From owner-freebsd-performance@FreeBSD.ORG Sun Feb 24 18:04:43 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9D3D516A481 for ; Sun, 24 Feb 2008 18:04:43 +0000 (UTC) (envelope-from radek@ceskedomeny.cz) Received: from margaret.starnet.cz (margaret.starnet.cz [62.240.182.134]) by mx1.freebsd.org (Postfix) with SMTP id C346B13C44B for ; Sun, 24 Feb 2008 18:04:42 +0000 (UTC) (envelope-from radek@ceskedomeny.cz) Received: (qmail 66301 invoked from network); 24 Feb 2008 19:04:37 +0100 Received: from unknown (HELO localhost) (77.48.47.100) by margaret.starnet.cz with SMTP; 24 Feb 2008 19:04:37 +0100 Date: Sun, 24 Feb 2008 19:04:29 +0100 From: "Bc. Radek Krejca" X-Mailer: The Bat! (v3.99.3) Professional Organization: STARNET, s. r. o. X-Priority: 3 (Normal) Message-ID: <338145956.20080224190429@starnet.cz> To: FreeBSD Mailing Lists In-Reply-To: <5f67a8c40802051205t74a38663xd692e2a754d3788b@mail.gmail.com> References: <107794589.20080205140018@starnet.cz> <5f67a8c40802051205t74a38663xd692e2a754d3788b@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Subject: Re[2]: FBSD 1GBit router? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: "Bc. Radek Krejca" List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 24 Feb 2008 18:04:43 -0000 Hi, ZB> - upgrade at least to 6.3. upgrading to 7.0 might also be better, depe= nding ZB> on hardware choices ZB> - ensure your ethernet cards are on fast enough busses. 'em' (Intel Et= her ZB> Express 1000) flavor ports are my personal favorite ZB> - enable polling (this will make a _huge_ difference by itself) ZB> - your hardware is (likely) dual core. Make sure every piece of hardwa= re in ZB> use doesn't involve any giant locks. Under 6.x consider the mpsafenet ZB> sysctl. This is also a point on which 7.0 will shine. I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. --=20 S pozdravem, Bc. Radek Krejca ICQ: 65895541 From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 01:32:32 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9B2C316A400 for ; Mon, 25 Feb 2008 01:32:32 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.175]) by mx1.freebsd.org (Postfix) with ESMTP id 4092913C469 for ; Mon, 25 Feb 2008 01:32:32 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: by ug-out-1314.google.com with SMTP id y2so691371uge.37 for ; Sun, 24 Feb 2008 17:32:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; bh=r8PCbcPmO3L27wZMF5i9jRZVp1lNyJDVOgU+9sHvEiw=; b=cmwu3EW7UQ9/NZBlNWN4szFv6jXcpWolZwBXy23H3sUKaV5Gq+OOp5cIWkE4/s9/a374c+4qeM8mLmehz5PW4UsTiiuEkmCOPjzaAkvY7+0UiWjhOEA/ySoViuoATJS8qO4tMqgKH9HG0hO6LurBrLg8ZF2+6b87MolpLt7ky0w= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=ZZSFAq+SjuNfRV9KEnRFg6cVqT2Se8vyXHtIOFOXFwea6pb6TXlbSfART0IS7Gq1NLRN1ZxgaQqONBVsPr3L/us6JnmYtdah0OGVI/+lDoK0NnhPvAcL7qXmyZVNxZRVKNUnCYdpmv3dtGNrV9Ky/RLed8J3dJWLdJsXOaxgY8c= Received: by 10.66.237.14 with SMTP id k14mr2426684ugh.72.1203901525390; Sun, 24 Feb 2008 17:05:25 -0800 (PST) Received: by 10.66.219.18 with HTTP; Sun, 24 Feb 2008 17:05:25 -0800 (PST) Message-ID: <3aaaa3a0802241705k749cc4a2n9b668c6b22339824@mail.gmail.com> Date: Mon, 25 Feb 2008 01:05:25 +0000 From: Chris To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: maxphys and block sizes on slices 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, 25 Feb 2008 01:32:32 -0000 Hi. I got a server that is primarily handling large files not massive files but files that are 15meg+ in size and very few smaller files. So I decided to use the following options in newfs. -f 4096 -b 32768 Eventually I realised this was a bad decision especially when I noticed vfs.bufdefragcnt growing. In addition I have noticed all servers that are using the default settings have 128kbytes per transfer and appear to use what maxphys is set to whilst the ones with the custom newfs options are locked to 64kb/transfer even if dfltphys and maxphys are increased. I did increase BKVASIZE to 32768 to stop the bufdefragcnt tho. My lesson is learned tho new servers I setup I will keep the default block sizes unless someone has experience of better settings. For now I want to make the best of the settings I got in place. 1 - is the 64kB per transfer not adjustable and is a penalty for choosing the large block size? It is nearly always penned at 64kB with 100s transfers per second. 2 - is there a way to adjust the block sizes without wiping the data? 3 - How big an impact does a growing vfs.bufdefragcnt make on performance? after I fixed it I have noticed no difference. 4 - Is there anything in general reccomended to set for a server that handles large files but not many of them. 5 - What are the reccomended values on newfs for large files, the defaults? and does the 1/8th rule have to apply for frag size vs block size? 6 - finally I have read vfs.hirunningspace boosts write speeds by buffering more but it can be detrimental to read speeds is this true? Thanks From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 03:36:37 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 835D716A400 for ; Mon, 25 Feb 2008 03:36:37 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from el-out-1112.google.com (el-out-1112.google.com [209.85.162.183]) by mx1.freebsd.org (Postfix) with ESMTP id 13F0413C448 for ; Mon, 25 Feb 2008 03:36:36 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by el-out-1112.google.com with SMTP id r27so1142997ele.3 for ; Sun, 24 Feb 2008 19:36:36 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; bh=fsZZFx+KggW6SzmMol5X7OFUAB/pndNAbo+5poPUfRo=; b=uuNUz5aU4K1hp3Iu7iXL315kFU8z4dU74R/eY2YVgztZFIZ3iDziwd/wyT0jRWNCuwMCsNN2wD3+qsJhPHeyFk/3EvLAcTL77zAADfsrTv3hDXqbRGbslZ9d9vxQgn5+on5e7kc8dHJL4wTCbVePjz/iHTPkcuhxvlmzvIGVV0s= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=VAMInjyUQaF30Nms2ohw0XeMR7pX2sIkImJiXOEyrFb/GqK/ZuucsPz6pTtiFtZLkRIQnaduHTspaHPofcyLOXych4crZuHum1r83a+1c9bHHPEmCyyYgTPqoaMAHcVaUB5Jr1J3W3nMJAgtZKtpcLabXVH14Qd5eZtHbl8+l3Y= Received: by 10.142.237.20 with SMTP id k20mr1748890wfh.112.1203910595763; Sun, 24 Feb 2008 19:36:35 -0800 (PST) Received: by 10.143.125.7 with HTTP; Sun, 24 Feb 2008 19:36:35 -0800 (PST) Message-ID: Date: Mon, 25 Feb 2008 12:36:35 +0900 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: "Bc. Radek Krejca" In-Reply-To: <338145956.20080224190429@starnet.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <107794589.20080205140018@starnet.cz> <5f67a8c40802051205t74a38663xd692e2a754d3788b@mail.gmail.com> <338145956.20080224190429@starnet.cz> X-Google-Sender-Auth: 2d82af5213b22bd4 Cc: FreeBSD Mailing Lists Subject: Re: Re[2]: FBSD 1GBit router? 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, 25 Feb 2008 03:36:37 -0000 On 25/02/2008, Bc. Radek Krejca wrote: > Hi, > > ZB> - upgrade at least to 6.3. upgrading to 7.0 might also be better, depending > ZB> on hardware choices > ZB> - ensure your ethernet cards are on fast enough busses. 'em' (Intel Ether > ZB> Express 1000) flavor ports are my personal favorite > ZB> - enable polling (this will make a _huge_ difference by itself) > ZB> - your hardware is (likely) dual core. Make sure every piece of hardware in > ZB> use doesn't involve any giant locks. Under 6.x consider the mpsafenet > ZB> sysctl. This is also a point on which 7.0 will shine. > > I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. What PPS is that then? Adrian -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 07:08:15 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 96FA616A400 for ; Mon, 25 Feb 2008 07:08:15 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from mail08.syd.optusnet.com.au (mail08.syd.optusnet.com.au [211.29.132.189]) by mx1.freebsd.org (Postfix) with ESMTP id 34FAA13C467 for ; Mon, 25 Feb 2008 07:08:14 +0000 (UTC) (envelope-from brde@optusnet.com.au) Received: from c220-239-252-11.carlnfd3.nsw.optusnet.com.au (c220-239-252-11.carlnfd3.nsw.optusnet.com.au [220.239.252.11]) by mail08.syd.optusnet.com.au (8.13.1/8.13.1) with ESMTP id m1P78BpS027645 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 25 Feb 2008 18:08:12 +1100 Date: Mon, 25 Feb 2008 18:08:10 +1100 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: Chris In-Reply-To: <3aaaa3a0802241705k749cc4a2n9b668c6b22339824@mail.gmail.com> Message-ID: <20080225173908.X44080@delplex.bde.org> References: <3aaaa3a0802241705k749cc4a2n9b668c6b22339824@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: maxphys and block sizes on slices 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, 25 Feb 2008 07:08:15 -0000 On Mon, 25 Feb 2008, Chris wrote: > I got a server that is primarily handling large files not massive > files but files that are 15meg+ in size and very few smaller files. > > So I decided to use the following options in newfs. > > -f 4096 -b 32768 > > Eventually I realised this was a bad decision especially when I > noticed vfs.bufdefragcnt growing. > > In addition I have noticed all servers that are using the default > settings have 128kbytes per transfer and appear to use what maxphys is > set to whilst the ones with the custom newfs options are locked to > 64kb/transfer even if dfltphys and maxphys are increased. I did ATA drives had a DMA limit of 64K when I last looked. SCSI (da) drives have a more bogus limit of DFLTPHYS (default 64K), so increasing DFLTPHYS is likely to break some drives. There seem to be reports of usb drives that can't even handle 64K, so the default DFLTPHYS breaks them. There is als MAXBSIZE (default 64K). Non-clustered i/o must use this. Only clustered i/o can use MAXPHYS, and then only if the drive supports it of course. > increase BKVASIZE to 32768 to stop the bufdefragcnt tho. My lesson is > learned tho new servers I setup I will keep the default block sizes > unless someone has experience of better settings. For now I want to > make the best of the settings I got in place. I've never seen block sizes above 32K work better (on low end hardware). Sizes above about 1M work worse even for read/write(2) since they ensure thrashing for the L2 cache, and small sizes like 512 can work better for read()/write(2) because the fit in the L1 cache. > 1 - is the 64kB per transfer not adjustable and is a penalty for > choosing the large block size? It is nearly always penned at 64kB > with 100s transfers per second. AFAIK (not far, but I tried increasing it), it cannot be increased for ATA drives. ATA drives in PIO mode used to support block sizes of 256 or 255 sectors (128K or 128K-512), but this seems to be broken, and PIO mode is too slow for any drive less than 10-12 years old. > 2 - is there a way to adjust the block sizes without wiping the data? Low-level sizes can be changed. Clustered i/o then uses larger sizes. > 3 - How big an impact does a growing vfs.bufdefragcnt make on > performance? after I fixed it I have noticed no difference. It used to be very expensive. Seems not so bad now. > 4 - Is there anything in general reccomended to set for a server that > handles large files but not many of them. Implement extents. > 5 - What are the reccomended values on newfs for large files, the > defaults? and does the 1/8th rule have to apply for frag size vs block > size? Don't know. I only care about small files :-). > 6 - finally I have read vfs.hirunningspace boosts write speeds by > buffering more but it can be detrimental to read speeds is this true? I don't know of any especially bad interactions, but in general, if there are say 50MB of writes pending on a 50MB/sec disk, then reads will have to wait a second or more sometimes. In congested cases, getblk() takes more than a second sometimes (mainly under load with large fs block sizes, and for slow devices like DVDs). I haven't determined if it is waiting for the disk or the software. Bruce From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 13:34:30 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 36BF216A406 for ; Mon, 25 Feb 2008 13:34:30 +0000 (UTC) (envelope-from daniel@dgnetwork.com.br) Received: from mail.mastercabo.com.br (mail.mastercabo.com.br [200.179.179.14]) by mx1.freebsd.org (Postfix) with SMTP id 35B7A13C474 for ; Mon, 25 Feb 2008 13:34:28 +0000 (UTC) (envelope-from daniel@dgnetwork.com.br) Received: (qmail 78733 invoked by uid 1008); 25 Feb 2008 13:34:27 -0000 X-Spam-Checker-Version: SpamAssassin 3.1.6-unknown (2006-10-03) on srvmail2 X-Spam-Level: X-Spam-Status: No, score=-1.7 required=4.7 tests=AWL,BAYES_00 autolearn=ham version=3.1.6-unknown Received: from unknown (HELO ?10.0.0.10?) (daniel@dgnetwork.com.br@200.243.216.34) by mail.mastercabo.com.br with SMTP; 25 Feb 2008 13:34:20 -0000 Message-ID: <47C2C215.3040802@dgnetwork.com.br> Date: Mon, 25 Feb 2008 10:26:45 -0300 From: =?ISO-8859-1?Q?Daniel_Dias_Gon=E7alves?= Organization: DGNET Network Solutions User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <107794589.20080205140018@starnet.cz> <5f67a8c40802051205t74a38663xd692e2a754d3788b@mail.gmail.com> <338145956.20080224190429@starnet.cz> In-Reply-To: <338145956.20080224190429@starnet.cz> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-net@freebsd.org Subject: Re: FBSD 1GBit router? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: daniel@dgnetwork.com.br List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 25 Feb 2008 13:34:30 -0000 Bc. Radek Krejca escreveu: > Hi, > > ZB> - upgrade at least to 6.3. upgrading to 7.0 might also be better, depending > ZB> on hardware choices > ZB> - ensure your ethernet cards are on fast enough busses. 'em' (Intel Ether > ZB> Express 1000) flavor ports are my personal favorite > ZB> - enable polling (this will make a _huge_ difference by itself) > ZB> - your hardware is (likely) dual core. Make sure every piece of hardware in > ZB> use doesn't involve any giant locks. Under 6.x consider the mpsafenet > ZB> sysctl. This is also a point on which 7.0 will shine. > > I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. > > Is recommendable set MPSAFENET to 1 in versions 6.x to improve the performance? and POLLING in the following system with 8 interfaces IF_EM ?? CPU: Intel(R) Xeon(TM) CPU 3.20GHz (3200.13-MHz 686-class CPU) Logical CPUs per core: 2 FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs SMP: AP CPU #1 Launched! Interfaces if_em: vendor = 'Intel Corporation' device = '82546EB Dual Port Gigabit Ethernet Controller' -- Daniel From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 14:32:01 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AC2BE16A406 for ; Mon, 25 Feb 2008 14:32:01 +0000 (UTC) (envelope-from if@xip.at) Received: from chile.gbit.at (ns1.xip.at [193.239.188.99]) by mx1.freebsd.org (Postfix) with ESMTP id 0416A13C467 for ; Mon, 25 Feb 2008 14:32:00 +0000 (UTC) (envelope-from if@xip.at) Received: (qmail 16339 invoked from network); 25 Feb 2008 15:05:18 +0100 Received: from unknown (HELO filebunker.xip.at) (86.59.10.180) by chile.gbit.at with (DHE-RSA-AES256-SHA encrypted) SMTP; 25 Feb 2008 15:05:18 +0100 Date: Mon, 25 Feb 2008 15:05:18 +0100 (CET) From: Ingo Flaschberger To: =?ISO-8859-15?Q?Daniel_Dias_Gon=E7alves?= In-Reply-To: <47C2C215.3040802@dgnetwork.com.br> Message-ID: References: <107794589.20080205140018@starnet.cz> <5f67a8c40802051205t74a38663xd692e2a754d3788b@mail.gmail.com> <338145956.20080224190429@starnet.cz> <47C2C215.3040802@dgnetwork.com.br> User-Agent: Alpine 1.00 (LFD 882 2007-12-20) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Mon, 25 Feb 2008 14:47:26 +0000 Cc: freebsd-net@freebsd.org, freebsd-performance@freebsd.org Subject: Re: FBSD 1GBit router? 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, 25 Feb 2008 14:32:01 -0000 Hi, >> ZB> - upgrade at least to 6.3. upgrading to 7.0 might also be better, >> depending >> ZB> on hardware choices >> ZB> - ensure your ethernet cards are on fast enough busses. 'em' (Intel >> Ether >> ZB> Express 1000) flavor ports are my personal favorite >> ZB> - enable polling (this will make a _huge_ difference by itself) >> ZB> - your hardware is (likely) dual core. Make sure every piece of >> hardware in >> ZB> use doesn't involve any giant locks. Under 6.x consider the mpsafenet >> ZB> sysctl. This is also a point on which 7.0 will shine. >> >> I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. older fbsd's are faster than newer. How are the nic's connected to the cpu? lspci -v Kind regards, Ingo Flaschberger From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 20:17:58 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 764C116A420; Mon, 25 Feb 2008 20:17:58 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 7C94813C4F2; Mon, 25 Feb 2008 20:17:57 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C32274.2060706@FreeBSD.org> Date: Mon, 25 Feb 2008 21:17:56 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: Oliver Herold , freebsd-questions@freebsd.org, "freebsd-performance@freebsd.org" References: <20080225133347.GA2446@asgard.home> In-Reply-To: <20080225133347.GA2446@asgard.home> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 25 Feb 2008 20:17:58 -0000 Oliver Herold wrote: > Hi, > > I saw this bind benchmarks just some minutes ago, > > http://new.isc.org/proj/dnsperf/OStest.html > > is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is > this something verified only for the state of development back in August > 2007? I have been trying to replicate this. ISC have kindly given me access to their test data but I am seeing Linux performing much slower than FreeBSD with the same ISC workload. http://people.freebsd.org/~kris/scaling/bind-pt.png Summary: * FreeBSD 7.0-R with 4BSD scheduler has close to ideal scaling on this test. * The drop above 6 threads is due to limitations within BIND. * Linux 2.6.24 has about 35% lower performance than FreeBSD, which is significantly at variance with the ISC results. It also doesn't scale above 3 CPUs. * I am trying to understand what is different about the ISC configuration but have not yet found the cause. They were testing 2.6.20.7 so it is possible that there was a major regression before the 2.6.22 and .24 kernels I tested. Or maybe something is broken with the Intel gige driver in Linux (they were using broadcom hardware). The graph is showing performance over 10ge, but I get the same peak performance over gige when I query from 2 clients (the client benchmark is very sensitive to network latency so a single client is not enough to saturate BIND over gige). * 7.0 with ULE has a bug on this workload (actually to do with workloads involving high interrupt rates). It is fixed in 8.0. * Changes we have in progress to improve UDP performance do not help much with this particular workload (only about 5%), but with more scalable applications we see 30-40% improvement. e.g. NSD (ports/dns/nsd) is a much faster and more scalable DNS server than BIND (because it is better optimized for the smaller set of features it supports). Kris From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 20:50:15 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DB92F16A56D for ; Mon, 25 Feb 2008 20:50:15 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.170]) by mx1.freebsd.org (Postfix) with ESMTP id DF37813C46B for ; Mon, 25 Feb 2008 20:50:14 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: by ug-out-1314.google.com with SMTP id y2so1051294uge.37 for ; Mon, 25 Feb 2008 12:50:12 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=KeXShDpTDJEN/6K/0Ptvv4eMe9FxtEM9fw6LIC2tObU=; b=O5b/r6lHE/6RTtMaoFr2vJwZSt0NlbTOpa5IdgCgI+7UYEPc+4/KZt504xUqh519cbXL2mJi6yg5JKuVrTkLTlj4GPSCWLMubZ7vatM6rhy5P3ER+8OAfLnjHI8ydwOjNrxDq0AV1vkoc2bHztYdk/e303dJwG20bbZrjxoO7aQ= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=xWjp1CXxOJ671wDenbf0RuxIdGTFjUh2uPk+Sqiaw0GXKhXhEgHimp3LisRRCDT5maQ3UgS9VjlG972V8zFidIsC4b3MiYpKt9TqDJS59zLEoqPJUL9pYVpvVTkC+TvYHykJooEPaF2SIC8iak0M6VUVLCTgi8m4geo7/uLrJOs= Received: by 10.67.88.10 with SMTP id q10mr3760483ugl.52.1203972612469; Mon, 25 Feb 2008 12:50:12 -0800 (PST) Received: by 10.66.219.18 with HTTP; Mon, 25 Feb 2008 12:50:12 -0800 (PST) Message-ID: <3aaaa3a0802251250y248da081h4049d43f75ee2ee9@mail.gmail.com> Date: Mon, 25 Feb 2008 20:50:12 +0000 From: Chris To: "Kris Kennaway" In-Reply-To: <47C32274.2060706@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20080225133347.GA2446@asgard.home> <47C32274.2060706@FreeBSD.org> Cc: "freebsd-performance@freebsd.org" , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 25 Feb 2008 20:50:16 -0000 > > * 7.0 with ULE has a bug on this workload (actually to do with workloads > involving high interrupt rates). It is fixed in 8.0. Kris can you say anything more about interrupt workload bugs on ULE? On all my 7.0 servers I now am using ULE even on the UP ones as it was said there is slight improvements for UP also but all the machines can get intterupts intensive, lots of high speed transfers using nic interrupts. In this scenario am I better of using 4BSD? Chris From owner-freebsd-performance@FreeBSD.ORG Mon Feb 25 21:23:40 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C1B5316A400; Mon, 25 Feb 2008 21:23:40 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 4F82F13C45D; Mon, 25 Feb 2008 21:23:36 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C331D7.6040001@FreeBSD.org> Date: Mon, 25 Feb 2008 22:23:35 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: Chris References: <20080225133347.GA2446@asgard.home> <47C32274.2060706@FreeBSD.org> <3aaaa3a0802251250y248da081h4049d43f75ee2ee9@mail.gmail.com> In-Reply-To: <3aaaa3a0802251250y248da081h4049d43f75ee2ee9@mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: "freebsd-performance@freebsd.org" , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 25 Feb 2008 21:23:40 -0000 Chris wrote: >> * 7.0 with ULE has a bug on this workload (actually to do with workloads >> involving high interrupt rates). It is fixed in 8.0. > > Kris can you say anything more about interrupt workload bugs on ULE? > On all my 7.0 servers I now am using ULE even on the UP ones as it was > said there is slight improvements for UP also but all the machines can > get intterupts intensive, lots of high speed transfers using nic > interrupts. In this scenario am I better of using 4BSD? I can't say for sure, you would have to do measurements of your throughput. It probably won't matter on UP though. Kris From owner-freebsd-performance@FreeBSD.ORG Tue Feb 26 00:31:13 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 394B416A400; Tue, 26 Feb 2008 00:31:13 +0000 (UTC) (envelope-from SRS0=3f34d093e2f56729cd6e7ef292df5e91d2e17e8a=622=es.net=oberman@es.net) Received: from postal1.es.net (postoffice4.tagpma.org [IPv6:2001:400:6000:1::66]) by mx1.freebsd.org (Postfix) with ESMTP id 16AF213C457; Tue, 26 Feb 2008 00:31:11 +0000 (UTC) (envelope-from SRS0=3f34d093e2f56729cd6e7ef292df5e91d2e17e8a=622=es.net=oberman@es.net) Received: from ptavv.es.net (ptavv.es.net [198.128.4.29]) by postal4.es.net (Postal Node 4) with ESMTP (SSL) id GCF63908; Mon, 25 Feb 2008 16:31:08 -0800 Received: from ptavv.es.net (ptavv.es.net [127.0.0.1]) by ptavv.es.net (Tachyon Server) with ESMTP id 54CD94500E; Mon, 25 Feb 2008 16:31:07 -0800 (PST) To: Ingo Flaschberger In-Reply-To: Your message of "Mon, 25 Feb 2008 15:05:18 +0100." Mime-Version: 1.0 Content-Type: multipart/signed; boundary="==_Exmh_1203985867_10451P"; micalg=pgp-sha1; protocol="application/pgp-signature" Content-Transfer-Encoding: 7bit Date: Mon, 25 Feb 2008 16:31:07 -0800 From: "Kevin Oberman" Message-Id: <20080226003107.54CD94500E@ptavv.es.net> X-Sender-IP: 198.128.4.29 X-Sender-Domain: es.net X-Recipent: ; ; ; ; X-Sender: X-To_Name: Ingo Flaschberger X-To_Domain: xip.at X-To: Ingo Flaschberger X-To_Email: if@xip.at X-To_Alias: if X-Mailman-Approved-At: Tue, 26 Feb 2008 00:54:27 +0000 Cc: =?ISO-8859-15?Q?Daniel_Dias_Gon=E7alves?= , freebsd-net@freebsd.org, freebsd-performance@freebsd.org Subject: Re: FBSD 1GBit router? 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, 26 Feb 2008 00:31:13 -0000 --==_Exmh_1203985867_10451P Content-Type: text/plain; charset=us-ascii Content-Disposition: inline > Date: Mon, 25 Feb 2008 15:05:18 +0100 (CET) > From: Ingo Flaschberger > Sender: owner-freebsd-net@freebsd.org > > Hi, > > >> ZB> - upgrade at least to 6.3. upgrading to 7.0 might also be better, > >> depending > >> ZB> on hardware choices > >> ZB> - ensure your ethernet cards are on fast enough busses. 'em' (Intel > >> Ether > >> ZB> Express 1000) flavor ports are my personal favorite > >> ZB> - enable polling (this will make a _huge_ difference by itself) > >> ZB> - your hardware is (likely) dual core. Make sure every piece of > >> hardware in > >> ZB> use doesn't involve any giant locks. Under 6.x consider the mpsafenet > >> ZB> sysctl. This is also a point on which 7.0 will shine. > >> > >> I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. > > older fbsd's are faster than newer. > > How are the nic's connected to the cpu? > > lspci -v V7 is not (in my experience) slower than V4, v5, or v6. I have run a lot of tests at speeds MUCH higher than 1Gb. With 10Gb cards, I can sustain transfer rates of over 9Gbps (assuming low RTT and suitable hardware). 1Gbps is not even a challenge...even over a 100 ms. RTT. Note that high throughput may require some tuning. Transmit and receive windows need to be rather large if the RTT is very long at all. (See "bandwidth-delay product" in Stevens or some other TCP reference.) -- R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 Key fingerprint:059B 2DDF 031C 9BA3 14A4 EADA 927D EBB3 987B 3751 --==_Exmh_1203985867_10451P Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.8 (FreeBSD) Comment: Exmh version 2.5 06/03/2002 iD8DBQFHw13Lkn3rs5h7N1ERAkJ8AJ92pDS77AS2zrQT1fJ/6atsZV60ywCgjrCI 5CzU5TmKkm4SXje0F7kXzy0= =QVe/ -----END PGP SIGNATURE----- --==_Exmh_1203985867_10451P-- From owner-freebsd-performance@FreeBSD.ORG Tue Feb 26 00:43:20 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5119E16A407 for ; Tue, 26 Feb 2008 00:43:20 +0000 (UTC) (envelope-from if@xip.at) Received: from chile.gbit.at (ns1.xip.at [193.239.188.99]) by mx1.freebsd.org (Postfix) with ESMTP id 8EB7113C468 for ; Tue, 26 Feb 2008 00:43:18 +0000 (UTC) (envelope-from if@xip.at) Received: (qmail 32150 invoked from network); 26 Feb 2008 01:43:17 +0100 Received: from unknown (HELO filebunker.xip.at) (86.59.10.180) by chile.gbit.at with (DHE-RSA-AES256-SHA encrypted) SMTP; 26 Feb 2008 01:43:17 +0100 Date: Tue, 26 Feb 2008 01:43:16 +0100 (CET) From: Ingo Flaschberger To: Kevin Oberman In-Reply-To: <20080226003107.54CD94500E@ptavv.es.net> Message-ID: References: <20080226003107.54CD94500E@ptavv.es.net> User-Agent: Alpine 1.00 (LFD 882 2007-12-20) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; format=flowed; charset=US-ASCII X-Mailman-Approved-At: Tue, 26 Feb 2008 01:46:02 +0000 Cc: =?ISO-8859-15?Q?Daniel_Dias_Gon=E7alves?= , freebsd-net@freebsd.org, freebsd-performance@freebsd.org Subject: Re: FBSD 1GBit router? 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, 26 Feb 2008 00:43:20 -0000 Dear Kevin, >>>> I upgrade to 7.0RC3 but still the same. 418Mbit is the roof. >> >> older fbsd's are faster than newer. >> >> How are the nic's connected to the cpu? >> >> lspci -v > > V7 is not (in my experience) slower than V4, v5, or v6. v6 is at least slower than v4. http://www.tancsa.com/blast.html (look at the table at the end) > I have run a lot > of tests at speeds MUCH higher than 1Gb. With 10Gb cards, I can sustain > transfer rates of over 9Gbps (assuming low RTT and suitable > hardware). 1Gbps is not even a challenge...even over a 100 ms. RTT. You can route 9Gbps - or only source or sink 9gbps? What packet size? Whats the maximum pps (with 64byte packets)? (Thats the real interesting value, not mbps) I have a 1.2Ghz Pentium-M appliance, with 4x 32bit, 33MHz pci intel e1000 cards. With maximum tuning I can "route" ~400mbps with big packets and ~80mbps with 64byte packets. around 100kpps, whats not bad for a pci architecture. To reach higher bandwiths, better busses are needed. pci-express cards are currently the best choice. one dedicated pci-express lane (1.25gbps) has more bandwith than a whole 32bit, 33mhz pci-bus. > Note that high throughput may require some tuning. Transmit and receive > windows need to be rather large if the RTT is very long at all. (See > "bandwidth-delay product" in Stevens or some other TCP reference.) I'm not shure if he's using the nic for a server or for a router? Kind regards, Ingo Flaschberger From owner-freebsd-performance@FreeBSD.ORG Tue Feb 26 02:07:47 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A77C916A400 for ; Tue, 26 Feb 2008 02:07:47 +0000 (UTC) (envelope-from boheme@gmail.com) Received: from fg-out-1718.google.com (fg-out-1718.google.com [72.14.220.154]) by mx1.freebsd.org (Postfix) with ESMTP id 35C1713C461 for ; Tue, 26 Feb 2008 02:07:46 +0000 (UTC) (envelope-from boheme@gmail.com) Received: by fg-out-1718.google.com with SMTP id 16so1506242fgg.35 for ; Mon, 25 Feb 2008 18:07:45 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=7buJ47txogJLRoBOUnL3JhjPapP084mBTx0KwYHkZaE=; b=ZjXq8Fcd6nbT23fXVlcliFgaekFlw/3+x6xhizOo8YdJVRlQUGaIm/hkd8qO5cNaZPvyiIQXjipGzxQeDoUJbjtFPGVw1K1iFRhjRE9Z/VUUiFMy7eKpGMYF3Znms43Yc2+guBO4WM2puF7p6rhWtOLY/6tehVa7rN5SP3t9qcQ= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Xzj8t+pX4zlJkEgUoEX3/eKCKgu1qTDCUmbXDJG17X+GvIdV9A8z38PjIfZj84EVkgT9O1R9qOXE+TPQgNEW6sZgvewE9q1hdCCXjqdBnGVS9XiSbxC6UH3Gh2sUnZsR5W/sL7uC1uagUZwqK+oPyN7dG6oEMr90FRLh453UCDM= Received: by 10.86.99.9 with SMTP id w9mr3777637fgb.22.1203989912088; Mon, 25 Feb 2008 17:38:32 -0800 (PST) Received: by 10.86.89.19 with HTTP; Mon, 25 Feb 2008 17:38:32 -0800 (PST) Message-ID: Date: Mon, 25 Feb 2008 17:38:32 -0800 From: "Chris Knight" To: "Bc. Radek Krejca" In-Reply-To: <107794589.20080205140018@starnet.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <107794589.20080205140018@starnet.cz> Cc: FreeBSD Mailing Lists Subject: Re: FBSD 1GBit router? 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, 26 Feb 2008 02:07:47 -0000 What kind of network cards are you using, and what bus type are they using? >From my experience, I was never able to get over ~300Mbps routing from one PCI-X NIC to another PCI-X NIC. I switched out the bus to a PCI-Express and put a couple of Intel PCI-E 4x gigabit cards in and I was able to get over 950Mbps throughput. Sorry I don't have my sysctl.conf settings, that box was reallocated after we replaced it with some Cisco junk. -Chris On Tue, Feb 5, 2008 at 5:00 AM, Bc. Radek Krejca wrote: > Hi, > > I have FreeBSD box as router > FreeBSD pvt-gw.starnet.cz 6.1-RELEASE-p12 FreeBSD 6.1-RELEASE-p12 #2: Wed Jan 31 21:28:44 CET 2007 root@pvt-gw.starnet.cz:/usr/obj/usr/src/sys/DL360-G4 i386 > But speed is only about 382 Mbit. I have following values in > sysctl.conf: > > net.inet.ip.fastforwarding=1 > net.inet.tcp.recvspace=262144 > net.inet.tcp.sendspace=262144 > kern.ipc.maxsockbuf=33554432 > > I need about 600-700 Mbit. Is any chance on freebsd? Hardware is HP > DL360-G4, interrupt takes about 55 % of CPU. I tested it over > netperf and result is about 382 Mbit. > > > -- > Regards, > Bc. Radek Krejca > ICQ: 65895541 > > > _______________________________________________ > 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 Tue Feb 26 11:50:09 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E1DBC1065670; Tue, 26 Feb 2008 11:50:09 +0000 (UTC) (envelope-from ohartman@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 A22AD13CF47; Tue, 26 Feb 2008 08:33:26 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1JTvFd-0008RY-7F>; Tue, 26 Feb 2008 09:33:25 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1JTvFd-0005kK-6O>; Tue, 26 Feb 2008 09:33:25 +0100 Message-ID: <47C3CEC3.40402@zedat.fu-berlin.de> Date: Tue, 26 Feb 2008 08:33:07 +0000 From: "O. Hartmann" Organization: Freie =?ISO-8859-15?Q?Universit=E4t_Berlin?= User-Agent: Thunderbird 2.0.0.9 (X11/20080122) MIME-Version: 1.0 To: Kris Kennaway References: <20080225133347.GA2446@asgard.home> <47C32274.2060706@FreeBSD.org> In-Reply-To: <47C32274.2060706@FreeBSD.org> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: 130.133.86.198 Cc: "freebsd-performance@freebsd.org" , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 26 Feb 2008 11:50:16 -0000 Kris Kennaway wrote: [SCHNIPP] > > * 7.0 with ULE has a bug on this workload (actually to do with workloads > involving high interrupt rates). It is fixed in 8.0. will this patch also be available for 7.0? Regards, Oliver From owner-freebsd-performance@FreeBSD.ORG Tue Feb 26 19:25:34 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D39541065675; Tue, 26 Feb 2008 19:25:34 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id A379513C455; Tue, 26 Feb 2008 19:25:33 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C467AD.6090403@FreeBSD.org> Date: Tue, 26 Feb 2008 20:25:33 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 To: "O. Hartmann" References: <20080225133347.GA2446@asgard.home> <47C32274.2060706@FreeBSD.org> <47C3CEC3.40402@zedat.fu-berlin.de> In-Reply-To: <47C3CEC3.40402@zedat.fu-berlin.de> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Cc: "freebsd-performance@freebsd.org" , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 26 Feb 2008 19:25:35 -0000 O. Hartmann wrote: > Kris Kennaway wrote: > [SCHNIPP] >> >> * 7.0 with ULE has a bug on this workload (actually to do with >> workloads involving high interrupt rates). It is fixed in 8.0. > > will this patch also be available for 7.0? If you mean "will it be merged to RELENG_7", absolutely. If you mean "will an errata be released and merged to RELENG_7_0", that is up to the release engineers. Kris From owner-freebsd-performance@FreeBSD.ORG Tue Feb 26 22:00:05 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EE5EE106566B for ; Tue, 26 Feb 2008 22:00:05 +0000 (UTC) (envelope-from dak.col@gmail.com) Received: from wa-out-1112.google.com (wa-out-1112.google.com [209.85.146.179]) by mx1.freebsd.org (Postfix) with ESMTP id C139613C465 for ; Tue, 26 Feb 2008 22:00:05 +0000 (UTC) (envelope-from dak.col@gmail.com) Received: by wa-out-1112.google.com with SMTP id k17so2681465waf.3 for ; Tue, 26 Feb 2008 14:00:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=i0cp4PboJU1i5X2v4P9jxuEzgxq6j8wIW+BhIRYQGVw=; b=m+eildAmUvE5GSc/FY2siiG2GC4vZ8uyuXMPNOFD1kclIgRc2+D21Ttk5YMNNeVzOxeGDkYaSRCStOGSf7/Rl+zy4Gx4i4M+3lkc9A7VuH27IsA0WFmDMrlRC1WaARosxeA6VdDypRYXf+57I9AHcLL8x/L8xozSHfUrL1+ptAA= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=IOKO7+pyiUc6Sgy5ltlbmDI3aII/UvJtg5ddBmO44JWGAPBn2dcUCGd5faTazZzOEcbzvmvEEeEL3lY9jrnEZDxMIK3T08S2wNbVx0Lb1dkJFsMpHtFofDD3o/wX7NStaFmyZNtTjDSTx9h72GrrmL7ceTJuhFzNpAOCCO7MNbw= Received: by 10.114.166.1 with SMTP id o1mr6200000wae.71.1204061523820; Tue, 26 Feb 2008 13:32:03 -0800 (PST) Received: by 10.114.25.9 with HTTP; Tue, 26 Feb 2008 13:32:03 -0800 (PST) Message-ID: <3b93bd110802261332j1794cba5x522906dcd58907eb@mail.gmail.com> Date: Tue, 26 Feb 2008 16:32:03 -0500 From: Natham To: "Kris Kennaway" , freebsd-questions@freebsd.org, freebsd-performance@freebsd.org In-Reply-To: <47C4671A.40909@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <3b93bd110802260825s26247ee9oe38fa3ad78632d15@mail.gmail.com> <47C4671A.40909@FreeBSD.org> X-Mailman-Approved-At: Tue, 26 Feb 2008 22:02:56 +0000 Cc: Subject: Re: Performance Issues on 6.3 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, 26 Feb 2008 22:00:06 -0000 On Tue, Feb 26, 2008 at 2:23 PM, Kris Kennaway wrote: > Natham wrote: > > > Both RAID got low performance, where can i check to fis that problem? > > How did you determine that it is your RAID that is performing poorly, > and not your network card or your samba or something on the other system? > > Kris > I dont. i check the performance for network trasfer only thats what i mean (trought samba). When im rebuilding the RAID 1 i got about 40mb/s from each disk. I think its a network issue or samba, but i dont know where to look at. Thanks. Diego Arias From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 06:44:27 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 970A01065672; Wed, 27 Feb 2008 06:44:27 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from mail.freebsd-corp-net-guide.com (mail.freebsd-corp-net-guide.com [65.75.192.90]) by mx1.freebsd.org (Postfix) with ESMTP id 24F8D13C442; Wed, 27 Feb 2008 06:44:27 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from TEDSDSK (nat-rtr.freebsd-corp-net-guide.com [65.75.197.130]) by mail.freebsd-corp-net-guide.com (8.13.8/8.13.8) with SMTP id m1R6HIEh014826; Tue, 26 Feb 2008 22:17:19 -0800 (PST) (envelope-from tedm@toybox.placo.com) From: "Ted Mittelstaedt" To: "Kris Kennaway" , "Oliver Herold" , , Date: Tue, 26 Feb 2008 22:18:18 -0800 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.6604 (9.0.2911.0) X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1914 In-Reply-To: <47C32274.2060706@FreeBSD.org> Importance: Normal X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (mail.freebsd-corp-net-guide.com [65.75.192.90]); Tue, 26 Feb 2008 22:17:20 -0800 (PST) Cc: Subject: RE: FreeBSD bind performance in FreeBSD 7 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: Wed, 27 Feb 2008 06:44:27 -0000 > -----Original Message----- > From: owner-freebsd-questions@freebsd.org > [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway > Sent: Monday, February 25, 2008 12:18 PM > To: Oliver Herold; freebsd-questions@freebsd.org; > freebsd-performance@freebsd.org > Subject: Re: FreeBSD bind performance in FreeBSD 7 > > > Oliver Herold wrote: > > Hi, > > > > I saw this bind benchmarks just some minutes ago, > > > > http://new.isc.org/proj/dnsperf/OStest.html > > > > is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is > > this something verified only for the state of development back in August > > 2007? > > I have been trying to replicate this. ISC have kindly given me access > to their test data but I am seeing Linux performing much slower than > FreeBSD with the same ISC workload. > Kris, Every couple years we go through this with ISC. They come out with a new version of BIND then claim that nothing other than Linux can run it well. I've seen this nonsense before and it's tiresome. Incidentally, the query tool they used, queryperf, has been changed to dnsperf. Someone needs to look at that port - /usr/ports/dns/dnsperf - as it has a build depend of bind9 - well bind 9.3.4 is part of 6.3-RELEASE and I was rather irked when I ran the dnsperf port maker and the maker stupidly began the process of downloading and building the same version of BIND that I was already running on my server. > > * I am trying to understand what is different about the ISC > configuration but have not yet found the cause. It's called "Anti-FreeBSD bias". You won't find anything. > e.g. NSD > (ports/dns/nsd) is a much faster and more scalable DNS server than BIND > (because it is better optimized for the smaller set of features it > supports). > When you make remarks like that it's no wonder ISC is in the business of slamming FreeBSD. People used to make the same claims about djbdns but I noticed over the last few years they don't seem to be doing that anymore. If nsd is so much better than yank bind out of the base FreeBSD and replace it with nsd. Of course that will make more work for me when I regen our nameservers here since nsd will be the first thing on the "rm" list. Ted From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 07:07:33 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 260221065674; Wed, 27 Feb 2008 07:07:33 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from mail.freebsd-corp-net-guide.com (mail.freebsd-corp-net-guide.com [65.75.192.90]) by mx1.freebsd.org (Postfix) with ESMTP id D844313C4DD; Wed, 27 Feb 2008 07:07:32 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from TEDSDSK (nat-rtr.freebsd-corp-net-guide.com [65.75.197.130]) by mail.freebsd-corp-net-guide.com (8.13.8/8.13.8) with SMTP id m1R77VOj015202; Tue, 26 Feb 2008 23:07:32 -0800 (PST) (envelope-from tedm@toybox.placo.com) From: "Ted Mittelstaedt" To: "Natham" , "Kris Kennaway" , , Date: Tue, 26 Feb 2008 23:08:31 -0800 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.6604 (9.0.2911.0) X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1914 In-Reply-To: <3b93bd110802261332j1794cba5x522906dcd58907eb@mail.gmail.com> Importance: Normal X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (mail.freebsd-corp-net-guide.com [65.75.192.90]); Tue, 26 Feb 2008 23:07:32 -0800 (PST) Cc: Subject: RE: Performance Issues on 6.3 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: Wed, 27 Feb 2008 07:07:33 -0000 > -----Original Message----- > From: owner-freebsd-questions@freebsd.org > [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Natham > Sent: Tuesday, February 26, 2008 1:32 PM > To: Kris Kennaway; freebsd-questions@freebsd.org; > freebsd-performance@freebsd.org > Subject: Re: Performance Issues on 6.3 >=20 >=20 > On Tue, Feb 26, 2008 at 2:23 PM, Kris Kennaway = wrote: > > Natham wrote: > > > > > Both RAID got low performance, where can i check to fis that = problem? > > > > How did you determine that it is your RAID that is performing = poorly, > > and not your network card or your samba or something on the=20 > other system? > > > > Kris > > > I dont. i check the performance for network trasfer only thats what i > mean (trought samba). When im rebuilding the RAID 1 i got about 40mb/s > from each disk. > I think its a network issue or samba, but i dont know where to look = at. >=20 Looking at the RAID array if you think it's Samba or the network is probably not a good idea. You can eliminate the network pretty quick, open a command window on your Windows boxes then FTP into the server (turn on FTP on the server of course) and transfer some files back and forth. Have you perhaps considered subscribing to the samba mailing list and asking them? Or looking through the samba mailing list archives? Ted From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 08:26:09 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 07268106566C for ; Wed, 27 Feb 2008 08:26:09 +0000 (UTC) (envelope-from stas@ht-systems.ru) Received: from smtp.ht-systems.ru (mr0.ht-systems.ru [78.110.50.55]) by mx1.freebsd.org (Postfix) with ESMTP id 8496713C455 for ; Wed, 27 Feb 2008 08:26:08 +0000 (UTC) (envelope-from stas@ht-systems.ru) Received: from [78.110.49.49] (helo=quasar.ht-systems.ru) by smtp.ht-systems.ru with esmtpa (Exim 4.62) (envelope-from ) id 1JUHc6-0003pE-Jo; Wed, 27 Feb 2008 11:26:06 +0300 Received: by quasar.ht-systems.ru (Postfix, from userid 1024) id 8B3107D11C8; Wed, 27 Feb 2008 11:26:05 +0300 (MSK) Date: Wed, 27 Feb 2008 11:26:05 +0300 From: Stanislav Sedov To: Arkadi Shishlov Message-ID: <20080227082605.GL51827@dracon.ht-systems.ru> References: <479B1185.8020604@quip.cz> <479D89C9.7060300@chistydom.ru> <479DD94C.7010409@mawer.org> <479DE578.7060202@quip.cz> <20080214163037.GA51014@dracon.ht-systems.ru> <47B478E6.8080902@mebius.lv> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <47B478E6.8080902@mebius.lv> Organization: The FreeBSD Project X-Voice: +7 916 849 20 23 X-XMPP: ssedov@jabber.ru X-Yahoo: stanislav_sedov X-PGP-Fingerprint: F21E D6CC 5626 9609 6CE2 A385 2BF5 5993 EB26 9581 X-University: MEPhI X-Mailer: carrier-pigeon X-Operating-System: FreeBSD quasar.ht-systems.ru 7.0-PRERELEASE FreeBSD 7.0-PRERELEASE Cc: freebsd-performance@freebsd.org Subject: Re: PHP with open_basedir performance problem 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: Wed, 27 Feb 2008 08:26:09 -0000 On Thu, Feb 14, 2008 at 07:22:46PM +0200 Arkadi Shishlov mentioned: > Stanislav Sedov wrote: >> I'd suggest you to disable open_basedir at all or roll out specialized >> implementation. I had a lot of similar problems with open_basedir in >> the past, so I just rewrote it to match our specific security policy. > > Can you share a hint how exactly this specialized implementation may look like? > The requirement is simple: php script working under apache mod_php can't > open files outside of virtual host document root whenever php safe mode is > enabled or disabled. Website owners can create symlinks. > I understand the open_basedir is kinda flawed security measure, and > safe_mode is a primary safeguard with mod_php, but it would be nice to get > it working under FreeBSD too. Well, my security mechanizms are pretty simple and use some combination of MAC and bare uids/gid to enforce required permissions. The code is about 100 lines of code, much less then original open_basedir implementation. In any case, the code won't be usuful to you as is, it works combined with ad-hoc apache module, that sets required flags, variables, etc. > >> Most basedir problems are linked with the fact it produce a lot of lstast/ >> readlinks on every require, include or open command. On Linux it pereforms >> even worse, as they implemented readlink there by hand, and, of course, >> their implementation isn't particulry good. > > But there is no high sys cpu usage on Linux in contrary to FreeBSD, as > reported by original author of the thread..? > Do you have numbers or benchmark ready? I see the number of syscalls > required is astonishing (on Linux) but doesn't cause any problem at first > look. > I don't have specific benchmark numbers, and it's true, that top on Linux don't show such sys time usage, as on FreeBSD boxes. However, the overall performance of boxes on FreeBSD is 30-40% higher, that Linux ones. This numbers is empirical, but I'm pretty sure in them: in past I migrated Linux hosting to FreeBSD-based, and after that, I was able to add a bunch of new users to that boxes without performance impact. In fact, the load average on these boxes are MUCH lower, that was on Linux. Also, I notices, that stat() costs much more on Linux, that FreeBSD. I don't certainly know, why Linux shows low sys time usage, probably it's just bugs in accounting. My basedir patches was implemented later on FreeBSD boxes, and I never returned to Linux. Thus I can't say whether it impacts Linux performance, or nor... -- Stanislav Sedov ST4096-RIPE From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 08:34:16 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 47278106566B for ; Wed, 27 Feb 2008 08:34:16 +0000 (UTC) (envelope-from vadim_nuclight@mail.ru) Received: from mx4.mail.ru (fallback.mail.ru [194.67.57.14]) by mx1.freebsd.org (Postfix) with ESMTP id 033E813C45A for ; Wed, 27 Feb 2008 08:34:15 +0000 (UTC) (envelope-from vadim_nuclight@mail.ru) Received: from mx30.mail.ru (mx30.mail.ru [194.67.23.238]) by mx4.mail.ru (mPOP.Fallback_MX) with ESMTP id 8D1B2AB7C0E for ; Wed, 27 Feb 2008 11:04:21 +0300 (MSK) Received: from [78.140.3.71] (port=63269 helo=nuclight.avtf.net) by mx30.mail.ru with esmtp id 1JUHGv-000D4A-00; Wed, 27 Feb 2008 11:04:13 +0300 To: "Niki Denev" References: <2e77fc10802212218k6acc7850m746a6c3d61c36937@mail.gmail.com> Message-ID: Date: Wed, 27 Feb 2008 14:04:10 +0600 From: "Vadim Goncharov" Organization: AVTF TPU Hostel Content-Type: text/plain; format=flowed; delsp=yes; charset=koi8-r MIME-Version: 1.0 Content-Transfer-Encoding: 8bit In-Reply-To: <2e77fc10802212218k6acc7850m746a6c3d61c36937@mail.gmail.com> User-Agent: Opera M2/7.54 (Win32, build 3865) Cc: freebsd-performance@freebsd.org Subject: Re: interface aliases - not so curious 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: Wed, 27 Feb 2008 08:34:16 -0000 22.02.08 @ 12:18 Niki Denev wrote: > On Thu, Feb 21, 2008 at 2:18 PM, Vadim Goncharov > wrote: >> Hi! >> >> After looking at humorous quoting about a man trying to ban unused >> addresses in >> his network by putting 65535 ifcong_XXX_aliasYYY lines to rc.conf, I >> decided to >> check this performance issue on a 6.2-RELEASE (GENERIC) and compare it >> with >> Linux. Below are results from two machines. >> >> First, I've found that both FreeBSD and Linux clearly use linked-list >> insertion >> to tail of queue, because time was growing as O(N^2). Then, Linux >> deleted it >> slowly at first, then faster (is it using LIFO?..). >> >> But Linux with iproute2 was 6 times faster on addition (FreeBSD did it >> ONE HOUR!), >> and even more faster on deletion. Why?.. [...skip...] > The hardware seems very different between the two cases. > Pentium D's are probably much slower than the new Xeons, and > have less cache. > Also, is your Pentium D machine really SMP or just HTT? I've shown dmesg output in my letter, SMP GENERIC kernel told both CPUs are activated. HTT is present in features, I didn't any tuning with the machine, so probably it is real SMP, I don't know :) Although this part is really curious rather than practical, we should think about another performance-related thing: as addresses are stored in linked list, what is overhead on multi-interface machine on EVERY inbound packet? Imagine an mpd PPPoE router with 2000 interfaces - every packet will cause lookup into this list in ip_input() - and ENTIRE list for every forwarded packet. If ipfw is enebled with ``me'' rules - EVERY such rule will cause such overhead, too. Should we turn an alias address list into Radix or hash, as it was with VLAN interfaces? -- WBR, Vadim Goncharov From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 11:28:30 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D4F791065670 for ; Wed, 27 Feb 2008 11:28:30 +0000 (UTC) (envelope-from pmurray@nevada.net.nz) Received: from bellagio.open2view.net (bellagio.open2view.net [210.48.79.75]) by mx1.freebsd.org (Postfix) with ESMTP id A298C8FC1F for ; Wed, 27 Feb 2008 11:28:30 +0000 (UTC) (envelope-from pmurray@nevada.net.nz) Received: from [10.1.1.9] (219-89-71-208.ipnets.xtra.co.nz [219.89.71.208]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) by bellagio.open2view.net (Postfix) with ESMTP id E68707F074B for ; Thu, 28 Feb 2008 00:09:12 +1300 (NZDT) Message-Id: From: Philip Murray To: freebsd-performance@freebsd.org Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (Apple Message framework v919.2) Date: Thu, 28 Feb 2008 00:09:04 +1300 X-Mailer: Apple Mail (2.919.2) Subject: Slow iSCSI performance 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: Wed, 27 Feb 2008 11:28:30 -0000 Hi, I'm trying to use the new iSCSI initiator (thanks!) with 7, but I'm getting dismal performance. A simple dd will will max out at about 2MB/ sec, and untarring the likes of the ports tree is a painful task. The target is another FreeBSD 7 machine running the NetBSD target daemon from ports exporting a ZVOL from ZFS (also tried with a file on UFS). It'll start off relatively fast and then suddenly dies after a few seconds, and then eventually will start again: tty da0 da1 pass0 cpu tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy in id 0 78 63.90 494 30.80 0.00 0 0.00 0.00 0 0.00 0 0 5 2 93 0 77 63.89 575 35.90 0.00 0 0.00 0.00 0 0.00 0 0 8 3 89 0 77 63.86 581 36.26 0.00 0 0.00 0.00 0 0.00 0 0 5 4 91 0 77 63.64 268 16.64 0.00 0 0.00 0.00 0 0.00 0 0 3 2 95 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 0 100 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 0 100 The two hosts are connected with GbE, and iperf can saturate it without trouble (~987Mb/sec in both directions). Any ideas where to start looking for the culprit? Cheers Phil From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 11:54:14 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 603411065671 for ; Wed, 27 Feb 2008 11:54:14 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: from blah.sun-fish.com (blah.sun-fish.com [217.18.249.150]) by mx1.freebsd.org (Postfix) with ESMTP id 28D108FC1A for ; Wed, 27 Feb 2008 11:54:14 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: by blah.sun-fish.com (Postfix, from userid 1002) id 1F04C1B10EF2; Wed, 27 Feb 2008 12:54:13 +0100 (CET) X-Spam-Checker-Version: SpamAssassin 3.2.3 (2007-08-08) on blah.cmotd.com X-Spam-Level: X-Spam-Status: No, score=-10.6 required=5.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.2.3 Received: from hater.haters.org (hater.cmotd.com [192.168.3.125]) by blah.sun-fish.com (Postfix) with ESMTP id 0195E1B10EE8; Wed, 27 Feb 2008 12:54:06 +0100 (CET) Message-ID: <47C54F5E.4040903@moneybookers.com> Date: Wed, 27 Feb 2008 13:54:06 +0200 From: Stefan Lambrev User-Agent: Thunderbird 2.0.0.9 (X11/20080212) MIME-Version: 1.0 To: Philip Murray References: In-Reply-To: Content-Type: text/plain; charset=windows-1251; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Slow iSCSI performance 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: Wed, 27 Feb 2008 11:54:14 -0000 Greeting, Philip Murray wrote: > Hi, > > I'm trying to use the new iSCSI initiator (thanks!) with 7, but I'm > getting dismal performance. A simple dd will will max out at about > 2MB/sec, and untarring the likes of the ports tree is a painful task. I have similar experience. In my case I was using for initiator Linux host and FreeBSD with iscsi-target from ports. I didn't have enough time to dig where the problem is. > > The target is another FreeBSD 7 machine running the NetBSD target > daemon from ports exporting a ZVOL from ZFS (also tried with a file on > UFS). > > > It'll start off relatively fast and then suddenly dies after a few > seconds, and then eventually will start again: > > tty da0 da1 pass0 > cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy > in id > 0 78 63.90 494 30.80 0.00 0 0.00 0.00 0 0.00 0 0 5 > 2 93 > 0 77 63.89 575 35.90 0.00 0 0.00 0.00 0 0.00 0 0 8 > 3 89 > 0 77 63.86 581 36.26 0.00 0 0.00 0.00 0 0.00 0 0 5 > 4 91 > 0 77 63.64 268 16.64 0.00 0 0.00 0.00 0 0.00 0 0 3 > 2 95 > 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 > 0 100 > 0 77 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0 0 0 > 0 100 > > > The two hosts are connected with GbE, and iperf can saturate it > without trouble (~987Mb/sec in both directions). > > Any ideas where to start looking for the culprit? > > Cheers > > Phil > > > > > > > > _______________________________________________ > 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" -- Best Wishes, Stefan Lambrev ICQ# 24134177 From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 12:12:47 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2DCB4106566C for ; Wed, 27 Feb 2008 12:12:47 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id E8C438FC19 for ; Wed, 27 Feb 2008 12:12:42 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1JUL9E-0005vt-65 for freebsd-performance@freebsd.org; Wed, 27 Feb 2008 12:12:32 +0000 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 12:12:32 +0000 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 12:12:32 +0000 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: Ivan Voras Date: Wed, 27 Feb 2008 13:15:30 +0100 Lines: 44 Message-ID: References: <47C54F5E.4040903@moneybookers.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig5858DE1B077642FC9C6D295F" X-Complaints-To: usenet@ger.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 2.0.0.6 (X11/20071022) In-Reply-To: <47C54F5E.4040903@moneybookers.com> X-Enigmail-Version: 0.95.0 Sender: news Subject: Re: Slow iSCSI performance 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: Wed, 27 Feb 2008 12:12:47 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig5858DE1B077642FC9C6D295F Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Stefan Lambrev wrote: > Greeting, >=20 > Philip Murray wrote: >> Hi, >> >> I'm trying to use the new iSCSI initiator (thanks!) with 7, but I'm >> getting dismal performance. A simple dd will will max out at about >> 2MB/sec, and untarring the likes of the ports tree is a painful task. > I have similar experience. In my case I was using for initiator Linux > host and FreeBSD with iscsi-target from ports. > I didn't have enough time to dig where the problem is. >> >> The target is another FreeBSD 7 machine running the NetBSD target >> daemon from ports exporting a ZVOL from ZFS (also tried with a file on= >> UFS). See this: http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.html= --------------enig5858DE1B077642FC9C6D295F Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQFHxVRoldnAQVacBcgRAq65AKC4a1nin5GLwmrkDgZTH6QZpibo5wCdHW6e taQ2YkQ3PIybZ4uK2GQPaOc= =7yia -----END PGP SIGNATURE----- --------------enig5858DE1B077642FC9C6D295F-- From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 07:32:30 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C799C106566C for ; Wed, 27 Feb 2008 07:32:30 +0000 (UTC) (envelope-from punosevac@math.arizona.edu) Received: from smtp-gs.math.arizona.edu (math051.cs.arizona.edu [150.135.82.51]) by mx1.freebsd.org (Postfix) with ESMTP id A0E5A13C45A for ; Wed, 27 Feb 2008 07:32:30 +0000 (UTC) (envelope-from punosevac@math.arizona.edu) Received: from Debian-exim by smtp-gs.math.arizona.edu with local-bsmtp (Exim 4.63) (envelope-from ) id 1JUGVm-00078G-0b for freebsd-performance@freebsd.org; Wed, 27 Feb 2008 00:15:30 -0700 Received: from 71-220-154-220.tcsn.qwest.net ([71.220.154.220] helo=.domain.actdsltmp) by smtp-gs.math.arizona.edu with esmtpsa (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.63) (envelope-from ) id 1JUGVa-00077N-EX; Wed, 27 Feb 2008 00:15:18 -0700 Message-ID: <47C50E03.5030501@math.arizona.edu> Date: Wed, 27 Feb 2008 00:15:15 -0700 From: Predrag Punosevac User-Agent: Thunderbird 2.0.0.6 (X11/20070916) MIME-Version: 1.0 To: Ted Mittelstaedt References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-ACL-Warn: The HELO/EHLO greeting .domain.actdsltmp is invalid X-Outgoing-Spam-Score: -2.5 (--) X-Mailman-Approved-At: Wed, 27 Feb 2008 12:21:23 +0000 Cc: freebsd-performance@freebsd.org, Kris Kennaway , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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: Wed, 27 Feb 2008 07:32:30 -0000 Ted Mittelstaedt wrote: > >> -----Original Message----- >> From: owner-freebsd-questions@freebsd.org >> [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway >> Sent: Monday, February 25, 2008 12:18 PM >> To: Oliver Herold; freebsd-questions@freebsd.org; >> freebsd-performance@freebsd.org >> Subject: Re: FreeBSD bind performance in FreeBSD 7 >> >> >> Oliver Herold wrote: >> >>> Hi, >>> >>> I saw this bind benchmarks just some minutes ago, >>> >>> http://new.isc.org/proj/dnsperf/OStest.html >>> >>> is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is >>> this something verified only for the state of development back in August >>> 2007? >>> >> I have been trying to replicate this. ISC have kindly given me access >> to their test data but I am seeing Linux performing much slower than >> FreeBSD with the same ISC workload. >> >> > > Kris, > > Every couple years we go through this with ISC. They come out with > a new version of BIND then claim that nothing other than Linux can > run it well. I've seen this nonsense before and it's tiresome. > > Incidentally, the query tool they used, queryperf, has been changed > to dnsperf. Someone needs to look at that port - /usr/ports/dns/dnsperf - > as it has a build depend of bind9 - well bind 9.3.4 is part of 6.3-RELEASE > and I was rather irked when I ran the dnsperf port maker and the > maker stupidly began the process of downloading and building the > same version of BIND that I was already running on my server. > > >> * I am trying to understand what is different about the ISC >> configuration but have not yet found the cause. >> > > It's called "Anti-FreeBSD bias". You won't find anything. > > You just described the tests up to isomorphism in the terminology of mathematics which is more familiar subject to me :-) The results of OpenBSD has been discussed and analyzed on the misc.at.openbsd.org. Even to a hobbyist like myself was not clear why did they chose to test OpenBSD 4.1 when only in two month the stable version of OpenBSD will be 4.3. For those unfamiliar performance of OpenBSD 4.2 as a DNS server has been dramatically improved from the 4.1 version. The question of multi-threading (no-no in OpenBSD world) and its role in above results was also analyzed. >> e.g. NSD >> (ports/dns/nsd) is a much faster and more scalable DNS server than BIND >> (because it is better optimized for the smaller set of features it >> supports). >> >> > > When you make remarks like that it's no wonder ISC is in the business > of slamming FreeBSD. People used to make the same claims about djbdns > but I noticed over the last few years they don't seem to be doing > that anymore. > > If nsd is so much better than yank bind out of the base FreeBSD and > replace it with nsd. Of course that will make more work for me > when I regen our nameservers here since nsd will be the first thing > on the "rm" list. > > I sincerely hope for the above. Hopefully Ted finally can buy that Mercedes to his wife which she deserves so much ;-) . Cheers, Predrag > Ted > > _______________________________________________ > freebsd-questions@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > To unsubscribe, send any mail to "freebsd-questions-unsubscribe@freebsd.org" > From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 12:21:38 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4A1281065676 for ; Wed, 27 Feb 2008 12:21:38 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: from blah.sun-fish.com (blah.sun-fish.com [217.18.249.150]) by mx1.freebsd.org (Postfix) with ESMTP id 184AB8FC2E for ; Wed, 27 Feb 2008 12:21:37 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: by blah.sun-fish.com (Postfix, from userid 1002) id C78CF1B10EDC; Wed, 27 Feb 2008 13:21:36 +0100 (CET) X-Spam-Checker-Version: SpamAssassin 3.2.3 (2007-08-08) on blah.cmotd.com X-Spam-Level: X-Spam-Status: No, score=-10.6 required=5.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.2.3 Received: from hater.haters.org (hater.cmotd.com [192.168.3.125]) by blah.sun-fish.com (Postfix) with ESMTP id 655391B10EF1 for ; Wed, 27 Feb 2008 13:21:26 +0100 (CET) Message-ID: <47C555C6.4020703@moneybookers.com> Date: Wed, 27 Feb 2008 14:21:26 +0200 From: Stefan Lambrev User-Agent: Thunderbird 2.0.0.9 (X11/20080212) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <47C54F5E.4040903@moneybookers.com> In-Reply-To: Content-Type: text/plain; charset=windows-1251; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: Slow iSCSI performance 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: Wed, 27 Feb 2008 12:21:38 -0000 Greetings. Ivan Voras wrote: > Stefan Lambrev wrote: > >> Greeting, >> >> Philip Murray wrote: >> >>> Hi, >>> >>> I'm trying to use the new iSCSI initiator (thanks!) with 7, but I'm >>> getting dismal performance. A simple dd will will max out at about >>> 2MB/sec, and untarring the likes of the ports tree is a painful task. >>> >> I have similar experience. In my case I was using for initiator Linux >> host and FreeBSD with iscsi-target from ports. >> I didn't have enough time to dig where the problem is. >> >>> The target is another FreeBSD 7 machine running the NetBSD target >>> daemon from ports exporting a ZVOL from ZFS (also tried with a file on >>> UFS). >>> > > > See this: > http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.html > I do not see the patch in this thread :) Is there a patch for 7.0-RELEASE? (If not already patched?) -- Best Wishes, Stefan Lambrev ICQ# 24134177 From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 12:41:37 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4C7261065672 for ; Wed, 27 Feb 2008 12:41:37 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id 1B7808FC1F for ; Wed, 27 Feb 2008 12:41:37 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1JULbL-0007Mp-A0 for freebsd-performance@freebsd.org; Wed, 27 Feb 2008 12:41:35 +0000 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 12:41:35 +0000 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 12:41:35 +0000 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: Ivan Voras Date: Wed, 27 Feb 2008 13:44:39 +0100 Lines: 34 Message-ID: References: <47C54F5E.4040903@moneybookers.com> <47C555C6.4020703@moneybookers.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig313A81AF4077C6103D1C854B" X-Complaints-To: usenet@ger.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 2.0.0.6 (X11/20071022) In-Reply-To: <47C555C6.4020703@moneybookers.com> X-Enigmail-Version: 0.95.0 Sender: news Subject: Re: Slow iSCSI performance 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: Wed, 27 Feb 2008 12:41:37 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig313A81AF4077C6103D1C854B Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Stefan Lambrev wrote: > Greetings. >=20 > Ivan Voras wrote: >> http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.h= tml >> =20 > I do not see the patch in this thread :) > Is there a patch for 7.0-RELEASE? (If not already patched?) Try asking the author of the patch. --------------enig313A81AF4077C6103D1C854B Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQFHxVs3ldnAQVacBcgRAu4PAJ99UDH9BA7DoJ/e615V9T9pTaWEQQCg6Jrn F/HZue8HrWq+Pp3jlndZqaQ= =kslB -----END PGP SIGNATURE----- --------------enig313A81AF4077C6103D1C854B-- From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 13:42:11 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8F8961065674 for ; Wed, 27 Feb 2008 13:42:11 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.freebsd.org (Postfix) with ESMTP id DC1D48FC21 for ; Wed, 27 Feb 2008 13:42:09 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from list by ciao.gmane.org with local (Exim 4.43) id 1JUMXr-0001s8-0G for freebsd-performance@freebsd.org; Wed, 27 Feb 2008 13:42:03 +0000 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 13:42:02 +0000 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Wed, 27 Feb 2008 13:42:02 +0000 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: Ivan Voras Date: Wed, 27 Feb 2008 14:45:07 +0100 Lines: 34 Message-ID: References: <47C54F5E.4040903@moneybookers.com> <47C555C6.4020703@moneybookers.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig10FF85B9A236CD28F352CC42" X-Complaints-To: usenet@ger.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Thunderbird 2.0.0.6 (X11/20071022) In-Reply-To: <47C555C6.4020703@moneybookers.com> X-Enigmail-Version: 0.95.0 Sender: news Subject: Re: Slow iSCSI performance 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: Wed, 27 Feb 2008 13:42:11 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig10FF85B9A236CD28F352CC42 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Stefan Lambrev wrote: > Greetings. >=20 > Ivan Voras wrote: >> See this: >> http://lists.freebsd.org/pipermail/freebsd-scsi/2008-February/003383.h= tml >> =20 > I do not see the patch in this thread :) > Is there a patch for 7.0-RELEASE? (If not already patched?) The patch is posted now. --------------enig10FF85B9A236CD28F352CC42 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQFHxWljldnAQVacBcgRAi5pAKDMAgpRjPNbxCYXbfJ/C4FZXHB3eACguu1p NcLCPXLYpRhQnSEpwV7/UHw= =JEh4 -----END PGP SIGNATURE----- --------------enig10FF85B9A236CD28F352CC42-- From owner-freebsd-performance@FreeBSD.ORG Wed Feb 27 17:06:52 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C606E106566C; Wed, 27 Feb 2008 17:06:52 +0000 (UTC) (envelope-from sam@errno.com) Received: from ebb.errno.com (ebb.errno.com [69.12.149.25]) by mx1.freebsd.org (Postfix) with ESMTP id A7F858FC28; Wed, 27 Feb 2008 17:06:52 +0000 (UTC) (envelope-from sam@errno.com) Received: from trouble.errno.com (trouble.errno.com [10.0.0.248]) (authenticated bits=0) by ebb.errno.com (8.13.6/8.12.6) with ESMTP id m1RGrb6v017855 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 27 Feb 2008 08:53:38 -0800 (PST) (envelope-from sam@errno.com) Message-ID: <47C59591.6040600@errno.com> Date: Wed, 27 Feb 2008 08:53:37 -0800 From: Sam Leffler User-Agent: Thunderbird 2.0.0.9 (X11/20071125) MIME-Version: 1.0 To: Ted Mittelstaedt References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-DCC--Metrics: ebb.errno.com; whitelist Cc: freebsd-performance@freebsd.org, Kris Kennaway , Oliver Herold , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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: Wed, 27 Feb 2008 17:06:52 -0000 Ted Mittelstaedt wrote: > >> -----Original Message----- >> From: owner-freebsd-questions@freebsd.org >> [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway >> Sent: Monday, February 25, 2008 12:18 PM >> To: Oliver Herold; freebsd-questions@freebsd.org; >> freebsd-performance@freebsd.org >> Subject: Re: FreeBSD bind performance in FreeBSD 7 >> >> >> Oliver Herold wrote: >> >>> Hi, >>> >>> I saw this bind benchmarks just some minutes ago, >>> >>> http://new.isc.org/proj/dnsperf/OStest.html >>> >>> is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is >>> this something verified only for the state of development back in August >>> 2007? >>> >> I have been trying to replicate this. ISC have kindly given me access >> to their test data but I am seeing Linux performing much slower than >> FreeBSD with the same ISC workload. >> >> > > Kris, > > Every couple years we go through this with ISC. They come out with > a new version of BIND then claim that nothing other than Linux can > run it well. I've seen this nonsense before and it's tiresome. > > Incidentally, the query tool they used, queryperf, has been changed > to dnsperf. Someone needs to look at that port - /usr/ports/dns/dnsperf - > as it has a build depend of bind9 - well bind 9.3.4 is part of 6.3-RELEASE > and I was rather irked when I ran the dnsperf port maker and the > maker stupidly began the process of downloading and building the > same version of BIND that I was already running on my server. > > >> * I am trying to understand what is different about the ISC >> configuration but have not yet found the cause. >> > > It's called "Anti-FreeBSD bias". You won't find anything. > > >> e.g. NSD >> (ports/dns/nsd) is a much faster and more scalable DNS server than BIND >> (because it is better optimized for the smaller set of features it >> supports). >> >> > > When you make remarks like that it's no wonder ISC is in the business > of slamming FreeBSD. People used to make the same claims about djbdns > but I noticed over the last few years they don't seem to be doing > that anymore. > > If nsd is so much better than yank bind out of the base FreeBSD and > replace it with nsd. Of course that will make more work for me > when I regen our nameservers here since nsd will be the first thing > on the "rm" list. > Please save your rhetoric for some other forum. The ISC folks have been working with us to understand what's going on. I'm not aware of any anit-FreeBSD slams going on; mostly uninformed comments. We believe FreeBSD does very well in any comparisons of the sort being discussed and there's still lots of room for improvement. As to nsd vs bind, understand they are very different applications w/ totally different goals. Comparing performance is not entirely fair and certainly is difficult. Kris investigated the performance of nsd mostly to understand how bind might scale if certain architectural changes were made to eliminate known bottlenecks in the application. Sam From owner-freebsd-performance@FreeBSD.ORG Thu Feb 28 01:46:03 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8B886106566B for ; Thu, 28 Feb 2008 01:46:03 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from ag-out-0708.google.com (ag-out-0708.google.com [72.14.246.248]) by mx1.freebsd.org (Postfix) with ESMTP id 37E8A8FC18 for ; Thu, 28 Feb 2008 01:46:02 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by ag-out-0708.google.com with SMTP id 5so8327001agb.7 for ; Wed, 27 Feb 2008 17:46:02 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; bh=lTzv/9A7EopMjL6ZJumMiDyagik9qnP3NhD39U4yBHI=; b=gZWYYngHpjcSvXpUyjoRy7CMypMOZdwIl5vWyB7V6gtJc6ZD7bUzcn5wnFvseKyUcXKsyKjBiXtGpUJ7LLtGd/UuRf+mdg+zPpxoqLItXNQuCJxiqCl3SxVjNGuWzZ9SABXIjvkn9KF93/zgbpGyCr8gYl/0M31uCUE0RULCvvY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=ka2B3w9TaXZTY1uKz73YGMj6G6ivsI3agFUQ90Yow6nOs+1F2k2Tfo2OH2ULM1JNhzwGPRYh6fIOYpovkijYMTE/WuVbisLVJxQDuVjD9sqLQl3KVYiEfQGh8+9B9PMvqo5Kh2J8EtkGjxvw4CMKPoPFidiFQObU8eG1ayt2+YA= Received: by 10.150.155.1 with SMTP id c1mr2579554ybe.155.1204163161657; Wed, 27 Feb 2008 17:46:01 -0800 (PST) Received: by 10.150.144.2 with HTTP; Wed, 27 Feb 2008 17:46:01 -0800 (PST) Message-ID: Date: Thu, 28 Feb 2008 10:46:01 +0900 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: "Sam Leffler" In-Reply-To: <47C59591.6040600@errno.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <47C59591.6040600@errno.com> X-Google-Sender-Auth: ddf582164e40737c Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , Ted Mittelstaedt , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 28 Feb 2008 01:46:03 -0000 (Sorry for top posting.) Its not actually -that- bad an idea to compare different applications. It sets the "bar" for how far the entire system {hardware, OS, application, network} can be pushed. If nsd beats bind9 by say 5 or 10% over all, then its nothing to write home about. If nsd beats bind9 by 50% and shows similar kernel/interrupt space time use then thats something to stare at. Even if its just because nsd 'does less' and gives more CPU time to system/interrupt processing you've identified that the system -can- be pushed harder, and perhaps working with the bind9 guys a little more can identify what they're doing wrong. Thats how I noticed the performance differences between various platforms running Squid a few years ago - for example, gettimeofday() being called way, way too frequently - and I compare Squid's kernel/interrupt time; syscall footprint; hwpmc/oprofile traces; etc against other proxy-capable applications (varnish, lighttpd, apache) to see exactly what they're doing differently. 2c, adrian On 28/02/2008, Sam Leffler wrote: > Ted Mittelstaedt wrote: > > > >> -----Original Message----- > >> From: owner-freebsd-questions@freebsd.org > >> [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway > >> Sent: Monday, February 25, 2008 12:18 PM > >> To: Oliver Herold; freebsd-questions@freebsd.org; > >> freebsd-performance@freebsd.org > >> Subject: Re: FreeBSD bind performance in FreeBSD 7 > >> > >> > >> Oliver Herold wrote: > >> > >>> Hi, > >>> > >>> I saw this bind benchmarks just some minutes ago, > >>> > >>> http://new.isc.org/proj/dnsperf/OStest.html > >>> > >>> is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is > >>> this something verified only for the state of development back in August > >>> 2007? > >>> > >> I have been trying to replicate this. ISC have kindly given me access > >> to their test data but I am seeing Linux performing much slower than > >> FreeBSD with the same ISC workload. > >> > >> > > > > Kris, > > > > Every couple years we go through this with ISC. They come out with > > a new version of BIND then claim that nothing other than Linux can > > run it well. I've seen this nonsense before and it's tiresome. > > > > Incidentally, the query tool they used, queryperf, has been changed > > to dnsperf. Someone needs to look at that port - /usr/ports/dns/dnsperf - > > as it has a build depend of bind9 - well bind 9.3.4 is part of 6.3-RELEASE > > and I was rather irked when I ran the dnsperf port maker and the > > maker stupidly began the process of downloading and building the > > same version of BIND that I was already running on my server. > > > > > >> * I am trying to understand what is different about the ISC > >> configuration but have not yet found the cause. > >> > > > > It's called "Anti-FreeBSD bias". You won't find anything. > > > > > >> e.g. NSD > >> (ports/dns/nsd) is a much faster and more scalable DNS server than BIND > >> (because it is better optimized for the smaller set of features it > >> supports). > >> > >> > > > > When you make remarks like that it's no wonder ISC is in the business > > of slamming FreeBSD. People used to make the same claims about djbdns > > but I noticed over the last few years they don't seem to be doing > > that anymore. > > > > If nsd is so much better than yank bind out of the base FreeBSD and > > replace it with nsd. Of course that will make more work for me > > when I regen our nameservers here since nsd will be the first thing > > on the "rm" list. > > > > > Please save your rhetoric for some other forum. The ISC folks have been > working with us to understand what's going on. I'm not aware of any > anit-FreeBSD slams going on; mostly uninformed comments. > > We believe FreeBSD does very well in any comparisons of the sort being > discussed and there's still lots of room for improvement. > > As to nsd vs bind, understand they are very different applications w/ > totally different goals. Comparing performance is not entirely fair and > certainly is difficult. Kris investigated the performance of nsd mostly > to understand how bind might scale if certain architectural changes were > made to eliminate known bottlenecks in the application. > > > Sam > > _______________________________________________ > 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" > -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Thu Feb 28 08:48:08 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 79DFE1065677 for ; Thu, 28 Feb 2008 08:48:08 +0000 (UTC) (envelope-from radek@ceskedomeny.cz) Received: from margaret.starnet.cz (margaret.starnet.cz [62.240.182.134]) by mx1.freebsd.org (Postfix) with SMTP id AD8E88FC1F for ; Thu, 28 Feb 2008 08:48:07 +0000 (UTC) (envelope-from radek@ceskedomeny.cz) Received: (qmail 94614 invoked from network); 28 Feb 2008 09:48:04 +0100 Received: from unknown (HELO localhost) (77.48.45.228) by margaret.starnet.cz with SMTP; 28 Feb 2008 09:48:04 +0100 Date: Thu, 28 Feb 2008 09:47:58 +0100 From: "Bc. Radek Krejca" X-Mailer: The Bat! (v3.99.3) Professional Organization: STARNET, s. r. o. X-Priority: 3 (Normal) Message-ID: <1369675267.20080228094758@starnet.cz> To: FreeBSD Mailing Lists In-Reply-To: <107794589.20080205140018@starnet.cz> References: <107794589.20080205140018@starnet.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Subject: Re: FBSD 1GBit router? - solved X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: "Bc. Radek Krejca" List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 28 Feb 2008 08:48:08 -0000 Hi, thank you very much. Problem wasn't netither in version of bsd nor in configuration. Problem was in hardware. I change bge ethernet card to intel and it working. --=20 S pozdravem, Bc. Radek Krejca ICQ: 65895541 From owner-freebsd-performance@FreeBSD.ORG Thu Feb 28 11:21:04 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D7A381065672; Thu, 28 Feb 2008 11:21:04 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 379168FC19; Thu, 28 Feb 2008 11:21:03 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C6991E.1050502@FreeBSD.org> Date: Thu, 28 Feb 2008 12:21:02 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.12 (Macintosh/20080213) MIME-Version: 1.0 To: Adrian Chadd References: <47C59591.6040600@errno.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Oliver Herold , freebsd-questions@freebsd.org, Ted Mittelstaedt Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 28 Feb 2008 11:21:05 -0000 Adrian Chadd wrote: > (Sorry for top posting.) > > Its not actually -that- bad an idea to compare different applications. > It sets the "bar" for how far the entire system {hardware, OS, > application, network} can be pushed. > > If nsd beats bind9 by say 5 or 10% over all, then its nothing to write > home about. If nsd beats bind9 by 50% and shows similar > kernel/interrupt space time use then thats something to stare at. Even > if its just because nsd 'does less' and gives more CPU time to > system/interrupt processing you've identified that the system -can- be > pushed harder, and perhaps working with the bind9 guys a little more > can identify what they're doing wrong. > > Thats how I noticed the performance differences between various > platforms running Squid a few years ago - for example, gettimeofday() > being called way, way too frequently - and I compare Squid's > kernel/interrupt time; syscall footprint; hwpmc/oprofile traces; etc > against other proxy-capable applications (varnish, lighttpd, apache) > to see exactly what they're doing differently. Yep, and in this case NSD is currently 90% faster with prospects to push it even higher with some further kernel changes (so far we have improved it by 45%). BIND is limited by its own architecture, so improvements cannot be made by modifying the kernel. Anyway, the motivation here is not a DNS deathmatch, but part of our ongoing effort to look for aspects of FreeBSD performance that can be improved. Currently we are looking at UDP performance, and DNS serving was thought to be a good model for that. It turns out that BIND does not stress the kernel, but NSD does. Kris From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 07:45:38 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AAA2C106566C; Fri, 29 Feb 2008 07:45:38 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from mail.freebsd-corp-net-guide.com (mail.freebsd-corp-net-guide.com [65.75.192.90]) by mx1.freebsd.org (Postfix) with ESMTP id 5A5E78FC20; Fri, 29 Feb 2008 07:45:38 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from TEDSDSK (nat-rtr.freebsd-corp-net-guide.com [65.75.197.130]) by mail.freebsd-corp-net-guide.com (8.13.8/8.13.8) with SMTP id m1T7iAN2045639; Thu, 28 Feb 2008 23:44:12 -0800 (PST) (envelope-from tedm@toybox.placo.com) From: "Ted Mittelstaedt" To: "Sam Leffler" Date: Thu, 28 Feb 2008 23:45:12 -0800 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.6604 (9.0.2911.0) X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1914 In-Reply-To: <47C59591.6040600@errno.com> Importance: Normal X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (mail.freebsd-corp-net-guide.com [65.75.192.90]); Thu, 28 Feb 2008 23:44:13 -0800 (PST) Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , freebsd-questions@freebsd.org Subject: RE: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 07:45:38 -0000 > -----Original Message----- > From: owner-freebsd-questions@freebsd.org > [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Sam Leffler > Sent: Wednesday, February 27, 2008 8:54 AM > To: Ted Mittelstaedt > Cc: freebsd-performance@freebsd.org; Kris Kennaway; Oliver Herold; > freebsd-questions@freebsd.org > Subject: Re: FreeBSD bind performance in FreeBSD 7 > > > Ted Mittelstaedt wrote: > > > >> -----Original Message----- > >> From: owner-freebsd-questions@freebsd.org > >> [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway > >> Sent: Monday, February 25, 2008 12:18 PM > >> To: Oliver Herold; freebsd-questions@freebsd.org; > >> freebsd-performance@freebsd.org > >> Subject: Re: FreeBSD bind performance in FreeBSD 7 > >> > >> > >> Oliver Herold wrote: > >> > >>> Hi, > >>> > >>> I saw this bind benchmarks just some minutes ago, > >>> > >>> http://new.isc.org/proj/dnsperf/OStest.html > >>> > >>> is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is > >>> this something verified only for the state of development > back in August > >>> 2007? > >>> > >> I have been trying to replicate this. ISC have kindly given me access > >> to their test data but I am seeing Linux performing much slower than > >> FreeBSD with the same ISC workload. > >> > >> > > > > Kris, > > > > Every couple years we go through this with ISC. They come out with > > a new version of BIND then claim that nothing other than Linux can > > run it well. I've seen this nonsense before and it's tiresome. > > > > Incidentally, the query tool they used, queryperf, has been changed > > to dnsperf. Someone needs to look at that port - > /usr/ports/dns/dnsperf - > > as it has a build depend of bind9 - well bind 9.3.4 is part of > 6.3-RELEASE > > and I was rather irked when I ran the dnsperf port maker and the > > maker stupidly began the process of downloading and building the > > same version of BIND that I was already running on my server. > > > > > >> * I am trying to understand what is different about the ISC > >> configuration but have not yet found the cause. > >> > > > > It's called "Anti-FreeBSD bias". You won't find anything. > > > > > >> e.g. NSD > >> (ports/dns/nsd) is a much faster and more scalable DNS server than BIND > >> (because it is better optimized for the smaller set of features it > >> supports). > >> > >> > > > > When you make remarks like that it's no wonder ISC is in the business > > of slamming FreeBSD. People used to make the same claims about djbdns > > but I noticed over the last few years they don't seem to be doing > > that anymore. > > > > If nsd is so much better than yank bind out of the base FreeBSD and > > replace it with nsd. Of course that will make more work for me > > when I regen our nameservers here since nsd will be the first thing > > on the "rm" list. > > > > Please save your rhetoric for some other forum. The ISC folks have been > working with us to understand what's going on. Did anyone try disabling the onboard NIC and put in an Intel Pro/1000 in the PCI express slot in the server and retest with both Linux and FreeBSD? As I run Proliants for a living, this stuck out to me like a sore thumb. The onboard NIC in the systems they used for the testbed is just shit. Hell, just about anything Broadcom makes is shit. They even managed to screw up the 3c905 ASIC when 3com switched to using them as the supplier (from Lucent)( - I've watched those card versions panic Linux systems and drop massive packets in FreeBSD, when the Lucent-made chipped cards worked fine. > I'm not aware of any > anit-FreeBSD slams going on; mostly uninformed comments. > It's customary in the industry before publishing rather unflattering results to call in the team in charge of the unflattering product and give them a chance to verify that the tester really knew what they were doing. FreeBSD has got slammed a number of times in the past by testers who didn't do this. In fact as I recall the impetus for fixing the extended greater than 16MB memory test was due to a slam in a trade rag from a tester who didn't bother recompiling the FreeBSD kernel to recognize the complete amount of ram in the server, and running it up against Linux. Maybe I am wrong and the ISC team did in fact call you guys in before publishing the results - but the wording of the entire site (not just the test results) indicated they did their testing and informed FreeBSD after the fact. after publishing. Not nice. Ted From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 14:10:53 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 90CEF106566C for ; Fri, 29 Feb 2008 14:10:53 +0000 (UTC) (envelope-from noisex@apollo.lv) Received: from smtp1.apollo.lv (smtp1.apollo.lv [80.232.168.211]) by mx1.freebsd.org (Postfix) with ESMTP id DB1808FC12 for ; Fri, 29 Feb 2008 14:10:52 +0000 (UTC) (envelope-from noisex@apollo.lv) X-Cloudmark-Score: 0.000000 [] X-Virusscan: Clamd Received: from [195.122.14.116] (HELO dreamwork) by smtp1.apollo.lv (CommuniGate Pro SMTP 5.1.12) with ESMTP id 331932184 for freebsd-performance@freebsd.org; Fri, 29 Feb 2008 16:10:50 +0200 From: "Noisex" To: References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> In-Reply-To: <47C6991E.1050502@FreeBSD.org> Date: Fri, 29 Feb 2008 16:10:49 +0200 Message-ID: <01ce01c87adc$e2796720$a76c3560$@lv> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 12.0 thread-index: Ach5/CWfAYzWoTpkS9CHSsA09qL+rwA2tDqA Content-Language: lv Subject: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 14:10:53 -0000 Hi! The first of all i want felicitate FreeBSD development team and all FBSD community with 7.0 come-out. Ok, the question is not about performance, but anyway maybe you have some ideas how to solve problem in short time - i don't want rebuld all needed packages :) This morning i decided to upgrade one of the my boxes from 6.3 to 7.0 using http://www.daemonology.net/blog/2007-11-11-freebsd-major-version-upgrade.htm l script not native freebsd-update(). Scenario: # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz.asc # gpg --verify freebsd-update-upgrade.tgz.asc freebsd-update-upgrade.tgz # tar -xf freebsd-update-upgrade.tgz # sh freebsd-update.sh -f freebsd-update.conf -r 7.0-RELEASE upgrade # sh freebsd-update.sh -f freebsd-update.conf install # shutdown -r now # sh freebsd-update.sh -f freebsd-update.conf install # portupgrade -faP # sh freebsd-update.sh -f freebsd-update.conf install # shutdown -r now All goes fine till second reboot. After reboot, i couldn't logon to remote box, because default shell is bash, and i got error on SSH login: /libexec/ld-elf.so.1: Shared object "libncurses.so.6" not found, required by "-bash" Thanx GOD, this box is with ILO management and i didnt need go to the data center, so i connect through this one, reboot server to single-user mode, mount all necessary partitions, changed default shell to csh...I have a look to dmesg/messages and a roger that some services also didn't start up because some of the shared libs are missing or something like that: Checked some daemons depencies with ldd and libs like: libc, libm, libthr, libcrypt, libcrypto are missing, or version is changed etc. Question: what i did wrong in upgrade process? And how can i fix this errors now i short time, because portupgrade now also not working because ruby depencies/libs is missing and go on problems. Manualy rebuild every all packages is pain in the ass on Friday night :D Cheers, Noisex From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 14:26:18 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DC8F01065675 for ; Fri, 29 Feb 2008 14:26:18 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: from blah.sun-fish.com (blah.sun-fish.com [217.18.249.150]) by mx1.freebsd.org (Postfix) with ESMTP id 583048FC13 for ; Fri, 29 Feb 2008 14:26:18 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: by blah.sun-fish.com (Postfix, from userid 1002) id 1D5531B10F2C; Fri, 29 Feb 2008 15:26:17 +0100 (CET) X-Spam-Checker-Version: SpamAssassin 3.2.3 (2007-08-08) on blah.cmotd.com X-Spam-Level: X-Spam-Status: No, score=-10.0 required=5.0 tests=ALL_TRUSTED,BAYES_00, J_CHICKENPOX_61 autolearn=no version=3.2.3 Received: from hater.haters.org (hater.cmotd.com [192.168.3.125]) by blah.sun-fish.com (Postfix) with ESMTP id 83E231B10EF4; Fri, 29 Feb 2008 15:26:13 +0100 (CET) Message-ID: <47C81604.7030304@moneybookers.com> Date: Fri, 29 Feb 2008 16:26:12 +0200 From: Stefan Lambrev User-Agent: Thunderbird 2.0.0.12 (X11/20080229) MIME-Version: 1.0 To: Noisex References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> In-Reply-To: <01ce01c87adc$e2796720$a76c3560$@lv> Content-Type: text/plain; charset=windows-1251; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.91.2/6042/Fri Feb 29 13:55:01 2008 on blah.cmotd.com X-Virus-Status: Clean Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 14:26:19 -0000 Greetings, Noisex wrote: > Hi! The first of all i want felicitate FreeBSD development team and all FBSD > community with 7.0 come-out. > > Ok, the question is not about performance, but anyway maybe you have > some ideas how to solve problem in short time - i don't want rebuld all > needed packages :) > Yes -stable or -questions will be more proper mail list to ask this :) If you will not update any ports/packages you should install compat6x and then you will be able to run bash compiled for 6.X. The upgrade procedure is discussed every time when new major version is released, so you can read this thread - http://lists.freebsd.org/pipermail/freebsd-stable/2008-February/040809.html There is very good explanation what are the problems if you do not reinstall all of your ports/packages. > This morning i decided to upgrade one of the my boxes from 6.3 to 7.0 using > http://www.daemonology.net/blog/2007-11-11-freebsd-major-version-upgrade.htm > l script not native freebsd-update(). > > Scenario: > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz.asc > # gpg --verify freebsd-update-upgrade.tgz.asc freebsd-update-upgrade.tgz > # tar -xf freebsd-update-upgrade.tgz > # sh freebsd-update.sh -f freebsd-update.conf -r 7.0-RELEASE upgrade > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > # sh freebsd-update.sh -f freebsd-update.conf install > # portupgrade -faP > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > > > All goes fine till second reboot. > > After reboot, i couldn't logon to remote box, because default shell is bash, > and i got error on SSH login: > > /libexec/ld-elf.so.1: Shared object "libncurses.so.6" not found, required by > "-bash" > > Thanx GOD, this box is with ILO management and i didnt need go to the data > But if you follow documentation you will see that you need access to the server - via serial or local, because you have to run mergemaster and installworld in single user mode. So you can't blame anybody just because you try to upgrade without following the instructions? > center, so i connect through this one, reboot server to single-user mode, > mount all necessary partitions, changed default shell to csh...I have a look > to dmesg/messages and a roger that some services also didn't start up > because some of the shared libs are missing or something like that: > > Checked some daemons depencies with ldd and libs like: libc, libm, libthr, > libcrypt, libcrypto are missing, or version is changed etc. > > Question: what i did wrong in upgrade process? And how can i fix this errors > now i short time, because portupgrade now also not working because ruby > depencies/libs is missing and go on problems. > > Manualy rebuild every all packages is pain in the ass on Friday night :D > compat6x can help you to run the apps and to postpone the upgrade of everything for Monday morning ;) -- Best Wishes, Stefan Lambrev ICQ# 24134177 From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 14:33:25 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1CD481065671 for ; Fri, 29 Feb 2008 14:33:25 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 0B1028FC1C; Fri, 29 Feb 2008 14:33:23 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C817B0.1040602@FreeBSD.org> Date: Fri, 29 Feb 2008 15:33:20 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.12 (Macintosh/20080213) MIME-Version: 1.0 To: Noisex References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> In-Reply-To: <01ce01c87adc$e2796720$a76c3560$@lv> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 14:33:25 -0000 Noisex wrote: > Hi! The first of all i want felicitate FreeBSD development team and all FBSD > community with 7.0 come-out. > > Ok, the question is not about performance, but anyway maybe you have > some ideas how to solve problem in short time - i don't want rebuld all > needed packages :) > > This morning i decided to upgrade one of the my boxes from 6.3 to 7.0 using > http://www.daemonology.net/blog/2007-11-11-freebsd-major-version-upgrade.htm > l script not native freebsd-update(). > > Scenario: > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz.asc > # gpg --verify freebsd-update-upgrade.tgz.asc freebsd-update-upgrade.tgz > # tar -xf freebsd-update-upgrade.tgz > # sh freebsd-update.sh -f freebsd-update.conf -r 7.0-RELEASE upgrade > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > # sh freebsd-update.sh -f freebsd-update.conf install > # portupgrade -faP > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > > > All goes fine till second reboot. > > After reboot, i couldn't logon to remote box, because default shell is bash, > and i got error on SSH login: > > /libexec/ld-elf.so.1: Shared object "libncurses.so.6" not found, required by > "-bash" If the portupgrade -faP completed successfully and your bash was installed from ports then it should have been rebuilt. If you have non-port 6.x software installed then you need to add the compat6x port to keep it running. Kris From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 15:03:56 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 23F841065670 for ; Fri, 29 Feb 2008 15:03:56 +0000 (UTC) (envelope-from noisex@apollo.lv) Received: from smtp1.apollo.lv (smtp1.apollo.lv [80.232.168.211]) by mx1.freebsd.org (Postfix) with ESMTP id 6D04E8FC18 for ; Fri, 29 Feb 2008 15:03:54 +0000 (UTC) (envelope-from noisex@apollo.lv) X-Cloudmark-Score: 0.000000 [] X-Virusscan: Clamd Received: from [195.122.14.116] (HELO dreamwork) by smtp1.apollo.lv (CommuniGate Pro SMTP 5.1.12) with ESMTP id 331992842 for freebsd-performance@freebsd.org; Fri, 29 Feb 2008 17:03:53 +0200 From: "Noisex" To: References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> <47C817B0.1040602@FreeBSD.org> In-Reply-To: <47C817B0.1040602@FreeBSD.org> Date: Fri, 29 Feb 2008 17:03:51 +0200 Message-ID: <01d201c87ae4$4b902850$e2b078f0$@lv> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 12.0 thread-index: Ach64CFMv10qdDoQRoy7gxJnMCp4RwAA2SEg Content-Language: lv Subject: RE: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 15:03:56 -0000 Kris, as i said, i made portupgrade -faP ...and in update process i saw that many ports upgraded. I don't why old version become as current version. Now i've installed compat6x (thanx Stefan Lambrev) -> it's works...but anyway now i will try fix pkgdb and reinstall all necessary ports. -----Original Message----- From: owner-freebsd-performance@freebsd.org [mailto:owner-freebsd-performance@freebsd.org] On Behalf Of Kris Kennaway Sent: Friday, February 29, 2008 4:33 PM To: Noisex Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) Noisex wrote: > Hi! The first of all i want felicitate FreeBSD development team and all FBSD > community with 7.0 come-out. > > Ok, the question is not about performance, but anyway maybe you have > some ideas how to solve problem in short time - i don't want rebuld all > needed packages :) > > This morning i decided to upgrade one of the my boxes from 6.3 to 7.0 using > http://www.daemonology.net/blog/2007-11-11-freebsd-major-version-upgrade.htm > l script not native freebsd-update(). > > Scenario: > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz > # fetch http://people.freebsd.org/~cperciva/freebsd-update-upgrade.tgz.asc > # gpg --verify freebsd-update-upgrade.tgz.asc freebsd-update-upgrade.tgz > # tar -xf freebsd-update-upgrade.tgz > # sh freebsd-update.sh -f freebsd-update.conf -r 7.0-RELEASE upgrade > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > # sh freebsd-update.sh -f freebsd-update.conf install > # portupgrade -faP > # sh freebsd-update.sh -f freebsd-update.conf install > # shutdown -r now > > > All goes fine till second reboot. > > After reboot, i couldn't logon to remote box, because default shell is bash, > and i got error on SSH login: > > /libexec/ld-elf.so.1: Shared object "libncurses.so.6" not found, required by > "-bash" If the portupgrade -faP completed successfully and your bash was installed from ports then it should have been rebuilt. If you have non-port 6.x software installed then you need to add the compat6x port to keep it running. Kris _______________________________________________ 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 Fri Feb 29 15:11:16 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 69F621065673 for ; Fri, 29 Feb 2008 15:11:16 +0000 (UTC) (envelope-from kris@FreeBSD.org) Received: from weak.local (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 956E88FC1F; Fri, 29 Feb 2008 15:11:15 +0000 (UTC) (envelope-from kris@FreeBSD.org) Message-ID: <47C82092.5040504@FreeBSD.org> Date: Fri, 29 Feb 2008 16:11:14 +0100 From: Kris Kennaway User-Agent: Thunderbird 2.0.0.12 (Macintosh/20080213) MIME-Version: 1.0 To: Noisex References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> <47C817B0.1040602@FreeBSD.org> <01d201c87ae4$4b902850$e2b078f0$@lv> In-Reply-To: <01d201c87ae4$4b902850$e2b078f0$@lv> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 29 Feb 2008 15:11:16 -0000 Noisex wrote: > Kris, as i said, i made portupgrade -faP ...and in update process i saw that > many ports upgraded. I don't why old version become as current version. Now > i've installed compat6x (thanx Stefan Lambrev) -> it's works...but anyway > now i will try fix pkgdb and reinstall all necessary ports. The unspoken part of running portupgrade -faP is checking the output summary to verify that it completed correctly. Did you confirm that no packages failed to rebuild? I'm really not seeing how portupgrade could have rebuilt it successfully and yet it was still the old 6.x version. Kris From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 15:26:49 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CC1B71065671 for ; Fri, 29 Feb 2008 15:26:49 +0000 (UTC) (envelope-from noisex@apollo.lv) Received: from smtp1.apollo.lv (smtp1.apollo.lv [80.232.168.211]) by mx1.freebsd.org (Postfix) with ESMTP id 52C5A8FC22 for ; Fri, 29 Feb 2008 15:26:48 +0000 (UTC) (envelope-from noisex@apollo.lv) X-Cloudmark-Score: 0.000000 [] X-Virusscan: Clamd Received: from [195.122.14.116] (HELO dreamwork) by smtp1.apollo.lv (CommuniGate Pro SMTP 5.1.12) with ESMTP id 332009845 for freebsd-performance@freebsd.org; Fri, 29 Feb 2008 17:26:47 +0200 From: "Noisex" To: References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> <47C817B0.1040602@FreeBSD.org> <01d201c87ae4$4b902850$e2b078f0$@lv> <47C82092.5040504@FreeBSD.org> In-Reply-To: <47C82092.5040504@FreeBSD.org> Date: Fri, 29 Feb 2008 17:26:45 +0200 Message-ID: <01d301c87ae7$7e2b2550$7a816ff0$@lv> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook 12.0 thread-index: Ach65XR1X4DOomwlT1KkfJmYWwYcMQAAKyUg Content-Language: lv Subject: RE: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 15:26:49 -0000 I don't remember during portupgrade process was some kind of errors - how much i saw of course. It's bad that my SSH client (SecureCRT) is configured with only 1024 row buffer - i can't scroll it back, or i didn't log upgrade process to file...so i can't be sure to 100% that there wasn't errors :( However that may be now i getting all functionality back step by step :) Noisex -----Original Message----- From: owner-freebsd-performance@freebsd.org [mailto:owner-freebsd-performance@freebsd.org] On Behalf Of Kris Kennaway Sent: Friday, February 29, 2008 5:11 PM To: Noisex Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) Noisex wrote: > Kris, as i said, i made portupgrade -faP ...and in update process i saw that > many ports upgraded. I don't why old version become as current version. Now > i've installed compat6x (thanx Stefan Lambrev) -> it's works...but anyway > now i will try fix pkgdb and reinstall all necessary ports. The unspoken part of running portupgrade -faP is checking the output summary to verify that it completed correctly. Did you confirm that no packages failed to rebuild? I'm really not seeing how portupgrade could have rebuilt it successfully and yet it was still the old 6.x version. Kris _______________________________________________ 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 Fri Feb 29 15:38:16 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D416D1065670 for ; Fri, 29 Feb 2008 15:38:16 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: from blah.sun-fish.com (blah.sun-fish.com [217.18.249.150]) by mx1.freebsd.org (Postfix) with ESMTP id 852908FC1B for ; Fri, 29 Feb 2008 15:38:16 +0000 (UTC) (envelope-from stefan.lambrev@moneybookers.com) Received: by blah.sun-fish.com (Postfix, from userid 1002) id 656A21B10F22; Fri, 29 Feb 2008 16:38:15 +0100 (CET) X-Spam-Checker-Version: SpamAssassin 3.2.3 (2007-08-08) on blah.cmotd.com X-Spam-Level: X-Spam-Status: No, score=-10.6 required=5.0 tests=ALL_TRUSTED,BAYES_00 autolearn=ham version=3.2.3 Received: from hater.haters.org (hater.cmotd.com [192.168.3.125]) by blah.sun-fish.com (Postfix) with ESMTP id 8477C1B10EF4; Fri, 29 Feb 2008 16:38:09 +0100 (CET) Message-ID: <47C826E0.7070903@moneybookers.com> Date: Fri, 29 Feb 2008 17:38:08 +0200 From: Stefan Lambrev User-Agent: Thunderbird 2.0.0.12 (X11/20080229) MIME-Version: 1.0 To: Noisex References: <47C59591.6040600@errno.com> <47C6991E.1050502@FreeBSD.org> <01ce01c87adc$e2796720$a76c3560$@lv> <47C817B0.1040602@FreeBSD.org> <01d201c87ae4$4b902850$e2b078f0$@lv> <47C82092.5040504@FreeBSD.org> <01d301c87ae7$7e2b2550$7a816ff0$@lv> In-Reply-To: <01d301c87ae7$7e2b2550$7a816ff0$@lv> Content-Type: text/plain; charset=windows-1251; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.91.2/6044/Fri Feb 29 15:17:12 2008 on blah.cmotd.com X-Virus-Status: Clean Cc: freebsd-performance@freebsd.org Subject: Re: Upgrade from 6.3 to 7.0: Result ->Shared object not found :) 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, 29 Feb 2008 15:38:16 -0000 Greetings, Noisex wrote: > I don't remember during portupgrade process was some kind of errors - how > much i saw of course. It's bad that my SSH client (SecureCRT) is configured > with only 1024 row buffer - i can't scroll it back, or i didn't log upgrade > process to file...so i can't be sure to 100% that there wasn't errors :( > portupgrade shows summary at the end which is less then 1024 lines ;) Also you can use script(1) to log, so you can analyze the output latter. I'm not sure how script will run, if it is started in screen (ports/sysutils/screen) which I always use when I do long upgrades over the network, but you can try for yourself :) > However that may be now i getting all functionality back step by step :) > Yes but next time when you update port/package you can be bitten badly if things are not in sync. -- Best Wishes, Stefan Lambrev ICQ# 24134177 From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 15:44:57 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C28721065673 for ; Fri, 29 Feb 2008 15:44:57 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.172]) by mx1.freebsd.org (Postfix) with ESMTP id 3FBD18FC2A for ; Fri, 29 Feb 2008 15:44:57 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: by ug-out-1314.google.com with SMTP id y2so379616uge.37 for ; Fri, 29 Feb 2008 07:44:56 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=z+LUgcFK8NBjJx73DNcrOUvFjG7qwgAukDryp95EIoM=; b=nxw97OHQbSGabefXCsMgstlzKxQOJJKPLE7VnyBjoxRkMfTRvJRhqbCMXu726OTEoVSujaKbmJmBUryDa8vQmKhIZdR6pCUO6RBw1zrKKegxSrFo5i/uWbSSXjbP1FSruXUaA7WGZfbL3pxPzSnKXk4uO3oO1g8Pi2RGmsOHjNY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Cl89unVAjjQ4xcX07QdSnAk2M0Chovu3XBE4+MxGS7drzB/tTSPUnzBADVqsdV1UEYYMTI+r8kJG/x+cLeZojpWythUKstwioxXaRNos4xw0UhdlQqwFyv6pemBBcVz2SoL3ANYsrhlsob8M/5fOebAXlmpbCiFCj4ZnIl9n/cc= Received: by 10.67.15.8 with SMTP id s8mr1657532ugi.42.1204299896108; Fri, 29 Feb 2008 07:44:56 -0800 (PST) Received: by 10.66.219.18 with HTTP; Fri, 29 Feb 2008 07:44:55 -0800 (PST) Message-ID: <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> Date: Fri, 29 Feb 2008 15:44:55 +0000 From: Chris To: "Ted Mittelstaedt" In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <47C59591.6040600@errno.com> Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 15:44:57 -0000 On 29/02/2008, Ted Mittelstaedt wrote: > > > > -----Original Message----- > > From: owner-freebsd-questions@freebsd.org > > [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Sam Leffler > > Sent: Wednesday, February 27, 2008 8:54 AM > > To: Ted Mittelstaedt > > Cc: freebsd-performance@freebsd.org; Kris Kennaway; Oliver Herold; > > freebsd-questions@freebsd.org > > Subject: Re: FreeBSD bind performance in FreeBSD 7 > > > > > > Ted Mittelstaedt wrote: > > > > > >> -----Original Message----- > > >> From: owner-freebsd-questions@freebsd.org > > >> [mailto:owner-freebsd-questions@freebsd.org]On Behalf Of Kris Kennaway > > >> Sent: Monday, February 25, 2008 12:18 PM > > >> To: Oliver Herold; freebsd-questions@freebsd.org; > > >> freebsd-performance@freebsd.org > > >> Subject: Re: FreeBSD bind performance in FreeBSD 7 > > >> > > >> > > >> Oliver Herold wrote: > > >> > > >>> Hi, > > >>> > > >>> I saw this bind benchmarks just some minutes ago, > > >>> > > >>> http://new.isc.org/proj/dnsperf/OStest.html > > >>> > > >>> is this true for FreeBSD 7 (current state: RELENG_7/7.0R) too? Or is > > >>> this something verified only for the state of development > > back in August > > >>> 2007? > > >>> > > >> I have been trying to replicate this. ISC have kindly given me access > > >> to their test data but I am seeing Linux performing much slower than > > >> FreeBSD with the same ISC workload. > > >> > > >> > > > > > > Kris, > > > > > > Every couple years we go through this with ISC. They come out with > > > a new version of BIND then claim that nothing other than Linux can > > > run it well. I've seen this nonsense before and it's tiresome. > > > > > > Incidentally, the query tool they used, queryperf, has been changed > > > to dnsperf. Someone needs to look at that port - > > /usr/ports/dns/dnsperf - > > > as it has a build depend of bind9 - well bind 9.3.4 is part of > > 6.3-RELEASE > > > and I was rather irked when I ran the dnsperf port maker and the > > > maker stupidly began the process of downloading and building the > > > same version of BIND that I was already running on my server. > > > > > > > > >> * I am trying to understand what is different about the ISC > > >> configuration but have not yet found the cause. > > >> > > > > > > It's called "Anti-FreeBSD bias". You won't find anything. > > > > > > > > >> e.g. NSD > > >> (ports/dns/nsd) is a much faster and more scalable DNS server than BIND > > >> (because it is better optimized for the smaller set of features it > > >> supports). > > >> > > >> > > > > > > When you make remarks like that it's no wonder ISC is in the business > > > of slamming FreeBSD. People used to make the same claims about djbdns > > > but I noticed over the last few years they don't seem to be doing > > > that anymore. > > > > > > If nsd is so much better than yank bind out of the base FreeBSD and > > > replace it with nsd. Of course that will make more work for me > > > when I regen our nameservers here since nsd will be the first thing > > > on the "rm" list. > > > > > > > Please save your rhetoric for some other forum. The ISC folks have been > > working with us to understand what's going on. > > Did anyone try disabling the onboard NIC and put in an Intel > Pro/1000 in the PCI express slot in the server and retest with > both Linux and FreeBSD? As I run Proliants for a living, > this stuck out to me like a sore thumb. The onboard NIC > in the systems they used for the testbed is just shit. Hell, > just about anything Broadcom makes is shit. They even managed > to screw up the 3c905 ASIC when 3com switched to using them > as the supplier (from Lucent)( - I've watched those card versions > panic Linux systems and drop massive packets in FreeBSD, > when the Lucent-made chipped cards worked fine. > > > I'm not aware of any > > anit-FreeBSD slams going on; mostly uninformed comments. > > > > It's customary in the industry before publishing rather unflattering > results to call in the team in charge of the unflattering > product and give them a chance to verify that the tester > really knew what they were doing. > > FreeBSD has got slammed a number of times in the past by > testers who didn't do this. In fact as I recall the impetus > for fixing the > extended greater than 16MB memory test was due to a > slam in a trade rag from a tester who didn't bother > recompiling the FreeBSD kernel to recognize the complete > amount of ram in the server, and running it up against Linux. > > Maybe I am wrong and the ISC team did in fact call you guys > in before publishing the results - but the wording of > the entire site (not just the test results) indicated > they did their testing and informed FreeBSD after the fact. > after publishing. Not nice. > > Ted > A weakness of freebsd is its fussyness over hardware in particular network cards, time and time again I see posts here telling people to go out buying expensive intel pro 1000 cards just so they can use the operating system properly when I think its reasonable to expect mainstream hardware to work, eg. realtek is mainstream and common as a onboard nic but the support in freebsd is poor and only serving datacentres to shy away from freebsd. If the same hardware performs better in linux then the hardware isnt to blame for worser performance in fbsd. Chris From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 16:47:16 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F36A0106567A for ; Fri, 29 Feb 2008 16:47:15 +0000 (UTC) (envelope-from tevans.uk@googlemail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.170]) by mx1.freebsd.org (Postfix) with ESMTP id 1B73E8FC35 for ; Fri, 29 Feb 2008 16:47:14 +0000 (UTC) (envelope-from tevans.uk@googlemail.com) Received: by ug-out-1314.google.com with SMTP id y2so412981uge.37 for ; Fri, 29 Feb 2008 08:47:13 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:received:received:subject:from:to:cc:in-reply-to:references:content-type:date:message-id:mime-version:x-mailer; bh=mYD5W7WDyQ8BfppDPEhc8LbA+SEyBnkg4ReTlpGpfZE=; b=xzKBLIHPwCrRut6DcTCV/O5OF2I3lgTJPFTdlcVaZvMdfpNFYaPBB2fE4sFIQzuRBGxdqRysncsw8Wrwq8v7rbKseVoh5lZEX1qeybUmAm4ZODW77Dg2g21hX1XJM/psom3a1mdIj+nAO2I3aM0TkcQ/9ITmOL2xE8za56zJqQQ= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date:message-id:mime-version:x-mailer; b=VykBecdu8dwuYBhEgrsEvsbLj9B/+Hv52T9n8SULW8AXzsjIawTFzDjwKFjrwGNPWRsrR4mJTNgyFrH8XVpyg/BYKtDdbD2F8qxN+YP/9uoJSvgSXr/e/+tEGxiDxRKd7k5rvPlkRC/r0vzyHeTKJ8nPffeWSRcIoqH3UDSDK70= Received: by 10.67.196.2 with SMTP id y2mr1697950ugp.60.1204302132774; Fri, 29 Feb 2008 08:22:12 -0800 (PST) Received: from ?127.0.0.1? ( [217.206.187.79]) by mx.google.com with ESMTPS id y34sm17434915iky.6.2008.02.29.08.22.09 (version=SSLv3 cipher=RC4-MD5); Fri, 29 Feb 2008 08:22:11 -0800 (PST) From: Tom Evans To: Chris In-Reply-To: <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-2XhLoQnYu/F9+1q6pWma" Date: Fri, 29 Feb 2008 16:22:08 +0000 Message-Id: <1204302128.2126.150.camel@localhost> Mime-Version: 1.0 X-Mailer: Evolution 2.10.2 FreeBSD GNOME Team Port Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , Ted Mittelstaedt , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 16:47:16 -0000 --=-2XhLoQnYu/F9+1q6pWma Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Fri, 2008-02-29 at 15:44 +0000, Chris wrote: > On 29/02/2008, Ted Mittelstaedt wrote: >=20 > A weakness of freebsd is its fussyness over hardware in particular > network cards, time and time again I see posts here telling people to > go out buying expensive intel pro 1000 cards just so they can use the > operating system properly when I think its reasonable to expect > mainstream hardware to work, eg. realtek is mainstream and common as a > onboard nic but the support in freebsd is poor and only serving > datacentres to shy away from freebsd. If the same hardware performs > better in linux then the hardware isnt to blame for worser performance > in fbsd. >=20 > Chris Not to come down too hard on you, but the reason why Pro/1000 chipsets are reasonably pricey, and uncommon to find as an integrated NIC, except on server boards or intel own brand mobos, is that it is decent hardware, and hence costs real money to use. Consumer NICs like Realtek, Via Rhine and (imo) Marvell are cheap tat that 'just about' works, until you put it under heavy stress. I have encountered a series of Marvell based chips on my personal home computers that work about as well as a slap around the face. Also, even from the 'good' manufacturers, like broadcom and intel, you have 'consumer' parts, which are reasonably cheap, like bge(4) supported parts, and 'professional' parts, like bce(4) parts. One should work fine under moderate load, one should work fine under heavy load. One will cost $4, one will cost $100. I'm not saying the drivers are bug-free, but if you want performance and reliability, you get an em(4) or another professional chipset. Only a few months ago at work, we had to order around 75 Pro/1000s as we had had enough of crashes from our bce(4) based integrated NICs on our Dell 2950s. Fortunately for our wallet, we managed to fix the issues in the driver/hardware before our supplier could source that many - thanks David Christensen! Personally, I wouldn't put something in a data-centre with only a vr(4) or re(4), regardless of OS.=20 Tom --=-2XhLoQnYu/F9+1q6pWma Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (FreeBSD) iD8DBQBHyDEtlcRvFfyds/cRAhg1AKCVJDbdNpSk9n5zfzJPVgoaAMAJXQCgsWAi bW9DDnv5mLgobqfedC0yCSA= =COTj -----END PGP SIGNATURE----- --=-2XhLoQnYu/F9+1q6pWma-- From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 16:51:27 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3A9AD106566B; Fri, 29 Feb 2008 16:51:27 +0000 (UTC) (envelope-from mike@sentex.net) Received: from smarthost1.sentex.ca (smarthost1.sentex.ca [64.7.153.18]) by mx1.freebsd.org (Postfix) with ESMTP id EB51C8FC3A; Fri, 29 Feb 2008 16:51:26 +0000 (UTC) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by smarthost1.sentex.ca (8.14.2/8.14.2) with ESMTP id m1TGpP6k011213; Fri, 29 Feb 2008 11:51:25 -0500 (EST) (envelope-from mike@sentex.net) Received: from mdt-xp.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.8/8.13.3) with ESMTP id m1TGpOtb072637 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 29 Feb 2008 11:51:25 -0500 (EST) (envelope-from mike@sentex.net) Message-Id: <200802291651.m1TGpOtb072637@lava.sentex.ca> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Fri, 29 Feb 2008 11:49:25 -0500 To: Chris , "Ted Mittelstaedt" From: Mike Tancsa In-Reply-To: <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com > References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 16:51:27 -0000 At 10:44 AM 2/29/2008, Chris wrote: >A weakness of freebsd is its fussyness over hardware in particular >network cards, time and time again I see posts here telling people to >go out buying expensive intel pro 1000 cards just so they can use the >operating system properly when I think its reasonable to expect >mainstream hardware to work, eg. realtek is mainstream and common as a A realtek as in rl (not re) works quite well (as in stable, predictable performance)-- we buy these for about $5 each from our supplier and are quite common. While it would be nice that all network cards worked as well as the em nics, its an issue that is easy to work around-- after all, I would rather be limited by my nic driver choice as opposed to vm and network stack issues which I cant work around. Also thankfully, a large chunk of the server MB market uses em nics. Yes, bge/bce based nics do seem to perform poorly on FreeBSD. Hopefully Broadcom might put similar resources into driver development as Intel does/has. ---Mike From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 16:54:39 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 64C1D1065677 for ; Fri, 29 Feb 2008 16:54:39 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.172]) by mx1.freebsd.org (Postfix) with ESMTP id DFE1B8FC2D for ; Fri, 29 Feb 2008 16:54:38 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: by ug-out-1314.google.com with SMTP id y2so416760uge.37 for ; Fri, 29 Feb 2008 08:54:38 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=bpu5YaazFNF7LPDPPQd6UT38FE33a8idjfJUAlCQfsk=; b=TCJZcTM0ybMVeKLcvggsFFW05cmRxX5GNzv4myuK6kvQcpEAnEkovA/zTbJdENz34rkzKIKFvQpOoCeNrZ6pB5A5yJvKsZdCZAu9wmfMdNKW56sBlF/vYAJU3kg3gsnBP+3AlMeeKk6V6HyWU5o85LuRn2nNaaL8NlIf6HSbrMY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=ieZ+9Zp5Utf/ThzJ97xjg9zCWtLQrDveCkalUijKT2NecqPtnO+URi+KEpnVZU27QJAAtjCjLVdYjeanxdgb7Gow1ryo5ChHvpSWkp5EC3XphnFT/kzk4++LwGNR+dX8PlQEiCaeGiQU5cQisza2LZ9vPG7wbbiHfL9MbYQZKvs= Received: by 10.66.245.2 with SMTP id s2mr1248715ugh.16.1204304077564; Fri, 29 Feb 2008 08:54:37 -0800 (PST) Received: by 10.66.219.18 with HTTP; Fri, 29 Feb 2008 08:54:37 -0800 (PST) Message-ID: <3aaaa3a0802290854t639559b6if0adc4009997e9db@mail.gmail.com> Date: Fri, 29 Feb 2008 16:54:37 +0000 From: Chris To: "Tom Evans" In-Reply-To: <1204302128.2126.150.camel@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> <1204302128.2126.150.camel@localhost> Cc: freebsd-performance@freebsd.org, Oliver Herold , Kris Kennaway , Ted Mittelstaedt , freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 16:54:39 -0000 On 29/02/2008, Tom Evans wrote: > On Fri, 2008-02-29 at 15:44 +0000, Chris wrote: > > On 29/02/2008, Ted Mittelstaedt wrote: > > > > A weakness of freebsd is its fussyness over hardware in particular > > network cards, time and time again I see posts here telling people to > > go out buying expensive intel pro 1000 cards just so they can use the > > operating system properly when I think its reasonable to expect > > mainstream hardware to work, eg. realtek is mainstream and common as a > > onboard nic but the support in freebsd is poor and only serving > > datacentres to shy away from freebsd. If the same hardware performs > > better in linux then the hardware isnt to blame for worser performance > > in fbsd. > > > > Chris > > Not to come down too hard on you, but the reason why Pro/1000 chipsets > are reasonably pricey, and uncommon to find as an integrated NIC, except > on server boards or intel own brand mobos, is that it is decent > hardware, and hence costs real money to use. Consumer NICs like Realtek, > Via Rhine and (imo) Marvell are cheap tat that 'just about' works, until > you put it under heavy stress. I have encountered a series of Marvell > based chips on my personal home computers that work about as well as a > slap around the face. Also, even from the 'good' manufacturers, like > broadcom and intel, you have 'consumer' parts, which are reasonably > cheap, like bge(4) supported parts, and 'professional' parts, like > bce(4) parts. One should work fine under moderate load, one should work > fine under heavy load. One will cost $4, one will cost $100. > > I'm not saying the drivers are bug-free, but if you want performance and > reliability, you get an em(4) or another professional chipset. Only a > few months ago at work, we had to order around 75 Pro/1000s as we had > had enough of crashes from our bce(4) based integrated NICs on our Dell > 2950s. Fortunately for our wallet, we managed to fix the issues in the > driver/hardware before our supplier could source that many - thanks > David Christensen! > > Personally, I wouldn't put something in a data-centre with only a vr(4) > or re(4), regardless of OS. > > Tom > > > You working round what I just said. A nic should perform equally well as it does in other operating systems just because its cheaper its not an excuse for buggy performance. There is also other good network cards apart from intel pro 1000. I am talking about stability not performance, I expect a intel pro 1000 to outperform a realtek however I expect both to be stable in terms of connectivity. I expect a realtek in freebsd to perform as well as a realtek in windows and linux. :) We have our own opinions but for many tasks a vr re bge etc. even a rl does the job its required just fine. I have seen linux servers using rl adaptors outperform freebsd servers with superior cards because the linux driver is better. I do agree its a sad state of affairs datacentres like to rent out servers built from desktop parts but unfurtenatly thats the market for you unless paying a premium or going with own hardware colocated. Chris From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 17:16:53 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 16D3B1065670; Fri, 29 Feb 2008 17:16:53 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from mail.freebsd-corp-net-guide.com (mail.freebsd-corp-net-guide.com [65.75.192.90]) by mx1.freebsd.org (Postfix) with ESMTP id C26B28FC25; Fri, 29 Feb 2008 17:16:52 +0000 (UTC) (envelope-from tedm@toybox.placo.com) Received: from TEDSDSK (nat-rtr.freebsd-corp-net-guide.com [65.75.197.130]) by mail.freebsd-corp-net-guide.com (8.13.8/8.13.8) with SMTP id m1THGpvp049557; Fri, 29 Feb 2008 09:16:52 -0800 (PST) (envelope-from tedm@toybox.placo.com) From: "Ted Mittelstaedt" To: "Chris" Date: Fri, 29 Feb 2008 09:17:57 -0800 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.6604 (9.0.2911.0) X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1914 In-Reply-To: <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> Importance: Normal X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (mail.freebsd-corp-net-guide.com [65.75.192.90]); Fri, 29 Feb 2008 09:16:52 -0800 (PST) Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: RE: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 17:16:53 -0000 > -----Original Message----- > From: Chris [mailto:chrcoluk@gmail.com] > Sent: Friday, February 29, 2008 7:45 AM > To: Ted Mittelstaedt > Cc: Sam Leffler; freebsd-performance@freebsd.org; Oliver Herold; Kris > Kennaway; freebsd-questions@freebsd.org > Subject: Re: FreeBSD bind performance in FreeBSD 7 > > A weakness of freebsd is its fussyness over hardware in particular > network cards, time and time again I see posts here telling people to > go out buying expensive intel pro 1000 cards just so they can use the > operating system properly when I think its reasonable to expect > mainstream hardware to work, eg. realtek is mainstream and common as a > onboard nic but the support in freebsd is poor and only serving > datacentres to shy away from freebsd. If the same hardware performs > better in linux then the hardware isnt to blame for worser performance > in fbsd. > Device drivers and hardware are a cooperative effort. The ideal is a well-written device driver and well-designed hardware. Unfortunately the reality of it appears to be that it costs a LOT more money to hire good silicon designers than it costs to hire good programmers - so a depressing amount of computer hardware out there is very poor hardware, but the hardware's shortcomings are made up by almost Herculean efforts of the software developers. I should have thought the invention of the Winmodem (windows-only modem) would have made this obvious to the general public years ago. Unfortunately, the hardware vendors make a lot of effort to conceal the crappiness of their designs and most customers just care if the device works, they don't care if the only way the device can work is if 60% of their system's CPU is tied up servicing a device driver that is making up for hardware shortcomings, so it is still rather difficult for a customer to become informed about what is good and what isn't - other than trial and error. I hardly think that the example I cited - the 3com 3c905 PCI network adapter - is an example of poor support in FreeBSD. The FreeBSD driver for the 509 worked perfectly well when the 309 used a Lucent-built ASIC. When 3com decided to save 50 cents a card by switching to Broadcom for the ASIC manufacturing, the FreeBSD driver didn't work very well with those cards - nor did the Linux driver for that matter. This clearly wasn't a driver problem it was a problem with Broadcom not following 3com's design specs properly. 3com did the only thing they could - which was to put a hack into the Windows driver - but of course, nobody bothered telling the Linux or FreeBSD community about it, we had to find out by dicking around with the driver code. If datacenters want to purchase poor hardware and run their stuff on it, that's their choice. Just because a piece of hardware is "mainstream" doesen't mean it's good. It mainly means it's inexpensive. Ted From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 18:20:37 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7F2CE106567E; Fri, 29 Feb 2008 18:20:37 +0000 (UTC) (envelope-from fred@bsdhost.net) Received: from dos.kaslist.com (dos.kaslist.com [66.160.134.9]) by mx1.freebsd.org (Postfix) with ESMTP id 6A97B8FC43; Fri, 29 Feb 2008 18:20:37 +0000 (UTC) (envelope-from fred@bsdhost.net) Received: from dos.kaslist.com [66.160.134.9] by dos.kaslist.com with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.69) (envelope-from ) id 1JV9Aa-000LUM-PH; Fri, 29 Feb 2008 09:37:16 -0800 X-Gpg-Fingerprint: A906 101E 2CCD BB18 D7BD 09AE E7EA 02EC 3B48 7EE9 From: Fred C To: Chris In-Reply-To: <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> X-Gpg-Url: http://fred.velvnet.com/gnupg/3B487EE9.asc References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> Message-Id: <9026507D-14BE-4631-8237-711C929A23B4@bsdhost.net> Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (Apple Message framework v919.2) Date: Fri, 29 Feb 2008 09:37:13 -0800 X-Mailer: Apple Mail (2.919.2) X-Mailman-Approved-At: Fri, 29 Feb 2008 18:40:34 +0000 Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 29 Feb 2008 18:20:37 -0000 On Feb 29, 2008, at 7:44 AM, Chris wrote: > > A weakness of freebsd is its fussyness over hardware in particular > network cards, time and time again I see posts here telling people to > go out buying expensive intel pro 1000 cards just so they can use the > operating system properly when I think its reasonable to expect > mainstream hardware to work, eg. realtek is mainstream and common as a > onboard nic but the support in freebsd is poor and only serving > datacentres to shy away from freebsd. If the same hardware performs > better in linux then the hardware isnt to blame for worser performance > in fbsd. > The weakness comes mainly from the hardware. It is like Nascar, you don't run Nascar in your everyday Prius. You need a car with stronger and ultra performing components. Your Prius maybe fine for your commute and your grocery shopping, but when it comes to a race it will perform very badly. Here the problem is the same. For your everyday home desktop machine any low end network card is fine. But when you want to handle several thousand connections per seconds you need some some hardware who can handle it. -- Fred C! PGP-KeyID: E7EA02EC3B487EE9 PGP-FingerPrint: A906101E2CCDBB18D7BD09AEE7EA02EC3B487EE9 From owner-freebsd-performance@FreeBSD.ORG Fri Feb 29 23:57:32 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4181D106566B; Fri, 29 Feb 2008 23:57:32 +0000 (UTC) (envelope-from wjw@digiware.nl) Received: from mail.digiware.nl (www.tegenbosch28.nl [217.21.251.97]) by mx1.freebsd.org (Postfix) with ESMTP id E58E58FC14; Fri, 29 Feb 2008 23:57:31 +0000 (UTC) (envelope-from wjw@digiware.nl) Received: from localhost (localhost.digiware.nl [127.0.0.1]) by mail.digiware.nl (Postfix) with ESMTP id C954217390; Sat, 1 Mar 2008 00:33:30 +0100 (CET) X-Virus-Scanned: amavisd-new at digiware.nl Received: from mail.digiware.nl ([127.0.0.1]) by localhost (rack1.digiware.nl [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id n6Bu6pzGW9ND; Sat, 1 Mar 2008 00:33:28 +0100 (CET) Received: from [192.168.2.10] (unknown [192.168.2.10]) by mail.digiware.nl (Postfix) with ESMTP id 7A34817335; Sat, 1 Mar 2008 00:33:28 +0100 (CET) Message-ID: <47C8964C.9080309@digiware.nl> Date: Sat, 01 Mar 2008 00:33:32 +0100 From: Willem Jan Withagen Organization: Digiware User-Agent: Thunderbird 2.0.0.12 (Windows/20080213) MIME-Version: 1.0 To: Ingo Flaschberger References: <20080226003107.54CD94500E@ptavv.es.net> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sat, 01 Mar 2008 00:25:48 +0000 Cc: =?ISO-8859-1?Q?alves?= , =?ISO-8859-1?Q?Daniel_Dias_Gon=E7?=, freebsd-net@freebsd.org, freebsd-performance@freebsd.org, Kevin Oberman Subject: Re: FBSD 1GBit router? 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, 29 Feb 2008 23:57:32 -0000 > I have a 1.2Ghz Pentium-M appliance, with 4x 32bit, 33MHz pci intel > e1000 cards. > With maximum tuning I can "route" ~400mbps with big packets and ~80mbps > with 64byte packets. > around 100kpps, whats not bad for a pci architecture. > > To reach higher bandwiths, better busses are needed. > pci-express cards are currently the best choice. > one dedicated pci-express lane (1.25gbps) has more bandwith than a whole > 32bit, 33mhz pci-bus. Like you say routing 400 Mb/s is close to the max of the PCI bus, which has a theoretical max of 33*4*8 ~ 1Gbps. Now routing is 500Mb/s in, 500Mb/s out. So you are within 80% of the bus-max, not counting memory-access and others. PCI express will give you a bus per PCI-E device into a central hub, thus upping the limit to the speed of the FrontSideBus in Intel architectures. Which at the moment is a lot higher than what a single PCI bus does. What it does not explain is why you can only get 80Mb/s with 64byte packets, which would suggest other bottlenecks than just the bus. --WjW From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 01:03:19 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DF269106567D for ; Sat, 1 Mar 2008 01:03:19 +0000 (UTC) (envelope-from if@xip.at) Received: from chile.gbit.at (ns1.xip.at [193.239.188.99]) by mx1.freebsd.org (Postfix) with ESMTP id 457BC8FC19 for ; Sat, 1 Mar 2008 01:03:18 +0000 (UTC) (envelope-from if@xip.at) Received: (qmail 21564 invoked from network); 1 Mar 2008 02:03:16 +0100 Received: from unknown (HELO filebunker.xip.at) (86.59.10.180) by chile.gbit.at with (DHE-RSA-AES256-SHA encrypted) SMTP; 1 Mar 2008 02:03:16 +0100 Date: Sat, 1 Mar 2008 02:03:16 +0100 (CET) From: Ingo Flaschberger To: Willem Jan Withagen In-Reply-To: <47C8964C.9080309@digiware.nl> Message-ID: References: <20080226003107.54CD94500E@ptavv.es.net> <47C8964C.9080309@digiware.nl> User-Agent: Alpine 1.00 (LFD 882 2007-12-20) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Sat, 01 Mar 2008 01:10:50 +0000 Cc: alves , freebsd-net@freebsd.org, freebsd-performance@freebsd.org, =?ISO-8859-1?Q?Daniel_Dias_Gon=E7?=@FreeBSD.ORG, Kevin Oberman Subject: Re: FBSD 1GBit router? 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, 01 Mar 2008 01:03:20 -0000 >> I have a 1.2Ghz Pentium-M appliance, with 4x 32bit, 33MHz pci intel e1000 >> cards. >> With maximum tuning I can "route" ~400mbps with big packets and ~80mbps >> with 64byte packets. >> around 100kpps, whats not bad for a pci architecture. >> >> To reach higher bandwiths, better busses are needed. >> pci-express cards are currently the best choice. >> one dedicated pci-express lane (1.25gbps) has more bandwith than a whole >> 32bit, 33mhz pci-bus. > > Like you say routing 400 Mb/s is close to the max of the PCI bus, which > has a theoretical max of 33*4*8 ~ 1Gbps. Now routing is 500Mb/s in, 500Mb/s > out. So you are within 80% of the bus-max, not counting memory-access and > others. yes. > PCI express will give you a bus per PCI-E device into a central hub, thus > upping the limit to the speed of the FrontSideBus in Intel architectures. > Which at the moment is a lot higher than what a single PCI bus does. Thats why my next router will be based at this box: http://www.axiomtek.com/products/ViewProduct.asp?view=429 Hopefully there will be direct memory bus connected nic's in future. (HyperTransport connected nic's) > What it does not explain is why you can only get 80Mb/s with 64byte packets, > which would suggest other bottlenecks than just the bus. Perhaps something with interrupts: http://books.google.at/books?id=pr4fspaQqZkC&pg=PA144&lpg=PA144&dq=pci+interrupt+delay&source=web&ots=zbvVU2CgVx&sig=APe9YjdtK35ccnow7BDI2hzie7s&hl=de#PPA144,M1 MSI (Message-signalled Interrupts) are not very common on PCI architekture; PCI-E use only MSI. The kpps keept always around 100, equally if I used fast-forwarding, fast-interrupts, or higher HZ values than 1000HZ. But 100kpps is great for a router hardware of about 600eur. Kind regards, Ingo Flaschberger From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 02:06:35 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8DF60106566C for ; Sat, 1 Mar 2008 02:06:35 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from ti-out-0910.google.com (ti-out-0910.google.com [209.85.142.190]) by mx1.freebsd.org (Postfix) with ESMTP id 153468FC16 for ; Sat, 1 Mar 2008 02:06:34 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by ti-out-0910.google.com with SMTP id j2so4221797tid.3 for ; Fri, 29 Feb 2008 18:06:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; bh=U8hAxqSkA/r0eYgM9kSXW0H8ommH9Q/QhWX+Ay/HhQM=; b=vsVpnzvq1Lz6VZm8DZ1vnTKB4AxaglpQz4kUq29FaE28BeqDcO8qYxs7zsp0o3ha6nq+1ApP+TQQqbCNb6xEG8UC3ng5ttcSMQ9LbAVnRx5NW3tG8RjBmxipYW3zXfOl+/X2Kzl1qmOmiy+WyUcx3RdqFmD6clkrjVPZ2a/GzHU= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=nLQ4QqoRWXRSebyQTM3P3CmEIFEKNhzi6QP1MG18CR4WWZLve+Be8efqU8smSfM30a3P1BPOHZM0cy8fap6p1ffXZJAbnfYbJTzeK8hU2rOwW9GkSDBUuvBMNkdYmzqLPl/qVrMXWxIKprJTZgyH2ZoYF2fT9cLitDMEI/eznVU= Received: by 10.151.146.18 with SMTP id y18mr3624096ybn.3.1204337189951; Fri, 29 Feb 2008 18:06:29 -0800 (PST) Received: by 10.150.144.2 with HTTP; Fri, 29 Feb 2008 18:06:29 -0800 (PST) Message-ID: Date: Sat, 1 Mar 2008 11:06:29 +0900 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: Chris In-Reply-To: <3aaaa3a0802290854t639559b6if0adc4009997e9db@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> <1204302128.2126.150.camel@localhost> <3aaaa3a0802290854t639559b6if0adc4009997e9db@mail.gmail.com> X-Google-Sender-Auth: 0bcabb9655f30f33 Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 01 Mar 2008 02:06:35 -0000 On 01/03/2008, Chris wrote: > You working round what I just said. A nic should perform equally well > as it does in other operating systems just because its cheaper its not > an excuse for buggy performance. There is also other good network > cards apart from intel pro 1000. I am talking about stability not > performance, I expect a intel pro 1000 to outperform a realtek however > I expect both to be stable in terms of connectivity. I expect a > realtek in freebsd to perform as well as a realtek in windows and > linux. :) Patches please! Adrian -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 02:21:00 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1156A1065670 for ; Sat, 1 Mar 2008 02:21:00 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.171]) by mx1.freebsd.org (Postfix) with ESMTP id 908588FC1E for ; Sat, 1 Mar 2008 02:20:59 +0000 (UTC) (envelope-from chrcoluk@gmail.com) Received: by ug-out-1314.google.com with SMTP id y2so684150uge.37 for ; Fri, 29 Feb 2008 18:20:58 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=DuJKr/kUGzyoSSfQlHyKmx3T7Sh6t/VLM0azk/RaLnU=; b=UYLl0YNatZxo2LIMxWYYqwYHcJKPrOZ+mUfaBewO4KVyR6MrA6dOBTym8NjSW3VrOClo9u51h8HhknGDUUGRIJyYNAi0KFCsEeWHLeTfdkjp9ZL9d5gdOpllIRHji8GR32FMXj6e9GGRFlPRNLguSW7FufO50DgmYQEardq+5/Y= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=YFkaHx1gYsDt3cyGVJa0/bdC7xvNDLeCfaK8rlrE1Rebcj+Hl6RwTFlb590YROcbCc68SIohBJ8CxPf2x7QSjmJji44m4c3fT4trnGrHHS5y8kdL7zVRNvpk+FIdPeav0ZIcUzjEl/l7jFQuKydboSHQZfE/YltDbkGyjxPU47Y= Received: by 10.67.29.4 with SMTP id g4mr2478148ugj.82.1204338058567; Fri, 29 Feb 2008 18:20:58 -0800 (PST) Received: by 10.66.219.18 with HTTP; Fri, 29 Feb 2008 18:20:58 -0800 (PST) Message-ID: <3aaaa3a0802291820j58a24de7wb39ebf2a2653f579@mail.gmail.com> Date: Sat, 1 Mar 2008 02:20:58 +0000 From: Chris To: "Adrian Chadd" In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> <1204302128.2126.150.camel@localhost> <3aaaa3a0802290854t639559b6if0adc4009997e9db@mail.gmail.com> Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 01 Mar 2008 02:21:00 -0000 On 01/03/2008, Adrian Chadd wrote: > On 01/03/2008, Chris wrote: > > > You working round what I just said. A nic should perform equally well > > as it does in other operating systems just because its cheaper its not > > an excuse for buggy performance. There is also other good network > > cards apart from intel pro 1000. I am talking about stability not > > performance, I expect a intel pro 1000 to outperform a realtek however > > I expect both to be stable in terms of connectivity. I expect a > > realtek in freebsd to perform as well as a realtek in windows and > > linux. :) > > Patches please! > > > Adrian > > > -- > Adrian Chadd - adrian@freebsd.org > Ironically the latest server I got last night has a intel pro 1000 a rarity :) I am just giving feedback as when I speak to people in the datacentre and hosting business the biggest gripe with freebsd is hardware compatability, as I adore freebsd I ignore this and work round it but its defenitly reducing take up. Of course I know current re issues are getting attention which I am thankful for, I fully understand the time and effort required to write drivers patches etc. and have got no critisicms for the people who do this my complaint is more focused on people claiming there is no issues its just the hardware. Thanks Chris From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 11:31:35 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 7083A1065670; Sat, 1 Mar 2008 11:31:35 +0000 (UTC) (envelope-from wjw@digiware.nl) Received: from mail.digiware.nl (www.tegenbosch28.nl [217.21.251.97]) by mx1.freebsd.org (Postfix) with ESMTP id C19658FC21; Sat, 1 Mar 2008 11:31:34 +0000 (UTC) (envelope-from wjw@digiware.nl) Received: from localhost (localhost.digiware.nl [127.0.0.1]) by mail.digiware.nl (Postfix) with ESMTP id 1EE761736D; Sat, 1 Mar 2008 12:31:28 +0100 (CET) X-Quarantine-ID: X-Virus-Scanned: amavisd-new at digiware.nl X-Amavis-Alert: BAD HEADER, Non-encoded 8-bit data (char C3 hex): CC: ...com.br>, "Daniel Dias Gon\303\247"@FreeBSD.ORG,[...] Received: from mail.digiware.nl ([127.0.0.1]) by localhost (rack1.digiware.nl [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id e4MVsuD8DiHk; Sat, 1 Mar 2008 12:31:19 +0100 (CET) Received: from [192.168.2.10] (unknown [192.168.2.10]) by mail.digiware.nl (Postfix) with ESMTP id 48D5B17309; Sat, 1 Mar 2008 12:31:19 +0100 (CET) Message-ID: <47C93E8B.3010609@digiware.nl> Date: Sat, 01 Mar 2008 12:31:23 +0100 From: Willem Jan Withagen Organization: Digiware User-Agent: Thunderbird 2.0.0.12 (Windows/20080213) MIME-Version: 1.0 To: Ingo Flaschberger References: <20080226003107.54CD94500E@ptavv.es.net> <47C8964C.9080309@digiware.nl> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sat, 01 Mar 2008 12:30:12 +0000 Cc: alves , freebsd-net@freebsd.org, "Daniel Dias Gonç"@FreeBSD.ORG, freebsd-performance@freebsd.org, Kevin Oberman Subject: Re: FBSD 1GBit router? 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, 01 Mar 2008 11:31:35 -0000 Ingo Flaschberger wrote: > >>> I have a 1.2Ghz Pentium-M appliance, with 4x 32bit, 33MHz pci >>> intel e1000 cards. With maximum tuning I can "route" ~400mbps >>> with big packets and ~80mbps with 64byte packets. around 100kpps, >>> whats not bad for a pci architecture. >>> >>> To reach higher bandwiths, better busses are needed. pci-express >>> cards are currently the best choice. one dedicated pci-express >>> lane (1.25gbps) has more bandwith than a whole 32bit, 33mhz >>> pci-bus. >> >> Like you say routing 400 Mb/s is close to the max of the PCI bus, >> which has a theoretical max of 33*4*8 ~ 1Gbps. Now routing is >> 500Mb/s in, 500Mb/s out. So you are within 80% of the bus-max, not >> counting memory-access and others. > > yes. > >> PCI express will give you a bus per PCI-E device into a central >> hub, thus upping the limit to the speed of the FrontSideBus in >> Intel architectures. Which at the moment is a lot higher than what >> a single PCI bus does. > > Thats why my next router will be based at this box: > http://www.axiomtek.com/products/ViewProduct.asp?view=429 Nice piece of hardware. Don't like the 2.5" one disk option though. And not shure what to think of: "Seven 10/100/1000Mbps (through PCI-E by one interface) ports (RJ-45)" Which seems to suggest everything comes in thru on PCI-E interface. That than better have 8 or 16 lanes. > Hopefully there will be direct memory bus connected nic's in future. > (HyperTransport connected nic's) Well that is going to be an AMD only solution, and I'm not even shure that AMD would like to have other things than CPU's on that bus. > >> What it does not explain is why you can only get 80Mb/s with 64byte >> packets, which would suggest other bottlenecks than just the bus. > > Perhaps something with interrupts: > http://books.google.at/books?id=pr4fspaQqZkC&pg=PA144&lpg=PA144&dq=pci+interrupt+delay&source=web&ots=zbvVU2CgVx&sig=APe9YjdtK35ccnow7BDI2hzie7s&hl=de#PPA144,M1 > > > > MSI (Message-signalled Interrupts) are not very common on PCI > architekture; PCI-E use only MSI. > > The kpps keept always around 100, equally if I used fast-forwarding, > fast-interrupts, or higher HZ values than 1000HZ. MSI is not used for regular PCI busses.Could be that PCI-E does use it. I believe youon that. But even than I'd like to know where the bottleneck is in the 100kp/s limit with 64byte pakkets. > But 100kpps is great for a router hardware of about 600eur. I've seen routers 10 times that expensive, not able to that. --WjW From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 12:45:12 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3660E1065673; Sat, 1 Mar 2008 12:45:12 +0000 (UTC) (envelope-from chris@hitnet.RWTH-Aachen.DE) Received: from mta-1.ms.rz.rwth-aachen.de (mta-1.ms.rz.RWTH-Aachen.DE [134.130.7.72]) by mx1.freebsd.org (Postfix) with ESMTP id D47558FC1A; Sat, 1 Mar 2008 12:45:11 +0000 (UTC) (envelope-from chris@hitnet.RWTH-Aachen.DE) Received: from ironport-out-1.rz.rwth-aachen.de ([134.130.3.58]) by mta-1.ms.rz.RWTH-Aachen.de (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) with ESMTP id <0JX1000F0WP96610@mta-1.ms.rz.RWTH-Aachen.de>; Sat, 01 Mar 2008 13:15:09 +0100 (CET) Received: from smarthost-1.ms.rz.rwth-aachen.de (HELO smarthost.rwth-aachen.de) ([134.130.7.89]) by ironport-in-1.rz.rwth-aachen.de with ESMTP; Sat, 01 Mar 2008 13:15:10 +0100 Received: from bigboss.hitnet.rwth-aachen.de (bigspace.hitnet.RWTH-Aachen.DE [137.226.181.2]) by smarthost.rwth-aachen.de (8.13.8+Sun/8.13.8/1) with ESMTP id m21CF9XX002906; Sat, 01 Mar 2008 13:15:09 +0100 (CET) Received: from haakonia.hitnet.rwth-aachen.de ([137.226.181.92]) by bigboss.hitnet.rwth-aachen.de with esmtps (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.63) (envelope-from ) id 1JVQcP-0007Wa-Pi; Sat, 01 Mar 2008 13:15:09 +0100 Received: by haakonia.hitnet.rwth-aachen.de (Postfix, from userid 1001) id 07B463F433; Thu, 06 Mar 2008 02:37:37 +0100 (CET) Date: Thu, 06 Mar 2008 02:37:36 +0100 From: Christian Brueffer In-reply-to: <3aaaa3a0802291820j58a24de7wb39ebf2a2653f579@mail.gmail.com> To: Chris Message-id: <20080306013736.GD1500@haakonia.hitnet.RWTH-Aachen.DE> MIME-version: 1.0 Content-type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary=VV4b6MQE+OnNyhkM Content-disposition: inline X-IronPort-AV: E=Sophos;i="4.25,431,1199660400"; d="scan'208";a="53104148" X-Operating-System: FreeBSD 6.3-STABLE 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: <47C59591.6040600@errno.com> <3aaaa3a0802290744x25a81d68vf0ff101f6b7a819e@mail.gmail.com> <1204302128.2126.150.camel@localhost> <3aaaa3a0802290854t639559b6if0adc4009997e9db@mail.gmail.com> <3aaaa3a0802291820j58a24de7wb39ebf2a2653f579@mail.gmail.com> User-Agent: Mutt/1.5.11 X-Mailman-Approved-At: Sat, 01 Mar 2008 13:02:50 +0000 Cc: Adrian Chadd , freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: FreeBSD bind performance in FreeBSD 7 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, 01 Mar 2008 12:45:12 -0000 --VV4b6MQE+OnNyhkM Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Mar 01, 2008 at 02:20:58AM +0000, Chris wrote: > On 01/03/2008, Adrian Chadd wrote: > > On 01/03/2008, Chris wrote: > > > > > You working round what I just said. A nic should perform equally well > > > as it does in other operating systems just because its cheaper its n= ot > > > an excuse for buggy performance. There is also other good network > > > cards apart from intel pro 1000. I am talking about stability not > > > performance, I expect a intel pro 1000 to outperform a realtek howev= er > > > I expect both to be stable in terms of connectivity. I expect a > > > realtek in freebsd to perform as well as a realtek in windows and > > > linux. :) > > > > Patches please! > > > > > > Adrian > > > > > > -- > > Adrian Chadd - adrian@freebsd.org > > >=20 > Ironically the latest server I got last night has a intel pro 1000 a rari= ty :) >=20 > I am just giving feedback as when I speak to people in the datacentre > and hosting business the biggest gripe with freebsd is hardware > compatability, as I adore freebsd I ignore this and work round it but > its defenitly reducing take up. >=20 > Of course I know current re issues are getting attention which I am > thankful for, I fully understand the time and effort required to write > drivers patches etc. and have got no critisicms for the people who do > this my complaint is more focused on people claiming there is no > issues its just the hardware. >=20 Pyun YongHyeon has fixed a lot of driver issues (i.e. re(4), bfr(4), vr(4)) over the last few months, many are already in CURRENT or RELENG_7 (not sure how many of them made it into 7.0-RELEASE) or posted as patches to the current@ mailing list. If you have problems, please see if they persist with a CURRENT snapshot. If they do, please post to the current@ mailing list with details. - 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 --VV4b6MQE+OnNyhkM Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (FreeBSD) iD8DBQFHz0rgbHYXjKDtmC0RAmjwAJoCsP1l1EZCY8P0APJM6gZ0r4CeFgCg5SWV Lt0C6XvcWdn22iV5ApSXmXE= =uvpp -----END PGP SIGNATURE----- --VV4b6MQE+OnNyhkM-- From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 15:08:06 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 16C68106566C for ; Sat, 1 Mar 2008 15:08:06 +0000 (UTC) (envelope-from if@xip.at) Received: from chile.gbit.at (ns1.xip.at [193.239.188.99]) by mx1.freebsd.org (Postfix) with ESMTP id 750F58FC15 for ; Sat, 1 Mar 2008 15:08:04 +0000 (UTC) (envelope-from if@xip.at) Received: (qmail 3258 invoked from network); 1 Mar 2008 16:08:03 +0100 Received: from unknown (HELO filebunker.xip.at) (86.59.10.180) by chile.gbit.at with (DHE-RSA-AES256-SHA encrypted) SMTP; 1 Mar 2008 16:08:03 +0100 Date: Sat, 1 Mar 2008 16:08:02 +0100 (CET) From: Ingo Flaschberger To: Willem Jan Withagen In-Reply-To: <47C93E8B.3010609@digiware.nl> Message-ID: References: <20080226003107.54CD94500E@ptavv.es.net> <47C8964C.9080309@digiware.nl> <47C93E8B.3010609@digiware.nl> User-Agent: Alpine 1.00 (LFD 882 2007-12-20) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Sat, 01 Mar 2008 15:20:29 +0000 Cc: alves , freebsd-net@freebsd.org, freebsd-performance@freebsd.org, "=?x-unknown?B?IkRhbmllbA==?= Dias =?x-unknown?B?R29uw6ci?="@FreeBSD.ORG, Kevin Oberman Subject: Re: FBSD 1GBit router? 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, 01 Mar 2008 15:08:06 -0000 >> Thats why my next router will be based at this box: >> http://www.axiomtek.com/products/ViewProduct.asp?view=429 > > Nice piece of hardware. > Don't like the 2.5" one disk option though. > > And not shure what to think of: > "Seven 10/100/1000Mbps (through PCI-E by one > interface) ports (RJ-45)" > Which seems to suggest everything comes in thru on PCI-E interface. > That than better have 8 or 16 lanes. Each 1000Mbps port is connected via 1 lane PCI-E, which is fast enough. 1 lane: 250Mbyte/sec -> 2Gpbs >> Hopefully there will be direct memory bus connected nic's in future. >> (HyperTransport connected nic's) > > Well that is going to be an AMD only solution, and I'm not even shure > that AMD would like to have other things than CPU's on that bus. > >> >>> What it does not explain is why you can only get 80Mb/s with 64byte >>> packets, which would suggest other bottlenecks than just the bus. >> >> Perhaps something with interrupts: >> http://books.google.at/books?id=pr4fspaQqZkC&pg=PA144&lpg=PA144&dq=pci+interrupt+delay&source=web&ots=zbvVU2CgVx&sig=APe9YjdtK35ccnow7BDI2hzie7s&hl=de#PPA144,M1 >> >> >> >> MSI (Message-signalled Interrupts) are not very common on PCI architekture; >> PCI-E use only MSI. >> >> The kpps keept always around 100, equally if I used fast-forwarding, >> fast-interrupts, or higher HZ values than 1000HZ. > > MSI is not used for regular PCI busses.Could be that PCI-E does use it. > I believe youon that. But even than I'd like to know where the bottleneck is > in the 100kp/s limit with 64byte pakkets. As I also tested with polling (currently I use interface polling for the router) and also reached only 100kpps, the bottleneck must be someting different. >> But 100kpps is great for a router hardware of about 600eur. > > I've seen routers 10 times that expensive, not able to that. me too. Kind regards, Ingo Flaschberger From owner-freebsd-performance@FreeBSD.ORG Sat Mar 1 22:15:15 2008 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 60141106566C; Sat, 1 Mar 2008 22:15:15 +0000 (UTC) (envelope-from arkadi@mebius.lv) Received: from iklase.hosting.lv (iklase.hosting.lv [213.21.217.185]) by mx1.freebsd.org (Postfix) with ESMTP id D49E88FC25; Sat, 1 Mar 2008 22:15:14 +0000 (UTC) (envelope-from arkadi@mebius.lv) Received: from mail.hosting.lv ([62.85.37.83]:1894 "EHLO mail.hosting.lv" rhost-flags-OK-OK-OK-OK) by iklase.hosting.lv with ESMTP id S10031195AbYCAVgz (ORCPT + 1 other); Sat, 1 Mar 2008 23:36:55 +0200 Received: from [87.246.143.141] by mail.hosting.lv with esmtpsa (TLSv1:AES256-SHA:256) id 1JVZNS-000KXX-Hb; Sat, 01 Mar 2008 23:36:24 +0200 Message-ID: <47C9CC12.1090509@mebius.lv> Date: Sat, 01 Mar 2008 23:35:14 +0200 From: Arkadi Shishlov Organization: Mebius IT User-Agent: Thunderbird 2.0.0.9 (X11/20071031) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <479B1185.8020604@quip.cz> <479D89C9.7060300@chistydom.ru> <479DD94C.7010409@mawer.org> <479DE578.7060202@quip.cz> <20080214163037.GA51014@dracon.ht-systems.ru> <47B478E6.8080902@mebius.lv> <20080227082605.GL51827@dracon.ht-systems.ru> In-Reply-To: <20080227082605.GL51827@dracon.ht-systems.ru> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Score: -1.2 (-) Cc: Stanislav Sedov Subject: Re: PHP with open_basedir performance problem 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, 01 Mar 2008 22:15:15 -0000 Stanislav Sedov wrote: > On Thu, Feb 14, 2008 at 07:22:46PM +0200 Arkadi Shishlov mentioned: >> Stanislav Sedov wrote: >>> Most basedir problems are linked with the fact it produce a lot of lstast/ >>> readlinks on every require, include or open command. On Linux it pereforms >>> even worse, as they implemented readlink there by hand, and, of course, >>> their implementation isn't particulry good. >> But there is no high sys cpu usage on Linux in contrary to FreeBSD, as >> reported by original author of the thread..? >> Do you have numbers or benchmark ready? I see the number of syscalls >> required is astonishing (on Linux) but doesn't cause any problem at first >> look. > > I don't have specific benchmark numbers, and it's true, that top on Linux > don't show such sys time usage, as on FreeBSD boxes. However, the overall > performance of boxes on FreeBSD is 30-40% higher, that Linux ones. This numbers > is empirical, but I'm pretty sure in them: in past I migrated Linux hosting > to FreeBSD-based, and after that, I was able to add a bunch of new users to > that boxes without performance impact. In fact, the load average on these > boxes are MUCH lower, that was on Linux. Also, I notices, that stat() costs > much more on Linux, that FreeBSD. I don't certainly know, why Linux shows low > sys time usage, probably it's just bugs in accounting. I can confirm the FreeBSD was significantly faster than Linux in the open_basedir test I just conducted. With open_basedir check enabled, FreeBSD throughput dropped 2x, Linux 3x, and FreeBSD is 2x faster than Linux in this situation. The test system is Pentium4 3.8GHz HT, 2MB cache, 2.5GB RAM. FreeBSD 7.0-RELEASE i386. Linux kernel 2.6.24.2 i386. Both kernels are SMP. Software is lighttpd 1.4.18, PHP 5.2.5 in FastCGI mode, without op-code cache. The index.php that was tested by ApacheBench is a do-nothing script, that just includes other scripts (in sub-dir.), that in turn include other scripts, bringing total count of includes to 25 - like in a typical PHP application. Website document root depth is 4 (/usr/local/www/data). I've varied test parameters and filesystem setup (tmpfs, mdmfs), but in overall the picture is: http | no open_basedir | with open_basedir response size> 25kB | 50B | 50B -------------+----------+----------+------------------ FreeBSD | 192/125 | 243/ 89 | 99/247 Linux | 165/116 | 152/126 | 50/382 [Requests per second / 99% of requests served within N ms] ApacheBench concurency level is 15. 10 FastCGI processes. TOP shows approximatelly 20% user / 80% system time split for both Linux and FreeBSD in all tests (so accounting is likely correct on Linux).