From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 05:32:12 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8A4A716A4DF for ; Mon, 7 Aug 2006 05:32:12 +0000 (UTC) (envelope-from anders@FreeBSD.org) Received: from fupp.net (totem.fix.no [80.91.36.20]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1606C43D49 for ; Mon, 7 Aug 2006 05:32:11 +0000 (GMT) (envelope-from anders@FreeBSD.org) Received: from localhost (totem.fix.no [80.91.36.20]) by fupp.net (Postfix) with ESMTP id 833988D9897; Mon, 7 Aug 2006 07:32:10 +0200 (CEST) Received: from fupp.net ([80.91.36.20]) by localhost (totem.fix.no [80.91.36.20]) (amavisd-new, port 10024) with LMTP id 36013-07; Mon, 7 Aug 2006 07:32:08 +0200 (CEST) Received: by fupp.net (Postfix, from userid 1000) id 09F3E8D9896; Mon, 7 Aug 2006 07:32:07 +0200 (CEST) Date: Mon, 7 Aug 2006 07:32:07 +0200 From: Anders Nordby To: =?iso-8859-1?Q?S=E9bastien_A=2E?= VALSEMEY Message-ID: <20060807053207.GA38003@totem.fix.no> References: <009e01c68e18$0e1738c0$0da7a8c0@FR.B3W> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <009e01c68e18$0e1738c0$0da7a8c0@FR.B3W> X-PGP-Key: http://anders.fix.no/pgp/ X-PGP-Key-FingerPrint: 1E0F C53C D8DF 6A8F EAAD 19C5 D12A BC9F 0083 5956 User-Agent: Mutt/1.5.11 Cc: freebsd-net@freebsd.org Subject: Re: IPF and OOW problems X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 05:32:12 -0000 Hi, The current version of IP Filter in FreeBSD has bugs in the handling of TCP out-of-window checks. Check/follow http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/98978 for a solution. On Mon, Jun 12, 2006 at 02:02:17PM +0200, Sébastien A. VALSEMEY wrote: > Hello, > > I currently have a FreeBSD 6.1-STABLE box configured as a router/firewall with ipfilter v4.1.8. > > > WAN_IP/32 > | > tun0 > | > |---------| > | FreeBSD | > |---------| > / \ > xl0 xl1 > / \ > > 192.168.0.0/24 DMZ_BLOCK/29 > > I often experience in my ipf logs such packet drops (the following example is for an active upload on a FTP server located on the > first IP of the DMZ network). My IPs have been voluntary hidden for privacy purposes. > > ipmon[329]: 13:12:41.185263 tun0 @0:110 b REMOTE_WAN_IP,8600 -> DMZ_IP_1,20 PR tcp len 20 1300 -A IN OOW > ipmon[329]: 13:12:41.186493 tun0 @0:110 b REMOTE_WAN_IP,8600 -> DMZ_IP_1,20 PR tcp len 20 356 -AP IN OOW > > Packet drop occurs a few seconds after the beginning of the transfer, even allowing a few kilobytes to be uploaded, which means that > the connection establishes well. > > And on another hand, when I try to reach DMZ machines from the LAN (for example via RDP), I am systematically dropped with the same > kind of OOW packet, I mean the connection is not even established. > > As ICMP is allowed on the whole network, I can traceroute and reach each host in the network, from inside and outside (except for > the natted LAN...). The IP masquerading for hosts located on LAN works perfectly as they can go on the Internet without any problem. > > When I add the two following lines in my ipf ruleset, everything runs smoothly (but insecured!): > pass in quick all > pass out quick all > > I heard that such problems occur with the same version of ipf on Solaris > (http://msgs.securepoint.com/cgi-bin/get/ipfilter-0605/28.html), but I am not sure it happens because of that. > > What I did wrong? > > Thank you by advance for your help. > > Here are extracts from my main configuration files: > > [/etc/rc.conf] > <... *snip*! ...> > firewall_enable="NO" > firewall_script="/etc/rc.firewall" > firewall_type="/etc/rc.firewall.rules" > firewall_logging="YES" > gateway_enable="YES" > icmp_drop_redirects="YES" > ifconfig_lo0="inet 127.0.0.1" > ifconfig_xl0="inet 192.168.0.254 netmask 255.255.255.0" > ifconfig_xl1="inet DMZ_IP_6 netmask 255.255.255.248" > ipfilter_enable="YES" > ipfilter_rules="/etc/ipf.rules" > ipnat_enable="YES" > ipnat_program="/sbin/ipnat" > ipnat_rules="/etc/ipnat.rules" > ipnat_flags="" > ipmon_enable="YES" > ipmon_program="/sbin/ipmon" > ipmon_flags="-Ds" > kern_securelevel="0" > kern_securelevel_enable="NO" > network_interfaces="lo0 xl0 xl1" > ppp_enable="YES" > ppp_mode="ddial" > ppp_nat="NO" > ppp_profile="My_ISP_PROFILE" > <... *snip*! ...> > > > > [/etc/ipf.rules] > # Allow localhost traffic > pass in quick on lo0 all > pass out quick on lo0 all > > # Allow all outgoing traffic from this gateway > pass out quick on tun0 from any to any keep state > pass out quick on tun0 proto tcp from any to any keep state > pass out quick on xl0 from any to 192.168.0.0/24 keep state > pass out quick on xl0 proto tcp from any to 192.168.0.0/24 keep state > pass out quick on xl1 from any to DMZ_BLOCK/29 keep state > pass out quick on xl1 proto tcp from any to DMZ_BLOCK/29 keep state > > # Allow ICMP traffic (for testing purposes) > pass in quick on xl0 proto icmp from 192.168.0.0/24 to any keep state > pass in quick on xl1 proto icmp from DMZ_BLOCK/29 to any keep state > pass in quick on tun0 proto icmp from any to 192.168.0.0/24 keep state > pass in quick on tun0 proto icmp from any to DMZ_BLOCK/29 keep state > pass out quick proto icmp from any to any keep state > > # Allow FTP server > pass in quick on tun0 proto tcp from any to DMZ_IP_1/32 port = ftp-data keep state > pass in quick on xl0 proto tcp from 192.168.0.0/24 to DMZ_IP_1/32 port = ftp-data keep state > pass in quick on tun0 proto tcp from any to DMZ_IP_1/32 port = ftp keep state > pass in quick on xl0 proto tcp from 192.168.0.0/24 to DMZ_IP_1/32 port = ftp keep state > # This is for the passive ports range... > pass in quick on tun0 proto tcp from any to DMZ_IP_1/32 port 4000 >< 4049 keep state > pass in quick on xl0 proto tcp from 192.168.0.0/24 to DMZ_IP_1/32 port 4000 >< 4049 keep state > > # Allow Terminal services > pass in quick on tun0 proto tcp from any to DMZ_IP_1/32 port = rdp keep state > pass in quick on xl0 proto tcp from 192.168.0.0/24 to DMZ_IP_1/32 port = rdp keep state > > # Default > block in log all > block return-rst in log proto tcp from any to any > block return-icmp-as-dest(port-unr) in log proto udp from any to any > > > [/etc/ipnat.rules] > map tun0 192.168.0.0/24 -> WAN_IP/32 > map tun0 192.168.0.0/24 -> WAN_IP/32 portmap tcp/udp auto > > > [KERNEL_CONFIG] > device bpf > options IPFIREWALL > options IPFIREWALL_VERBOSE > options IPFIREWALL_DEFAULT_TO_ACCEPT > options IPFILTER > options IPFILTER_LOG > options IPFILTER_DEFAULT_BLOCK > options NETGRAPH > options NETGRAPH_ETHER > options NETGRAPH_PPP > options NETGRAPH_PPPOE > options NETGRAPH_SOCKET > > > > > > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" -- Anders. From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 09:41:02 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9280B16A4EF; Mon, 7 Aug 2006 09:41:02 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id BCE9E43D64; Mon, 7 Aug 2006 09:41:00 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k779ewJN052657 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 7 Aug 2006 13:40:58 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k779ewdO052656; Mon, 7 Aug 2006 13:40:58 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Mon, 7 Aug 2006 13:40:57 +0400 From: Gleb Smirnoff To: soc-victor@FreeBSD.org Message-ID: <20060807094057.GT96644@FreeBSD.org> Mail-Followup-To: Gleb Smirnoff , soc-victor@freebsd.org, freebsd-current@freebsd.org, freebsd-net@freebsd.org References: <49402550608041418j1b4d2ac9r66cae310c11e7ec5@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <49402550608041418j1b4d2ac9r66cae310c11e7ec5@mail.gmail.com> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org, freebsd-current@FreeBSD.org Subject: Re: SMUX (RFC 1227) implementation for BSNMPd X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 09:41:02 -0000 On Sat, Aug 05, 2006 at 12:18:19AM +0300, victor cruceru wrote: v> Hi folks, v> I'm glad to announce an implementation of the venerable SNMP SMUX v> protocol for FreeBSD SNMP agent, bsnmpd. v> You can grab it from its wiki page http://wikitest.freebsd.org/SnmpSmux v> There you will find instructions about how to build it (it is a patch v> against -current) and how to play with it. v> For now it is only a bsnmpd module (the "server side") - but if v> someone is interested I have plans to write a libsmux library and API v> to be used in building smux peers (the "client side"). Cool! As soon as libsmux is done, I must chase myself to write SNMP support for mpd. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 14:16:15 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DAEF916A4DA; Mon, 7 Aug 2006 14:16:15 +0000 (UTC) (envelope-from dan@dan.emsphone.com) Received: from dan.emsphone.com (dan.emsphone.com [199.67.51.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8103543D46; Mon, 7 Aug 2006 14:16:15 +0000 (GMT) (envelope-from dan@dan.emsphone.com) Received: (from dan@localhost) by dan.emsphone.com (8.13.6/8.13.6) id k77EGEdb021505; Mon, 7 Aug 2006 09:16:14 -0500 (CDT) (envelope-from dan) Date: Mon, 7 Aug 2006 09:16:14 -0500 From: Dan Nelson To: Gleb Smirnoff , soc-victor@FreeBSD.org, freebsd-current@FreeBSD.org, freebsd-net@FreeBSD.org Message-ID: <20060807141614.GA16880@dan.emsphone.com> References: <49402550608041418j1b4d2ac9r66cae310c11e7ec5@mail.gmail.com> <20060807094057.GT96644@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20060807094057.GT96644@FreeBSD.org> X-OS: FreeBSD 6.1-STABLE X-message-flag: Outlook Error User-Agent: Mutt/1.5.12-2006-07-14 Cc: Subject: Re: SMUX (RFC 1227) implementation for BSNMPd X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 14:16:16 -0000 In the last episode (Aug 07), Gleb Smirnoff said: > On Sat, Aug 05, 2006 at 12:18:19AM +0300, victor cruceru wrote: > > I'm glad to announce an implementation of the venerable SNMP SMUX > > protocol for FreeBSD SNMP agent, bsnmpd. You can grab it from its > > wiki page http://wikitest.freebsd.org/SnmpSmux There you will find > > instructions about how to build it (it is a patch against -current) > > and how to play with it. For now it is only a bsnmpd module (the > > "server side") - but if someone is interested I have plans to write > > a libsmux library and API to be used in building smux peers (the > > "client side"). > > Cool! As soon as libsmux is done, I must chase myself to > write SNMP support for mpd. I thought SMUX was obsoleted many years ago by AgentX (RFC 2257) ? -- Dan Nelson dnelson@allantgroup.com From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 14:37:42 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 862FD16A503 for ; Mon, 7 Aug 2006 14:37:42 +0000 (UTC) (envelope-from victor.cruceru@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.226]) by mx1.FreeBSD.org (Postfix) with ESMTP id B217943D46 for ; Mon, 7 Aug 2006 14:37:41 +0000 (GMT) (envelope-from victor.cruceru@gmail.com) Received: by wx-out-0506.google.com with SMTP id i27so509651wxd for ; Mon, 07 Aug 2006 07:37:40 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:reply-to:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=SD1wUpk3lzKbBTgUz6MlrhYtgLjYNPgRQsGZdvm1tzbiF8b0dg/IBmeFozKuVglrXxu57jzSSnmby5iwLFWRcJUHEkK1rPPESv1JcfNkuuD6JWu0iL9BXiLP9+al1nJNlPT/bX1fRipe+5IqQ4V9VfB61DR4VzvWR/SSmdJsm/Y= Received: by 10.70.100.1 with SMTP id x1mr9054839wxb; Mon, 07 Aug 2006 07:37:40 -0700 (PDT) Received: by 10.70.78.9 with HTTP; Mon, 7 Aug 2006 07:37:40 -0700 (PDT) Message-ID: <49402550608070737p5b2604i5134aa5a6168049e@mail.gmail.com> Date: Mon, 7 Aug 2006 17:37:40 +0300 From: "victor cruceru" To: "Dan Nelson" In-Reply-To: <20060807141614.GA16880@dan.emsphone.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <49402550608041418j1b4d2ac9r66cae310c11e7ec5@mail.gmail.com> <20060807094057.GT96644@FreeBSD.org> <20060807141614.GA16880@dan.emsphone.com> Cc: freebsd-net@freebsd.org, freebsd-current@freebsd.org Subject: Re: SMUX (RFC 1227) implementation for BSNMPd X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: soc-victor@freebsd.org List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 14:37:42 -0000 Hi Dan, Yes, this is true. But for a simple IPC between master agent and sub-agents I think it is still good enough. On 8/7/06, Dan Nelson wrote: > In the last episode (Aug 07), Gleb Smirnoff said: > > On Sat, Aug 05, 2006 at 12:18:19AM +0300, victor cruceru wrote: > > > I'm glad to announce an implementation of the venerable SNMP SMUX > > > protocol for FreeBSD SNMP agent, bsnmpd. You can grab it from its > > > wiki page http://wikitest.freebsd.org/SnmpSmux There you will find > > > instructions about how to build it (it is a patch against -current) > > > and how to play with it. For now it is only a bsnmpd module (the > > > "server side") - but if someone is interested I have plans to write > > > a libsmux library and API to be used in building smux peers (the > > > "client side"). > > > > Cool! As soon as libsmux is done, I must chase myself to > > write SNMP support for mpd. > > I thought SMUX was obsoleted many years ago by AgentX (RFC 2257) ? > > -- > Dan Nelson > dnelson@allantgroup.com > -- victor cruceru ------------------------------------------------ Non est respondendum ad omnia. ( Cicero, Pro Murena Oratio ) ------------------------------------------------ From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 14:46:54 2006 Return-Path: X-Original-To: net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2378416A4DD for ; Mon, 7 Aug 2006 14:46:54 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5701E43D62 for ; Mon, 7 Aug 2006 14:46:01 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k77Ejwbm055599 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 7 Aug 2006 18:45:58 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k77Ejvkc055598; Mon, 7 Aug 2006 18:45:58 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Mon, 7 Aug 2006 18:45:57 +0400 From: Gleb Smirnoff To: Luigi Rizzo Message-ID: <20060807144557.GF96644@cell.sick.ru> References: <20060726071232.A96367@xorpc.icir.org> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <20060726071232.A96367@xorpc.icir.org> User-Agent: Mutt/1.5.6i Cc: net@FreeBSD.org Subject: Re: multiple DSL modems and pppoe sessions on the same ethernet ? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 14:46:54 -0000 On Wed, Jul 26, 2006 at 07:12:32AM -0700, Luigi Rizzo wrote: L> The problem is, my provider does not provide specific service names, L> but it will accept anything i supply. So when i run the three ppp instances, L> they will all match, and the code in ng_pppoe.c will happily take the L> first reply as good. L> L> The only approach left is then implement some form of MAC filtering, L> e.g. overloading the 'service name' to specify the mac address of the L> modem i am interested in. L> There is a couple of ways to implement this, one is patching the L> receive path (ng_pppoe_rcvdata(), case PADO_CODE) to filter replies L> based on the source mac address, and the other one is to patch L> the code transmitting the PADI packet to replace the broadcast L> dst address with the unicast MAC taken from the "service name". The second option I think is a violation of the protocol, so I suppose filtering on receive path is better. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Mon Aug 7 17:16:22 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 540D616A4DA; Mon, 7 Aug 2006 17:16:22 +0000 (UTC) (envelope-from joe@tao.org.uk) Received: from mailhost.tao.org.uk (transwarp.tao.org.uk [87.74.4.34]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8410443D77; Mon, 7 Aug 2006 17:16:13 +0000 (GMT) (envelope-from joe@tao.org.uk) Received: from genius.tao.org.uk (genius.pact.cpes.susx.ac.uk [139.184.130.240]) by mailhost.tao.org.uk (Postfix) with ESMTP id D6501645D; Mon, 7 Aug 2006 18:16:11 +0100 (BST) Received: by genius.tao.org.uk (Postfix, from userid 100) id 7EC504073; Mon, 7 Aug 2006 18:16:05 +0100 (BST) Date: Mon, 7 Aug 2006 18:16:05 +0100 From: Josef Karthauser To: Phil Regnauld Message-ID: <20060807171605.GC838@genius.tao.org.uk> Mail-Followup-To: Josef Karthauser , Phil Regnauld , Dmitry Morozovsky , Pawel Jakub Dawidek , Chris , freebsd-net@freebsd.org, freebsd-current@freebsd.org References: <20060628103238.GA815@genius.tao.org.uk> <20060628103949.GJ2005@catpipe.net> <3aaaa3a0606281940k63c77ebfga84a854b2cd4ed84@mail.gmail.com> <20060801084156.GD3440@genius.tao.org.uk> <20060801084053.GE22731@catpipe.net> <20060803110525.GE804@genius.tao.org.uk> <20060804183146.N15526@woozle.rinet.ru> <20060804150057.GP29827@catpipe.net> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="96YOpH+ONegL0A3E" Content-Disposition: inline In-Reply-To: <20060804150057.GP29827@catpipe.net> User-Agent: Mutt/1.5.11 Cc: Chris , freebsd-net@freebsd.org, freebsd-current@freebsd.org, Pawel Jakub Dawidek , Dmitry Morozovsky Subject: Re: Can I pursuade someone to commit this patch? (Re: Multiple IP addresses in a jail.) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 07 Aug 2006 17:16:22 -0000 --96YOpH+ONegL0A3E Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Aug 04, 2006 at 05:00:58PM +0200, Phil Regnauld wrote: > Dmitry Morozovsky (marck) writes: > >=20 > > I suppose pinging pjd@ did not work? ;) >=20 > Good question -- why did Pawel not commit them himself if he could ? :) >=20 No idea. I sent him an email asking on 28 Jun 2006, but I've not had a reply. Joe --=20 Josef Karthauser (joe@tao.org.uk) http://www.josef-k.net/ Physics Particle Theory (student) http://www.pact.cpes.sussex.ac.uk/ =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D An eclectic mix of fact an= d theory. =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --96YOpH+ONegL0A3E Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (FreeBSD) iEYEARECAAYFAkTXdVUACgkQXVIcjOaxUBY2pACgmh0+l8OjkqIxB5sC1n4eW3TU fGUAn1PYZXH2JNL338QZxroxMgmSGRJr =3EmF -----END PGP SIGNATURE----- --96YOpH+ONegL0A3E-- From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 05:40:56 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4F92716A4DA; Tue, 8 Aug 2006 05:40:56 +0000 (UTC) (envelope-from prvs=julian=368479a79@elischer.org) Received: from a50.ironport.com (a50.ironport.com [63.251.108.112]) by mx1.FreeBSD.org (Postfix) with ESMTP id D4D4743D45; Tue, 8 Aug 2006 05:40:55 +0000 (GMT) (envelope-from prvs=julian=368479a79@elischer.org) Received: from unknown (HELO [192.168.2.3]) ([10.251.60.101]) by a50.ironport.com with ESMTP; 07 Aug 2006 22:40:55 -0700 Message-ID: <44D823E6.1000900@elischer.org> Date: Mon, 07 Aug 2006 22:40:54 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.13) Gecko/20060414 X-Accept-Language: en-us, en MIME-Version: 1.0 To: "Andrey V. Elsukov" References: <200608051358.k75DwpYr070713@repoman.freebsd.org> <20060807092251.GS96644@FreeBSD.org> <44D774E9.4010309@elischer.org> <44D80E8D.7010709@yandex.ru> In-Reply-To: <44D80E8D.7010709@yandex.ru> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit Cc: Gleb Smirnoff , Stefan Farfeleder , net@freebsd.org Subject: Re: cvs commit: src/sbin/ipfw ipfw2.c X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 05:40:56 -0000 Andrey V. Elsukov wrote: > Julian Elischer wrote: > >> great.. I have been in ipfw(2) the last week and have some sugestions >> for >> increasing its efficiency.. especially the code that times out >> dynamic rules. > > Can you explain your suggestions in detail? > I sent the following to luigi: I repeat it here.. ------------ start comment to Luigi -------------- I haven't coded it yet but we run with maybe 50,000 dynamic rules at a time. (hopefully a lot more, maybe 200,000 in the near future) We need to simplify the code that times out the rules so that it doesn't have to scan through ALL the dynamic rules every clocktick. Basically I was thinking of implementing a timing wheel representing the next "600" seconds or so. (600 slots). "now" moves around the wheel. (The size of the wheel is the size of the largest lifetime value.) (maybe with a backup wheel at 600 seconds per slot or something) Each dynamic entry has an extra linkage to allow it to be linked onto the appropriate slot. whenever you use an entry you take it out of where-ever it is and put it into it's new slot X seconds into the future. At each tick you take all the entries that have reached "now" and do whatever needs t be done on only those entries. thus at each tick you only have a small amount of work to do instead fo looking at all 50,000 entries. From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 07:47:11 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7064D16A4E0; Tue, 8 Aug 2006 07:47:11 +0000 (UTC) (envelope-from pjd@garage.freebsd.pl) Received: from mail.garage.freebsd.pl (arm132.internetdsl.tpnet.pl [83.17.198.132]) by mx1.FreeBSD.org (Postfix) with ESMTP id 919CE43D45; Tue, 8 Aug 2006 07:47:10 +0000 (GMT) (envelope-from pjd@garage.freebsd.pl) Received: by mail.garage.freebsd.pl (Postfix, from userid 65534) id 275615138A; Tue, 8 Aug 2006 09:47:08 +0200 (CEST) Received: from localhost (dlx245.neoplus.adsl.tpnet.pl [83.24.53.245]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.garage.freebsd.pl (Postfix) with ESMTP id 81CB550EA7; Tue, 8 Aug 2006 09:47:02 +0200 (CEST) Date: Tue, 8 Aug 2006 09:45:50 +0200 From: Pawel Jakub Dawidek To: Josef Karthauser , Phil Regnauld , Dmitry Morozovsky , Chris , bz@FreeBSD.org, freebsd-net@freebsd.org, freebsd-current@freebsd.org Message-ID: <20060808074550.GB1190@garage.freebsd.pl> References: <20060628103238.GA815@genius.tao.org.uk> <20060628103949.GJ2005@catpipe.net> <3aaaa3a0606281940k63c77ebfga84a854b2cd4ed84@mail.gmail.com> <20060801084156.GD3440@genius.tao.org.uk> <20060801084053.GE22731@catpipe.net> <20060803110525.GE804@genius.tao.org.uk> <20060804183146.N15526@woozle.rinet.ru> <20060804150057.GP29827@catpipe.net> <20060807171605.GC838@genius.tao.org.uk> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="s2ZSL+KKDSLx8OML" Content-Disposition: inline In-Reply-To: <20060807171605.GC838@genius.tao.org.uk> X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 7.0-CURRENT i386 User-Agent: mutt-ng/devel-r804 (FreeBSD) X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on mail.garage.freebsd.pl X-Spam-Level: X-Spam-Status: No, score=-0.5 required=3.0 tests=BAYES_00,RCVD_IN_NJABL_DUL, RCVD_IN_SORBS_DUL autolearn=no version=3.0.4 Cc: Subject: Re: Can I pursuade someone to commit this patch? (Re: Multiple IP addresses in a jail.) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 07:47:11 -0000 --s2ZSL+KKDSLx8OML Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Aug 07, 2006 at 06:16:05PM +0100, Josef Karthauser wrote: > On Fri, Aug 04, 2006 at 05:00:58PM +0200, Phil Regnauld wrote: > > Dmitry Morozovsky (marck) writes: > > >=20 > > > I suppose pinging pjd@ did not work? ;) > >=20 > > Good question -- why did Pawel not commit them himself if he could ? :) > >=20 >=20 > No idea. I sent him an email asking on 28 Jun 2006, but I've not had a > reply. Sorry guys for the delay. I answer this very question too many time... :) There are few reason: - From what I remember there were still some small issues in those patch, but I know people are using them in production with success, so maybe there are already gone or those issues don't exist for their workload. - What I'd really like to see in the tree is vimage or per-jail network virtual interface or something, where one can bind selected IP addresses to. - Currently Bjoern Zeeb is working on those patches and IPv6 for jails, so he is the right person to ask the question. PS. I'm CCing it. --=20 Pawel Jakub Dawidek http://www.wheel.pl pjd@FreeBSD.org http://www.FreeBSD.org FreeBSD committer Am I Evil? Yes, I Am! --s2ZSL+KKDSLx8OML Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (FreeBSD) iD8DBQFE2EEuForvXbEpPzQRAj+eAJwOj9eb82KI6BLg56tXBB0FlEG8BwCg4ygR OgqxFBwNVFxe9s/G6c0Sq7c= =c8d+ -----END PGP SIGNATURE----- --s2ZSL+KKDSLx8OML-- From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 13:20:34 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4F04516A4DF for ; Tue, 8 Aug 2006 13:20:34 +0000 (UTC) (envelope-from andre@freebsd.org) Received: from c00l3r.networx.ch (c00l3r.networx.ch [62.48.2.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id D7BCB43D49 for ; Tue, 8 Aug 2006 13:20:31 +0000 (GMT) (envelope-from andre@freebsd.org) Received: (qmail 56795 invoked from network); 8 Aug 2006 13:10:56 -0000 Received: from c00l3r.networx.ch (HELO [127.0.0.1]) ([62.48.2.2]) (envelope-sender ) by c00l3r.networx.ch (qmail-ldap-1.03) with SMTP for ; 8 Aug 2006 13:10:56 -0000 Message-ID: <44D88FA1.1000108@freebsd.org> Date: Tue, 08 Aug 2006 15:20:33 +0200 From: Andre Oppermann User-Agent: Thunderbird 1.5.0.4 (Windows/20060516) MIME-Version: 1.0 To: Pawel Jakub Dawidek References: <20060628103238.GA815@genius.tao.org.uk> <20060628103949.GJ2005@catpipe.net> <3aaaa3a0606281940k63c77ebfga84a854b2cd4ed84@mail.gmail.com> <20060801084156.GD3440@genius.tao.org.uk> <20060801084053.GE22731@catpipe.net> <20060803110525.GE804@genius.tao.org.uk> <20060804183146.N15526@woozle.rinet.ru> <20060804150057.GP29827@catpipe.net> <20060807171605.GC838@genius.tao.org.uk> <20060808074550.GB1190@garage.freebsd.pl> In-Reply-To: <20060808074550.GB1190@garage.freebsd.pl> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Josef Karthauser , Chris , freebsd-current@freebsd.org, freebsd-net@freebsd.org, Dmitry Morozovsky , bz@FreeBSD.org Subject: Re: Can I pursuade someone to commit this patch? (Re: Multiple IP addresses in a jail.) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 13:20:34 -0000 Pawel Jakub Dawidek wrote: > On Mon, Aug 07, 2006 at 06:16:05PM +0100, Josef Karthauser wrote: >> On Fri, Aug 04, 2006 at 05:00:58PM +0200, Phil Regnauld wrote: >>> Dmitry Morozovsky (marck) writes: >>>> I suppose pinging pjd@ did not work? ;) >>> Good question -- why did Pawel not commit them himself if he could ? :) >>> >> No idea. I sent him an email asking on 28 Jun 2006, but I've not had a >> reply. > > Sorry guys for the delay. > > I answer this very question too many time... :) > > There are few reason: > - From what I remember there were still some small issues in those > patch, but I know people are using them in production with success, so > maybe there are already gone or those issues don't exist for their > workload. > - What I'd really like to see in the tree is vimage or per-jail network > virtual interface or something, where one can bind selected IP > addresses to. I proposed this at BSDCan earlier this year and have found a way to implement it in a pretty clean way, however PHK was against it in general because it would make jails 'too heavyweight'. > - Currently Bjoern Zeeb is working on those patches and IPv6 for jails, > so he is the right person to ask the question. > > PS. I'm CCing it. -- Andre From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 13:28:25 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3C8D716A4EA; Tue, 8 Aug 2006 13:28:25 +0000 (UTC) (envelope-from stb@lassitu.de) Received: from koef.zs64.net (koef.zs64.net [213.238.47.30]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4B88F43D62; Tue, 8 Aug 2006 13:28:19 +0000 (GMT) (envelope-from stb@lassitu.de) Received: (from stb@koef.zs64.net) (authenticated) by koef.zs64.net (8.13.7/8.13.7) with ESMTP id k78DRvVe006207 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NO); Tue, 8 Aug 2006 15:28:07 +0200 (CEST) (envelope-from stb@lassitu.de) In-Reply-To: <44D823E6.1000900@elischer.org> References: <200608051358.k75DwpYr070713@repoman.freebsd.org> <20060807092251.GS96644@FreeBSD.org> <44D774E9.4010309@elischer.org> <44D80E8D.7010709@yandex.ru> <44D823E6.1000900@elischer.org> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <1FC5A721-62C6-4052-B870-7DB906F1BEB3@lassitu.de> Content-Transfer-Encoding: 7bit From: Stefan Bethke Date: Tue, 8 Aug 2006 15:27:55 +0200 To: Julian Elischer X-Mailer: Apple Mail (2.752.2) Cc: Stefan Farfeleder , "Andrey V. Elsukov" , net@freebsd.org Subject: Re: cvs commit: src/sbin/ipfw ipfw2.c X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 13:28:25 -0000 Am 08.08.2006 um 07:40 schrieb Julian Elischer: > Each dynamic entry has an extra linkage to allow it to be linked > onto the appropriate slot. whenever you use an entry you take it out > of where-ever it is and put it into it's new slot X seconds into > the future. Wouldn't that be essentially a per-packet operation? You'd have to at least check whether the rule is still in the appropriate slot each time you reset the timer. Stefan -- Stefan Bethke Fon +49 170 346 0140 From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 16:24:31 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E747B16A4E1; Tue, 8 Aug 2006 16:24:31 +0000 (UTC) (envelope-from rizzo@icir.org) Received: from xorpc.icir.org (xorpc.icir.org [192.150.187.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6AE2C43D5C; Tue, 8 Aug 2006 16:24:31 +0000 (GMT) (envelope-from rizzo@icir.org) Received: from xorpc.icir.org (localhost [127.0.0.1]) by xorpc.icir.org (8.12.11/8.12.11) with ESMTP id k78GORns025575; Tue, 8 Aug 2006 09:24:27 -0700 (PDT) (envelope-from rizzo@xorpc.icir.org) Received: (from rizzo@localhost) by xorpc.icir.org (8.12.11/8.12.3/Submit) id k78GOQXN025574; Tue, 8 Aug 2006 09:24:26 -0700 (PDT) (envelope-from rizzo) Date: Tue, 8 Aug 2006 09:24:26 -0700 From: Luigi Rizzo To: Julian Elischer Message-ID: <20060808092426.B24892@xorpc.icir.org> References: <200608051358.k75DwpYr070713@repoman.freebsd.org> <20060807092251.GS96644@FreeBSD.org> <44D774E9.4010309@elischer.org> <44D80E8D.7010709@yandex.ru> <44D823E6.1000900@elischer.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <44D823E6.1000900@elischer.org>; from julian@elischer.org on Mon, Aug 07, 2006 at 10:40:54PM -0700 Cc: Stefan Farfeleder , "Andrey V. Elsukov" , net@freebsd.org Subject: Re: cvs commit: src/sbin/ipfw ipfw2.c X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 16:24:32 -0000 On Mon, Aug 07, 2006 at 10:40:54PM -0700, Julian Elischer wrote: > Andrey V. Elsukov wrote: > > > Julian Elischer wrote: > > > >> great.. I have been in ipfw(2) the last week and have some sugestions > >> for > >> increasing its efficiency.. especially the code that times out > >> dynamic rules. > > > > Can you explain your suggestions in detail? > > > I sent the following to luigi: > I repeat it here.. > > ------------ start comment to Luigi -------------- > > I haven't coded it yet but we run with maybe 50,000 dynamic rules at a > time. (hopefully a lot more, maybe 200,000 in the near future) > We need to simplify the code that times out the rules so that it doesn't > have to > scan through ALL the dynamic rules every clocktick. agreed. On the other hand, i think that a simpler solution could be used. Consider that the granularity of keepalives and expire can be much coarser than 1 tick - basically there are no adverse side effects if you round it up to 500-1000ms. So i'd just keep everything as it is now, except that at every call ipfw_tick() will only scan curr_dyn_buckets/HZ lists. This should reduce the load by 2-3 orders of magnitude and is trivial to implement. cheers luigi > Basically I was thinking of implementing a timing wheel representing > the next "600" seconds or so. > (600 slots). "now" moves around the wheel. > (The size of the wheel is the size of the largest lifetime value.) > (maybe with a backup wheel at 600 seconds per slot or something) > > Each dynamic entry has an extra linkage to allow it to be linked > onto the appropriate slot. whenever you use an entry you take it out > of where-ever it is and put it into it's new slot X seconds into the > future. > > At each tick you take all the entries that have reached "now" > and do whatever needs t be done on only those entries. > thus at each tick you only have a small amount of work to > do instead fo looking at all 50,000 entries. > > > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 21:27:01 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F41CA16A4DA; Tue, 8 Aug 2006 21:27:00 +0000 (UTC) (envelope-from dylan@dylex.dylex.net) Received: from dylex.dylex.net (dsl092-008-121.sfo1.dsl.speakeasy.net [66.92.8.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4FFD343D4C; Tue, 8 Aug 2006 21:26:59 +0000 (GMT) (envelope-from dylan@dylex.dylex.net) Received: from dylex.dylex.net (localhost.dylex.net [127.0.0.1]) by dylex.dylex.net (8.13.6/8.13.6) with ESMTP id k78LQvdC029203; Tue, 8 Aug 2006 14:26:58 -0700 (PDT) (envelope-from dylan@dylex.dylex.net) Received: (from dylan@localhost) by dylex.dylex.net (8.13.6/8.13.6/Submit) id k78LQv7i029202; Tue, 8 Aug 2006 17:26:57 -0400 (EDT) (envelope-from dylan) Date: Tue, 8 Aug 2006 17:26:57 -0400 From: Dylan Alex Simon To: Doug Barton Message-ID: <20060808212657.GA29190@dylex.dylex.net> References: <20060805153714.GA22424@dylex.dylex.net> <44D4E939.3060607@FreeBSD.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <44D4E939.3060607@FreeBSD.org> Cc: freebsd-net@FreeBSD.org Subject: Re: wpa_supplicant on ndis cannot associate X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 21:27:01 -0000 > Are you by any chance not broadcasting the ssid on the WAP? I had problems > similar to what you described when I turned that feature off, but when I > turned it back on (so the WAP was broadcasting its ssid again) everything > worked fine with wpa-psk and TKIP, and -D ndis. (I could not get any > "higher" level of WPA working, but that's another story.) The SSID is being broadcast (and shows up on the scan). Actually, trying in a controlled setup, it does work when I use RSN/WPA-PSK/TKIP with -D ndis. However, it does not work with an open AP (no encryption/authentication). wpa_supplicant seems to say that it will work with open networks if so configured (key_mgmt=NONE). Is this not the case? I roam between a few open networks that use a separate vpn layer for security, and I'd really like to have it automatically figure out which to use (and then setup the right vpn too). I considered using dhclient.conf media settings, but it sounds like that won't work either. :-Dylan From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 21:31:43 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1721316A4DE for ; Tue, 8 Aug 2006 21:31:43 +0000 (UTC) (envelope-from dougb@FreeBSD.org) Received: from mail2.fluidhosting.com (mx23.fluidhosting.com [204.14.89.6]) by mx1.FreeBSD.org (Postfix) with SMTP id 6D55443D58 for ; Tue, 8 Aug 2006 21:31:42 +0000 (GMT) (envelope-from dougb@FreeBSD.org) Received: (qmail 6303 invoked by uid 399); 8 Aug 2006 21:31:41 -0000 Received: from localhost (HELO ?192.168.0.3?) (dougb@dougbarton.us@127.0.0.1) by localhost with SMTP; 8 Aug 2006 21:31:41 -0000 Message-ID: <44D902B9.1010404@FreeBSD.org> Date: Tue, 08 Aug 2006 14:31:37 -0700 From: Doug Barton Organization: http://www.FreeBSD.org/ User-Agent: Thunderbird 1.5.0.5 (X11/20060729) MIME-Version: 1.0 To: Dylan Alex Simon References: <20060805153714.GA22424@dylex.dylex.net> <44D4E939.3060607@FreeBSD.org> <20060808212657.GA29190@dylex.dylex.net> In-Reply-To: <20060808212657.GA29190@dylex.dylex.net> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-net@FreeBSD.org Subject: Re: wpa_supplicant on ndis cannot associate X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 21:31:43 -0000 Dylan Alex Simon wrote: >> Are you by any chance not broadcasting the ssid on the WAP? I had problems >> similar to what you described when I turned that feature off, but when I >> turned it back on (so the WAP was broadcasting its ssid again) everything >> worked fine with wpa-psk and TKIP, and -D ndis. (I could not get any >> "higher" level of WPA working, but that's another story.) > > The SSID is being broadcast (and shows up on the scan). Actually, trying in a > controlled setup, it does work when I use RSN/WPA-PSK/TKIP with -D ndis. > However, it does not work with an open AP (no encryption/authentication). > wpa_supplicant seems to say that it will work with open networks if so > configured (key_mgmt=NONE). Is this not the case? It has not been the case in my experience. I have not been successful in getting wpa_supplicant to either set plain old WEP keys, or attach to an unencrypted network. Doug -- This .signature sanitized for your protection From owner-freebsd-net@FreeBSD.ORG Tue Aug 8 21:57:09 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9A7C516A4DF; Tue, 8 Aug 2006 21:57:09 +0000 (UTC) (envelope-from brooks@lor.one-eyed-alien.net) Received: from sccmmhc91.asp.att.net (sccmmhc91.asp.att.net [204.127.203.211]) by mx1.FreeBSD.org (Postfix) with ESMTP id 35E4743D72; Tue, 8 Aug 2006 21:56:46 +0000 (GMT) (envelope-from brooks@lor.one-eyed-alien.net) Received: from lor.one-eyed-alien.net ([12.207.12.9]) by sccmmhc91.asp.att.net (sccmmhc91) with ESMTP id <20060808215644m910085gvle>; Tue, 8 Aug 2006 21:56:45 +0000 Received: from lor.one-eyed-alien.net (localhost [127.0.0.1]) by lor.one-eyed-alien.net (8.13.6/8.13.6) with ESMTP id k78LugSw099441; Tue, 8 Aug 2006 16:56:42 -0500 (CDT) (envelope-from brooks@lor.one-eyed-alien.net) Received: (from brooks@localhost) by lor.one-eyed-alien.net (8.13.6/8.13.6/Submit) id k78LuflE099440; Tue, 8 Aug 2006 16:56:41 -0500 (CDT) (envelope-from brooks) Date: Tue, 8 Aug 2006 16:56:41 -0500 From: Brooks Davis To: Doug Barton Message-ID: <20060808215641.GA99402@lor.one-eyed-alien.net> References: <20060805153714.GA22424@dylex.dylex.net> <44D4E939.3060607@FreeBSD.org> <20060808212657.GA29190@dylex.dylex.net> <44D902B9.1010404@FreeBSD.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="FCuugMFkClbJLl1L" Content-Disposition: inline In-Reply-To: <44D902B9.1010404@FreeBSD.org> User-Agent: Mutt/1.5.11 Cc: freebsd-net@freebsd.org, Dylan Alex Simon Subject: Re: wpa_supplicant on ndis cannot associate X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Aug 2006 21:57:09 -0000 --FCuugMFkClbJLl1L Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Aug 08, 2006 at 02:31:37PM -0700, Doug Barton wrote: > Dylan Alex Simon wrote: > >> Are you by any chance not broadcasting the ssid on the WAP? I had prob= lems > >> similar to what you described when I turned that feature off, but when= I > >> turned it back on (so the WAP was broadcasting its ssid again) everyth= ing > >> worked fine with wpa-psk and TKIP, and -D ndis. (I could not get any > >> "higher" level of WPA working, but that's another story.) > >=20 > > The SSID is being broadcast (and shows up on the scan). Actually, tryi= ng in a > > controlled setup, it does work when I use RSN/WPA-PSK/TKIP with -D ndis. > > However, it does not work with an open AP (no encryption/authentication= ). > > wpa_supplicant seems to say that it will work with open networks if so > > configured (key_mgmt=3DNONE). Is this not the case? >=20 > It has not been the case in my experience. I have not been successful in > getting wpa_supplicant to either set plain old WEP keys, or attach to an > unencrypted network. It works fine for me with iwi and ath devices. The code is almost entierly different in the ndis case though. -- Brooks --FCuugMFkClbJLl1L Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2 (FreeBSD) iD8DBQFE2QiZXY6L6fI4GtQRAg+yAJ4+i42WUdBTCVObZo0ibHbRuCZCAgCeKz8/ uJWagMX5xk8u2TeO7jfYax8= =1w5Z -----END PGP SIGNATURE----- --FCuugMFkClbJLl1L-- From owner-freebsd-net@FreeBSD.ORG Wed Aug 9 09:38:16 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BE40016A4DA for ; Wed, 9 Aug 2006 09:38:16 +0000 (UTC) (envelope-from uwe@laverenz.de) Received: from natlemon.rzone.de (natlemon.rzone.de [81.169.145.170]) by mx1.FreeBSD.org (Postfix) with ESMTP id F38A043D4C for ; Wed, 9 Aug 2006 09:38:15 +0000 (GMT) (envelope-from uwe@laverenz.de) Received: from athena.laverenz.de (p5480EF76.dip.t-dialin.net [84.128.239.118]) by post.webmailer.de (8.13.6/8.13.6) with ESMTP id k799cCfv017257 for ; Wed, 9 Aug 2006 11:38:12 +0200 (MEST) Received: from localhost (localhost.localdomain [127.0.0.1]) by athena.laverenz.de (Postfix) with ESMTP id B0906E3D805D for ; Wed, 9 Aug 2006 11:38:11 +0200 (CEST) Received: from athena.laverenz.de ([127.0.0.1]) by localhost (athena [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 23110-06 for ; Wed, 9 Aug 2006 11:38:11 +0200 (CEST) Received: by athena.laverenz.de (Postfix, from userid 2000) id B2CA4E3D805C; Wed, 9 Aug 2006 11:38:10 +0200 (CEST) Date: Wed, 9 Aug 2006 11:38:10 +0200 From: Uwe Laverenz To: freebsd-net@freebsd.org Message-ID: <20060809093810.GA22798@laverenz.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Organization: private site Sender: uwe@laverenz.de User-Agent: Mutt/1.5.9i X-Virus-Scanned: by amavisd-new-20030616-p10 (Debian) at laverenz.de Subject: iwi: firmware error X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Aug 2006 09:38:16 -0000 Hi all, I've installed RELENG_6 on a Thinkpad R51 and would like to use the built-in wireless card with wpa_supplicant. Everything works as expected but there is one problem I can't solve on my own: the iwi-driver complains about problems with the firmware, especially when there is wireless traffic: iwi0: firmware error The device goes down immediately and sometimes comes up again after a while. The system runs RELENG_6 as of last sunday, the firmware is 3.0 from /usr/ports/net/iwi-firmware-kmod. I have a similar setup on a T41 with ath0 which runs quite well. My questions: - Is this a known problem with iwi? - What can I do to debug and/or solve this problem? - Should I file a PR? Thank you! Uwe From owner-freebsd-net@FreeBSD.ORG Wed Aug 9 11:36:07 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5376A16A4DA for ; Wed, 9 Aug 2006 11:36:07 +0000 (UTC) (envelope-from roshind@mail.ru) Received: from f49.mail.ru (f49.mail.ru [194.67.57.85]) by mx1.FreeBSD.org (Postfix) with ESMTP id E20D743D4C for ; Wed, 9 Aug 2006 11:36:06 +0000 (GMT) (envelope-from roshind@mail.ru) Received: from mail by f49.mail.ru with local id 1GAmM1-000I0z-00 for freebsd-net@freebsd.org; Wed, 09 Aug 2006 15:36:05 +0400 Received: from [81.94.128.242] by win.mail.ru with HTTP; Wed, 09 Aug 2006 15:36:05 +0400 From: Dima Roshin To: freebsd-net@freebsd.org Mime-Version: 1.0 X-Mailer: mPOP Web-Mail 2.19 X-Originating-IP: [81.94.128.242] Date: Wed, 09 Aug 2006 15:36:05 +0400 Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: 8bit Message-Id: Subject: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Dima Roshin List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Aug 2006 11:36:07 -0000 Greeting colleagues. I've got two DL-360(pciX bus) servers, with BCM5704 NetXtreme Dual Gigabit Adapters(bge). The Uname is 6.1-RELEASE-p3. The bge interfaces of the both servers are connected with each other with a cat6 patchcord. Here are my settings: kernel config: options DEVICE_POLLING options HZ=1000 # sysctl.conf: kern.polling.enable=1 net.inet.ip.intr_queue_maxlen=5000 kern.ipc.maxsockbuf=8388608 net.inet.tcp.sendspace=3217968 net.inet.tcp.recvspace=3217968 net.inet.tcp.rfc1323=1 bge1: flags=8843 mtu 9000 options=5b inet 192.168.0.1 netmask 0xffffff00 broadcast 192.168.0.255 ether 00:17:a4:3a:e1:81 media: Ethernet autoselect (1000baseTX ) status: active (note mtu 9000) and here are tests results: netperf: TCP STREAM TEST to 192.168.0.1 Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 6217968 6217968 6217968 10.22 320.04 UDP UNIDIRECTIONAL SEND TEST to 192.168.0.1 Socket Message Elapsed Messages Size Size Time Okay Errors Throughput bytes bytes secs # # 10^6bits/sec 9216 9216 10.00 118851 1724281 876.20 41600 10.00 0 0.00] iperf: gate2# iperf -s -N ------------------------------------------------------------ Server listening on TCP port 5001 TCP window size: 3.07 MByte (default) ------------------------------------------------------------ [ 4] local 192.168.0.2 port 5001 connected with 192.168.0.1 port 52597 [ 4] 0.0-10.1 sec 384 MBytes 319 Mbits/sec Also I can say, that I've managed to achieve about 500mbit.s by tuning tcp window with -w key in iperf. How can we explain such a low tcp performance? What else is to tune? Is there somebody who achieved gigabit speed with tcp on freebsd? Thanks. From owner-freebsd-net@FreeBSD.ORG Wed Aug 9 12:12:06 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 73F9816A4DF for ; Wed, 9 Aug 2006 12:12:06 +0000 (UTC) (envelope-from roshind@mail.ru) Received: from f60.mail.ru (f60.mail.ru [194.67.57.94]) by mx1.FreeBSD.org (Postfix) with ESMTP id F258943D6B for ; Wed, 9 Aug 2006 12:12:05 +0000 (GMT) (envelope-from roshind@mail.ru) Received: from mail by f60.mail.ru with local id 1GAmuq-000CR8-00 for freebsd-net@freebsd.org; Wed, 09 Aug 2006 16:12:04 +0400 Received: from [81.94.128.242] by win.mail.ru with HTTP; Wed, 09 Aug 2006 16:12:04 +0400 From: Dima Roshin To: freebsd-net@freebsd.org Mime-Version: 1.0 X-Mailer: mPOP Web-Mail 2.19 X-Originating-IP: [81.94.128.242] Date: Wed, 09 Aug 2006 16:12:04 +0400 In-Reply-To: =?koi8-r?Q?<44D9CCEA.2050103=40ide.resurscentrum.se>?= Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: 8bit Message-Id: Subject: Re[2]: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Dima Roshin List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Aug 2006 12:12:06 -0000 Thanks Jon, I did it on both sides, thats much better now: gate1# sysctl kern.polling.idle_poll=1 kern.polling.idle_poll: 0 -> 1 gate1# sysctl net.inet.ip.fastforwarding net.inet.ip.fastforwarding: 0 gate1# sysctl net.inet.ip.fastforwarding=1 net.inet.ip.fastforwarding: 0 -> 1 gate1# iperf -c 192.168.0.2 -N -w 196000 ------------------------------------------------------------ Client connecting to 192.168.0.2, TCP port 5001 TCP window size: 192 KByte (WARNING: requested 191 KByte) ------------------------------------------------------------ [ 3] local 192.168.0.1 port 63941 connected with 192.168.0.2 port 5001 [ 3] 0.0-10.0 sec 762 MBytes 639 Mbits/sec But there is still some bottleneck, and I can't understand where. -----Original Message----- From: Jon Otterholm To: Dima Roshin Date: Wed, 09 Aug 2006 13:54:18 +0200 Subject: Re: Gigabit ethernet questions? > > Dima Roshin wrote: > > Greeting colleagues. I've got two DL-360(pciX bus) servers, with BCM5704 NetXtreme Dual Gigabit Adapters(bge). The Uname is 6.1-RELEASE-p3. The bge interfaces of the both servers are connected with each other with a cat6 patchcord. > > Here are my settings: > > kernel config: > > options DEVICE_POLLING > > options HZ=1000 # > > > > sysctl.conf: > > kern.polling.enable=1 > > net.inet.ip.intr_queue_maxlen=5000 > > kern.ipc.maxsockbuf=8388608 > > net.inet.tcp.sendspace=3217968 > > net.inet.tcp.recvspace=3217968 > > net.inet.tcp.rfc1323=1 > > > > bge1: flags=8843 mtu 9000 > > options=5b > > inet 192.168.0.1 netmask 0xffffff00 broadcast 192.168.0.255 > > ether 00:17:a4:3a:e1:81 > > media: Ethernet autoselect (1000baseTX ) > > status: active > > (note mtu 9000) > > > > and here are tests results: > > > > netperf: > > > > TCP STREAM TEST to 192.168.0.1 > > Recv Send Send > > Socket Socket Message Elapsed > > Size Size Size Time Throughput > > bytes bytes bytes secs. 10^6bits/sec > > > > 6217968 6217968 6217968 10.22 320.04 > > > > UDP UNIDIRECTIONAL SEND TEST to 192.168.0.1 > > Socket Message Elapsed Messages > > Size Size Time Okay Errors Throughput > > bytes bytes secs # # 10^6bits/sec > > > > 9216 9216 10.00 118851 1724281 876.20 > > 41600 10.00 0 0.00] > > > > > > > > iperf: > > gate2# iperf -s -N > > ------------------------------------------------------------ > > Server listening on TCP port 5001 > > TCP window size: 3.07 MByte (default) > > ------------------------------------------------------------ > > [ 4] local 192.168.0.2 port 5001 connected with 192.168.0.1 port 52597 > > [ 4] 0.0-10.1 sec 384 MBytes 319 Mbits/sec > > > > Also I can say, that I've managed to achieve about 500mbit.s by tuning tcp window with -w key in iperf. > > > > How can we explain such a low tcp performance? What else is to tune? Is there somebody who achieved gigabit speed with tcp on freebsd? > > > > Thanks. > > > > > > > > _______________________________________________ > > freebsd-net@freebsd.org mailing list > > http://lists.freebsd.org/mailman/listinfo/freebsd-net > > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > > > You also need kern.polling.idle_poll=1 and maybe > net.inet.ip.fastforwarding=1 though I never noticed any difference with > that one enabled. I got about 840Mbit/s routed through a dell 1850 > (EMT64 running AMD64) with em-interfaces (I only used one physical IF > though with 2 VLAN-if). > > From owner-freebsd-net@FreeBSD.ORG Wed Aug 9 17:05:03 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EC63516A4DF for ; Wed, 9 Aug 2006 17:05:03 +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 9D68643D53 for ; Wed, 9 Aug 2006 17:05:03 +0000 (GMT) (envelope-from sam@errno.com) Received: from [10.0.0.248] (trouble.errno.com [10.0.0.248]) (authenticated bits=0) by ebb.errno.com (8.13.6/8.12.6) with ESMTP id k79H521q075087 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 9 Aug 2006 10:05:03 -0700 (PDT) (envelope-from sam@errno.com) Message-ID: <44DA15BE.4070402@errno.com> Date: Wed, 09 Aug 2006 10:05:02 -0700 From: Sam Leffler User-Agent: Thunderbird 1.5.0.4 (X11/20060724) MIME-Version: 1.0 To: Uwe Laverenz References: <20060809093810.GA22798@laverenz.de> In-Reply-To: <20060809093810.GA22798@laverenz.de> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: freebsd-net@freebsd.org Subject: Re: iwi: firmware error X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 09 Aug 2006 17:05:04 -0000 Uwe Laverenz wrote: > Hi all, > > I've installed RELENG_6 on a Thinkpad R51 and would like to use the > built-in wireless card with wpa_supplicant. Everything works as expected > but there is one problem I can't solve on my own: the iwi-driver > complains about problems with the firmware, especially when there is > wireless traffic: > > iwi0: firmware error > > The device goes down immediately and sometimes comes up again after a > while. The system runs RELENG_6 as of last sunday, the firmware is 3.0 > from /usr/ports/net/iwi-firmware-kmod. > > I have a similar setup on a T41 with ath0 which runs quite well. > > My questions: > > - Is this a known problem with iwi? > > - What can I do to debug and/or solve this problem? > > - Should I file a PR? If your card is reset+usable after the error then this is a known problem. If you find things unusable then please collect some debug msgs from the driver by setting debug.iwi to 1 and file a PR. Sam From owner-freebsd-net@FreeBSD.ORG Thu Aug 10 05:57:06 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 92B8416A4DF for ; Thu, 10 Aug 2006 05:57:06 +0000 (UTC) (envelope-from mv@thebeastie.org) Received: from p4.roq.com (ns1.ecoms.com [207.44.130.137]) by mx1.FreeBSD.org (Postfix) with ESMTP id 28CF443D46 for ; Thu, 10 Aug 2006 05:57:06 +0000 (GMT) (envelope-from mv@thebeastie.org) Received: from p4.roq.com (localhost.roq.com [127.0.0.1]) by p4.roq.com (Postfix) with ESMTP id C47A94CE86 for ; Thu, 10 Aug 2006 05:57:49 +0000 (GMT) Received: from vaulte.jumbuck.com (ppp166-27.static.internode.on.net [150.101.166.27]) by p4.roq.com (Postfix) with ESMTP id D6C1B4CE85 for ; Thu, 10 Aug 2006 05:57:48 +0000 (GMT) Received: from vaulte.jumbuck.com (localhost [127.0.0.1]) by vaulte.jumbuck.com (Postfix) with ESMTP id 7B5C98A069; Thu, 10 Aug 2006 15:57:03 +1000 (EST) Received: from [192.168.46.102] (unknown [192.168.46.250]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by vaulte.jumbuck.com (Postfix) with ESMTP id 76DCB8A037; Thu, 10 Aug 2006 15:57:03 +1000 (EST) Message-ID: <44DACAAF.5020306@thebeastie.org> Date: Thu, 10 Aug 2006 15:57:03 +1000 From: Michael Vince User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.7.13) Gecko/20060727 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Dima Roshin References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV using ClamSMTP X-Virus-Scanned: ClamAV using ClamSMTP Cc: freebsd-net@freebsd.org Subject: Re: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 10 Aug 2006 05:57:06 -0000 JICUDN, I have been using nc,dd and systat to check TCP performance on my servers, the good thing about it is it requires little setup and gives results fast. For example on host A start the nc server. nc -4kl 3000 > /dev/null Then start another one on hostb sending data via nc from /dev/zero cat /dev/zero | dd bs=1m | nc hosta 3000 ^C0+226041 records in 0+226040 records out 14813757440 bytes transferred in 246.184967 secs (60173282 bytes/sec) You can take out the dd and just use systat -if depending on what you like. Mike Dima Roshin wrote: >Thanks Jon, I did it on both sides, thats much better now: > >gate1# sysctl kern.polling.idle_poll=1 >kern.polling.idle_poll: 0 -> 1 >gate1# sysctl net.inet.ip.fastforwarding >net.inet.ip.fastforwarding: 0 >gate1# sysctl net.inet.ip.fastforwarding=1 >net.inet.ip.fastforwarding: 0 -> 1 >gate1# iperf -c 192.168.0.2 -N -w 196000 >------------------------------------------------------------ >Client connecting to 192.168.0.2, TCP port 5001 >TCP window size: 192 KByte (WARNING: requested 191 KByte) >------------------------------------------------------------ >[ 3] local 192.168.0.1 port 63941 connected with 192.168.0.2 port 5001 >[ 3] 0.0-10.0 sec 762 MBytes 639 Mbits/sec > >But there is still some bottleneck, and I can't understand where. > > > >-----Original Message----- >From: Jon Otterholm >To: Dima Roshin >Date: Wed, 09 Aug 2006 13:54:18 +0200 >Subject: Re: Gigabit ethernet questions? > > > >>Dima Roshin wrote: >> >> >>> Greeting colleagues. I've got two DL-360(pciX bus) servers, with BCM5704 NetXtreme Dual Gigabit Adapters(bge). The Uname is 6.1-RELEASE-p3. The bge interfaces of the both servers are connected with each other with a cat6 patchcord. >>> Here are my settings: >>>kernel config: >>>options DEVICE_POLLING >>>options HZ=1000 # >>> >>>sysctl.conf: >>>kern.polling.enable=1 >>>net.inet.ip.intr_queue_maxlen=5000 >>>kern.ipc.maxsockbuf=8388608 >>>net.inet.tcp.sendspace=3217968 >>>net.inet.tcp.recvspace=3217968 >>>net.inet.tcp.rfc1323=1 >>> >>>bge1: flags=8843 mtu 9000 >>> options=5b >>> inet 192.168.0.1 netmask 0xffffff00 broadcast 192.168.0.255 >>> ether 00:17:a4:3a:e1:81 >>> media: Ethernet autoselect (1000baseTX ) >>> status: active >>>(note mtu 9000) >>> >>>and here are tests results: >>> >>>netperf: >>> >>>TCP STREAM TEST to 192.168.0.1 >>>Recv Send Send >>>Socket Socket Message Elapsed >>>Size Size Size Time Throughput >>>bytes bytes bytes secs. 10^6bits/sec >>> >>>6217968 6217968 6217968 10.22 320.04 >>> >>>UDP UNIDIRECTIONAL SEND TEST to 192.168.0.1 >>>Socket Message Elapsed Messages >>>Size Size Time Okay Errors Throughput >>>bytes bytes secs # # 10^6bits/sec >>> >>> 9216 9216 10.00 118851 1724281 876.20 >>>41600 10.00 0 0.00] >>> >>> >>> >>>iperf: >>>gate2# iperf -s -N >>>------------------------------------------------------------ >>>Server listening on TCP port 5001 >>>TCP window size: 3.07 MByte (default) >>>------------------------------------------------------------ >>>[ 4] local 192.168.0.2 port 5001 connected with 192.168.0.1 port 52597 >>>[ 4] 0.0-10.1 sec 384 MBytes 319 Mbits/sec >>> >>>Also I can say, that I've managed to achieve about 500mbit.s by tuning tcp window with -w key in iperf. >>> >>>How can we explain such a low tcp performance? What else is to tune? Is there somebody who achieved gigabit speed with tcp on freebsd? >>> >>>Thanks. >>> >>> >>> >>>_______________________________________________ >>>freebsd-net@freebsd.org mailing list >>>http://lists.freebsd.org/mailman/listinfo/freebsd-net >>>To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" >>> >>> >>> >>You also need kern.polling.idle_poll=1 and maybe >>net.inet.ip.fastforwarding=1 though I never noticed any difference with >>that one enabled. I got about 840Mbit/s routed through a dell 1850 >>(EMT64 running AMD64) with em-interfaces (I only used one physical IF >>though with 2 VLAN-if). >> >> >> >> >_______________________________________________ >freebsd-net@freebsd.org mailing list >http://lists.freebsd.org/mailman/listinfo/freebsd-net >To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > > From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 02:43:42 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1124316A4E0 for ; Fri, 11 Aug 2006 02:43:42 +0000 (UTC) (envelope-from brett@lariat.net) Received: from lariat.net (lariat.net [65.122.236.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3D2EC43D53 for ; Fri, 11 Aug 2006 02:43:38 +0000 (GMT) (envelope-from brett@lariat.net) Received: from Anne (IDENT:ppp1000.lariat.net@lariat.net [65.122.236.2]) by lariat.net (8.9.3/8.9.3) with ESMTP id UAA00486 for ; Thu, 10 Aug 2006 20:43:34 -0600 (MDT) X-message-flag: Warning! Use of Microsoft Outlook renders your system susceptible to Internet worms. Message-Id: <7.0.1.0.2.20060810201735.067258b0@lariat.net> X-Mailer: QUALCOMM Windows Eudora Version 7.0.1.0 Date: Thu, 10 Aug 2006 20:43:28 -0600 To: net@freebsd.org From: Brett Glass Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: Subject: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 02:43:42 -0000 I've been asked to work on a PPTP server for a large company which has up to 100 users tunneling in at once. They currently have a FreeBSD machine set up to use FreeBSD's userland PPP together with the PoPToP pptp daemon. (They have a hacked version of PoPToP which allows different instances of the daemon to invoke PPP with different labels, letting them set up for different sorts of connections on different IPs.) But as the number of users has grown, PoPToP has started to act strangely. It's giving them odd errors, saying that it's out of buffer space and such. I think it's stretched to the limit. I'm looking at building a VPN server for them using FreeBSD and mpd. But I've never used mpd before, primarily because it seems to work in mysterious ways. Its configuration is a bit odd, and it lacks some of the features of userland PPP. For example, you must put a separate entry for each incoming connection (or "link") in the configuration file. But since you don't know which incoming user is going to get which connection, you have to create dozens and dozens of identical links -- a tremendous waste of space! (Userland PPP lets you specify a single label to which all PPTP connections must go and creates "tun" devices on the fly as needed for the link.) What's more, you have to allocate Netgraph nodes for all of them in advance. You also do not have the ability to change the configuration for different users, because you don't know which user will get which of the links -- and the mpd.secret file, unlike the ppp.secret file, doesn't let you jump to a label once you find out the user's identity. The company wants to throttle bandwidth by user, so I need to be able to distinguish between users to do this. This company wants some users to have unroutable addresses that can't escape their network without NAT, and others to have routable addresses. I'm experimenting with what happens if you create two sets of links which "listen" on different IP addresses, but this will make the configuration file yet larger. Are there any mpd gurus out there who can give me a quick opinion as to whether it's feasible to use mpd for this application -- and spend some consulting time telling me how so that I don't have to flail around experimenting? If I can't use mpd and PoPToP isn't working, what other options are there for a good PPTP server? --Brett Glass From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 03:00:19 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B0A3416A4DE for ; Fri, 11 Aug 2006 03:00:19 +0000 (UTC) (envelope-from ganbold@micom.mng.net) Received: from publicd.ub.mng.net (publicd.ub.mng.net [202.179.0.88]) by mx1.FreeBSD.org (Postfix) with ESMTP id C200043D45 for ; Fri, 11 Aug 2006 03:00:18 +0000 (GMT) (envelope-from ganbold@micom.mng.net) Received: from [202.179.0.164] (helo=[192.168.0.18]) by publicd.ub.mng.net with esmtpa (Exim 4.61 (FreeBSD)) (envelope-from ) id 1GBNFs-000Dqn-D1; Fri, 11 Aug 2006 12:00:12 +0900 Message-ID: <44DBF2BB.5080202@micom.mng.net> Date: Fri, 11 Aug 2006 12:00:11 +0900 From: Ganbold User-Agent: Thunderbird 1.5.0.4 (X11/20060612) MIME-Version: 1.0 To: Brett Glass References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> In-Reply-To: <7.0.1.0.2.20060810201735.067258b0@lariat.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: net@freebsd.org Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 03:00:19 -0000 Brett Glass wrote: > I've been asked to work on a PPTP server for a large company which has > up to 100 users tunneling in at once. They currently have a FreeBSD > machine set up to use FreeBSD's userland PPP together with the PoPToP > pptp daemon. (They have a hacked version of PoPToP which allows > different instances of the daemon to invoke PPP with different labels, > letting them set up for different sorts of connections on different > IPs.) But as the number of users has grown, PoPToP has started to act > strangely. It's giving them odd errors, saying that it's out of buffer > space and such. I think it's stretched to the limit. > > I'm looking at building a VPN server for them using FreeBSD and mpd. > But I've never used mpd before, primarily because it seems to work in > mysterious ways. Its configuration is a bit odd, and it lacks some of > the features of userland PPP. For example, you must put a separate > entry for each incoming connection (or "link") in the configuration > file. But since you don't know which incoming user is going to get > which connection, you have to create dozens and dozens of identical > links -- a tremendous waste of space! (Userland PPP lets you specify a > single label to which all PPTP connections must go and creates "tun" > devices on the fly as needed for the link.) It will be much easier if you can write some script to generate mpd config files. I'm generating config files such way for PPPoE. > What's more, you have to allocate Netgraph nodes for all of them in > advance. You also do not have the ability to change the configuration > for different users, because you don't know which user will get which > of the links -- and the mpd.secret file, unlike the ppp.secret file, > doesn't let you jump to a label once you find out the user's identity. > The company wants to throttle bandwidth by user, so I need to be able > to distinguish between users to do this. Did you try Radius? > > This company wants some users to have unroutable addresses that can't > escape their network without NAT, and others to have routable > addresses. I'm experimenting with what happens if you create two sets > of links which "listen" on different IP addresses, but this will make > the configuration file yet larger. > > Are there any mpd gurus out there who can give me a quick opinion as > to whether it's feasible to use mpd for this application -- and spend > some consulting time telling me how so that I don't have to flail > around experimenting? If I can't use mpd and PoPToP isn't working, > what other options are there for a good PPTP server? > > --Brett Glass > > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > > > From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 03:32:49 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 93F3016A4DA for ; Fri, 11 Aug 2006 03:32:49 +0000 (UTC) (envelope-from brett@lariat.net) Received: from lariat.net (lariat.net [65.122.236.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0A8C443D46 for ; Fri, 11 Aug 2006 03:32:48 +0000 (GMT) (envelope-from brett@lariat.net) Received: from Anne (IDENT:ppp1000.lariat.net@lariat.net [65.122.236.2]) by lariat.net (8.9.3/8.9.3) with ESMTP id VAA01022; Thu, 10 Aug 2006 21:32:27 -0600 (MDT) X-message-flag: Warning! Use of Microsoft Outlook renders your system susceptible to Internet worms. Message-Id: <7.0.1.0.2.20060810212047.073f0078@lariat.net> X-Mailer: QUALCOMM Windows Eudora Version 7.0.1.0 Date: Thu, 10 Aug 2006 21:32:22 -0600 To: Ganbold From: Brett Glass In-Reply-To: <44DBF2BB.5080202@micom.mng.net> References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> <44DBF2BB.5080202@micom.mng.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: net@freebsd.org Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 03:32:49 -0000 At 09:00 PM 8/10/2006, Ganbold wrote: >It will be much easier if you can write some script to generate >mpd config files. I'm generating config files such way for PPPoE. Is there a way to avoid having to generate them at all? It seems to me that it would be very easy for mpd to create netgraph nodes on the fly as it needed them. >Did you try Radius? This company hasn't been using a RADIUS server. They have an Active Directory server (yuck!), but I don't know if it would be useful for this purpose. By the way, a related problem I'm encountering is that mpd seems to want some options set before authentication when they need to be set afterward based on the user's identity. For example, while the user's IP can be set when the user is identified and authenticated (via mpd.secret), the IP at the host end of the PPP link can't. So, you run into situations where the IP assigned to the incoming PPP/PPTP user isn't on the same subnet as the one assigned to the host, which seems to cause routing problems. --Brett Glass From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 03:39:51 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 55FE016A4DA for ; Fri, 11 Aug 2006 03:39:51 +0000 (UTC) (envelope-from prvs=julian=3713ce93d@elischer.org) Received: from a50.ironport.com (a50.ironport.com [63.251.108.112]) by mx1.FreeBSD.org (Postfix) with ESMTP id D2EB143D5E for ; Fri, 11 Aug 2006 03:39:50 +0000 (GMT) (envelope-from prvs=julian=3713ce93d@elischer.org) Received: from unknown (HELO [10.251.18.229]) ([10.251.18.229]) by a50.ironport.com with ESMTP; 10 Aug 2006 20:39:51 -0700 Message-ID: <44DBFC05.6080804@elischer.org> Date: Thu, 10 Aug 2006 20:39:49 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.13) Gecko/20060414 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Brett Glass References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> <44DBF2BB.5080202@micom.mng.net> <7.0.1.0.2.20060810212047.073f0078@lariat.net> In-Reply-To: <7.0.1.0.2.20060810212047.073f0078@lariat.net> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: Ganbold , net@freebsd.org Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 03:39:51 -0000 Brett Glass wrote: > At 09:00 PM 8/10/2006, Ganbold wrote: > >> It will be much easier if you can write some script to generate mpd >> config files. I'm generating config files such way for PPPoE. > > > Is there a way to avoid having to generate them at all? It seems to me > that it would be very easy for mpd to create netgraph nodes on the fly > as it needed them. mpd does all the netgraph manipulation itself. > >> Did you try Radius? > > > This company hasn't been using a RADIUS server. They have an Active > Directory server (yuck!), but I don't know if it would be useful for > this purpose. > > By the way, a related problem I'm encountering is that mpd seems to > want some options set before authentication when they need to be set > afterward based on the user's identity. For example, while the user's > IP can be set when the user is identified and authenticated (via > mpd.secret), the IP at the host end of the PPP link can't. So, you run > into situations where the IP assigned to the incoming PPP/PPTP user > isn't on the same subnet as the one assigned to the host, which seems > to cause routing problems. > > --Brett Glass > > > > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 04:13:38 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5C4B616A4E0 for ; Fri, 11 Aug 2006 04:13:38 +0000 (UTC) (envelope-from brett@lariat.net) Received: from lariat.net (lariat.net [65.122.236.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9B3BA43D4C for ; Fri, 11 Aug 2006 04:13:37 +0000 (GMT) (envelope-from brett@lariat.net) Received: from Anne (IDENT:ppp1000.lariat.net@lariat.net [65.122.236.2]) by lariat.net (8.9.3/8.9.3) with ESMTP id WAA01471; Thu, 10 Aug 2006 22:12:48 -0600 (MDT) X-message-flag: Warning! Use of Microsoft Outlook renders your system susceptible to Internet worms. Message-Id: <7.0.1.0.2.20060810220804.08de8568@lariat.net> X-Mailer: QUALCOMM Windows Eudora Version 7.0.1.0 Date: Thu, 10 Aug 2006 22:12:38 -0600 To: Julian Elischer From: Brett Glass In-Reply-To: <44DBFC05.6080804@elischer.org> References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> <44DBF2BB.5080202@micom.mng.net> <7.0.1.0.2.20060810212047.073f0078@lariat.net> <44DBFC05.6080804@elischer.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: Ganbold , net@freebsd.org Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 04:13:38 -0000 At 09:39 PM 8/10/2006, Julian Elischer wrote: >mpd does all the netgraph manipulation itself. Julian, as I recall you were one of the original employees of Whistle Communications, correct? Perhaps you can explain this: Why does mpd require all of those link configurations? Was mpd originally intended to be used as a client only? I'm struggling here because I can't find a PPP/PPTP implementation that's completely BSD licensed and really designed to be a large scale server. --Brett Glass From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 04:36:09 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C7A1D16A4DE for ; Fri, 11 Aug 2006 04:36:09 +0000 (UTC) (envelope-from uwe@laverenz.de) Received: from natreg.rzone.de (natreg.rzone.de [81.169.145.183]) by mx1.FreeBSD.org (Postfix) with ESMTP id 29DC643D46 for ; Fri, 11 Aug 2006 04:36:08 +0000 (GMT) (envelope-from uwe@laverenz.de) Received: from athena.laverenz.de (p5480EFC6.dip.t-dialin.net [84.128.239.198]) by post.webmailer.de (8.13.6/8.13.6) with ESMTP id k7B4a7ss009635 for ; Fri, 11 Aug 2006 06:36:07 +0200 (MEST) Received: from localhost (localhost.localdomain [127.0.0.1]) by athena.laverenz.de (Postfix) with ESMTP id 4EDE4E3D8D5E for ; Fri, 11 Aug 2006 06:36:06 +0200 (CEST) Received: from athena.laverenz.de ([127.0.0.1]) by localhost (athena [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 13337-04 for ; Fri, 11 Aug 2006 06:36:05 +0200 (CEST) Received: by athena.laverenz.de (Postfix, from userid 2000) id 30089E3D8D5D; Fri, 11 Aug 2006 06:36:05 +0200 (CEST) Date: Fri, 11 Aug 2006 06:36:05 +0200 From: Uwe Laverenz To: freebsd-net@freebsd.org Message-ID: <20060811043605.GA14432@laverenz.de> References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <7.0.1.0.2.20060810201735.067258b0@lariat.net> Organization: private site Sender: uwe@laverenz.de User-Agent: Mutt/1.5.9i X-Virus-Scanned: by amavisd-new-20030616-p10 (Debian) at laverenz.de Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 04:36:09 -0000 Hi Brett, On Thu, Aug 10, 2006 at 08:43:28PM -0600, Brett Glass wrote: > flail around experimenting? If I can't use mpd and PoPToP isn't > working, what other options are there for a good PPTP server? It's not PPTP, but maybe OpenVPN is an otion for you: /usr/ports/security/openvpn http://openvpn.net Uwe From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 08:06:03 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8D1DE16A4DA for ; Fri, 11 Aug 2006 08:06:03 +0000 (UTC) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by mx1.FreeBSD.org (Postfix) with ESMTP id EFEFE43D49 for ; Fri, 11 Aug 2006 08:06:02 +0000 (GMT) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by k2.vol.cz (8.12.11/8.12.9) with ESMTP id k7B860Da071026 for ; Fri, 11 Aug 2006 10:06:00 +0200 (CEST) (envelope-from daniel.ryslink@col.cz) Date: Fri, 11 Aug 2006 10:06:00 +0200 (CEST) From: Daniel Ryslink X-X-Sender: kamamura@k2.vol.cz To: freebsd-net@freebsd.org Message-ID: <20060811100536.V80282@k2.vol.cz> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-SpamTest-Info: Profile: Formal (493/060809) X-SpamTest-Info: Profile: Detect Standard (4/030526) X-SpamTest-Info: Profile: SysLog X-SpamTest-Info: Profile: Marking Spam - Subject (2/030321) X-SpamTest-Status: Not detected X-SpamTest-Version: SMTP-Filter Version 2.0.0 [0125], KAS/Release Subject: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 08:06:03 -0000 Hello, We have currently upgraded one of our routers to Gigabit connectivity and FreeBSD 6.1 Release. The hardware is Supermicro SuperServer 5015M-T - we have tried both the integrated NIC and yet another external Intel NIC - specifically Intel PRO/1000 MT Dual Port Server Adapter PWLA8492MT The problem is that several times a day, the following appears in messages: Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting accompanied with a loss of connectivity lasting for several seconds. We have tried using both the default driver that came with the FreeBSD installation as well as the newest driver from Intel dated 2th April 2006 compiled as a module, but the problem still persists. If anyone encountered the problem and has a solution, I would be very grateful. Best Regards Daniel Ryslink From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 10:07:48 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DD35016A4DA for ; Fri, 11 Aug 2006 10:07:48 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8D5DD43D46 for ; Fri, 11 Aug 2006 10:07:48 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 113C146C1E; Fri, 11 Aug 2006 06:07:48 -0400 (EDT) Date: Fri, 11 Aug 2006 11:07:47 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Dima Roshin In-Reply-To: Message-ID: <20060811105923.S45647@fledge.watson.org> References: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-net@freebsd.org Subject: Re: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 10:07:48 -0000 On Wed, 9 Aug 2006, Dima Roshin wrote: > Greeting colleagues. I've got two DL-360(pciX bus) servers, with BCM5704 > NetXtreme Dual Gigabit Adapters(bge). The Uname is 6.1-RELEASE-p3. The bge > interfaces of the both servers are connected with each other with a cat6 > patchcord. On any recent box, or even somewhat older ones, achieving gigabit speeds with decent frame sizes (~1500 or greater) should be trivial. Using two dual-Xeons in the netperf cluster (of similar configuration), without any optimization/configuration at all (not even default TCP buffer size changes), and likely with at least some debugging compiled in, I got 930mbps on the netperf TCP stream test. So if you're not getting that speed, you need to look at the configuration closely. In particular, I would... (0) Make sure expensive debugging features, such as WITNESS and INVARIANTS, are disabled. Make sure netperf is not compiled with -DHISTOGRAM, which is not the default (anymore). (1) Confirm that your cabling is all good, and probably replace the cable to be sure. Remove the switch from the loop to make sure it's not a switch problem. (2) Disable polling. One problem I've observed with polling is that you must poll at a very high rate on high speed links, or the polling rate is too small for the buffer on the ethernet card, so packets are dropped because it's drained too infrequently. With interrupt moderation on modern cards, you get significantly polling-like effects anyway, and to be honest, syncing or sourcing a gigabit on a decent box should work fine without special stack optimizations. I don't remember the numbers, but you may find that to make polling reliable, you need to further increase HZ. (3) Check for interrupt problems. Make sure that the receive interrupt rate isn't firing significantly faster than desired, that there's no interrupt shadowing to other interrupt handlers, etc. Also confirm that all PCI segments used for gigabit networking are 64-bit, not 32-bit. I believe PCI-X should be fine. (4) Use top -S and vmstat -systat 1 to characerize the system load during a test run (ideally start it running when the test starts, and capture the output 60 seconds in or so), as this is valuable debugging information that will help us decide what the source of the problem is. Where gigabit gets tricky is with small frame sizes, where the per-packet cost dominates -- i.e., 0-byte UDP payloads. At large frame sizes, raw TCP shouldn't be a problem. Robert N M Watson Computer Laboratory University of Cambridge From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:12:51 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3FCEF16A4DA for ; Fri, 11 Aug 2006 11:12:51 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5C6D343D5A for ; Fri, 11 Aug 2006 11:12:49 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7BBCfqm089804 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 15:12:42 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7BBCfF9089803; Fri, 11 Aug 2006 15:12:41 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 11 Aug 2006 15:12:40 +0400 From: Gleb Smirnoff To: Daniel Ryslink Message-ID: <20060811111240.GD96644@FreeBSD.org> Mail-Followup-To: Gleb Smirnoff , Daniel Ryslink , freebsd-net@freebsd.org References: <20060811100536.V80282@k2.vol.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <20060811100536.V80282@k2.vol.cz> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:12:51 -0000 Daniel, On Fri, Aug 11, 2006 at 10:06:00AM +0200, Daniel Ryslink wrote: D> We have currently upgraded one of our routers to Gigabit connectivity and D> FreeBSD 6.1 Release. D> D> The hardware is Supermicro SuperServer 5015M-T - we have tried both the D> integrated NIC and yet another external Intel NIC - specifically D> D> Intel PRO/1000 MT Dual Port Server Adapter D> PWLA8492MT D> D> The problem is that several times a day, the following appears in D> messages: D> D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting D> D> accompanied with a loss of connectivity lasting for several seconds. D> D> We have tried using both the default driver that came with the FreeBSD D> installation as well as the newest driver from Intel dated 2th April 2006 D> compiled as a module, but the problem still persists. D> D> If anyone encountered the problem and has a solution, I would be very D> grateful. Sometime ago this message was not printed, but the reset was processed and the loss of connectivity was also present. So, probably you hadn't noticed this problem before. How many times per day is this message printed? -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:15:45 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 611D116A4DA for ; Fri, 11 Aug 2006 11:15:45 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 607FE43D45 for ; Fri, 11 Aug 2006 11:15:44 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7BBFg1Q089841 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 15:15:42 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7BBFfb5089840; Fri, 11 Aug 2006 15:15:41 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 11 Aug 2006 15:15:41 +0400 From: Gleb Smirnoff To: mark Message-ID: <20060811111541.GE96644@FreeBSD.org> Mail-Followup-To: Gleb Smirnoff , mark , freebsd-net@freebsd.org References: <44D11785.1080107@immermail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <44D11785.1080107@immermail.com> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org Subject: Re: netgraph with 10Gig interfaces X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:15:45 -0000 On Wed, Aug 02, 2006 at 02:22:13PM -0700, mark wrote: m> I cannot get netgraph to work with 10Gig interfaces m> on FreeBSD 6.1. No errors, but no traffic seen. m> Config works with 1 Gig interfaces. Anyone know why? m> m> ngctl mkpeer . eiface hook ether m> ngctl mkpeer ngeth0: one2many lower one m> ngctl connect $if1: ngeth0:lower lower many0 m> ngctl connect $if2: ngeth0:lower lower many1 m> ifconfig ngeth0 -arp up And where is interface here? Either 10Gig or 1 Gig? I don't see one. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:16:45 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7F2F616A4DA for ; Fri, 11 Aug 2006 11:16:45 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id E372143D6A for ; Fri, 11 Aug 2006 11:16:38 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7BBGaRI089859 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 15:16:37 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7BBGaxY089858; Fri, 11 Aug 2006 15:16:36 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 11 Aug 2006 15:16:36 +0400 From: Gleb Smirnoff To: Nikolas Britton Message-ID: <20060811111636.GF96644@FreeBSD.org> Mail-Followup-To: Gleb Smirnoff , Nikolas Britton , freebsd-net@freebsd.org References: Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org Subject: Re: Intel PRO/1000 EB, 82563EB and 82564EB. X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:16:45 -0000 On Wed, Aug 02, 2006 at 06:02:20PM -0700, Nikolas Britton wrote: N> When is FreeBSD going to support the 82563EB/82564EB? Do we have anything N> yet? N> N> http://www.intel.com/design/network/products/lan/docs/82563_64_docs.htm It should be supported by fresh 6-STABLE. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:18:02 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4F82A16A4E2 for ; Fri, 11 Aug 2006 11:18:02 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 663B443D9E for ; Fri, 11 Aug 2006 11:18:01 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7BBHxuH089882 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 15:17:59 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7BBHwIT089881; Fri, 11 Aug 2006 15:17:59 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 11 Aug 2006 15:17:58 +0400 From: Gleb Smirnoff To: Markus Oestreicher Message-ID: <20060811111758.GG96644@FreeBSD.org> Mail-Followup-To: Gleb Smirnoff , Markus Oestreicher , freebsd-net@freebsd.org References: <44C8E83F.3050706@x-trader.de> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <44C8E83F.3050706@x-trader.de> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org Subject: Re: em improvements in 6.2? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:18:02 -0000 On Thu, Jul 27, 2006 at 06:22:23PM +0200, Markus Oestreicher wrote: M> Is planned to MFC the changes made to em(4) in January M> (taskqueue, adaptive polling) for 6.2-RELEASE? They've been merged recently. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:34:16 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 61D2916A4DA for ; Fri, 11 Aug 2006 11:34:16 +0000 (UTC) (envelope-from nikolas.britton@gmail.com) Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.190]) by mx1.FreeBSD.org (Postfix) with ESMTP id B16DD43D55 for ; Fri, 11 Aug 2006 11:34:14 +0000 (GMT) (envelope-from nikolas.britton@gmail.com) Received: by nf-out-0910.google.com with SMTP id g2so1021774nfe for ; Fri, 11 Aug 2006 04:34:13 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=r4KprCo0z1gjAjSxkAtp5XLMxogKXBaHW/KfzeVzYYcfAFEVsT5w5GovJpEdu+ErW7kwsnO2AnsoFaMj4tRohPJ2GnSfbu3MSYP6Dj8tE5ca17Fy9xIwUllJ4R0j4lTyKjmnTBzzYxTiU/nLCDIttt/r1LY8On0PhUa8Pplmabk= Received: by 10.78.107.8 with SMTP id f8mr2126594huc; Fri, 11 Aug 2006 04:34:13 -0700 (PDT) Received: by 10.78.143.11 with HTTP; Fri, 11 Aug 2006 04:34:13 -0700 (PDT) Message-ID: Date: Fri, 11 Aug 2006 06:34:13 -0500 From: "Nikolas Britton" To: "Gleb Smirnoff" , "Nikolas Britton" , freebsd-net@freebsd.org In-Reply-To: <20060811111636.GF96644@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20060811111636.GF96644@FreeBSD.org> Cc: Subject: Re: Intel PRO/1000 EB, 82563EB and 82564EB. X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:34:16 -0000 On 8/11/06, Gleb Smirnoff wrote: > On Wed, Aug 02, 2006 at 06:02:20PM -0700, Nikolas Britton wrote: > N> When is FreeBSD going to support the 82563EB/82564EB? Do we have anything > N> yet? > N> > N> http://www.intel.com/design/network/products/lan/docs/82563_64_docs.htm > > It should be supported by fresh 6-STABLE. > Yep! I'm already running the patch set that's now in 6.1-STABLE... Thanks again gleb for the patches. -- BSD Podcasts @: http://bsdtalk.blogspot.com/ http://freebsdforall.blogspot.com/ From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 11:42:40 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BEB8C16A4DE; Fri, 11 Aug 2006 11:42:40 +0000 (UTC) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by mx1.FreeBSD.org (Postfix) with ESMTP id EB9D643D66; Fri, 11 Aug 2006 11:42:34 +0000 (GMT) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by k2.vol.cz (8.12.11/8.12.9) with ESMTP id k7BBgWtI080992; Fri, 11 Aug 2006 13:42:32 +0200 (CEST) (envelope-from daniel.ryslink@col.cz) Date: Fri, 11 Aug 2006 13:42:32 +0200 (CEST) From: Daniel Ryslink X-X-Sender: kamamura@k2.vol.cz To: Gleb Smirnoff In-Reply-To: <20060811111240.GD96644@FreeBSD.org> Message-ID: <20060811133531.D80282@k2.vol.cz> References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-SpamTest-Info: Profile: Formal (493/060809) X-SpamTest-Info: Profile: Detect Standard (4/030526) X-SpamTest-Info: Profile: SysLog X-SpamTest-Info: Profile: Marking Spam - Subject (2/030321) X-SpamTest-Status: Not detected X-SpamTest-Version: SMTP-Filter Version 2.0.0 [0125], KAS/Release Cc: freebsd-net@FreeBSD.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 11:42:40 -0000 Hello, We have started to use the em driver only recently, after the upgrade to gigabit connectivity (100 MBit NICs from Intel used the fxp driver). As for the frequency of the incidents, here is a grep of the messages: ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ The driver used is version 3.2.18 (I wanted to use the Intel 6.1.4 as a module, but I have found out that I made a mistake and accidentally loaded the old 3.2.18 driver). I have dilemma now - which new driver to try? The 6.0.5 submitted to the current FreeBSD 6.1 branch (modified by you, I believe, on 8th August), or the newest driver from Intel 6.1.4? Do you think one of these drivers could solve my problems? I would be very thankful for any advice. Thank you Best Regards Daniel Ryslink On Fri, 11 Aug 2006, Gleb Smirnoff wrote: > Daniel, > > On Fri, Aug 11, 2006 at 10:06:00AM +0200, Daniel Ryslink wrote: > D> We have currently upgraded one of our routers to Gigabit connectivity and > D> FreeBSD 6.1 Release. > D> > D> The hardware is Supermicro SuperServer 5015M-T - we have tried both the > D> integrated NIC and yet another external Intel NIC - specifically > D> > D> Intel PRO/1000 MT Dual Port Server Adapter > D> PWLA8492MT > D> > D> The problem is that several times a day, the following appears in > D> messages: > D> > D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting > D> > D> accompanied with a loss of connectivity lasting for several seconds. > D> > D> We have tried using both the default driver that came with the FreeBSD > D> installation as well as the newest driver from Intel dated 2th April 2006 > D> compiled as a module, but the problem still persists. > D> > D> If anyone encountered the problem and has a solution, I would be very > D> grateful. > > Sometime ago this message was not printed, but the reset was processed > and the loss of connectivity was also present. So, probably you hadn't > noticed this problem before. > > How many times per day is this message printed? > > -- > Totus tuus, Glebius. > GLEBIUS-RIPN GLEB-RIPE > From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 12:58:31 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C535D16A4DF for ; Fri, 11 Aug 2006 12:58:31 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id A30D543D49 for ; Fri, 11 Aug 2006 12:58:30 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7BCwQub090498 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 16:58:26 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7BCwQiS090497; Fri, 11 Aug 2006 16:58:26 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 11 Aug 2006 16:58:25 +0400 From: Gleb Smirnoff To: Daniel Ryslink Message-ID: <20060811125825.GH96644@cell.sick.ru> Mail-Followup-To: Gleb Smirnoff , Daniel Ryslink , freebsd-net@FreeBSD.org References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <20060811133531.D80282@k2.vol.cz> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 12:58:31 -0000 Daniel, On Fri, Aug 11, 2006 at 01:42:32PM +0200, Daniel Ryslink wrote: D> We have started to use the em driver only recently, after the upgrade to D> gigabit connectivity (100 MBit NICs from Intel used the fxp driver). D> D> As for the frequency of the incidents, here is a grep of the messages: D> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ D> Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting D> Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting D> Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting D> Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting D> Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting D> Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting D> Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting D> Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting D> Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting D> Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting D> Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting D> Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting D> Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting D> Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ D> D> The driver used is version 3.2.18 (I wanted to use the Intel 6.1.4 as a D> module, but I have found out that I made a mistake and accidentally loaded D> the old 3.2.18 driver). D> D> I have dilemma now - which new driver to try? The 6.0.5 submitted to the D> current FreeBSD 6.1 branch (modified by you, I believe, on 8th August), or D> the newest driver from Intel 6.1.4? Do you think one of these drivers D> could solve my problems? I'm not sure whether new driver will solve your problems. You should give a try to 6.1-STABLE which has 6.0.5 in it. The difference between 6.1.4 and 6.0.5 is quite small, I doubt that 6.1.4 worth a try in your case. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 14:55:14 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9A27D16A4DD; Fri, 11 Aug 2006 14:55:14 +0000 (UTC) (envelope-from mark@immermail.com) Received: from mta2.lbl.gov (mta2.lbl.gov [128.3.41.12]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4AD6F43D53; Fri, 11 Aug 2006 14:55:14 +0000 (GMT) (envelope-from mark@immermail.com) Received: from mta2.lbl.gov (localhost [127.0.0.1]) by mta2.lbl.gov (8.13.7/8.13.7) with ESMTP id k7BEtDIw001496; Fri, 11 Aug 2006 07:55:13 -0700 (PDT) Received: from [172.16.1.37] ([71.141.151.6]) by mta2.lbl.gov (8.13.7/8.13.7) with ESMTP id k7BEtCoE001492 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 11 Aug 2006 07:55:12 -0700 (PDT) Message-ID: <44DC9A51.3030303@immermail.com> Date: Fri, 11 Aug 2006 07:55:13 -0700 From: mark User-Agent: Thunderbird 1.5.0.5 (Macintosh/20060719) MIME-Version: 1.0 To: Gleb Smirnoff , freebsd-net@FreeBSD.org References: <44D11785.1080107@immermail.com> <20060811111541.GE96644@FreeBSD.org> In-Reply-To: <20060811111541.GE96644@FreeBSD.org> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.88.4/1646/Fri Aug 11 02:51:17 2006 on mta2 X-Virus-Status: Clean Cc: Subject: Re: netgraph with 10Gig interfaces X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 14:55:14 -0000 Gleb Smirnoff wrote: > On Wed, Aug 02, 2006 at 02:22:13PM -0700, mark wrote: > m> I cannot get netgraph to work with 10Gig interfaces > m> on FreeBSD 6.1. No errors, but no traffic seen. > m> Config works with 1 Gig interfaces. Anyone know why? > m> > m> ngctl mkpeer . eiface hook ether > m> ngctl mkpeer ngeth0: one2many lower one > m> ngctl connect $if1: ngeth0:lower lower many0 > m> ngctl connect $if2: ngeth0:lower lower many1 > m> ifconfig ngeth0 -arp up > > And where is interface here? Either 10Gig or 1 Gig? I don't > see one. This snippet is from a script, and the variables '$if1' and '$if2' are set to the interfaces. In effect, the 'connect' lines above are actually (for Neterion 10Gig driver): ngctl connect xge0: ngeth0:lower lower many0 ngctl connect xge1: ngeth0:lower lower many0 Help appreciated. Thanks, Mark From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 16:22:24 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4936116A4DF for ; Fri, 11 Aug 2006 16:22:24 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.179]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1BF6443D49 for ; Fri, 11 Aug 2006 16:22:22 +0000 (GMT) (envelope-from jfvogel@gmail.com) Received: by py-out-1112.google.com with SMTP id c59so268169pyc for ; Fri, 11 Aug 2006 09:22:22 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Co7Q02Zrt5XLX28BKZIjEW7wWO2/xop5m27v3CWbXZLaDr+ChHFhzr2VWGlgsfLbxViMnYgLpnWzbFG3TSfuK6ojZ8iFJTh3kgz6zhrOdXbmudMnWG/woseLxrF1Cmvsf5AEE0LBAot6N9TnU4WTQBM0hiDGYvgpiJ5vh47UZ00= Received: by 10.35.111.14 with SMTP id o14mr6423697pym; Fri, 11 Aug 2006 09:22:22 -0700 (PDT) Received: by 10.35.119.1 with HTTP; Fri, 11 Aug 2006 09:22:22 -0700 (PDT) Message-ID: <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> Date: Fri, 11 Aug 2006 09:22:22 -0700 From: "Jack Vogel" To: "Gleb Smirnoff" , "Daniel Ryslink" , freebsd-net@freebsd.org In-Reply-To: <20060811125825.GH96644@cell.sick.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> Cc: Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 16:22:24 -0000 On 8/11/06, Gleb Smirnoff wrote: > Daniel, > > On Fri, Aug 11, 2006 at 01:42:32PM +0200, Daniel Ryslink wrote: > D> We have started to use the em driver only recently, after the upgrade to > D> gigabit connectivity (100 MBit NICs from Intel used the fxp driver). > D> > D> As for the frequency of the incidents, here is a grep of the messages: > D> > D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ > D> Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting > D> Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting > D> Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting > D> Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting > D> Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting > D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting > D> Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting > D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ > D> > D> The driver used is version 3.2.18 (I wanted to use the Intel 6.1.4 as a > D> module, but I have found out that I made a mistake and accidentally loaded > D> the old 3.2.18 driver). > D> > D> I have dilemma now - which new driver to try? The 6.0.5 submitted to the > D> current FreeBSD 6.1 branch (modified by you, I believe, on 8th August), or > D> the newest driver from Intel 6.1.4? Do you think one of these drivers > D> could solve my problems? > > I'm not sure whether new driver will solve your problems. You should give > a try to 6.1-STABLE which has 6.0.5 in it. The difference between 6.1.4 and > 6.0.5 is quite small, I doubt that 6.1.4 worth a try in your case. Gleb is right, the difference between my 6.0.5 and 6.1.4 driver are minor and don't seem to have anything to do with your problem. I am happy Gleb got my code merged with tip of STABLE and would take that driver code if I were you, it will become 6.2 before long :) Watchdogs happen because of transmit cleanup failing, your instances are pretty widely seperated, it looks like some external network problem perhaps? Jack Intel LAD From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 16:48:04 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 427C116A4DA; Fri, 11 Aug 2006 16:48:04 +0000 (UTC) (envelope-from landonf@opendarwin.org) Received: from goldfish.bikemonkey.org (goldfish.bikemonkey.org [64.81.64.61]) by mx1.FreeBSD.org (Postfix) with ESMTP id C0E8243D45; Fri, 11 Aug 2006 16:47:59 +0000 (GMT) (envelope-from landonf@opendarwin.org) Received: from [192.168.54.11] (nat.earth.threerings.net [64.127.109.100]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (No client certificate requested) by goldfish.bikemonkey.org (Postfix) with ESMTP id 71097AF601B; Fri, 11 Aug 2006 09:47:59 -0700 (PDT) In-Reply-To: <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg=pgp-sha1; boundary="Apple-Mail-3-914015310" Message-Id: Content-Transfer-Encoding: 7bit From: Landon Fuller Date: Fri, 11 Aug 2006 09:47:54 -0700 To: Jack Vogel X-Pgp-Agent: GPGMail 1.1.2 (Tiger) X-Mailer: Apple Mail (2.752.2) Cc: Daniel Ryslink , freebsd-net@freebsd.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 16:48:04 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --Apple-Mail-3-914015310 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed On Aug 11, 2006, at 09:22, Jack Vogel wrote: > On 8/11/06, Gleb Smirnoff wrote: >> Daniel, >> >> On Fri, Aug 11, 2006 at 01:42:32PM +0200, Daniel Ryslink wrote: >> D> We have started to use the em driver only recently, after the >> upgrade to >> D> gigabit connectivity (100 MBit NICs from Intel used the fxp >> driver). >> D> >> D> As for the frequency of the incidents, here is a grep of the >> messages: >> D> >> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >> D> Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting >> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >> D> >> D> The driver used is version 3.2.18 (I wanted to use the Intel >> 6.1.4 as a >> D> module, but I have found out that I made a mistake and >> accidentally loaded >> D> the old 3.2.18 driver). >> D> >> D> I have dilemma now - which new driver to try? The 6.0.5 >> submitted to the >> D> current FreeBSD 6.1 branch (modified by you, I believe, on 8th >> August), or >> D> the newest driver from Intel 6.1.4? Do you think one of these >> drivers >> D> could solve my problems? >> >> I'm not sure whether new driver will solve your problems. You >> should give >> a try to 6.1-STABLE which has 6.0.5 in it. The difference between >> 6.1.4 and >> 6.0.5 is quite small, I doubt that 6.1.4 worth a try in your case. > > Gleb is right, the difference between my 6.0.5 and 6.1.4 driver are > minor > and don't seem to have anything to do with your problem. > > I am happy Gleb got my code merged with tip of STABLE and would take > that driver code if I were you, it will become 6.2 before long :) > > Watchdogs happen because of transmit cleanup failing, your instances > are pretty widely seperated, it looks like some external network > problem > perhaps? We saw this issue here on SMP systems running 6.1; I've been meaning to set up a reproduction case in the lab and dig into the issue further. Disabling the mpsafe network stack (debug.mpsafenet=0) is our temporary work-around; rwatson mentioned that this has the effect of forcing the interrupt handler for if_em to not run in parallel with the transmit code, which is likely what caused the problem to disappear. -landonf --Apple-Mail-3-914015310 content-type: application/pgp-signature; x-mac-type=70674453; name=PGP.sig content-description: This is a digitally signed message part content-disposition: inline; filename=PGP.sig content-transfer-encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (Darwin) iD8DBQFE3LS9lplZCE/15mMRAgKZAKCPPrfnzKWXew4qkgbd8vUSrHuYWgCePn1U ww2/czPIdUTqsNnt8tmjAug= =6R/I -----END PGP SIGNATURE----- --Apple-Mail-3-914015310-- From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 16:48:26 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A936116A4DA for ; Fri, 11 Aug 2006 16:48:26 +0000 (UTC) (envelope-from prvs=julian=3713ce93d@elischer.org) Received: from a50.ironport.com (a50.ironport.com [63.251.108.112]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2D04443D4C for ; Fri, 11 Aug 2006 16:48:26 +0000 (GMT) (envelope-from prvs=julian=3713ce93d@elischer.org) Received: from unknown (HELO [192.168.2.3]) ([10.251.60.35]) by a50.ironport.com with ESMTP; 11 Aug 2006 09:48:26 -0700 Message-ID: <44DCB4D8.4020901@elischer.org> Date: Fri, 11 Aug 2006 09:48:24 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.13) Gecko/20060414 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Brett Glass References: <7.0.1.0.2.20060810201735.067258b0@lariat.net> <44DBF2BB.5080202@micom.mng.net> <7.0.1.0.2.20060810212047.073f0078@lariat.net> <44DBFC05.6080804@elischer.org> <7.0.1.0.2.20060810220804.08de8568@lariat.net> In-Reply-To: <7.0.1.0.2.20060810220804.08de8568@lariat.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Ganbold , Archie Cobbs , net@freebsd.org Subject: Re: Big PPTP server X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 16:48:26 -0000 Brett Glass wrote: > At 09:39 PM 8/10/2006, Julian Elischer wrote: > >> mpd does all the netgraph manipulation itself. > > > Julian, as I recall you were one of the original employees of Whistle > Communications, correct? Perhaps you can explain this: Why does mpd > require all of those link configurations? Was mpd originally intended > to be used as a client only? I'm struggling here because I can't find > a PPP/PPTP implementation that's completely BSD licensed and really > designed to be a large scale server. > > --Brett Glass That's more a question for archie as he wrote it, bit it was written to be a server on small appliance. Some people have been working on imporving mpd but I don't know much about it. From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 18:03:13 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7A62E16A4E1; Fri, 11 Aug 2006 18:03:13 +0000 (UTC) (envelope-from jmg@hydrogen.funkthat.com) Received: from hydrogen.funkthat.com (gate.funkthat.com [69.17.45.168]) by mx1.FreeBSD.org (Postfix) with ESMTP id EA23F43D49; Fri, 11 Aug 2006 18:03:12 +0000 (GMT) (envelope-from jmg@hydrogen.funkthat.com) Received: from hydrogen.funkthat.com (ncox62luygfqm9ik@localhost.funkthat.com [127.0.0.1]) by hydrogen.funkthat.com (8.13.6/8.13.3) with ESMTP id k7BI3CnF049159; Fri, 11 Aug 2006 11:03:12 -0700 (PDT) (envelope-from jmg@hydrogen.funkthat.com) Received: (from jmg@localhost) by hydrogen.funkthat.com (8.13.6/8.13.3/Submit) id k7BI3CT1049158; Fri, 11 Aug 2006 11:03:12 -0700 (PDT) (envelope-from jmg) Date: Fri, 11 Aug 2006 11:03:12 -0700 From: John-Mark Gurney To: Robert Watson Message-ID: <20060811180312.GL99774@funkthat.com> Mail-Followup-To: Robert Watson , Dima Roshin , freebsd-net@freebsd.org References: <20060811105923.S45647@fledge.watson.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20060811105923.S45647@fledge.watson.org> User-Agent: Mutt/1.4.2.1i X-Operating-System: FreeBSD 5.4-RELEASE-p6 i386 X-PGP-Fingerprint: B7 EC EF F8 AE ED A7 31 96 7A 22 B3 D8 56 36 F4 X-Files: The truth is out there X-URL: http://resnet.uoregon.edu/~gurney_j/ X-Resume: http://resnet.uoregon.edu/~gurney_j/resume.html Cc: freebsd-net@FreeBSD.org, Dima Roshin Subject: Re: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: John-Mark Gurney List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 18:03:13 -0000 Robert Watson wrote this message on Fri, Aug 11, 2006 at 11:07 +0100: > (4) Use top -S and vmstat -systat 1 to characerize the system load during a do you mean systat -vmstat 1 ? P.S. I normally use 2 instead of 1 since there is enough information on the screen that it takes longer than 1 second for me to read most of it... -- John-Mark Gurney Voice: +1 415 225 5579 "All that I will do, has been done, All that I have, has not." From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 18:04:36 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F00D316A4DE for ; Fri, 11 Aug 2006 18:04:35 +0000 (UTC) (envelope-from davidch@broadcom.com) Received: from MMS3.broadcom.com (mms3.broadcom.com [216.31.210.19]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5B87F43D6E for ; Fri, 11 Aug 2006 18:04:34 +0000 (GMT) (envelope-from davidch@broadcom.com) Received: from 10.10.64.154 by MMS3.broadcom.com with ESMTP (Broadcom SMTP Relay (Email Firewall v6.2.0)); Fri, 11 Aug 2006 11:04:20 -0700 X-Server-Uuid: B238DE4C-2139-4D32-96A8-DD564EF2313E Received: by mail-irva-10.broadcom.com (Postfix, from userid 47) id BA8242AE; Fri, 11 Aug 2006 11:04:20 -0700 (PDT) Received: from mail-irva-8.broadcom.com (mail-irva-8 [10.10.64.221]) by mail-irva-10.broadcom.com (Postfix) with ESMTP id 67A082AE; Fri, 11 Aug 2006 11:04:20 -0700 (PDT) Received: from mail-irva-12.broadcom.com (mail-irva-12.broadcom.com [10.10.64.146]) by mail-irva-8.broadcom.com (MOS 3.7.5a-GA) with ESMTP id ECI18952; Fri, 11 Aug 2006 11:04:19 -0700 (PDT) Received: from NT-IRVA-0750.brcm.ad.broadcom.com (nt-irva-0750 [10.8.194.64]) by mail-irva-12.broadcom.com (Postfix) with ESMTP id DFBA569CA4; Fri, 11 Aug 2006 11:04:19 -0700 (PDT) X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Date: Fri, 11 Aug 2006 11:04:19 -0700 Message-ID: <09BFF2FA5EAB4A45B6655E151BBDD90301B7B6B9@NT-IRVA-0750.brcm.ad.broadcom.com> In-Reply-To: Thread-Topic: Gigabit ethernet questions? Thread-Index: Aca7qB2iA0jVLfN2ShSQlECDAkgv/gBxjm0Q From: "David Christensen" To: "Dima Roshin" , freebsd-net@freebsd.org X-TMWD-Spam-Summary: SEV=1.1; DFV=A2006081106; IFV=2.0.6,4.0-7; RPD=4.00.0004; RPDID=303030312E30413031303230342E34344443433545442E303034382D412D; ENG=IBF; TS=20060811180422; CAT=NONE; CON=NONE; X-MMS-Spam-Filter-ID: A2006081106_4.00.0004_2.0.6,4.0-7 X-WSS-ID: 68C2192E1OO12185780-01-01 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Cc: Subject: RE: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 18:04:36 -0000 > Greeting colleagues. I've got two DL-360(pciX bus) servers,=20 > with BCM5704 NetXtreme Dual Gigabit Adapters(bge). The Uname=20 > is 6.1-RELEASE-p3. The bge interfaces of the both servers are=20 > connected with each other with a cat6 patchcord. > Here are my settings: > kernel config: > options DEVICE_POLLING=20 > options HZ=3D1000 # >=20 > sysctl.conf: > kern.polling.enable=3D1 > net.inet.ip.intr_queue_maxlen=3D5000 > kern.ipc.maxsockbuf=3D8388608 > net.inet.tcp.sendspace=3D3217968 > net.inet.tcp.recvspace=3D3217968 > net.inet.tcp.rfc1323=3D1 >=20 > bge1: flags=3D8843 mtu 9000 > options=3D5b > inet 192.168.0.1 netmask 0xffffff00 broadcast 192.168.0.255 > ether 00:17:a4:3a:e1:81 > media: Ethernet autoselect (1000baseTX ) > status: active > (note mtu 9000) >=20 > and here are tests results: >=20 > netperf: >=20 > TCP STREAM TEST to 192.168.0.1 > Recv Send Send > Socket Socket Message Elapsed > Size Size Size Time Throughput > bytes bytes bytes secs. 10^6bits/sec >=20 > 6217968 6217968 6217968 10.22 320.04 >=20 > UDP UNIDIRECTIONAL SEND TEST to 192.168.0.1 > Socket Message Elapsed Messages > Size Size Time Okay Errors Throughput > bytes bytes secs # # 10^6bits/sec >=20 > 9216 9216 10.00 118851 1724281 876.20 > 41600 10.00 0 0.00] >=20 >=20 >=20 > iperf: > gate2# iperf -s -N > ------------------------------------------------------------ > Server listening on TCP port 5001 > TCP window size: 3.07 MByte (default) > ------------------------------------------------------------ > [ 4] local 192.168.0.2 port 5001 connected with 192.168.0.1=20 > port 52597 > [ 4] 0.0-10.1 sec 384 MBytes 319 Mbits/sec >=20 > Also I can say, that I've managed to achieve about 500mbit.s=20 > by tuning tcp window with -w key in iperf. >=20 > How can we explain such a low tcp performance? What else is=20 > to tune? Is there somebody who achieved gigabit speed with=20 > tcp on freebsd? You're test is non-optimal for the 5704 since the ports are linked=20 together back-to-back. In a dual port configuration such as the 5704 each port must arbitrate for access to the PCI bus. Due to an errata for the 5704, the BGE_PCIDMAWCTL_ONEDMA_ATONCE bit is set which allows only one port access to the PCI bus at a time for the duration of the DMA transaction, rather than allowing the two ports to interleave DMAs. Your test configuration is a worst case scenario since both ports are=20 active in both directions at the same time. If you can change your=20 test to use a second system you should see the TCP performance rise substantially. Dave From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 18:04:45 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E1BE616A4DA for ; Fri, 11 Aug 2006 18:04:45 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9C83F43D45 for ; Fri, 11 Aug 2006 18:04:45 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 68A2646CD0; Fri, 11 Aug 2006 14:04:44 -0400 (EDT) Date: Fri, 11 Aug 2006 19:04:44 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: John-Mark Gurney In-Reply-To: <20060811180312.GL99774@funkthat.com> Message-ID: <20060811190427.O8215@fledge.watson.org> References: <20060811105923.S45647@fledge.watson.org> <20060811180312.GL99774@funkthat.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-net@FreeBSD.org, Dima Roshin Subject: Re: Gigabit ethernet questions? X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 18:04:46 -0000 On Fri, 11 Aug 2006, John-Mark Gurney wrote: > Robert Watson wrote this message on Fri, Aug 11, 2006 at 11:07 +0100: >> (4) Use top -S and vmstat -systat 1 to characerize the system load during a > > do you mean systat -vmstat 1 ? > > P.S. I normally use 2 instead of 1 since there is enough information on the > screen that it takes longer than 1 second for me to read most of it... Er, yes, what you said. Robert N M Watson Computer Laboratory University of Cambridge From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 18:06:25 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F3EF516A4DF for ; Fri, 11 Aug 2006 18:06:24 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2389F43DB7 for ; Fri, 11 Aug 2006 18:06:01 +0000 (GMT) (envelope-from jfvogel@gmail.com) Received: by py-out-1112.google.com with SMTP id c59so313650pyc for ; Fri, 11 Aug 2006 11:06:01 -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=hg8dpNx12i0UE/yLbvSPdtD48B5J6LFX5w+iSATZQ5Vw35/i0iHD6tMt8vGD2YL3Kmd9ygVttrrF9iIq8gA6faaJZ988WVmP6pZB9uP2xk1DC2pZjq+jxjf51GD1ke/xjtHuDcdTmMqq2TiCuCMPMkHml8ST4G8NxEyxhAHE7l8= Received: by 10.35.77.1 with SMTP id e1mr6581205pyl; Fri, 11 Aug 2006 11:06:00 -0700 (PDT) Received: by 10.35.119.1 with HTTP; Fri, 11 Aug 2006 11:06:00 -0700 (PDT) Message-ID: <2a41acea0608111106t6a6dcc84l35eb2cae5dbd42c1@mail.gmail.com> Date: Fri, 11 Aug 2006 11:06:00 -0700 From: "Jack Vogel" To: "Landon Fuller" In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> Cc: Daniel Ryslink , freebsd-net@freebsd.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 18:06:25 -0000 On 8/11/06, Landon Fuller wrote: > > We saw this issue here on SMP systems running 6.1; I've been meaning > to set up a reproduction case in the lab and dig into the issue further. > Disabling the mpsafe network stack (debug.mpsafenet=0) is our > temporary work-around; rwatson mentioned that this has the effect of > forcing the interrupt handler for if_em to not run in parallel with > the transmit code, which is likely what caused the problem to disappear. Hmmm, I have code running right now that is required for new hardware, but I think will benefit all, that only has the hardware writeback and interrupt on the EOP descriptor. As it is now we have every descriptor written back. I havent had it put thru extensive tests yet, but I expect it to significantly reduce interrupts. I hope to be submitting this stuff together with TSO support to CURRENT soon, stay tuned. Jack Intel LAD From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 21:18:55 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BBCB816A4DF for ; Fri, 11 Aug 2006 21:18:55 +0000 (UTC) (envelope-from thomas@FreeBSD.ORG) Received: from melamine.cuivre.fr.eu.org (melusine.cuivre.fr.eu.org [82.225.155.84]) by mx1.FreeBSD.org (Postfix) with ESMTP id 22F9143D45 for ; Fri, 11 Aug 2006 21:18:55 +0000 (GMT) (envelope-from thomas@FreeBSD.ORG) Received: by melamine.cuivre.fr.eu.org (Postfix, from userid 1000) id 511385C61F; Fri, 11 Aug 2006 23:18:54 +0200 (CEST) Date: Fri, 11 Aug 2006 23:18:54 +0200 From: Thomas Quinot To: freebsd-net@freebsd.org Message-ID: <20060811211854.GA76597@melamine.cuivre.fr.eu.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="ibTvN161/egqYuK8" Content-Disposition: inline X-message-flag: WARNING! Using Outlook can damage your computer. User-Agent: Mutt/1.5.11 Subject: RFReview: remove aync IO from yppush X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 21:18:55 -0000 --ibTvN161/egqYuK8 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable All, Our implementation of yppush is severely flawed, in that it makes unsafe and unnecessary use of asynchronous I/O (F_ASYNC, SIGIO) on RPC sockets. This specifically causes incorrect behaviour when pushing maps to multiple server, and SIGIO occurs while a memory allocation operation is in progress, because the processing done during the handling of SIGIO itself attemps to use the memory allocator, which is not reentrant. So, I'm proposing to get rid of all the asynchronous I/O stuff there, and implement that properly using select(2) and a clear single thread of control. I have successfully tested the patch below on my system, both with a single outgoing job and with multiple parallel jobs, and it seems to work correctly. It should be completely equivalent functionally to the previous implementation, except that it ensures the absence of unsafe reentrant processing. I would appreciate reviews and comments on this patch; I intend to commit it in a few days' time, unless an objection is raised. Ideally I think it would be nice to then MFC it in time for 6.2, but that will really depend on the feedback on the change, and RE's call on the matter. Thomas. Index: yppush_main.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D RCS file: /space/mirror/ncvs/src/usr.sbin/yppush/yppush_main.c,v retrieving revision 1.20 diff -u -r1.20 yppush_main.c --- yppush_main.c 12 Apr 2005 15:02:57 -0000 1.20 +++ yppush_main.c 11 Aug 2006 21:17:21 -0000 @@ -63,14 +63,12 @@ int verbose =3D 0; /* Toggle verbose mode. */ unsigned long yppush_transid =3D 0; int yppush_timeout =3D 80; /* Default timeout. */ -int yppush_jobs =3D 0; /* Number of allowed concurrent jobs. */ +int yppush_jobs =3D 1; /* Number of allowed concurrent jobs. */ int yppush_running_jobs =3D 0; /* Number of currently running jobs. */ -int yppush_alarm_tripped =3D 0; =20 /* Structure for holding information about a running job. */ struct jobs { unsigned long tid; - int sock; int port; ypxfrstat stat; unsigned long prognum; @@ -82,6 +80,8 @@ =20 struct jobs *yppush_joblist; /* Linked list of running jobs. */ =20 +static int yppush_svc_run(int); + /* * Local error messages. */ @@ -171,11 +171,7 @@ yp_error("%d transfer%sstill pending", still_pending, still_pending > 1 ? "s " : " "); - yppush_alarm_tripped =3D 0; - alarm(YPPUSH_RESPONSE_TIMEOUT); - pause(); - alarm(0); - if (yppush_alarm_tripped =3D=3D 1) { + if (yppush_svc_run (YPPUSH_RESPONSE_TIMEOUT) =3D=3D 0) { yp_error("timed out"); now =3D 1; } @@ -212,37 +208,30 @@ yppush_exit(1); } =20 - if (sig =3D=3D SIGALRM) { - alarm(0); - yppush_alarm_tripped++; - } - return; } =20 /* * Dispatch loop for callback RPC services. + * Return value: + * -1 error + * 0 timeout + * >0 request serviced */ -static void -yppush_svc_run(void) +static int +yppush_svc_run(int timeout_secs) { -#ifdef FD_SETSIZE + int rc; fd_set readfds; -#else - int readfds; -#endif /* def FD_SETSIZE */ struct timeval timeout; =20 timeout.tv_usec =3D 0; - timeout.tv_sec =3D 5; + timeout.tv_sec =3D timeout_secs; =20 retry: -#ifdef FD_SETSIZE readfds =3D svc_fdset; -#else - readfds =3D svc_fds; -#endif /* def FD_SETSIZE */ - switch (select(_rpc_dtablesize(), &readfds, NULL, NULL, &timeout)) { + rc =3D select(svc_maxfd + 1, &readfds, NULL, NULL, &timeout); + switch (rc) { case -1: if (errno =3D=3D EINTR) goto retry; @@ -255,25 +244,7 @@ svc_getreqset(&readfds); break; } - return; -} - -/* - * Special handler for asynchronous socket I/O. We mark the - * sockets of the callback handlers as O_ASYNC and handle SIGIO - * events here, which will occur when the callback handler has - * something interesting to tell us. - */ -static void -async_handler(int sig) -{ - yppush_svc_run(); - - /* reset any pending alarms. */ - alarm(0); - yppush_alarm_tripped++; - kill(getpid(), SIGALRM); - return; + return rc; } =20 /* @@ -415,7 +386,6 @@ job->stat =3D 0; job->tid =3D tid; job->port =3D xprt->xp_port; - job->sock =3D xprt->xp_fd; /*XXX: Evil!! EEEEEEEVIL!!! */ job->server =3D strdup(server); job->map =3D strdup(map); job->prognum =3D prognum; @@ -423,27 +393,6 @@ job->next =3D yppush_joblist; yppush_joblist =3D job; =20 - /* - * Set the RPC sockets to asynchronous mode. This will - * cause the system to smack us with a SIGIO when an RPC - * callback is delivered. This in turn allows us to handle - * the callback even though we may be in the middle of doing - * something else at the time. - * - * XXX This is a horrible thing to do for two reasons, - * both of which have to do with portability: - * 1) We really ought not to be sticking our grubby mits - * into the RPC service transport handle like this. - * 2) Even in this day and age, there are still some *NIXes - * that don't support async socket I/O. - */ - if (fcntl(xprt->xp_fd, F_SETOWN, getpid()) =3D=3D -1 || - fcntl(xprt->xp_fd, F_SETFL, O_ASYNC) =3D=3D -1) { - yp_error("failed to set async I/O mode: %s", - strerror(errno)); - yppush_exit(1); - } - if (verbose) { yp_error("initiating transfer: %s -> %s (transid =3D %lu)", yppush_mapname, server, tid); @@ -482,27 +431,12 @@ snprintf(server, sizeof(server), "%.*s", vallen, val); =20 /* - * Restrict the number of concurrent jobs. If yppush_jobs number + * Restrict the number of concurrent jobs: if yppush_jobs number * of jobs have already been dispatched and are still pending, * wait for one of them to finish so we can reuse its slot. */ - if (yppush_jobs <=3D 1) { - yppush_alarm_tripped =3D 0; - while (!yppush_alarm_tripped && yppush_running_jobs) { - alarm(yppush_timeout); - yppush_alarm_tripped =3D 0; - pause(); - alarm(0); - } - } else { - yppush_alarm_tripped =3D 0; - while (!yppush_alarm_tripped && yppush_running_jobs >=3D yppush_jobs) { - alarm(yppush_timeout); - yppush_alarm_tripped =3D 0; - pause(); - alarm(0); - } - } + while (yppush_running_jobs >=3D yppush_jobs && (yppush_svc_run (yppush_ti= meout) > 0)) + ; =20 /* Cleared for takeoff: set everything in motion. */ if (yp_push(server, yppush_mapname, yppush_transid)) @@ -633,22 +567,6 @@ signal(SIGINT, handler); signal(SIGABRT, handler); =20 - /* - * Set up the SIGIO handler. Make sure that some of the - * other signals are blocked while the handler is running so - * select() doesn't get interrupted. - */ - sigemptyset(&sa.sa_mask); - sigaddset(&sa.sa_mask, SIGIO); /* Goes without saying. */ - sigaddset(&sa.sa_mask, SIGPIPE); - sigaddset(&sa.sa_mask, SIGCHLD); - sigaddset(&sa.sa_mask, SIGALRM); - sigaddset(&sa.sa_mask, SIGINT); - sa.sa_handler =3D async_handler; - sa.sa_flags =3D 0; - - sigaction(SIGIO, &sa, NULL); - /* set initial transaction ID */ yppush_transid =3D time((time_t *)NULL); =20 --ibTvN161/egqYuK8 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (FreeBSD) iD8DBQFE3PQ9AE1UuDk9JGkRAlOSAJ40nrQNq7Ms7km1LWm/4AA8fptCyACeNBhk W+Hcu1ifBQWjrNIGax8TyEk= =57Kg -----END PGP SIGNATURE----- --ibTvN161/egqYuK8-- From owner-freebsd-net@FreeBSD.ORG Fri Aug 11 23:55:57 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BA5AF16A4DD for ; Fri, 11 Aug 2006 23:55:57 +0000 (UTC) (envelope-from simonw@matteworld.com) Received: from pop-borzoi.atl.sa.earthlink.net (pop-borzoi.atl.sa.earthlink.net [207.69.195.70]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7AD2143D45 for ; Fri, 11 Aug 2006 23:55:55 +0000 (GMT) (envelope-from simonw@matteworld.com) Received: from user-119bq9k.biz.mindspring.com ([66.149.233.52] helo=matteworld.com) by pop-borzoi.atl.sa.earthlink.net with esmtp (Exim 3.36 #1) id 1GBgr4-00005v-00 for freebsd-net@freebsd.org; Fri, 11 Aug 2006 19:55:54 -0400 Message-ID: <44DD1909.40703@matteworld.com> Date: Fri, 11 Aug 2006 16:55:53 -0700 From: Simon Walton User-Agent: Mozilla/5.0 (X11; U; IRIX IP32; en-US; rv:1.6) Gecko/20040505 X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-net@freebsd.org Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Subject: Long keepidle time X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 11 Aug 2006 23:55:57 -0000 Is there any reason why the default initial timeout for keep alive packets needs to be as long as two hours? This period causes the dynamic rules in my firewall filter to timeout. Is there a major objection to reducing the default idle time to say 3 to 5 minutes? Simon Walton From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 01:32:58 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 02E0516A4DA for ; Sat, 12 Aug 2006 01:32:58 +0000 (UTC) (envelope-from silby@silby.com) Received: from relay00.pair.com (relay00.pair.com [209.68.5.9]) by mx1.FreeBSD.org (Postfix) with SMTP id 832F843D49 for ; Sat, 12 Aug 2006 01:32:57 +0000 (GMT) (envelope-from silby@silby.com) Received: (qmail 99132 invoked from network); 12 Aug 2006 01:32:56 -0000 Received: from unknown (HELO localhost) (unknown) by unknown with SMTP; 12 Aug 2006 01:32:56 -0000 X-pair-Authenticated: 209.68.2.70 Date: Fri, 11 Aug 2006 20:33:27 -0500 (CDT) From: Mike Silbersack To: Simon Walton In-Reply-To: <44DD1909.40703@matteworld.com> Message-ID: <20060811203041.E44075@odysseus.silby.com> References: <44DD1909.40703@matteworld.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-net@freebsd.org Subject: Re: Long keepidle time X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 01:32:58 -0000 On Fri, 11 Aug 2006, Simon Walton wrote: > Is there any reason why the default initial timeout for keep alive > packets needs to be as long as two hours? This period causes the dynamic > rules in my firewall filter to timeout. > > Is there a major objection to reducing the default idle time to > say 3 to 5 minutes? > > Simon Walton On reason behind a 2 hour keepalive is so that you don't have a 2 minute network outage that causes all your connections to timeout. Of course, as you point out, in the modern age of firewalls, more frequent keepalives can be a good thing. I don't forsee us changing FreeBSD's default keepalive setting, but you're more than welcome to change the setting on your own system. Also note that ipfw2 sends keepalive packets on its own, maybe you could switch to it and/or add that functionality to your favorite firewall package. :) Mike "Silby" Silbersack From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 07:50:53 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 40B3016A4DF; Sat, 12 Aug 2006 07:50:53 +0000 (UTC) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by mx1.FreeBSD.org (Postfix) with ESMTP id 823D743D46; Sat, 12 Aug 2006 07:50:50 +0000 (GMT) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by k2.vol.cz (8.12.11/8.12.9) with ESMTP id k7C7onXA044554; Sat, 12 Aug 2006 09:50:49 +0200 (CEST) (envelope-from daniel.ryslink@col.cz) Date: Sat, 12 Aug 2006 09:50:49 +0200 (CEST) From: Daniel Ryslink X-X-Sender: kamamura@k2.vol.cz To: Jack Vogel In-Reply-To: <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> Message-ID: <20060812094736.Q43868@k2.vol.cz> References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-SpamTest-Info: Profile: Formal (494/060811) X-SpamTest-Info: Profile: Detect Standard (4/030526) X-SpamTest-Info: Profile: SysLog X-SpamTest-Info: Profile: Marking Spam - Subject (2/030321) X-SpamTest-Status: Not detected X-SpamTest-Version: SMTP-Filter Version 2.0.0 [0125], KAS/Release Cc: freebsd-net@freebsd.org Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 07:50:53 -0000 Hello, Yesterday, I deployed the Intel driver version 6.1.4 compiled as a module, but the problem still prevails. Do you have any other suggestions than debug.mpsafenet=0 ? Thank you Regards Daniel Ryslink On Fri, 11 Aug 2006, Jack Vogel wrote: > On 8/11/06, Gleb Smirnoff wrote: >> Daniel, >> >> On Fri, Aug 11, 2006 at 01:42:32PM +0200, Daniel Ryslink wrote: >> D> We have started to use the em driver only recently, after the upgrade to >> D> gigabit connectivity (100 MBit NICs from Intel used the fxp driver). >> D> >> D> As for the frequency of the incidents, here is a grep of the messages: >> D> >> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >> D> Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting >> D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting >> D> Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting >> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >> D> >> D> The driver used is version 3.2.18 (I wanted to use the Intel 6.1.4 as a >> D> module, but I have found out that I made a mistake and accidentally >> loaded >> D> the old 3.2.18 driver). >> D> >> D> I have dilemma now - which new driver to try? The 6.0.5 submitted to the >> D> current FreeBSD 6.1 branch (modified by you, I believe, on 8th August), >> or >> D> the newest driver from Intel 6.1.4? Do you think one of these drivers >> D> could solve my problems? >> >> I'm not sure whether new driver will solve your problems. You should give >> a try to 6.1-STABLE which has 6.0.5 in it. The difference between 6.1.4 and >> 6.0.5 is quite small, I doubt that 6.1.4 worth a try in your case. > > Gleb is right, the difference between my 6.0.5 and 6.1.4 driver are minor > and don't seem to have anything to do with your problem. > > I am happy Gleb got my code merged with tip of STABLE and would take > that driver code if I were you, it will become 6.2 before long :) > > Watchdogs happen because of transmit cleanup failing, your instances > are pretty widely seperated, it looks like some external network problem > perhaps? > > Jack > Intel LAD > From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 08:06:42 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DC67016A4DA for ; Sat, 12 Aug 2006 08:06:41 +0000 (UTC) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by mx1.FreeBSD.org (Postfix) with ESMTP id 53ADC43D45 for ; Sat, 12 Aug 2006 08:06:40 +0000 (GMT) (envelope-from daniel.ryslink@col.cz) Received: from k2.vol.cz (k2.vol.cz [195.250.128.82]) by k2.vol.cz (8.12.11/8.12.9) with ESMTP id k7C86d4a045102; Sat, 12 Aug 2006 10:06:39 +0200 (CEST) (envelope-from daniel.ryslink@col.cz) Date: Sat, 12 Aug 2006 10:06:39 +0200 (CEST) From: Daniel Ryslink X-X-Sender: kamamura@k2.vol.cz To: Landon Fuller In-Reply-To: Message-ID: <20060812100354.I43868@k2.vol.cz> References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-SpamTest-Info: Profile: Formal (494/060811) X-SpamTest-Info: Profile: Detect Standard (4/030526) X-SpamTest-Info: Profile: SysLog X-SpamTest-Info: Profile: Marking Spam - Subject (2/030321) X-SpamTest-Status: Not detected X-SpamTest-Version: SMTP-Filter Version 2.0.0 [0125], KAS/Release Cc: freebsd-net@freebsd.org, Jack Vogel Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 08:06:42 -0000 Hello, Our machine is not running in SMP mode, it's single CPU with hyperthreading switched off. I would also like to point out that similar problem occured on yet another machine running as a web server with FreeBSD 6.1 and em driver. Also, hardware problems are unlikely, since we tried three different servers already and we have also changed ethernet cables on the whole route to the uplink switch. Best Regards Daniel Ryslink On Fri, 11 Aug 2006, Landon Fuller wrote: > > On Aug 11, 2006, at 09:22, Jack Vogel wrote: > >> On 8/11/06, Gleb Smirnoff wrote: >>> Daniel, >>> >>> On Fri, Aug 11, 2006 at 01:42:32PM +0200, Daniel Ryslink wrote: >>> D> We have started to use the em driver only recently, after the upgrade >>> to >>> D> gigabit connectivity (100 MBit NICs from Intel used the fxp driver). >>> D> >>> D> As for the frequency of the incidents, here is a grep of the messages: >>> D> >>> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >>> D> Aug 4 22:35:23 b2 kernel: em0: watchdog timeout -- resetting >>> D> Aug 5 00:09:20 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 5 06:08:59 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 6 12:38:16 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 6 20:39:47 b2 kernel: em0: watchdog timeout -- resetting >>> D> Aug 7 18:37:29 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 8 07:27:48 b2 kernel: em0: watchdog timeout -- resetting >>> D> Aug 8 09:38:17 b2 kernel: em0: watchdog timeout -- resetting >>> D> Aug 8 12:54:54 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 8 22:41:17 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 9 05:17:24 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 9 10:56:10 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 9 20:10:06 b2 kernel: em1: watchdog timeout -- resetting >>> D> Aug 11 08:41:44 b2 kernel: em0: watchdog timeout -- resetting >>> D> Aug 11 10:35:43 b2 kernel: em0: watchdog timeout -- resetting >>> D> ~~~~~~~~~~~~ ~~~~~~~~~~~~~~ >>> D> >>> D> The driver used is version 3.2.18 (I wanted to use the Intel 6.1.4 as a >>> D> module, but I have found out that I made a mistake and accidentally >>> loaded >>> D> the old 3.2.18 driver). >>> D> >>> D> I have dilemma now - which new driver to try? The 6.0.5 submitted to >>> the >>> D> current FreeBSD 6.1 branch (modified by you, I believe, on 8th August), >>> or >>> D> the newest driver from Intel 6.1.4? Do you think one of these drivers >>> D> could solve my problems? >>> >>> I'm not sure whether new driver will solve your problems. You should give >>> a try to 6.1-STABLE which has 6.0.5 in it. The difference between 6.1.4 >>> and >>> 6.0.5 is quite small, I doubt that 6.1.4 worth a try in your case. >> >> Gleb is right, the difference between my 6.0.5 and 6.1.4 driver are minor >> and don't seem to have anything to do with your problem. >> >> I am happy Gleb got my code merged with tip of STABLE and would take >> that driver code if I were you, it will become 6.2 before long :) >> >> Watchdogs happen because of transmit cleanup failing, your instances >> are pretty widely seperated, it looks like some external network problem >> perhaps? > > We saw this issue here on SMP systems running 6.1; I've been meaning to set > up a reproduction case in the lab and dig into the issue further. > Disabling the mpsafe network stack (debug.mpsafenet=0) is our temporary > work-around; rwatson mentioned that this has the effect of forcing the > interrupt handler for if_em to not run in parallel with the transmit code, > which is likely what caused the problem to disappear. > > -landonf From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 14:23:28 2006 Return-Path: X-Original-To: freebsd-net@freebsd.org Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6092216A4DD for ; Sat, 12 Aug 2006 14:23:28 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2170143D49 for ; Sat, 12 Aug 2006 14:23:28 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 9D22F46C03; Sat, 12 Aug 2006 10:23:27 -0400 (EDT) Date: Sat, 12 Aug 2006 15:23:27 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Mike Silbersack In-Reply-To: <20060811203041.E44075@odysseus.silby.com> Message-ID: <20060812152246.F45647@fledge.watson.org> References: <44DD1909.40703@matteworld.com> <20060811203041.E44075@odysseus.silby.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-net@freebsd.org, Simon Walton Subject: Re: Long keepidle time X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 14:23:28 -0000 On Fri, 11 Aug 2006, Mike Silbersack wrote: > On Fri, 11 Aug 2006, Simon Walton wrote: > >> Is there any reason why the default initial timeout for keep alive packets >> needs to be as long as two hours? This period causes the dynamic rules in >> my firewall filter to timeout. >> >> Is there a major objection to reducing the default idle time to say 3 to 5 >> minutes? > > On reason behind a 2 hour keepalive is so that you don't have a 2 minute > network outage that causes all your connections to timeout. > > Of course, as you point out, in the modern age of firewalls, more frequent > keepalives can be a good thing. > > I don't forsee us changing FreeBSD's default keepalive setting, but you're > more than welcome to change the setting on your own system. > > Also note that ipfw2 sends keepalive packets on its own, maybe you could > switch to it and/or add that functionality to your favorite firewall > package. :) FWIW, I believe pf also does this. We've run into some MAC Framework problems because firewalls generate keepalive packets in both pf and ipfw, since we don't know how to label these packets. Robert N M Watson Computer Laboratory University of Cambridge From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 16:29:54 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 78C6D16A4E8 for ; Sat, 12 Aug 2006 16:29:54 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from H43.C18.B96.tor.eicat.ca (H43.C18.B96.tor.eicat.ca [66.96.18.43]) by mx1.FreeBSD.org (Postfix) with ESMTP id 99C2243D5A for ; Sat, 12 Aug 2006 16:29:52 +0000 (GMT) (envelope-from mikej@rogers.com) Received: from [127.0.0.1] (desktop.home.local [172.16.0.200]) by H43.C18.B96.tor.eicat.ca (Postfix) with ESMTP id A91FE114C9 for ; Sat, 12 Aug 2006 12:30:13 -0400 (EDT) Message-ID: <44DE0208.2010101@rogers.com> Date: Sat, 12 Aug 2006 12:30:00 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.5 (Windows/20060719) MIME-Version: 1.0 To: net@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-SpamToaster-Information: This messages has been scanned by SpamToaster http://www.digitalprogression.ca X-SpamToaster: Found to be clean X-SpamToaster-SpamCheck: not spam, SpamAssassin (not cached, score=-2.49, required 3.5, ALL_TRUSTED -1.80, BAYES_00 -2.60, DK_POLICY_SIGNSOME 0.00, DNS_FROM_RFC_ABUSE 0.20, DNS_FROM_RFC_POST 1.71) X-SpamToaster-From: mikej@rogers.com X-Spam-Status: No Cc: Subject: CARP howto X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 16:29:54 -0000 Does anyone know a good CARP howto for FreeBSD? I've googled around, but i cant find anything specific to FreeBSD. From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 18:54:09 2006 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BF29E16A4DA for ; Sat, 12 Aug 2006 18:54:09 +0000 (UTC) (envelope-from citrin@citrin.ru) Received: from mail.classis.ru (classis.ru [213.248.60.120]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4DC6A43D45 for ; Sat, 12 Aug 2006 18:54:09 +0000 (GMT) (envelope-from citrin@citrin.ru) Received: from citrin.rambler.stack.net (ppp83-237-28-153.pppoe.mtu-net.ru [83.237.28.153]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) (Authenticated sender: citrin.citrin.ru) by mail.classis.ru (Postfix) with ESMTP id EE36E1229EAB for ; Sat, 12 Aug 2006 22:54:07 +0400 (MSD) Date: Sat, 12 Aug 2006 22:54:05 +0400 From: Anton Yuzhaninov X-Mailer: The Bat! (v3.62.14) Professional Organization: Rambler X-Priority: 3 (Normal) Message-ID: <17410703353.20060812225405@citrin.ru> To: Mike Jakubik In-Reply-To: <44DE0208.2010101@rogers.com> References: <44DE0208.2010101@rogers.com> MIME-Version: 1.0 Content-Type: multipart/signed; protocol="application/pkcs7-signature"; micalg=sha1; boundary="----------A11C31CB58693B3" X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Subject: Re: CARP howto X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 18:54:09 -0000 This is a cryptographically signed message in MIME format. ------------A11C31CB58693B3 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Saturday, August 12, 2006, 8:30:00 PM, Mike Jakubik wrote: MJ> Does anyone know a good CARP howto for FreeBSD? I've googled around, but MJ> i cant find anything specific to FreeBSD. You can use CARP howto for OpenBSD. --=20 WBR, Anton Yuzhaninov ------------A11C31CB58693B3-- From owner-freebsd-net@FreeBSD.ORG Sat Aug 12 19:03:03 2006 Return-Path: X-Original-To: freebsd-net@FreeBSD.org Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 569C116A4DD for ; Sat, 12 Aug 2006 19:03:03 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (cell.sick.ru [217.72.144.68]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9A18443D46 for ; Sat, 12 Aug 2006 19:03:02 +0000 (GMT) (envelope-from glebius@FreeBSD.org) Received: from cell.sick.ru (glebius@localhost [127.0.0.1]) by cell.sick.ru (8.13.4/8.13.3) with ESMTP id k7CJ2sUS098090 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Sat, 12 Aug 2006 23:02:54 +0400 (MSD) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.sick.ru (8.13.4/8.13.1/Submit) id k7CJ2r2i098089; Sat, 12 Aug 2006 23:02:53 +0400 (MSD) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.sick.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Sat, 12 Aug 2006 23:02:53 +0400 From: Gleb Smirnoff To: Daniel Ryslink Message-ID: <20060812190253.GK96644@cell.sick.ru> Mail-Followup-To: Gleb Smirnoff , Daniel Ryslink , Jack Vogel , freebsd-net@freebsd.org References: <20060811100536.V80282@k2.vol.cz> <20060811111240.GD96644@FreeBSD.org> <20060811133531.D80282@k2.vol.cz> <20060811125825.GH96644@cell.sick.ru> <2a41acea0608110922h4bed63b1ke09f91b610819805@mail.gmail.com> <20060812094736.Q43868@k2.vol.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <20060812094736.Q43868@k2.vol.cz> User-Agent: Mutt/1.5.6i Cc: freebsd-net@FreeBSD.org, Jack Vogel Subject: Re: Problems with em interfaces on FreeBSD 6.1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Aug 2006 19:03:03 -0000 On Sat, Aug 12, 2006 at 09:50:49AM +0200, Daniel Ryslink wrote: D> Yesterday, I deployed the Intel driver version 6.1.4 compiled as a module, D> but the problem still prevails. D> D> Do you have any other suggestions than debug.mpsafenet=0 ? The fact that debug.mpsafenet=0 fixes the problem is quite important. I think, we will find some fix in close future. The only problem is to find how to reproduce the problem _quickly_. In my setups the watchdog timeout happens few times per day. -- Totus tuus, Glebius. GLEBIUS-RIPN GLEB-RIPE