko/20060514 X-Accept-Language: ru, en MIME-Version: 1.0 To: freebsd-performance@freebsd.org Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sun, 12 Nov 2006 05:12:35 +0000 Subject: trouble with mysql replica and 3ware 9590 RAID controller X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 11 Nov 2006 18:37:08 -0000 Hello! I've encountered a trouble with very low performance of mysql replica on 9590SE controller. as replica, mysql performs only updates and no selects at all, but I cannot be satisfied by performance of this replica, because of 100% busy of disk array with about 3-4 MBytes/s activity, e.g. iostat -x: extended device statistics device r/s w/s kr/s kw/s wait svc_t %b da0 55.5 78.9 928.1 2047.6 1 108.0 98 and more sadly, disk wait time increases sometimes to 300 seconds and more. I've made NCQ on, changed strategy to perfom, but nothing helps. If I stop mysql, then I can write about 30-40 MBytes per second to this array (raid 1) And I should say that this replica worked just fine on slackware with p3 866 and IDE disks. Mysql version is 4.0.27, twa firmware is 3.04.01.010 -- SY, Marat From owner-freebsd-performance@FreeBSD.ORG Sun Nov 12 21:56:33 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 EA8D316A58C for ; Sun, 12 Nov 2006 21:56:33 +0000 (UTC) (envelope-from silencer@free-4ever.net) Received: from orthosie.free-4ever.net (orthosie.free-4ever.net [88.191.27.106]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7926E43D45 for ; Sun, 12 Nov 2006 21:56:33 +0000 (GMT) (envelope-from silencer@free-4ever.net) Received: from localhost (localhost.localdomain [127.0.0.1]) by orthosie.free-4ever.net (Postfix) with ESMTP id 078CF1BC60 for ; Sun, 12 Nov 2006 22:56:31 +0100 (CET) X-Virus-Scanned: Debian amavisd-new at free-4ever.net Received: from orthosie.free-4ever.net ([127.0.0.1]) by localhost (orthosie.free-4ever.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 2fHgUXuHu-rv for ; Sun, 12 Nov 2006 22:56:28 +0100 (CET) Received: from [192.168.128.200] (lysithea.free-4ever.net [62.147.158.56]) by orthosie.free-4ever.net (Postfix) with ESMTP id 5F62D1B5FF for ; Sun, 12 Nov 2006 22:56:28 +0100 (CET) Message-ID: <4557988B.4000902@free-4ever.net> Date: Sun, 12 Nov 2006 22:56:27 +0100 From: Guillaume User-Agent: IceDove 1.5.0.7 (X11/20061013) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: In-Reply-To: Content-Type: text/plain; charset=GB2312 Content-Transfer-Encoding: 8bit Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 12 Nov 2006 21:56:34 -0000 cool fire a écrit : > Hi silencer, > > i have 50+ 2900/3500 switches in my cacti, > > under every devices, i have all 24/48 ports monitored. > > BR > > coolfire > > Hi, That's not a lot for a Cacti server running on this hardware ! Do you use cactiD as pooler ? CactiD is a "C" poller to replace the php poller, the performence is really higher !! Guillaume -- Guillaume E-mail: silencer__free-4ever__net Blog: http://guillaume.free-4ever.net ---- Site: http://www.free-4ever.net From owner-freebsd-performance@FreeBSD.ORG Mon Nov 13 01:32:10 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 6F74316A407 for ; Mon, 13 Nov 2006 01:32:10 +0000 (UTC) (envelope-from drechsau@Geeks.ORG) Received: from mail.geeks.org (jacobs.geeks.org [204.153.247.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1302F43D46 for ; Mon, 13 Nov 2006 01:32:09 +0000 (GMT) (envelope-from drechsau@Geeks.ORG) Received: by mail.geeks.org (Postfix, from userid 1000) id 3B59315904F; Sun, 12 Nov 2006 19:32:09 -0600 (CST) Date: Sun, 12 Nov 2006 19:32:09 -0600 From: Mike Horwath To: Guillaume Message-ID: <20061113013209.GB65089@Geeks.ORG> Mail-Followup-To: Guillaume , freebsd-performance@freebsd.org References: <4557988B.4000902@free-4ever.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4557988B.4000902@free-4ever.net> X-PGP-Fingerprint: D8 24 CC E6 47 5F E4 60 BF B7 6E FA BF C7 6E C5 X-GPG-Fingerprint: 6A89 E78A B8B1 69D9 8CDB E966 4A5A C3F9 A1B0 C381 User-Agent: mutt-ng/devel-r804 (FreeBSD) Cc: freebsd-performance@freebsd.org Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Nov 2006 01:32:10 -0000 On Sun, Nov 12, 2006 at 10:56:27PM +0100, Guillaume wrote: > That's not a lot for a Cacti server running on this hardware ! > > Do you use cactiD as pooler ? > > CactiD is a "C" poller to replace the php poller, the performence is > really higher !! Not in my experience using FreeBSD 4.x... The system I do this on today will be getting an upgrade, so the issue will be mitigated I hope :) cactid does GREAT on a small number of polls, but seems to *skip* or *drop* readings on higher than ~1500 polls in my experience. The normal PHP poller handles the 1800+ polls without issue, just takes 2-3x longer (and still reasonable). -- Mike Horwath, reachable via drechsau@Geeks.ORG From owner-freebsd-performance@FreeBSD.ORG Mon Nov 13 09:18:24 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 8529A16AE9B for ; Mon, 13 Nov 2006 09:18:24 +0000 (UTC) (envelope-from silencer@free-4ever.net) Received: from orthosie.free-4ever.net (orthosie.free-4ever.net [88.191.27.106]) by mx1.FreeBSD.org (Postfix) with ESMTP id A4D5E43D49 for ; Mon, 13 Nov 2006 09:18:23 +0000 (GMT) (envelope-from silencer@free-4ever.net) Received: from localhost (localhost.localdomain [127.0.0.1]) by orthosie.free-4ever.net (Postfix) with ESMTP id ABB861BC6B for ; Mon, 13 Nov 2006 09:44:57 +0100 (CET) X-Virus-Scanned: Debian amavisd-new at free-4ever.net Received: from orthosie.free-4ever.net ([127.0.0.1]) by localhost (orthosie.free-4ever.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id x3pb1mOZaorx for ; Mon, 13 Nov 2006 09:44:55 +0100 (CET) Received: from [192.168.48.114] (unknown [83.145.94.46]) by orthosie.free-4ever.net (Postfix) with ESMTP id 806CB1BC60 for ; Mon, 13 Nov 2006 09:44:55 +0100 (CET) Message-ID: <45583087.2010503@free-4ever.net> Date: Mon, 13 Nov 2006 09:44:55 +0100 From: Guillaume User-Agent: IceDove 1.5.0.7 (X11/20061013) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: In-Reply-To: Content-Type: text/plain; charset=GB2312 Content-Transfer-Encoding: 8bit Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Nov 2006 09:18:24 -0000 cool fire a écrit : > > > hi Guillaume, > > the cactid can't update the graph > > BR > > > > ==== > FreeBSD The Power to Serve > ==== > > > From: Guillaume > To: freebsd-performance@freebsd.org > Subject: Re: cacti system tuning > Date: Sun, 12 Nov 2006 22:56:27 +0100 > MIME-Version: 1.0 > Received: from mx2.freebsd.org ([216.136.204.119]) by > bay0-mc2-f12.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.2444); > Sun, 12 Nov 2006 13:59:59 -0800 > Received: from hub.freebsd.org (hub.freebsd.org [216.136.204.18])by > mx2.freebsd.org (Postfix) with ESMTP id 6A6E114BE0C;Sun, 12 Nov 2006 > 21:56:46 +0000 (GMT)(envelope-from owner-freebsd-performance@freebsd.org) > Received: from hub.freebsd.org (localhost [127.0.0.1])by hub.freebsd.org > (Postfix) with ESMTP id 9E06816A5DC;Sun, 12 Nov 2006 21:56:43 +0000 > (UTC)(envelope-from owner-freebsd-performance@freebsd.org) > Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])by > hub.freebsd.org (Postfix) with ESMTP id EA8D316A58Cfor > ;Sun, 12 Nov 2006 21:56:33 +0000 > (UTC)(envelope-from silencer@free-4ever.net) > Received: from orthosie.free-4ever.net > (orthosie.free-4ever.net[88.191.27.106])by mx1.FreeBSD.org (Postfix) > with ESMTP id 7926E43D45for ;Sun, 12 > Nov 2006 21:56:33 +0000 (GMT)(envelope-from silencer@free-4ever.net) > Received: from localhost (localhost.localdomain [127.0.0.1])by > orthosie.free-4ever.net (Postfix) with ESMTP id 078CF1BC60for > ;Sun, 12 Nov 2006 22:56:31 +0100 (CET) > Received: from orthosie.free-4ever.net ([127.0.0.1])by localhost > (orthosie.free-4ever.net [127.0.0.1]) (amavisd-new,port 10024)with ESMTP > id 2fHgUXuHu-rv for ;Sun, 12 Nov 2006 > 22:56:28 +0100 (CET) > Received: from [192.168.128.200] (lysithea.free-4ever.net > [62.147.158.56])by orthosie.free-4ever.net (Postfix) with ESMTP id > 5F62D1B5FFfor ;Sun, 12 Nov 2006 > 22:56:28 +0100 (CET) > cool fire a écrit : >> Hi silencer, >> >> i have 50+ 2900/3500 switches in my cacti, >> >> under every devices, i have all 24/48 ports monitored. >> >> BR >> >> coolfire >> >> > > Hi, > > That's not a lot for a Cacti server running on this hardware ! > > Do you use cactiD as pooler ? > > CactiD is a "C" poller to replace the php poller, the performence is > really higher !! > > Guillaume > > > -- > Guillaume > E-mail: silencer__free-4ever__net > Blog: http://guillaume.free-4ever.net > ---- > Site: http://www.free-4ever.net > _______________________________________________ > 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" > > _________________________________________________________________ > 享用世界上最大的电子邮件系统— MSN Hotmail。 http://www.hotmail.com Hi, Did you configure it well ??? Cactid needs access to the database... Guillaume -- Guillaume E-mail: silencer__free-4ever__net Blog: http://guillaume.free-4ever.net ---- Site: http://www.free-4ever.net From owner-freebsd-performance@FreeBSD.ORG Mon Nov 13 09:35:03 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 9A25816A588 for ; Mon, 13 Nov 2006 09:35:03 +0000 (UTC) (envelope-from silencer@free-4ever.net) Received: from orthosie.free-4ever.net (orthosie.free-4ever.net [88.191.27.106]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1C67043D55 for ; Mon, 13 Nov 2006 09:35:02 +0000 (GMT) (envelope-from silencer@free-4ever.net) Received: from localhost (localhost.localdomain [127.0.0.1]) by orthosie.free-4ever.net (Postfix) with ESMTP id 445901BC68 for ; Mon, 13 Nov 2006 09:44:10 +0100 (CET) X-Virus-Scanned: Debian amavisd-new at free-4ever.net Received: from orthosie.free-4ever.net ([127.0.0.1]) by localhost (orthosie.free-4ever.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id n5Os2M+pjXzt for ; Mon, 13 Nov 2006 09:44:07 +0100 (CET) Received: from [192.168.48.114] (unknown [83.145.94.46]) by orthosie.free-4ever.net (Postfix) with ESMTP id 52D701B5FF for ; Mon, 13 Nov 2006 09:44:07 +0100 (CET) Message-ID: <45583056.8060103@free-4ever.net> Date: Mon, 13 Nov 2006 09:44:06 +0100 From: Guillaume User-Agent: IceDove 1.5.0.7 (X11/20061013) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <4557988B.4000902@free-4ever.net> <20061113013209.GB65089@Geeks.ORG> In-Reply-To: <20061113013209.GB65089@Geeks.ORG> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Nov 2006 09:35:03 -0000 Mike Horwath a 閏rit : > On Sun, Nov 12, 2006 at 10:56:27PM +0100, Guillaume wrote: >> That's not a lot for a Cacti server running on this hardware ! >> >> Do you use cactiD as pooler ? >> >> CactiD is a "C" poller to replace the php poller, the performence is >> really higher !! > > Not in my experience using FreeBSD 4.x... > > The system I do this on today will be getting an upgrade, so the issue > will be mitigated I hope :) > > cactid does GREAT on a small number of polls, but seems to *skip* or > *drop* readings on higher than ~1500 polls in my experience. > > The normal PHP poller handles the 1800+ polls without issue, just > takes 2-3x longer (and still reasonable). > I don't have too much experience with Cactid on Freebsd especially on old version. On my 6.1, Cactid runs very well with around 3000 pollings... Guillaume -- Guillaume E-mail: silencer__free-4ever__net Blog: http://guillaume.free-4ever.net ---- Site: http://www.free-4ever.net From owner-freebsd-performance@FreeBSD.ORG Mon Nov 13 19:19:15 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 D4B6616A4EB for ; Mon, 13 Nov 2006 19:19:15 +0000 (UTC) (envelope-from billf@elvis.mu.org) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6E18F43D93 for ; Mon, 13 Nov 2006 19:19:02 +0000 (GMT) (envelope-from billf@elvis.mu.org) Received: by elvis.mu.org (Postfix, from userid 1098) id 6118A1A4D8B; Mon, 13 Nov 2006 11:19:02 -0800 (PST) Date: Mon, 13 Nov 2006 11:19:02 -0800 From: Bill Fumerola To: Guillaume , freebsd-performance@freebsd.org Message-ID: <20061113191902.GJ28339@elvis.mu.org> References: <4557988B.4000902@free-4ever.net> <20061113013209.GB65089@Geeks.ORG> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061113013209.GB65089@Geeks.ORG> User-Agent: Mutt/1.4.2.2i X-Operating-System: FreeBSD 6.1-MUORG-20060531 amd64 X-PGP-Key: 1024D/7F868268 X-PGP-Fingerprint: 5B2D 908E 4C2B F253 DAEB FC01 8436 B70B 7F86 8268 Cc: Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Nov 2006 19:19:15 -0000 On Sun, Nov 12, 2006 at 07:32:09PM -0600, Mike Horwath wrote: > cactid does GREAT on a small number of polls, but seems to *skip* or > *drop* readings on higher than ~1500 polls in my experience. cactid is just rtgpoll (from rtg.sourceforge.net) with a few customizations. unfortunately, the copy is from an old codebase and there are problems in the threading & snmp code from those days. even more unfortunately, rtgpoll development seems to be hopelessly stalled due in part to project mismanagement. > The normal PHP poller handles the 1800+ polls without issue, just > takes 2-3x longer (and still reasonable). it's also much easier to debug problems with either the poller itself or the devices being polled. i'd use the php poller with cacti. -- - bill fumerola / billf@FreeBSD.org From owner-freebsd-performance@FreeBSD.ORG Mon Nov 13 19:48:00 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 E9DD016A4AB; Mon, 13 Nov 2006 19:48:00 +0000 (UTC) (envelope-from lamont@cluepon.com) Received: from clavin.cluepon.com (clavin.cluepon.com [64.154.215.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2932943D69; Mon, 13 Nov 2006 19:46:50 +0000 (GMT) (envelope-from lamont@cluepon.com) Received: from lamont by clavin.cluepon.com with local (Exim 3.03 #1) id 1GjhlX-0001JZ-00; Mon, 13 Nov 2006 11:46:47 -0800 Date: Mon, 13 Nov 2006 11:46:47 -0800 From: Lamont Lucas To: Bill Fumerola Message-ID: <20061113194647.GK52665@clavin.cluepon.com> References: <4557988B.4000902@free-4ever.net> <20061113013209.GB65089@Geeks.ORG> <20061113191902.GJ28339@elvis.mu.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061113191902.GJ28339@elvis.mu.org> Organization: Cluepon Consulting, Inc. User-Agent: Mutt/1.5.4i Cc: freebsd-performance@freebsd.org, Guillaume Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Nov 2006 19:48:01 -0000 On Mon, Nov 13, 2006 at 11:19:02AM -0800, Bill Fumerola wrote: > it's also much easier to debug problems with either the poller itself > or the devices being polled. > > i'd use the php poller with cacti. Agreed. I had problems with the poller taking too long to process our 1200 datasources but quickly resolved it by increasing the number of poller processes that could run at once, from the default 1 up to 4. My 6.1-release machine (2 cpus, plenty of ram) never breaks a sweat polling those hosts and processing the results. -- - Lamont "I am not an atomic playboy." From owner-freebsd-performance@FreeBSD.ORG Tue Nov 14 15:03:27 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 B25DA16A407 for ; Tue, 14 Nov 2006 15:03:27 +0000 (UTC) (envelope-from coolfire@live.fr) Received: from bay0-omc1-s24.bay0.hotmail.com (bay0-omc1-s24.bay0.hotmail.com [65.54.246.96]) by mx1.FreeBSD.org (Postfix) with ESMTP id D723E43D5A for ; Tue, 14 Nov 2006 15:03:26 +0000 (GMT) (envelope-from coolfire@live.fr) Received: from hotmail.com ([64.4.38.22]) by bay0-omc1-s24.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 14 Nov 2006 07:03:14 -0800 Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Tue, 14 Nov 2006 07:03:14 -0800 Message-ID: Received: from 64.4.38.200 by by116fd.bay116.hotmail.msn.com with HTTP; Tue, 14 Nov 2006 15:03:12 GMT X-Originating-IP: [219.136.29.199] X-Originating-Email: [coolfire@live.fr] X-Sender: coolfire@live.fr In-Reply-To: <20061113013209.GB65089@Geeks.ORG> From: "cool fire" To: drechsau@Geeks.ORG, silencer@free-4ever.net Date: Tue, 14 Nov 2006 23:03:12 +0800 Mime-Version: 1.0 Content-Type: text/plain; charset=gb2312; format=flowed X-OriginalArrivalTime: 14 Nov 2006 15:03:14.0101 (UTC) FILETIME=[020F8E50:01C707FE] Cc: freebsd-performance@freebsd.org Subject: Re: cacti system tuning X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 14 Nov 2006 15:03:27 -0000 hi Mike, thanks for sharing your experinces BR collfire ==== FreeBSD The Power to Serve ==== ----Original Message Follows---- From: Mike Horwath To: Guillaume CC: freebsd-performance@freebsd.org Subject: Re: cacti system tuning Date: Sun, 12 Nov 2006 19:32:09 -0600 MIME-Version: 1.0 Received: from mx2.freebsd.org ([216.136.204.119]) by bay0-mc12-f6.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.2444); Sun, 12 Nov 2006 17:33:07 -0800 Received: from hub.freebsd.org (hub.freebsd.org [216.136.204.18])by mx2.freebsd.org (Postfix) with ESMTP id 99DB55B2DC;Mon, 13 Nov 2006 01:32:19 +0000 (GMT)(envelope-from owner-freebsd-performance@freebsd.org) Received: from hub.freebsd.org (localhost [127.0.0.1])by hub.freebsd.org (Postfix) with ESMTP id 222BD16A53A;Mon, 13 Nov 2006 01:32:16 +0000 (UTC)(envelope-from owner-freebsd-performance@freebsd.org) Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])by hub.freebsd.org (Postfix) with ESMTP id 6F74316A407for ;Mon, 13 Nov 2006 01:32:10 +0000 (UTC)(envelope-from drechsau@Geeks.ORG) Received: from mail.geeks.org (jacobs.geeks.org [204.153.247.1])by mx1.FreeBSD.org (Postfix) with ESMTP id 1302F43D46for ;Mon, 13 Nov 2006 01:32:09 +0000 (GMT)(envelope-from drechsau@Geeks.ORG) Received: by mail.geeks.org (Postfix, from userid 1000)id 3B59315904F; Sun, 12 Nov 2006 19:32:09 -0600 (CST) X-Message-Info: LsUYwwHHNt2oZhWA5Cl1t95D+PyOXotfOG55VqAw0nI= X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Mail-Followup-To: Guillaume ,freebsd-performance@freebsd.org References: <4557988B.4000902@free-4ever.net> X-PGP-Fingerprint: D8 24 CC E6 47 5F E4 60 BF B7 6E FA BF C7 6E C5 X-GPG-Fingerprint: 6A89 E78A B8B1 69D9 8CDB E966 4A5A C3F9 A1B0 C381 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: owner-freebsd-performance@freebsd.org Return-Path: owner-freebsd-performance@freebsd.org X-OriginalArrivalTime: 13 Nov 2006 01:33:08.0034 (UTC) FILETIME=[AC2C9220:01C706C3] On Sun, Nov 12, 2006 at 10:56:27PM +0100, Guillaume wrote: > That's not a lot for a Cacti server running on this hardware ! > > Do you use cactiD as pooler ? > > CactiD is a "C" poller to replace the php poller, the performence is > really higher !! Not in my experience using FreeBSD 4.x... The system I do this on today will be getting an upgrade, so the issue will be mitigated I hope :) cactid does GREAT on a small number of polls, but seems to *skip* or *drop* readings on higher than ~1500 polls in my experience. The normal PHP poller handles the 1800+ polls without issue, just takes 2-3x longer (and still reasonable). -- Mike Horwath, reachable via drechsau@Geeks.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" _________________________________________________________________ 与联机的朋友进行交流，请使用 MSN Messenger: http://messenger.msn.com/cn From owner-freebsd-performance@FreeBSD.ORG Thu Nov 16 16:40:56 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org 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 DD98E16A40F; Thu, 16 Nov 2006 16:40:56 +0000 (UTC) (envelope-from marcelo@registro.br) Received: from clone.registro.br (clone.registro.br [200.160.2.4]) by mx1.FreeBSD.org (Postfix) with ESMTP id 51BE143D5C; Thu, 16 Nov 2006 16:40:56 +0000 (GMT) (envelope-from marcelo@registro.br) Received: by clone.registro.br (Postfix, from userid 1014) id 03E102A479; Thu, 16 Nov 2006 14:40:54 -0200 (BRST) Date: Thu, 16 Nov 2006 14:40:54 -0200 From: Marcelo Gardini do Amaral To: Robert Watson Message-ID: <20061116164053.GR57732@registro.br> References: <20061030192702.GG76994@registro.br> <20061111091844.I63959@fledge.watson.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061111091844.I63959@fledge.watson.org> User-Agent: Mutt/1.4.2.1i X-Mailman-Approved-At: Thu, 16 Nov 2006 17:21:36 +0000 Cc: freebsd-performance@freebsd.org, kreios@gmail.com Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 16 Nov 2006 16:40:56 -0000 > FYI: In response to feedback from ISC, there are UDP transmit optimizations > in FreeBSD 7.x. These have a relatively minor performance impact for > single-threaded applications, but in the special case of BIND accessing a > single UDP socket from many different threads, it significantly improves > performance. I'll look at MFC'ing these to 6.x after 6.2-RELEASE > (especially if reminded in a month or so :-). > > With regard to the possible bge issue -- I would encourage you to test > using a 7.x kernel, ideally with all the debugging disabled, and see if > there's been any improvement (or regression). There has been a lot of > change in these areas, and it would be helpful to know what, if any, impact > this has had. I made some tests using 7.x with all the debugging disabled: queries / s Int bind (d_t) bind (e_t) nsd (1_s) nsd (2_s) --- ---------- ---------- --------- --------- bge 15439 14733 12910 10946 em 37655 34092 42411 41974 d_t: disable threads e_t: enable threads (libpthread) 1_s: 1 server forked 2_s: 2 server forked Bind: 9.2.3 NSD: 3.0.2 em: Dell 1950, Intel NIC, SMP kernel bge: HP Blade BL35p, Broadcom NIC, SMP kernel Client: Dell 1750, Intel NIC, FreeBSD 4.11 UP, running queryperf The results are very good for em NIC, better than my numbers [1] with FreeBSD 6.1 some months ago. So I guess that we had an improvement :-) But I got the same poor performance with the bge interface. The problem remains. [1] http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011767.html Cheers, Marcelo -- Att., Marcelo Gardini NIC .br From owner-freebsd-performance@FreeBSD.ORG Fri Nov 17 09:14:22 2006 Return-Path: X-Original-To: freebsd-performance@FreeBSD.org 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 06FEE16A415; Fri, 17 Nov 2006 09:14:22 +0000 (UTC) (envelope-from bde@zeta.org.au) Received: from mailout1.pacific.net.au (mailout1-3.pacific.net.au [61.8.2.210]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9BF8743D45; Fri, 17 Nov 2006 09:14:21 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy2.pacific.net.au (mailproxy2.pacific.net.au [61.8.2.163]) by mailout1.pacific.net.au (Postfix) with ESMTP id 3FAB15A073F; Fri, 17 Nov 2006 20:14:20 +1100 (EST) Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy2.pacific.net.au (Postfix) with ESMTP id 420E827405; Fri, 17 Nov 2006 20:14:19 +1100 (EST) Date: Fri, 17 Nov 2006 20:14:18 +1100 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Marcelo Gardini do Amaral In-Reply-To: <20061116164053.GR57732@registro.br> Message-ID: <20061117201026.N11101@delplex.bde.org> References: <20061030192702.GG76994@registro.br> <20061111091844.I63959@fledge.watson.org> <20061116164053.GR57732@registro.br> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: kreios@gmail.com, freebsd-performance@FreeBSD.org, Robert Watson Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 17 Nov 2006 09:14:22 -0000 On Thu, 16 Nov 2006, Marcelo Gardini do Amaral wrote: > I made some tests using 7.x with all the debugging disabled: > > queries / s > > Int bind (d_t) bind (e_t) nsd (1_s) nsd (2_s) > --- ---------- ---------- --------- --------- > > bge 15439 14733 12910 10946 > em 37655 34092 42411 41974 > /// > The results are very good for em NIC, better than my numbers [1] with > FreeBSD 6.1 some months ago. So I guess that we had an improvement :-) > > But I got the same poor performance with the bge interface. The > problem remains. > > [1] http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011767.html Try my fix for bge's interrupt handling in freebsd-net. Bruce From owner-freebsd-performance@FreeBSD.ORG Fri Nov 17 16:35:37 2006 Return-Path: X-Original-To: freebsd-performance@FreeBSD.org 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 52BAB16A412; Fri, 17 Nov 2006 16:35:37 +0000 (UTC) (envelope-from marcelo@registro.br) Received: from clone.registro.br (clone.registro.br [200.160.2.4]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5CE9043D5A; Fri, 17 Nov 2006 16:35:36 +0000 (GMT) (envelope-from marcelo@registro.br) Received: by clone.registro.br (Postfix, from userid 1014) id 1D25A2A551; Fri, 17 Nov 2006 14:35:34 -0200 (BRST) Date: Fri, 17 Nov 2006 14:35:34 -0200 From: Marcelo Gardini do Amaral To: Bruce Evans Message-ID: <20061117163534.GA57732@registro.br> References: <20061030192702.GG76994@registro.br> <20061111091844.I63959@fledge.watson.org> <20061116164053.GR57732@registro.br> <20061117201026.N11101@delplex.bde.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061117201026.N11101@delplex.bde.org> User-Agent: Mutt/1.4.2.1i X-Mailman-Approved-At: Sat, 18 Nov 2006 03:33:52 +0000 Cc: kreios@gmail.com, freebsd-performance@FreeBSD.org, Robert Watson Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 17 Nov 2006 16:35:37 -0000 > >I made some tests using 7.x with all the debugging disabled: > > > > queries / s > > > >Int bind (d_t) bind (e_t) nsd (1_s) nsd (2_s) > >--- ---------- ---------- --------- --------- > > > >bge 15439 14733 12910 10946 > >em 37655 34092 42411 41974 > >/// > >The results are very good for em NIC, better than my numbers [1] with > >FreeBSD 6.1 some months ago. So I guess that we had an improvement :-) > > > >But I got the same poor performance with the bge interface. The > >problem remains. > > > >[1] > >http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011767.html > > Try my fix for bge's interrupt handling in freebsd-net. > > Bruce I tried but I didn't get any improvement. -- Att., Marcelo Gardini From owner-freebsd-performance@FreeBSD.ORG Sat Nov 18 10:41:36 2006 Return-Path: X-Original-To: freebsd-performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id E34EF16A47C; Sat, 18 Nov 2006 10:41:36 +0000 (UTC) (envelope-from bde@zeta.org.au) Received: from mailout1.pacific.net.au (mailout1-3.pacific.net.au [61.8.2.210]) by mx1.FreeBSD.org (Postfix) with ESMTP id D1F1E43D45; Sat, 18 Nov 2006 10:41:33 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy1.pacific.net.au (mailproxy1.pacific.net.au [61.8.2.162]) by mailout1.pacific.net.au (Postfix) with ESMTP id 003B05A0F74; Sat, 18 Nov 2006 21:41:34 +1100 (EST) Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy1.pacific.net.au (Postfix) with ESMTP id B08FA8C02; Sat, 18 Nov 2006 21:41:33 +1100 (EST) Date: Sat, 18 Nov 2006 21:41:27 +1100 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Marcelo Gardini do Amaral In-Reply-To: <20061117163534.GA57732@registro.br> Message-ID: <20061118202518.U15111@delplex.bde.org> References: <20061030192702.GG76994@registro.br> <20061111091844.I63959@fledge.watson.org> <20061116164053.GR57732@registro.br> <20061117201026.N11101@delplex.bde.org> <20061117163534.GA57732@registro.br> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: Robert Watson , freebsd-performance@FreeBSD.org, kreios@gmail.com Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 18 Nov 2006 10:41:37 -0000 On Fri, 17 Nov 2006, Marcelo Gardini do Amaral wrote: >>> I made some tests using 7.x with all the debugging disabled: >>> >>> queries / s >>> >>> Int bind (d_t) bind (e_t) nsd (1_s) nsd (2_s) >>> --- ---------- ---------- --------- --------- >>> >>> bge 15439 14733 12910 10946 >>> em 37655 34092 42411 41974 >>> ... >> >> Try my fix for bge's interrupt handling in freebsd-net. > > I tried but I didn't get any improvement. I also have some latency and overhead optimizations for bge. I think your test uses many threads to get parallelism so latency optimizations wouldn't help much for it, but perhaps the problem is that the type of interrupt moderation used by bge accidentally limits parallelism, and then my changes might help by accidentally increasing parallelism (they are only intended to help much for the non-parallel case). bge hardware has fairly sophisticated interupt moderation, but poor tuning of it results in it reducing to almost the equivalent of polling at a rate of 6667 Hz or 2*6667 Hz depending on whether the tx and rx polls accidentally get in sync. (Intentional use of polling would give even worse latency unless you pessimize HZ too.) To reach em's number of operations per second, bge would have to do operations in bursts of 7 or 3.5 operations per poll, and the details of the operations or the polling might prevent this. For a quick test of latency reduction, try initializing sc->bge_rx_coal_ticks to 150 instead of 1. Bruce From owner-freebsd-performance@FreeBSD.ORG Sat Nov 18 13:52:41 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 3CB5F16A407; Sat, 18 Nov 2006 13:52:41 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.FreeBSD.org (Postfix) with ESMTP id 46F9F43D46; Sat, 18 Nov 2006 13:52:37 +0000 (GMT) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.62) with esmtp (envelope-from ) id <1GlQcY-0001IB-Qy>; Sat, 18 Nov 2006 14:52:38 +0100 Received: from e178021011.adsl.alicedsl.de ([85.178.21.11] helo=[192.168.1.128]) by inpost2.zedat.fu-berlin.de (Exim 4.62) with esmtpsa (envelope-from ) id <1GlQcY-00054M-N1>; Sat, 18 Nov 2006 14:52:38 +0100 Message-ID: <455F1021.6040004@mail.zedat.fu-berlin.de> Date: Sat, 18 Nov 2006 14:52:33 +0100 From: "O. Hartmann" User-Agent: Thunderbird 1.5.0.8 (X11/20061110) MIME-Version: 1.0 To: Marcelo Gardini do Amaral References: <20061030192702.GG76994@registro.br> <20061111091844.I63959@fledge.watson.org> <20061116164053.GR57732@registro.br> In-Reply-To: <20061116164053.GR57732@registro.br> X-Enigmail-Version: 0.94.1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Originating-IP: 85.178.21.11 X-Mailman-Approved-At: Sat, 18 Nov 2006 13:53:41 +0000 Cc: freebsd-performance@freebsd.org, Robert Watson Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 18 Nov 2006 13:52:41 -0000 Marcelo Gardini do Amaral wrote: >> FYI: In response to feedback from ISC, there are UDP transmit optimizations >> in FreeBSD 7.x. These have a relatively minor performance impact for >> single-threaded applications, but in the special case of BIND accessing a >> single UDP socket from many different threads, it significantly improves >> performance. I'll look at MFC'ing these to 6.x after 6.2-RELEASE >> (especially if reminded in a month or so :-). >> >> With regard to the possible bge issue -- I would encourage you to test >> using a 7.x kernel, ideally with all the debugging disabled, and see if >> there's been any improvement (or regression). There has been a lot of >> change in these areas, and it would be helpful to know what, if any, impact >> this has had. >> > > > I made some tests using 7.x with all the debugging disabled: > > queries / s > > Int bind (d_t) bind (e_t) nsd (1_s) nsd (2_s) > --- ---------- ---------- --------- --------- > > bge 15439 14733 12910 10946 > em 37655 34092 42411 41974 > > > d_t: disable threads > e_t: enable threads (libpthread) > 1_s: 1 server forked > 2_s: 2 server forked > > Bind: 9.2.3 > NSD: 3.0.2 > em: Dell 1950, Intel NIC, SMP kernel > bge: HP Blade BL35p, Broadcom NIC, SMP kernel > Client: Dell 1750, Intel NIC, FreeBSD 4.11 UP, running queryperf > > > > The results are very good for em NIC, better than my numbers [1] with > FreeBSD 6.1 some months ago. So I guess that we had an improvement :-) > > But I got the same poor performance with the bge interface. The > problem remains. > > [1] http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011767.html > > Cheers, > Marcelo > > These results looks very puzzling to me. As far as I know, multithreading and/or multiprocessors should perform better anyway than a single threaded application within other applications on an UP box. Strange results ...And more strange than this is the result taken from the FBSD 4.11 box! Is there an explanation why FreeBSD performs so bad beyond 4.X and on SMP boxes? Please show me threads ... Thanks and regards, Oliver