From owner-freebsd-performance@FreeBSD.ORG Sun Aug 14 11:30:33 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B26FC16A41F for ; Sun, 14 Aug 2005 11:30:33 +0000 (GMT) (envelope-from nivo+sender+a818f9@yuckfou.org) Received: from ssdd.xs4all.nl (ssdd.xs4all.nl [195.64.89.117]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2E12143D46 for ; Sun, 14 Aug 2005 11:30:33 +0000 (GMT) (envelope-from nivo+sender+a818f9@yuckfou.org) Received: from localhost (localhost [127.0.0.1]) by imhotep.yuckfou.org (Postfix) with ESMTP id 4B3289FA for ; Sun, 14 Aug 2005 13:30:46 +0200 (CEST) Received: from ssdd.xs4all.nl ([127.0.0.1]) by localhost (imhotep.yuckfou.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 17335-07 for ; Sun, 14 Aug 2005 13:30:45 +0200 (CEST) Received: by imhotep.yuckfou.org (Postfix, from userid 1000) id F0F44451; Sun, 14 Aug 2005 13:30:44 +0200 (CEST) Received: from [192.168.2.239] (turbata-xp.gondel.local [192.168.2.239]) by localhost.yuckfou.org (tmda-ofmipd) with ESMTP; Sun, 14 Aug 2005 13:30:39 +0200 (CEST) Message-ID: <42FF2B50.80601@yuckfou.org> Date: Sun, 14 Aug 2005 13:30:24 +0200 User-Agent: Mozilla Thunderbird 1.0.6 (Windows/20050716) X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-performance@freebsd.org X-Enigmail-Version: 0.92.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit From: Nils Vogels X-Delivery-Agent: TMDA/1.0.3 (Seattle Slew) X-TMDA-Fingerprint: LXcNOiNpSnIUr0cB7m+0h/Ij3OI X-Virus-Scanned: amavisd-new at yuckfou.org X-Spam-Status: No, hits=-5.899 tagged_above=-999 required=6.31 tests=[ALL_TRUSTED=-3.3, BAYES_00=-2.599] X-Spam-Level: Subject: 5.4-REL-p6 bridging causes performance problems X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Nils Vogels List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 14 Aug 2005 11:30:33 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hi! I'm hoping this is the right list for my problem, if not, please redirect me ;) I am installing a Soekris net4801 with 3 NICs and a wireless card, using 5.4-REL-p6 and a custom kernel config. My kernel config can be found at http://www.is-root.com/node/62, my dmesg can be found at http://www.is-root.com/node/72 Basically, what I am aiming for with the kernel config is to create a smaller kernel, not supporting hardware the net4801 doesn't have (and will never have) After all is done, and my kernel boots, I am enabling the wireless interface via ifconfig ath0 up ssid my_sid mode 11g mediaopt hostap wepmode mixed wepkey 0xdeadbeef and enabling bridging using kldload bridge sysctl net.link.ether.bridge.enable=1 sysctl net.link.ether.bridge.config="ath0 sis0" sysctl net.inet.ip.check_interface=0 Packets are being forwarded, all is good. When I turn off my regular access point, forcing traffic to go through my net4801, my performance drops. An ftp-session from the LAN that sis0 is connected to tops at 30kilobytes per second, while when I disable the bridge and return to my normal access point, I get speeds in the range of 2.5Megabytes per second. I've searched the net, but am unable to find any clear hints as to where my problem might be, does any of you have an idea ? Greetings, Nils - -- Simple guidelines to happiness: Work like you don't need the money, love like your heart has never been broken and dance like no one can see you. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (MingW32) Comment: GnuPT 2.6.2.1 by EQUIPMENTE.DE Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFC/ytOMzNX/a06Wq0RArPWAJ47ZjMXb53yIbkspVTQdfOXeT9yHwCeNbwv A/D4Kh6wBYkcZjv/D40BWTY= =wmWX -----END PGP SIGNATURE----- From owner-freebsd-performance@FreeBSD.ORG Sun Aug 14 20:36:59 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A311216A41F for ; Sun, 14 Aug 2005 20:36:59 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from ms-smtp-03.nyroc.rr.com (ms-smtp-03.nyroc.rr.com [24.24.2.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4526343D53 for ; Sun, 14 Aug 2005 20:36:59 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from jdesk (cpe-66-66-155-141.rochester.res.rr.com [66.66.155.141]) by ms-smtp-03.nyroc.rr.com (8.12.10/8.12.10) with ESMTP id j7EKatP4018599; Sun, 14 Aug 2005 16:36:56 -0400 (EDT) Message-Id: <200508142036.j7EKatP4018599@ms-smtp-03.nyroc.rr.com> From: "Jason Coene" To: Date: Sun, 14 Aug 2005 16:37:00 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook, Build 11.0.5510 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 Thread-Index: AcWeK3oJNN1GByv7SUyryQVv38hvtAC5E2fw X-Virus-Scanned: Symantec AntiVirus Scan Engine Subject: TCP Transfers slowing down X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 14 Aug 2005 20:36:59 -0000 Hi All, I have a strange problem. We recently upgraded 6 web servers from FreeBSD 5.2-RELEASE to 5.4-RELEASE. Before the update, the servers would sustain high transfer rates (well over 4 Mbyte/sec), but since the update that has changed. A transfer will start out at normal speed (as high as we've ever seen), but it will immediately and consistently drop to between 200 and 300 KByte/sec. It will stay constant at that speed for the duration of the connection. It's not only Apache that does this, the built-in FTPD does it as well. The machines are connected via 10/100 Full duplex (forced at switch and NIC) to a Cisco switch that has a direct 1Gbps fibre uplink - none of this has changed since the upgrade. Kernel is a renamed GENERIC+SMP. The problem occurs on both our Single CPU P4 machines as well as our Dual Xeon machines. All using fxp0 as the external interface. I've attached a sample dmesg. I'm at a loss as to how this could happen with no configuration or infrastructure change, hopefully someone here has knowledge of what might be causing the problem! Thanks, Jason P.S. My apologies if you receive this twice, I tried sending two days ago but I don't believe it went through. From owner-freebsd-performance@FreeBSD.ORG Mon Aug 15 04:30:34 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 37ADA16A41F for ; Mon, 15 Aug 2005 04:30:34 +0000 (GMT) (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 A4B7C43D46 for ; Mon, 15 Aug 2005 04:30:33 +0000 (GMT) (envelope-from mike@sentex.net) Received: from pumice6.sentex.ca (pumice6.sentex.ca [64.7.153.21]) by smarthost1.sentex.ca (8.13.3/8.13.3) with ESMTP id j7F4TToq045110 for ; Mon, 15 Aug 2005 00:29:29 -0400 (EDT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by pumice6.sentex.ca (8.13.3/8.13.3) with ESMTP id j7F4UWMG016053; Mon, 15 Aug 2005 00:30:32 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simian.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.3/8.13.3) with ESMTP id j7F4UUk7050776 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 15 Aug 2005 00:30:30 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <6.2.3.4.0.20050815002800.043e5a00@64.7.153.2> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Mon, 15 Aug 2005 00:30:07 -0400 To: "Jason Coene" , From: Mike Tancsa In-Reply-To: <200508142036.j7EKatP4018599@ms-smtp-03.nyroc.rr.com> References: <200508142036.j7EKatP4018599@ms-smtp-03.nyroc.rr.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new X-Scanned-By: MIMEDefang 2.51 on 64.7.153.18 X-Scanned-By: MIMEDefang 2.51 on 64.7.153.21 Cc: Subject: Re: TCP Transfers slowing down 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, 15 Aug 2005 04:30:34 -0000 At 04:37 PM 14/08/2005, Jason Coene wrote: >Before the update, the servers would sustain high transfer rates (well over >4 Mbyte/sec), but since the update that has changed. A transfer will start >out at normal speed (as high as we've ever seen), but it will immediately >and consistently drop to between 200 and 300 KByte/sec. It will stay >constant at that speed for the duration of the connection. Can you post netstat -ni ifconfig fxp0 and a show int fa0/ as well as fa0/ ---Mike From owner-freebsd-performance@FreeBSD.ORG Mon Aug 15 05:36:23 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7140216A41F for ; Mon, 15 Aug 2005 05:36:23 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from ms-smtp-04.nyroc.rr.com (ms-smtp-04.nyroc.rr.com [24.24.2.58]) by mx1.FreeBSD.org (Postfix) with ESMTP id 75AA243D46 for ; Mon, 15 Aug 2005 05:36:22 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from jdesk (cpe-66-66-155-141.rochester.res.rr.com [66.66.155.141]) by ms-smtp-04.nyroc.rr.com (8.12.10/8.12.10) with ESMTP id j7F5aIpl016567; Mon, 15 Aug 2005 01:36:19 -0400 (EDT) Message-Id: <200508150536.j7F5aIpl016567@ms-smtp-04.nyroc.rr.com> From: "Jason Coene" To: "'Mike Tancsa'" , Date: Mon, 15 Aug 2005 01:36:18 -0400 MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="----=_NextPart_000_0000_01C5A139.BC7FB120" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 In-Reply-To: <6.2.3.4.0.20050815002800.043e5a00@64.7.153.2> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 Thread-Index: AcWhUhMdRdDNeVttSLaL0BdauWI/EwAB3Vkw X-Virus-Scanned: Symantec AntiVirus Scan Engine Cc: Subject: RE: TCP Transfers slowing down 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, 15 Aug 2005 05:36:23 -0000 This is a multi-part message in MIME format. ------=_NextPart_000_0000_01C5A139.BC7FB120 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Hi Mike, Thanks for the response. I've attached what you requested as a text file in case the following gets garbled by Outlook. Thanks, Jason -- >From a FreeBSD Machine: root@xxx.xxx.xxx> netstat -ni Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll em0 1500 00:0c:76:81:8d:f4 214153777 0 90481655 0 0 em0 1500 10.54.54/24 10.54.54.64 213309137 - 90480476 - - em0 1500 fe80:1::20c:7 fe80:1::20c:76ff: 0 - 5 - - fxp0 1500 00:0c:76:81:8d:f5 135087023 1 214628700 1 0 fxp0 1500 66.208.110/24 66.208.110.64 127803193 - 214627883 - - fxp0 1500 fe80:2::20c:7 fe80:2::20c:76ff: 0 - 5 - - lo0 16384 17472 0 17472 0 0 lo0 16384 127 127.0.0.1 17472 - 17472 - - lo0 16384 ::1/128 ::1 0 - 0 - - lo0 16384 fe80:3::1/64 fe80:3::1 0 - 0 - - pflog 33208 0 0 0 0 0 root@xxx.xxx.xxx> ifconfig fxp0 fxp0: flags=8843 mtu 1500 options=8 inet 66.208.110.64 netmask 0xffffff00 broadcast 66.208.110.255 inet6 fe80::20c:76ff:fe81:8df5%fxp0 prefixlen 64 scopeid 0x2 ether 00:0c:76:81:8d:f5 media: Ethernet 100baseTX status: active >From the Cisco: xxx.xxx.xxx#show int fa0/4 FastEthernet0/4 is up, line protocol is up (connected) Hardware is Fast Ethernet, address is 000b.5fb7.b204 (bia 000b.5fb7.b204) Description: Web Server 4 MTU 1500 bytes, BW 100000 Kbit, DLY 1000 usec, reliability 255/255, txload 1/255, rxload 3/255 Encapsulation ARPA, loopback not set Keepalive set (10 sec) Full-duplex, 100Mb/s input flow-control is off, output flow-control is off ARP type: ARPA, ARP Timeout 04:00:00 Last input never, output 00:00:00, output hang never Last clearing of "show interface" counters never Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 0 Queueing strategy: fifo Output queue :0/40 (size/max) 5 minute input rate 1406000 bits/sec, 100 packets/sec 5 minute output rate 57000 bits/sec, 71 packets/sec 1118722925 packets input, 2492078882 bytes, 0 no buffer Received 3702 broadcasts, 0 runts, 0 giants, 0 throttles 3 input errors, 0 CRC, 3 frame, 0 overrun, 25144 ignored 0 watchdog, 13 multicast, 0 pause input 0 input packets with dribble condition detected 720143589 packets output, 549572280 bytes, 0 underruns 0 output errors, 0 collisions, 2 interface resets 0 babbles, 0 late collision, 0 deferred 0 lost carrier, 0 no carrier, 0 PAUSE output 0 output buffer failures, 0 output buffers swapped out xxx.xxx.xxx#show run ! interface FastEthernet0/4 description Web Server 4 no ip address duplex full speed 100 ! > -----Original Message----- > From: Mike Tancsa [mailto:mike@sentex.net] > Sent: Monday, August 15, 2005 12:30 AM > To: Jason Coene; freebsd-performance@freebsd.org > Subject: Re: TCP Transfers slowing down > > At 04:37 PM 14/08/2005, Jason Coene wrote: > >Before the update, the servers would sustain high transfer rates (well > over > >4 Mbyte/sec), but since the update that has changed. A transfer will > start > >out at normal speed (as high as we've ever seen), but it will immediately > >and consistently drop to between 200 and 300 KByte/sec. It will stay > >constant at that speed for the duration of the connection. > > Can you post > netstat -ni > ifconfig fxp0 > and a > show int fa0/ > as well as fa0/ > > > ---Mike ------=_NextPart_000_0000_01C5A139.BC7FB120 Content-Type: text/plain; name="results.txt" Content-Transfer-Encoding: quoted-printable Content-Disposition: attachment; filename="results.txt" >From a FreeBSD Machine: root@xxx.xxx.xxx> netstat -ni Name Mtu Network Address Ipkts Ierrs Opkts = Oerrs Coll em0 1500 00:0c:76:81:8d:f4 214153777 0 90481655 = 0 0 em0 1500 10.54.54/24 10.54.54.64 213309137 - 90480476 = - - em0 1500 fe80:1::20c:7 fe80:1::20c:76ff: 0 - 5 = - - fxp0 1500 00:0c:76:81:8d:f5 135087023 1 214628700 = 1 0 fxp0 1500 66.208.110/24 66.208.110.64 127803193 - 214627883 = - - fxp0 1500 fe80:2::20c:7 fe80:2::20c:76ff: 0 - 5 = - - lo0 16384 17472 0 17472 = 0 0 lo0 16384 127 127.0.0.1 17472 - 17472 = - - lo0 16384 ::1/128 ::1 0 - 0 = - - lo0 16384 fe80:3::1/64 fe80:3::1 0 - 0 = - - pflog 33208 0 0 0 = 0 0 root@xxx.xxx.xxx> ifconfig fxp0 fxp0: flags=3D8843 mtu 1500 options=3D8 inet 66.208.110.64 netmask 0xffffff00 broadcast 66.208.110.255 inet6 fe80::20c:76ff:fe81:8df5%fxp0 prefixlen 64 scopeid 0x2 ether 00:0c:76:81:8d:f5 media: Ethernet 100baseTX status: active >From the Cisco: xxx.xxx.xxx#show int fa0/4 FastEthernet0/4 is up, line protocol is up (connected) Hardware is Fast Ethernet, address is 000b.5fb7.b204 (bia = 000b.5fb7.b204) Description: Web Server 4 MTU 1500 bytes, BW 100000 Kbit, DLY 1000 usec, reliability 255/255, txload 1/255, rxload 3/255 Encapsulation ARPA, loopback not set Keepalive set (10 sec) Full-duplex, 100Mb/s input flow-control is off, output flow-control is off ARP type: ARPA, ARP Timeout 04:00:00 Last input never, output 00:00:00, output hang never Last clearing of "show interface" counters never Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 0 Queueing strategy: fifo Output queue :0/40 (size/max) 5 minute input rate 1406000 bits/sec, 100 packets/sec 5 minute output rate 57000 bits/sec, 71 packets/sec 1118722925 packets input, 2492078882 bytes, 0 no buffer Received 3702 broadcasts, 0 runts, 0 giants, 0 throttles 3 input errors, 0 CRC, 3 frame, 0 overrun, 25144 ignored 0 watchdog, 13 multicast, 0 pause input 0 input packets with dribble condition detected 720143589 packets output, 549572280 bytes, 0 underruns 0 output errors, 0 collisions, 2 interface resets 0 babbles, 0 late collision, 0 deferred 0 lost carrier, 0 no carrier, 0 PAUSE output 0 output buffer failures, 0 output buffers swapped out xxx.xxx.xxx#show run ! interface FastEthernet0/4 description Web Server 4 no ip address duplex full speed 100 ! ------=_NextPart_000_0000_01C5A139.BC7FB120-- From owner-freebsd-performance@FreeBSD.ORG Mon Aug 15 11:42:42 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 37AAF16A41F for ; Mon, 15 Aug 2005 11:42:42 +0000 (GMT) (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 72F5F43D49 for ; Mon, 15 Aug 2005 11:42:41 +0000 (GMT) (envelope-from mike@sentex.net) Received: from pumice3.sentex.ca (pumice3.sentex.ca [64.7.153.26]) by smarthost1.sentex.ca (8.13.3/8.13.3) with ESMTP id j7FBfaQS057075 for ; Mon, 15 Aug 2005 07:41:36 -0400 (EDT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by pumice3.sentex.ca (8.13.3/8.13.3) with ESMTP id j7FBgd4E056748; Mon, 15 Aug 2005 07:42:39 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simian.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.3/8.13.3) with ESMTP id j7FBgbmN052160 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 15 Aug 2005 07:42:37 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <6.2.3.4.0.20050815073744.03e1f550@64.7.153.2> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Mon, 15 Aug 2005 07:42:16 -0400 To: "Jason Coene" , From: Mike Tancsa In-Reply-To: <200508150536.j7F5aIpl016567@ms-smtp-04.nyroc.rr.com> References: <6.2.3.4.0.20050815002800.043e5a00@64.7.153.2> <200508150536.j7F5aIpl016567@ms-smtp-04.nyroc.rr.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new X-Scanned-By: MIMEDefang 2.51 on 64.7.153.18 X-Scanned-By: MIMEDefang 2.51 on 64.7.153.26 Cc: Subject: RE: TCP Transfers slowing down 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, 15 Aug 2005 11:42:42 -0000 At 01:36 AM 15/08/2005, Jason Coene wrote: >Thanks for the response. I've attached what you requested as a text file in >case the following gets garbled by Outlook. Hi It all looks nice and clean. Is there a slow down between the boxes ? I dont see any errors to speak of. One thing you might try is to set the switch port to auto and the nic to auto. In the past there has been problems with flow control between the fxp and some switches. Putting it to auto should take care of that, but I dont think that is an issue. Still, worth a try. Also verify that its not some coincidental issue with your upstream by doing some transfer tests between each of the machines. ---Mike From owner-freebsd-performance@FreeBSD.ORG Mon Aug 15 18:45:31 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B9ADC16A421 for ; Mon, 15 Aug 2005 18:45:31 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from ms-smtp-01.nyroc.rr.com (ms-smtp-01.nyroc.rr.com [24.24.2.55]) by mx1.FreeBSD.org (Postfix) with ESMTP id 28D8543D5C for ; Mon, 15 Aug 2005 18:45:30 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from jdesk (cpe-66-66-155-141.rochester.res.rr.com [66.66.155.141]) by ms-smtp-01.nyroc.rr.com (8.12.10/8.12.10) with ESMTP id j7FIjRDX025218; Mon, 15 Aug 2005 14:45:28 -0400 (EDT) Message-Id: <200508151845.j7FIjRDX025218@ms-smtp-01.nyroc.rr.com> From: "Jason Coene" To: "'Mike Tancsa'" , Date: Mon, 15 Aug 2005 14:45:27 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcWhjn3sh95R0aBLSW61USyiUPaKZQAOjO7A In-Reply-To: <6.2.3.4.0.20050815073744.03e1f550@64.7.153.2> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 X-Virus-Scanned: Symantec AntiVirus Scan Engine Cc: Subject: RE: TCP Transfers slowing down 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, 15 Aug 2005 18:45:31 -0000 Hi Mike, Sorry, I should have clarified in my original e-mail. On the local network, transmissions work great, I can clear 6Mbyte/sec between 2 FreeBSD servers using eth0 and the switch. The problem occurs when going upstream. The reason why I'm thinking that this has to be something to do with a change in FreeBSD is circumstantial: - This problem didn't occur on 5.2-RELEASE (with no infrastructure changes) - An OpenBSD firewall (exact hardware, exact interface and switchport configuration) doesn't have the problem. - A FreeBSD 5.2.1-RELEASE machine (similar hardware, eth0 on the outside, same switch and interface configuration) doesn't have the problem. Do you know if there were any changes between 5.2 and 5.4 that may have an impact on this? Thanks, Jason > -----Original Message----- > From: owner-freebsd-performance@freebsd.org [mailto:owner-freebsd- > performance@freebsd.org] On Behalf Of Mike Tancsa > Sent: Monday, August 15, 2005 7:42 AM > To: Jason Coene; freebsd-performance@freebsd.org > Subject: RE: TCP Transfers slowing down > > At 01:36 AM 15/08/2005, Jason Coene wrote: > >Thanks for the response. I've attached what you requested as a text file > in > >case the following gets garbled by Outlook. > > Hi > It all looks nice and clean. Is there a slow down between > the boxes ? I dont see any errors to speak of. One thing you might > try is to set the switch port to auto and the nic to auto. In the > past there has been problems with flow control between the fxp and > some switches. Putting it to auto should take care of that, but I > dont think that is an issue. Still, worth a try. Also verify that > its not some coincidental issue with your upstream by doing some > transfer tests between each of the machines. > > ---Mike > > _______________________________________________ > 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 Mon Aug 15 21:41:05 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E31EC16A41F for ; Mon, 15 Aug 2005 21:41:05 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from ms-smtp-01.nyroc.rr.com (ms-smtp-01.nyroc.rr.com [24.24.2.55]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6511A43D53 for ; Mon, 15 Aug 2005 21:41:05 +0000 (GMT) (envelope-from jcoene@gotfrag.com) Received: from jdesk (cpe-66-66-155-141.rochester.res.rr.com [66.66.155.141]) by ms-smtp-01.nyroc.rr.com (8.12.10/8.12.10) with ESMTP id j7FLf1DX022600; Mon, 15 Aug 2005 17:41:02 -0400 (EDT) Message-Id: <200508152141.j7FLf1DX022600@ms-smtp-01.nyroc.rr.com> From: "Jason Coene" To: "'Scott Lambert'" Date: Mon, 15 Aug 2005 17:41:02 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook, Build 11.0.5510 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 In-Reply-To: <20050815210613.GA99663@sysmon.tcworks.net> Thread-Index: AcWh3SweOdIZ4LILSi6mvTI31MxKsQABD/pQ X-Virus-Scanned: Symantec AntiVirus Scan Engine Cc: freebsd-performance@freebsd.org Subject: RE: TCP Transfers slowing down 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, 15 Aug 2005 21:41:06 -0000 > > Do you know if there were any changes between 5.2 and 5.4 that may have > an > > impact on this? > > Just a thought, but I think SACK went in during that time period. > I'm not sure if this is a valid test, but I just found and disabled net.inet.tcp.sack.enable, it produced the same result. Jason From owner-freebsd-performance@FreeBSD.ORG Mon Aug 15 22:45:39 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C068216A41F; Mon, 15 Aug 2005 22:45:39 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from fileserver.fields.utoronto.ca (fileserver.fields.utoronto.ca [128.100.216.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5580243D45; Mon, 15 Aug 2005 22:45:39 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from fields.fields.utoronto.ca (fields.localdomain [192.168.216.11]) by fileserver.fields.utoronto.ca (8.12.8/8.12.8/Fields 6.0) with ESMTP id j7FMjbvf013450 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 15 Aug 2005 18:45:37 -0400 Received: from obsecurity.dyndns.org (localhost.localdomain [127.0.0.1]) by fields.fields.utoronto.ca (8.12.8/8.12.8/Fields WS 6.0) with ESMTP id j7FMjb6P021316; Mon, 15 Aug 2005 18:45:37 -0400 Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id 695CA51358; Mon, 15 Aug 2005 18:45:36 -0400 (EDT) Date: Mon, 15 Aug 2005 18:45:36 -0400 From: Kris Kennaway To: "Akhthar Parvez. K" Message-ID: <20050815224536.GA9218@xor.obsecurity.org> References: <200508130750.14779.akhthar@carmatec.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="LZvS9be/3tNcYl/X" Content-Disposition: inline In-Reply-To: <200508130750.14779.akhthar@carmatec.com> User-Agent: Mutt/1.4.2.1i Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: resource deadlock avoided?? 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, 15 Aug 2005 22:45:39 -0000 --LZvS9be/3tNcYl/X Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Aug 13, 2005 at 07:50:14AM +0530, Akhthar Parvez. K wrote: > Hi all, >=20 > I am gettting the following error message while accessing the interchange= =20 > admin panel.=20 >=20 > (perl), uid 1004: exited on signal 11 (core dumped) >=20 > I have no problem in accessing the main page. Does anyone know what could= be=20 > the problem? I had a look at sysctl directives, but did not notice anythi= ng=20 > particular. >=20 > I would also like to tune my FreeBSD server. The server has 2 cpus and RA= ID5.=20 > There are around 1000 accounts in it. Can anyone suggest the ideal values= for=20 > the sysctl variables. Your questions seem to be uncorrelated with your subject line :-) Kris --LZvS9be/3tNcYl/X Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (FreeBSD) iD8DBQFDARsQWry0BWjoQKURAhMOAKCuENch4nU+gLxpYP2ETS53ryMTIwCg19q1 hpvd67aSWVR96Lc8YS4Ds48= =ip1O -----END PGP SIGNATURE----- --LZvS9be/3tNcYl/X-- From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 08:12:03 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0113B16A41F for ; Wed, 17 Aug 2005 08:12:03 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from smtp1.adl2.internode.on.net (smtp1.adl2.internode.on.net [203.16.214.181]) by mx1.FreeBSD.org (Postfix) with ESMTP id 63F9A43D46 for ; Wed, 17 Aug 2005 08:12:01 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp19-170.static.internode.on.net [150.101.19.170]) by smtp1.adl2.internode.on.net (8.12.9/8.12.9) with ESMTP id j7H8Bxja056874 for ; Wed, 17 Aug 2005 17:42:00 +0930 (CST) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Wed, 17 Aug 2005 17:41:57 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Slow apache response 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, 17 Aug 2005 08:12:03 -0000 I am running a traffic exchange site and have just moved to a dedicated server (new server has been running 15 hours). Server is a P4 1.8G with 1024MB RAM Pages seem to be loading slower than the previous virtual server account but looking at top shows idle% to stay above 80 The mysql backend is located off the server and has not changed in any way when the web server changed. Wusage reports show upto 10,000 hits an hour for the end of yesterday and up to 18,000 hits a few hours ago. (these are the new server stats) One thing that has me curious is apache is started with 150 servers (which I am fine with) and currently I count 178 instances of apache running - but in top all but a couple show their state as lockf which I can't find a reference to. Apart from apache there is sendmail and ssh running (and the basics such as tty's, cron and syslog) All pages are php. Any ideas on how I can get response times up? -- Shane Ambler Shane@007Marketing.com From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 11:27:36 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3F06F16A41F for ; Wed, 17 Aug 2005 11:27:36 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id D16E643D46 for ; Wed, 17 Aug 2005 11:27:35 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.1/8.13.1) with ESMTP id j7HBRRHL002497; Wed, 17 Aug 2005 06:27:31 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <43031F32.5000502@centtech.com> Date: Wed, 17 Aug 2005 06:27:46 -0500 From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.10) Gecko/20050815 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Shane Ambler References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.82/1029/Wed Aug 17 05:01:16 2005 on mh1.centtech.com X-Virus-Status: Clean Cc: FreeBSD Mailing Lists Subject: Re: Slow apache response 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, 17 Aug 2005 11:27:36 -0000 Shane Ambler wrote: > I am running a traffic exchange site and have just moved to a dedicated > server (new server has been running 15 hours). > > Server is a P4 1.8G with 1024MB RAM > > Pages seem to be loading slower than the previous virtual server account but > looking at top shows idle% to stay above 80 > > The mysql backend is located off the server and has not changed in any way > when the web server changed. > > Wusage reports show upto 10,000 hits an hour for the end of yesterday and up > to 18,000 hits a few hours ago. (these are the new server stats) > > One thing that has me curious is apache is started with 150 servers (which I > am fine with) and currently I count 178 instances of apache running - but in > top all but a couple show their state as lockf which I can't find a > reference to. > > Apart from apache there is sendmail and ssh running (and the basics such as > tty's, cron and syslog) > > All pages are php. > > Any ideas on how I can get response times up? What state are the running httpd processes in (not the ones in lockf)? Also, did you compile apache from ports, or install via package, or other? Have you tried bumping up the number of servers to 200? Can you send the output of: netstat -m uname -a Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 12:13:46 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3DED116A41F for ; Wed, 17 Aug 2005 12:13:46 +0000 (GMT) (envelope-from kometen@gmail.com) Received: from wproxy.gmail.com (wproxy.gmail.com [64.233.184.194]) by mx1.FreeBSD.org (Postfix) with ESMTP id C26C843D49 for ; Wed, 17 Aug 2005 12:13:45 +0000 (GMT) (envelope-from kometen@gmail.com) Received: by wproxy.gmail.com with SMTP id i22so130243wra for ; Wed, 17 Aug 2005 05:13:45 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=qHeKxyarCHikcmSk5q1egGNw2jvq5GwxLFGC4cZK2IrYjtgwD7G/5nVoISpbH0sXVSaiqlmKqGarOtHJZoBTY85ZxnBFaCS0mwEjyzsARVk/iz2HhYaADNaXmKGS0n92o5VkLK0RMAVttJF7vSXKyEpYwtMLbxcbKYMO91OQiqE= Received: by 10.54.40.20 with SMTP id n20mr396815wrn; Wed, 17 Aug 2005 05:13:45 -0700 (PDT) Received: by 10.54.144.11 with HTTP; Wed, 17 Aug 2005 05:13:45 -0700 (PDT) Message-ID: Date: Wed, 17 Aug 2005 14:13:45 +0200 From: Claus Guttesen To: Shane Ambler In-Reply-To: Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: Cc: FreeBSD Mailing Lists Subject: Re: Slow apache response 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, 17 Aug 2005 12:13:46 -0000 > Apart from apache there is sendmail and ssh running (and the basics such = as > tty's, cron and syslog) >=20 > All pages are php. >=20 > Any ideas on how I can get response times up? Are you running apache 1.3 or 2.0? Is httpd.conf configured *not* to do reverse dns-look-up, 'HostnameLookups Off'. Try setting 'KeepAlive Off' if set to on. regards Claus From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 15:10:48 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 07FCA16A41F for ; Wed, 17 Aug 2005 15:10:48 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from ash25e.internode.on.net (ash25e.internode.on.net [203.16.214.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 50E2F43D49 for ; Wed, 17 Aug 2005 15:10:46 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp19-170.static.internode.on.net [150.101.19.170]) by ash25e.internode.on.net (8.12.9/8.12.6) with ESMTP id j7HFAiCO024684 for ; Thu, 18 Aug 2005 00:40:45 +0930 (CST) (envelope-from Shane@007Marketing.com) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Thu, 18 Aug 2005 00:40:42 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: <43031F32.5000502@centtech.com> Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Slow apache response 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, 17 Aug 2005 15:10:48 -0000 On 17/8/05 8:57 PM, "Eric Anderson" wrote: > Shane Ambler wrote: >> I am running a traffic exchange site and have just moved to a dedicated >> server (new server has been running 15 hours). >> >> Server is a P4 1.8G with 1024MB RAM >> >> Pages seem to be loading slower than the previous virtual server account but >> looking at top shows idle% to stay above 80 >> >> The mysql backend is located off the server and has not changed in any way >> when the web server changed. >> >> Wusage reports show upto 10,000 hits an hour for the end of yesterday and up >> to 18,000 hits a few hours ago. (these are the new server stats) >> >> One thing that has me curious is apache is started with 150 servers (which I >> am fine with) and currently I count 178 instances of apache running - but in >> top all but a couple show their state as lockf which I can't find a >> reference to. >> >> Apart from apache there is sendmail and ssh running (and the basics such as >> tty's, cron and syslog) >> >> All pages are php. >> >> Any ideas on how I can get response times up? > > What state are the running httpd processes in (not the ones in lockf)? > I'm seeing sbwait select kqread > Also, did you compile apache from ports, or install via package, or other? > The hosting provider (webair) installed from their own package Server version: Apache/1.3.33 (Unix) Server built: Feb 10 2005 12:34:22 If you are wondering about me asking them I have root access which to get I agreed to take full responsibility for admin etc. > Have you tried bumping up the number of servers to 200? > > Can you send the output of: > > netstat -m > uname -a > > netstat -m 131/784/26624 mbufs in use (current/peak/max): 110 mbufs allocated to data 21 mbufs allocated to packet headers 103/304/6656 mbuf clusters in use (current/peak/max) 804 Kbytes allocated to network (4% of mb_map in use) 0 requests for memory denied 0 requests for memory delayed 0 calls to protocol drain routines > uname -a FreeBSD mission.webair.com 4.11-RELEASE FreeBSD 4.11-RELEASE #0: Tue Aug 16 10:19:30 EDT 2005 root@mission.webair.com:/usr/src/sys/compile/asck1 i386 I compiled the kernel removing most device options and adding ipfw > Eric > > > -- Shane Ambler Sales Department 007Marketing.com Shane@007Marketing.com From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 15:11:03 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C70D116A41F for ; Wed, 17 Aug 2005 15:11:03 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from smtp1.adl2.internode.on.net (smtp1.adl2.internode.on.net [203.16.214.181]) by mx1.FreeBSD.org (Postfix) with ESMTP id D51DF43D48 for ; Wed, 17 Aug 2005 15:11:02 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp19-170.static.internode.on.net [150.101.19.170]) by smtp1.adl2.internode.on.net (8.12.9/8.12.9) with ESMTP id j7HFB0jT034605 for ; Thu, 18 Aug 2005 00:41:01 +0930 (CST) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Thu, 18 Aug 2005 00:40:58 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Slow apache response 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, 17 Aug 2005 15:11:03 -0000 On 17/8/05 9:43 PM, "Claus Guttesen" wrote: >> Apart from apache there is sendmail and ssh running (and the basics such as >> tty's, cron and syslog) >> >> All pages are php. >> >> Any ideas on how I can get response times up? > > Are you running apache 1.3 or 2.0? Is httpd.conf configured *not* to > do reverse dns-look-up, 'HostnameLookups Off'. Try setting 'KeepAlive > Off' if set to on. > Server version: Apache/1.3.33 (Unix) Server built: Feb 10 2005 12:34:22 KeepAlive on HostnameLookup off I'll try changing KeepAlive > regards > Claus > -- Shane Ambler Sales Department 007Marketing.com Shane@007Marketing.com From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 15:22:03 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A7B0616A41F for ; Wed, 17 Aug 2005 15:22:03 +0000 (GMT) (envelope-from luke@foolishgames.com) Received: from mail.foolishgames.com (mail.foolishgames.com [216.55.178.45]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2872A43D45 for ; Wed, 17 Aug 2005 15:22:03 +0000 (GMT) (envelope-from luke@foolishgames.com) Received: from [192.168.0.49] (24-176-56-252.dhcp.klmz.mi.charter.com [24.176.56.252]) (authenticated bits=0) by mail.foolishgames.com (8.13.4/8.12.11) with ESMTP id j7HFLvvN050381 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NO); Wed, 17 Aug 2005 08:21:58 -0700 (PDT) (envelope-from luke@foolishgames.com) X-Authentication-Warning: mail.foolishgames.com: Host 24-176-56-252.dhcp.klmz.mi.charter.com [24.176.56.252] claimed to be [192.168.0.49] Message-Id: <0C6CE027-FF31-4DAD-87DA-3F7CB6D20756@foolishgames.com> X-Habeas-Swe-6: email in exchange for a license for this Habeas Content-Transfer-Encoding: 7bit X-Habeas-Swe-3: like Habeas SWE (tm) Date: Wed, 17 Aug 2005 11:21:57 -0400 X-Habeas-Swe-8: Message (HCM) and not spam. Please report use of this From: Lucas Holt X-Habeas-Swe-5: Sender Warranted Email (SWE) (tm). The sender of this X-Habeas-Swe-2: brightly anticipated In-Reply-To: References: To: Shane Ambler X-Habeas-Swe-7: warrant mark warrants that this is a Habeas Compliant Mime-Version: 1.0 (Apple Message framework v733) X-Habeas-Swe-4: Copyright 2002 Habeas (tm) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed X-Habeas-Swe-1: winter into spring X-Habeas-Swe-9: mark in spam to . X-Mailer: Apple Mail (2.733) Cc: FreeBSD Mailing Lists Subject: Re: Slow apache response 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, 17 Aug 2005 15:22:03 -0000 On Aug 17, 2005, at 4:11 AM, Shane Ambler wrote: > I am running a traffic exchange site and have just moved to a > dedicated > server (new server has been running 15 hours). > > Server is a P4 1.8G with 1024MB RAM > > Pages seem to be loading slower than the previous virtual server > account but > looking at top shows idle% to stay above 80 > > The mysql backend is located off the server and has not changed in > any way > when the web server changed. > Is it possible that the old apache install had additional modules loaded to compress the output? I think its called mod_gzip in 1.3. I'm more familiar with apache 2. That would make pages load "faster" in the sense that less bandwith is required by the client and server. It would use more cpu and may not scale as well in terms of total responses. Also, you said the mysql database hasn't changed and that you were on a virtual server. Was the mysql database on the virtual server? There might be more latency to your database. Are you using a compressed or uncompressed mysql protocol? Lucas Holt Luke@FoolishGames.com ________________________________________________________ FoolishGames.com (Jewel Fan Site) JustJournal.com (Free blogging) FoolishGames.net (Enemy Territory IoM site) Think PC.. in 2006 you can own an Apple PCintosh. Whats next, windows works? From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 16:28:46 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D7C5A16A41F for ; Wed, 17 Aug 2005 16:28:46 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from ash25e.internode.on.net (ash25e.internode.on.net [203.16.214.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3E18D43D45 for ; Wed, 17 Aug 2005 16:28:45 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp19-170.static.internode.on.net [150.101.19.170]) by ash25e.internode.on.net (8.12.9/8.12.6) with ESMTP id j7HGShYu036716 for ; Thu, 18 Aug 2005 01:58:44 +0930 (CST) (envelope-from Shane@007Marketing.com) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Thu, 18 Aug 2005 01:58:41 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: <0C6CE027-FF31-4DAD-87DA-3F7CB6D20756@foolishgames.com> Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Slow apache response 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, 17 Aug 2005 16:28:47 -0000 On 18/8/05 12:51 AM, "Lucas Holt" wrote: > > On Aug 17, 2005, at 4:11 AM, Shane Ambler wrote: > >> I am running a traffic exchange site and have just moved to a >> dedicated >> server (new server has been running 15 hours). >> >> Server is a P4 1.8G with 1024MB RAM >> >> Pages seem to be loading slower than the previous virtual server >> account but >> looking at top shows idle% to stay above 80 >> >> The mysql backend is located off the server and has not changed in >> any way >> when the web server changed. >> > > Is it possible that the old apache install had additional modules > loaded to compress the output? I think its called mod_gzip in 1.3. > I'm more familiar with apache 2. That would make pages load "faster" > in the sense that less bandwith is required by the client and > server. It would use more cpu and may not scale as well in terms of > total responses. > Could be - I'll see if I can find out - my guess is that as they have used their own apache package to install it is the same one they use for all bsd setups (the virtual account was bsd as well) virtual account shows as 4.11-RELEASE-p11 dedicated shows 4.11-RELEASE The only difference I can find (I can still access the virtual account) Is mod_prxp that is on the virtual server and not the dedicated The full list of mods from the dedicated server (from phpinfo()) mod_php4, mod_ssl, mod_setenvif, mod_so, mod_unique_id, mod_log_forensic, mod_usertrack, mod_headers, mod_expires, mod_cern_meta, mod_proxy, mod_digest, mod_auth_dbm, mod_auth_anon, mod_auth, mod_access, mod_rewrite, mod_alias, mod_userdir, mod_speling, mod_actions, mod_imap, mod_asis, mod_cgi, mod_dir, mod_autoindex, mod_include, mod_info, mod_status, mod_negotiation, mod_mime, mod_mime_magic, mod_log_config, mod_define, mod_env, mod_vhost_alias, http_core Can probably trim this list a bit. > Also, you said the mysql database hasn't changed and that you were on > a virtual server. Was the mysql database on the virtual server? > There might be more latency to your database. Are you using a > compressed or uncompressed mysql protocol? > > The mysql server appears to be a dedicated db server provided by webair (sql5.webair.com) Standard mysql connection (using mysql_connect(host,user,pwd) in php) > Lucas Holt > Luke@FoolishGames.com > ________________________________________________________ > FoolishGames.com (Jewel Fan Site) > JustJournal.com (Free blogging) > FoolishGames.net (Enemy Territory IoM site) > > Think PC.. in 2006 you can own an Apple PCintosh. Whats next, windows > works? > > -- Shane Ambler Sales Department 007Marketing.com Shane@007Marketing.com From owner-freebsd-performance@FreeBSD.ORG Wed Aug 17 16:53:36 2005 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E8E1F16A41F for ; Wed, 17 Aug 2005 16:53:35 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from ash25e.internode.on.net (ash25e.internode.on.net [203.16.214.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5558543D45 for ; Wed, 17 Aug 2005 16:53:35 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp19-170.static.internode.on.net [150.101.19.170]) by ash25e.internode.on.net (8.12.9/8.12.6) with ESMTP id j7HGrXTp040498 for ; Thu, 18 Aug 2005 02:23:34 +0930 (CST) (envelope-from Shane@007Marketing.com) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Thu, 18 Aug 2005 02:23:30 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Slow apache response 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, 17 Aug 2005 16:53:36 -0000 On 18/8/05 12:40 AM, "Shane Ambler" wrote: > On 17/8/05 9:43 PM, "Claus Guttesen" wrote: > >>> Apart from apache there is sendmail and ssh running (and the basics such as >>> tty's, cron and syslog) >>> >>> All pages are php. >>> >>> Any ideas on how I can get response times up? >> >> Are you running apache 1.3 or 2.0? Is httpd.conf configured *not* to >> do reverse dns-look-up, 'HostnameLookups Off'. Try setting 'KeepAlive >> Off' if set to on. >> > Server version: Apache/1.3.33 (Unix) > Server built: Feb 10 2005 12:34:22 > > KeepAlive on > HostnameLookup off > > I'll try changing KeepAlive > Setting KeepAlive off seemed to make improvements initially but it has slowed down again (2 hours later) - maybe I need to look at caching? >> regards >> Claus >> -- Shane Ambler Sales Department 007Marketing.com Shane@007Marketing.com