From owner-freebsd-net@freebsd.org Sun Aug 30 00:05:03 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B78409C5743 for ; Sun, 30 Aug 2015 00:05:03 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A41041512 for ; Sun, 30 Aug 2015 00:05:03 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t7U053LV029656 for ; Sun, 30 Aug 2015 00:05:03 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 200221] em0 watchdog timeout under load Date: Sun, 30 Aug 2015 00:05:03 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.1-RELEASE X-Bugzilla-Keywords: IntelNetworking, needs-qa, patch X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: anthony@ury.org.uk X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 30 Aug 2015 00:05:03 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=200221 --- Comment #15 from anthony@ury.org.uk --- Apologies for the delay in updating - I had to wait for a period where I could reboot the server into a new kernel. I've patched CURRENT@286381 (and also CURRENT@285879) onto the changes from 10.1-RELEASE as described in Comment 12. After about a week in use, I've seen no watchdog timeout issues, so this patch seems to have solved the issue - thanks! I'll now try the patch onto the other server which uses the e1000 driver - although that one occurs rarely. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sun Aug 30 17:28:25 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 0491C9C60C8 for ; Sun, 30 Aug 2015 17:28:25 +0000 (UTC) (envelope-from eliezer@ngtech.co.il) Received: from mtaout24.012.net.il (mtaout24.012.net.il [80.179.55.180]) by mx1.freebsd.org (Postfix) with ESMTP id 7827A1C23 for ; Sun, 30 Aug 2015 17:28:24 +0000 (UTC) (envelope-from eliezer@ngtech.co.il) Received: from conversion-daemon.mtaout24.012.net.il by mtaout24.012.net.il (HyperSendmail v2007.08) id <0NTW00B00NQTSF00@mtaout24.012.net.il> for freebsd-net@freebsd.org; Sun, 30 Aug 2015 20:15:24 +0300 (IDT) Received: from mail.ngtech.co.il ([84.95.212.160]) by mtaout24.012.net.il (HyperSendmail v2007.08) with ESMTPSA id <0NTW00BY8NXOSK00@mtaout24.012.net.il> for freebsd-net@freebsd.org; Sun, 30 Aug 2015 20:15:24 +0300 (IDT) Received: by mail.ngtech.co.il (Postfix, from userid 5001) id 09D6F2397D; Sun, 30 Aug 2015 20:23:14 +0300 (IDT) Received: from [192.168.10.131] (unknown [192.168.10.131]) by mail.ngtech.co.il (Postfix) with ESMTPA id DE26123805 for ; Sun, 30 Aug 2015 20:23:12 +0300 (IDT) Date: Sun, 30 Aug 2015 20:23:13 +0300 From: Eliezer Croitoru Subject: Re: Issues with MASQUARDE and FreeBSD router. In-reply-to: <55DEC2BC.8030800@ngtech.co.il> X-012-Sender: eliezer-111@012.net.il To: freebsd-net@freebsd.org Message-id: <55E33C01.8040507@ngtech.co.il> MIME-version: 1.0 Content-type: text/plain; charset=windows-1252; format=flowed Content-transfer-encoding: 7bit X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on mail.ngtech.co.il References: <55DDEA51.8010902@ngtech.co.il> <55DEC2BC.8030800@ngtech.co.il> User-Agent: Mozilla/5.0 (Windows NT 6.3; WOW64; rv:38.0) Gecko/20100101 Thunderbird/38.2.0 X-Spam-Status: No, score=-1.0 required=3.0 tests=ALL_TRUSTED autolearn=ham autolearn_force=no version=3.4.0 X-Spam-Level: X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 30 Aug 2015 17:28:25 -0000 As a reference to this issue the bugzilla report at: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=165059#c9 The issue is that packets sums are being corrupted and there for cannot be accepted by the TCP stack of the destination machine. The issue might also effect UDP. *The issue only affects packets that are being routed throw the FreeBSD box and not regular sockets.* An exact same issue was there in OpenBSD 5.7 and on current(5.8) it got fixed. Eliezer On 27/08/2015 10:56, Eliezer Croitoru wrote: > I added a filter rule to iptables with a INVALID reject match and any > packet that is being passed throw the FreeBSD router is being marked by > itpables as INVALID. > An example for an INVALID packet: > http://ngtech.co.il/nat_issue/proxy2.pcap > > Eliezer > > On 26/08/2015 21:24, Eliezer Croitoru wrote: >> Hey lists, >> >> I had a similar issue in the past but now I have found the combination >> which results in the issue. >> My topology is between two KVM hosts. >> Server is on KVM1 ip address 192.168.10.1/24 >> Another whole network on the KVM2. >> And the traffic is: >> client 192.168.11.2/24 --> R1 - 192.168.11.254/24 >> R1 192.168.15.1/24 --> R2(NAT SERVER) 192.168.15.254/24 >> R3 eth4 NATed(masquerade) 192.168.10.179/24 --> Server 192.168.10.1/24 >> >> The Above is what is suppose to happen and the reality us that >> 192.168.10.1 receives a packet but from 192.168.11.2. >> >> I can reproduce the issue successfully replacing the R1 server from a >> linux box to a FreeBSD 10.1 box.(freebsd causes the issue) >> The routers I have used are: >> CentOS 7 >> VYOS 1.6 >> >> It is the same for both and I can reproduce the issue successfully. >> >> I have also tested the R1 replaced with: >> VYOS 1.7 >> CENTOS 7 >> DEBIAN 8 >> vSRX >> FreeBSD 4.11 with e1000 card, works fine. >> FreeBSD 10.1(amd64) with e1000 card, works fine. >> *FreeBSD 10.1(amd64) with virtio card, have an issue.* >> >> Now I am trying to figure out if it's a netfilter issue or FreeBSD >> virtio driver issue and if so what might be the direction to make this >> issue fixed. >> >> Tcpdump captures on the NAT router of different packets and sessions are >> here: >> http://ngtech.co.il/nat_issue/ >> >> If the issue is probably with the FreeBSD virtio drivers why would the >> MASQUERADE pass the packet to the destination server? >> >> Thanks, >> Eliezer >> >> >> > > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@freebsd.org Sun Aug 30 20:14:05 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 9BEA79C643B for ; Sun, 30 Aug 2015 20:14:05 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 88900F05 for ; Sun, 30 Aug 2015 20:14:05 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t7UKE5ma088371 for ; Sun, 30 Aug 2015 20:14:05 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202351] [ip6] [panic] Kernel panic in ip6_forward (different from 128247, 131038) Date: Sun, 30 Aug 2015 20:14:04 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: kp@freebsd.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 30 Aug 2015 20:14:05 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202351 Kristof Provost changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |kp@freebsd.org --- Comment #3 from Kristof Provost --- Can you test https://reviews.freebsd.org/D3534 ? I expect that things still won't be entirely perfect, but it should at least fix the panic. The issue is that when we use pf to filter on a bridge (i.e. net.link.bridge.pfil_bridge is set) we mistakenly thing that we're routing the packet because the rvcif and the output interface (ifp) are different. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sun Aug 30 21:00:22 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id ED1659C0C5A for ; Sun, 30 Aug 2015 21:00:22 +0000 (UTC) (envelope-from bugzilla-noreply@FreeBSD.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C827EC8D for ; Sun, 30 Aug 2015 21:00:22 +0000 (UTC) (envelope-from bugzilla-noreply@FreeBSD.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t7UL0MES072501 for ; Sun, 30 Aug 2015 21:00:22 GMT (envelope-from bugzilla-noreply@FreeBSD.org) Message-Id: <201508302100.t7UL0MES072501@kenobi.freebsd.org> From: bugzilla-noreply@FreeBSD.org To: freebsd-net@FreeBSD.org Subject: Problem reports for freebsd-net@FreeBSD.org that need special attention X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 Date: Sun, 30 Aug 2015 21:00:22 +0000 Content-Type: text/plain; charset="UTF-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 30 Aug 2015 21:00:23 -0000 To view an individual PR, use: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=(Bug Id). The following is a listing of current problems submitted by FreeBSD users, which need special attention. These represent problem reports covering all versions including experimental development code and obsolete releases. Status | Bug Id | Description ------------+-----------+--------------------------------------------------- Open | 194515 | Fatal Trap 12 Kernel with vimage Open | 199136 | [if_tap] Added down_on_close sysctl variable to t 2 problems total for which you should take action. From owner-freebsd-net@freebsd.org Mon Aug 31 04:05:33 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 754449C6DCF for ; Mon, 31 Aug 2015 04:05:33 +0000 (UTC) (envelope-from btw@mail.ustc.edu.cn) Received: from ustc.edu.cn (email6.ustc.edu.cn [IPv6:2001:da8:d800::8]) by mx1.freebsd.org (Postfix) with ESMTP id 3A84E2B2; Mon, 31 Aug 2015 04:05:31 +0000 (UTC) (envelope-from btw@mail.ustc.edu.cn) Received: from dell.my.domain (unknown [182.112.28.20]) by newmailweb.ustc.edu.cn (Coremail) with SMTP id LkAmygBnVwiE0uNVrLalAA--.7299S2; Mon, 31 Aug 2015 12:05:28 +0800 (CST) From: Tiwei Bie To: freebsd-net@freebsd.org Cc: adrian@freebsd.org, hiren@freebsd.org Subject: A bug in udp6_input() - should use proto instead of ip6->ip6_nxt Date: Mon, 31 Aug 2015 12:05:49 +0800 Message-Id: <1440993949-20698-1-git-send-email-btw@mail.ustc.edu.cn> X-Mailer: git-send-email 2.4.6 X-CM-TRANSID: LkAmygBnVwiE0uNVrLalAA--.7299S2 X-Coremail-Antispam: 1UD129KBjvJXoW7ZryDCw43Ww1UJw1DuFy5twb_yoW8Ww43pa y3JryDWa1UJrnrCr4Ikr4UWr4rGrs8C3yfuw4avry0kFW29r18tFWkJF4akrW8G3Wj93yY 9Fnxt3y5C3s7X3DanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUyIb7Iv0xC_KF4lb4IE77IF4wAFF20E14v26r1j6r4UM7CY07I2 0VC2zVCF04k26cxKx2IYs7xG6rWj6s0DM7CIcVAFz4kK6r1j6r18M28lY4IEw2IIxxk0rw A2F7IY1VAKz4vEj48ve4kI8wA2z4x0Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xII jxv20xvEc7CjxVAFwI0_Cr0_Gr1UM28EF7xvwVC2z280aVAFwI0_GcCE3s1l84ACjcxK6I 8E87Iv6xkF7I0E14v26rxl6s0DM2AIxVAIcxkEcVAq07x20xvEncxIr21l5I8CrVACY4xI 64kE6c02F40Ex7xfMcIj6xIIjxv20xvE14v26r106r15McIj6I8E87Iv67AKxVWUJVW8Jw Am72CE4IkC6x0Yz7v_Jr0_Gr1lF7xvr2IYc2Ij64vIr41l42xK82IYc2Ij64vIr41l4I8I 3I0E4IkC6x0Yz7v_Jr0_Gr1lx2IqxVAqx4xG67AKxVWUJVWUGwC20s026x8GjcxK67AKxV WUGVWUWwC2zVAF1VAY17CE14v26r1Y6r17MIIYrxkI7VAKI48JMIIF0xvE2Ix0cI8IcVAF wI0_Jr0_JF4lIxAIcVC0I7IYx2IY6xkF7I0E14v26r1j6r4UMIIF0xvE42xK8VAvwI8IcI k0rVW3JVWrJr1lIxAIcVC2z280aVAFwI0_Jr0_Gr1lIxAIcVC2z280aVCY1x0267AKxVWU JVW8JbIYCTnIWIevJa73UjIFyTuYvjxU2cdbUUUUU X-CM-SenderInfo: xewzqzxdloh3xvwfhvlgxou0/1tbiAQYRAVQhmDZvLQAQse X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 31 Aug 2015 04:05:33 -0000 I found a bug in udp6_input(). The 'proto' parameter should be used to get the protocol number (UDP or UDPLITE), instead of ip6->ip6_nxt. Because ip6->ip6_nxt may be the protocol number of extension header, such as: If a UDP packet is an "atomic" fragment, frag6_input() will return directly, and ip6->ip6_nxt will be IPPROTO_FRAGMENT (if the first extension header is the fragment header) instead of IPPROTO_UDP or IPPROTO_UDPLITE: int frag6_input(struct mbuf **mp, int *offp, int proto) { ...... /* * RFC 6946: Handle "atomic" fragments (offset and m bit set to 0) * upfront, unrelated to any reassembly. Just skip the fragment header. */ if ((ip6f->ip6f_offlg & ~IP6F_RESERVED_MASK) == 0) { /* XXX-BZ we want dedicated counters for this. */ IP6STAT_INC(ip6s_reassembled); in6_ifstat_inc(dstifp, ifs6_reass_ok); *offp = offset; return (ip6f->ip6f_nxt); } And this is the patch to fix this bug: diff --git a/sys/netinet6/udp6_usrreq.c b/sys/netinet6/udp6_usrreq.c index 98790a8..da72f00 100644 --- a/sys/netinet6/udp6_usrreq.c +++ b/sys/netinet6/udp6_usrreq.c @@ -207,7 +207,7 @@ udp6_input(struct mbuf **mp, int *offp, int proto) struct sockaddr_in6 fromsa; struct m_tag *fwd_tag; uint16_t uh_sum; - uint8_t nxt; + uint8_t nxt = proto; ifp = m->m_pkthdr.rcvif; ip6 = mtod(m, struct ip6_hdr *); @@ -233,7 +233,6 @@ udp6_input(struct mbuf **mp, int *offp, int proto) plen = ntohs(ip6->ip6_plen) - off + sizeof(*ip6); ulen = ntohs((u_short)uh->uh_ulen); - nxt = ip6->ip6_nxt; cscov_partial = (nxt == IPPROTO_UDPLITE) ? 1 : 0; if (nxt == IPPROTO_UDPLITE) { /* Zero means checksum over the complete packet. */ Best regards, Tiwei Bie From owner-freebsd-net@freebsd.org Mon Aug 31 09:28:20 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 9A95C9C7B91 for ; Mon, 31 Aug 2015 09:28:20 +0000 (UTC) (envelope-from bz@FreeBSD.org) Received: from mx1.sbone.de (mx1.sbone.de [IPv6:2a01:4f8:130:3ffc::401:25]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (Client CN "mx1.sbone.de", Issuer "SBone.DE" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 58AFFDED; Mon, 31 Aug 2015 09:28:20 +0000 (UTC) (envelope-from bz@FreeBSD.org) Received: from mail.sbone.de (mail.sbone.de [IPv6:fde9:577b:c1a9:31::2013:587]) (using TLSv1 with cipher ADH-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by mx1.sbone.de (Postfix) with ESMTPS id 7E91525D37D1; Mon, 31 Aug 2015 09:28:17 +0000 (UTC) Received: from content-filter.sbone.de (content-filter.sbone.de [IPv6:fde9:577b:c1a9:31::2013:2742]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.sbone.de (Postfix) with ESMTPS id 90CA4C7704A; Mon, 31 Aug 2015 09:28:16 +0000 (UTC) X-Virus-Scanned: amavisd-new at sbone.de Received: from mail.sbone.de ([IPv6:fde9:577b:c1a9:31::2013:587]) by content-filter.sbone.de (content-filter.sbone.de [fde9:577b:c1a9:31::2013:2742]) (amavisd-new, port 10024) with ESMTP id crphvtITpXAr; Mon, 31 Aug 2015 09:28:14 +0000 (UTC) Received: from [IPv6:fde9:577b:c1a9:4410:7515:be48:68e8:e50] (unknown [IPv6:fde9:577b:c1a9:4410:7515:be48:68e8:e50]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.sbone.de (Postfix) with ESMTPSA id DD62CC76FE0; Mon, 31 Aug 2015 09:28:12 +0000 (UTC) Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) Subject: Re: A bug in udp6_input() - should use proto instead of ip6->ip6_nxt From: "Bjoern A. Zeeb" In-Reply-To: <1440993949-20698-1-git-send-email-btw@mail.ustc.edu.cn> Date: Mon, 31 Aug 2015 09:28:07 +0000 Cc: freebsd-net@freebsd.org, adrian@freebsd.org, hiren@freebsd.org Content-Transfer-Encoding: quoted-printable Message-Id: <5FEE8C05-A25A-4A74-A8B0-4CA75A696D54@FreeBSD.org> References: <1440993949-20698-1-git-send-email-btw@mail.ustc.edu.cn> To: Tiwei Bie X-Mailer: Apple Mail (2.2104) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 31 Aug 2015 09:28:20 -0000 > On 31 Aug 2015, at 04:05 , Tiwei Bie wrote: >=20 > I found a bug in udp6_input(). The 'proto' parameter should be used to > get the protocol number (UDP or UDPLITE), instead of ip6->ip6_nxt. >=20 > Because ip6->ip6_nxt may be the protocol number of extension header, > such as: >=20 > If a UDP packet is an "atomic" fragment, frag6_input() will return > directly, and ip6->ip6_nxt will be IPPROTO_FRAGMENT (if the first > extension header is the fragment header) instead of IPPROTO_UDP or > IPPROTO_UDPLITE: Hmm, that might be a bug elsewhere but atomic fragments are soon to go = away again; wish people would listen in first place; but anyway. There are more of these bugs that came with the UDP-Lite code, such as = 4mapped addresses are not handled correctly in the output path, etc. Can you open a bug for this and we can attach all the UDP-Lite fixes to = it to properly document them and get them through review in a few days = and committed? Thanks, Bjoern= From owner-freebsd-net@freebsd.org Mon Aug 31 10:07:24 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 3FEAD9C7308 for ; Mon, 31 Aug 2015 10:07:24 +0000 (UTC) (envelope-from btw@mail.ustc.edu.cn) Received: from ustc.edu.cn (email6.ustc.edu.cn [IPv6:2001:da8:d800::8]) by mx1.freebsd.org (Postfix) with ESMTP id BD41D796; Mon, 31 Aug 2015 10:07:22 +0000 (UTC) (envelope-from btw@mail.ustc.edu.cn) Received: from dell (unknown [182.112.31.34]) by newmailweb.ustc.edu.cn (Coremail) with SMTP id LkAmygD318BPJ+RVSjqnAA--.2822S2; Mon, 31 Aug 2015 18:07:17 +0800 (CST) Date: Mon, 31 Aug 2015 18:07:38 +0800 From: Tiwei Bie To: "Bjoern A. Zeeb" Cc: freebsd-net@freebsd.org, adrian@freebsd.org, hiren@freebsd.org Subject: Re: A bug in udp6_input() - should use proto instead of ip6->ip6_nxt Message-ID: <20150831100738.GA94313@dell> References: <1440993949-20698-1-git-send-email-btw@mail.ustc.edu.cn> <5FEE8C05-A25A-4A74-A8B0-4CA75A696D54@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <5FEE8C05-A25A-4A74-A8B0-4CA75A696D54@FreeBSD.org> User-Agent: Mutt/1.5.23 (2014-03-12) X-CM-TRANSID: LkAmygD318BPJ+RVSjqnAA--.2822S2 X-Coremail-Antispam: 1UD129KBjvdXoWrKFWUJFyUCFy8JF47ZFW3Awb_yoWkCFXE9F y5Z34rC3yUAanFga13GF1FgrW7GrWqkFW5KF98XFs2yr93JrZruws3GasYvr1UJrnxWrnx uFn0vFya9rnF9jkaLaAFLSUrUUUUUb8apTn2vfkv8UJUUUU8Yxn0WfASr-VFAUDa7-sFnT 9fnUUIcSsGvfJTRUUUbF8YjsxI4VWDJwAYFVCjjxCrM7AC8VAFwI0_Jr0_Gr1l1xkIjI8I 6I8E6xAIw20EY4v20xvaj40_Wr0E3s1l1IIY67AEw4v_Jr0_Jr4l8cAvFVAK0II2c7xJM2 8CjxkF64kEwVA0rcxSw2x7M28EF7xvwVC0I7IYx2IY67AKxVW7JVWDJwA2z4x0Y4vE2Ix0 cI8IcVCY1x0267AKxVWxJVW8Jr1l84ACjcxK6I8E87Iv67AKxVW0oVCq3wA2z4x0Y4vEx4 A2jsIEc7CjxVAFwI0_GcCE3s1le2I262IYc4CY6c8Ij28IcVAaY2xG8wAqx4xG64xvF2IE w4CE5I8CrVC2j2WlYx0E2Ix0cI8IcVAFwI0_Jr0_Jr4lYx0Ex4A2jsIE14v26r1j6r4UMc vjeVCFs4IE7xkEbVWUJVW8JwACjcxG0xvEwIxGrwCF04k20xvY0x0EwIxGrwCFx2IqxVCF s4IE7xkEbVWUJVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r 1rMI8E67AF67kF1VAFwI0_JF0_Jw1lIxkGc2Ij64vIr41lIxAIcVC0I7IYx2IY67AKxVWU JVWUCwCI42IY6xIIjxv20xvEc7CjxVAFwI0_Jr0_Gr1lIxAIcVCF04k26cxKx2IYs7xG6r W3Jr0E3s1lIxAIcVC2z280aVAFwI0_Jr0_Gr1lIxAIcVC2z280aVCY1x0267AKxVW8JVW8 JrUvcSsGvfC2KfnxnUUI43ZEXa7IU8v_M3UUUUU== X-CM-SenderInfo: xewzqzxdloh3xvwfhvlgxou0/1tbiAQYSAVQhmDcQpwAEs9 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 31 Aug 2015 10:07:24 -0000 On Mon, Aug 31, 2015 at 09:28:07AM +0000, Bjoern A. Zeeb wrote: > > > On 31 Aug 2015, at 04:05 , Tiwei Bie wrote: > > > > I found a bug in udp6_input(). The 'proto' parameter should be used to > > get the protocol number (UDP or UDPLITE), instead of ip6->ip6_nxt. > > > > Because ip6->ip6_nxt may be the protocol number of extension header, > > such as: > > > > If a UDP packet is an "atomic" fragment, frag6_input() will return > > directly, and ip6->ip6_nxt will be IPPROTO_FRAGMENT (if the first > > extension header is the fragment header) instead of IPPROTO_UDP or > > IPPROTO_UDPLITE: > > Hmm, that might be a bug elsewhere but atomic fragments are soon to go away again; wish people would listen in first place; but anyway. > > There are more of these bugs that came with the UDP-Lite code, such as 4mapped addresses are not handled correctly in the output path, etc. > > Can you open a bug for this and we can attach all the UDP-Lite fixes to it to properly document them and get them through review in a few days and committed? > Sure! ^_^ Here is the link: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202788 Best regards, Tiwei Bie From owner-freebsd-net@freebsd.org Mon Aug 31 16:39:57 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id CCF8B9C6FA2 for ; Mon, 31 Aug 2015 16:39:57 +0000 (UTC) (envelope-from hr1sh1@yahoo.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id AB9921B39 for ; Mon, 31 Aug 2015 16:39:57 +0000 (UTC) (envelope-from hr1sh1@yahoo.com) Received: by mailman.ysv.freebsd.org (Postfix) id A8E339C6F9F; Mon, 31 Aug 2015 16:39:57 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A877C9C6F9E for ; Mon, 31 Aug 2015 16:39:57 +0000 (UTC) (envelope-from hr1sh1@yahoo.com) Received: from nm26-vm10.bullet.mail.gq1.yahoo.com (nm26-vm10.bullet.mail.gq1.yahoo.com [98.136.216.137]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7C52A1B38 for ; Mon, 31 Aug 2015 16:39:57 +0000 (UTC) (envelope-from hr1sh1@yahoo.com) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1441038855; bh=9yqvKfcxpSbSWHvtAhxDOcknO8nzjFYrsul1eqt7Cbk=; h=From:Subject:Date:To:From:Subject; b=rrDyRbhhlyTIlEDUnpTGjBFdUPXfKGyRbBqrCCgx0+pru8lBTzaJlj92j2dNj+ApQ2cBZhEBxjpXskhOHL3cf4tWxWgHcx6pDv0iB0VO0SJzE1ARpwS2Qt1VO0envVHbnCvHHk66sujsiAvNRPdrSuRwFnumkhjSvAJRHxDWaamprdSYSW3zpB6Z5Z2AAKzxyLZkw4z11xleUXYs701uS6abr8Ghhbb8caP1zeUTPxhkzSEgkbrOZ5+s2I1Ug5W4xoF9t3r4PmT4JBpP7Aq/z5yURZAgFQxh7z+vr00EaxXdjt8lXtGAj+x3ECF9/YDGUUBF49cq8cQnVjotsUAAOw== Received: from [98.137.12.58] by nm26.bullet.mail.gq1.yahoo.com with NNFMP; 31 Aug 2015 16:34:15 -0000 Received: from [98.136.164.71] by tm3.bullet.mail.gq1.yahoo.com with NNFMP; 31 Aug 2015 16:34:15 -0000 Received: from [127.0.0.1] by smtp233.mail.gq1.yahoo.com with NNFMP; 31 Aug 2015 16:34:15 -0000 X-Yahoo-Newman-Id: 67490.36142.bm@smtp233.mail.gq1.yahoo.com X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: D_Lk7H0VM1k3ZcYYuLcqnpxjw_ZiFgkdm1B2GcwWomXczpa 32i.Hm0CZ63yXee.WcxVlQ76sLuJ2iMVgOZ2aU6rJ1dwb2usTi2XtsgtHLjb 2JRmDX5x1PZIbz4rlDl7v1pLsQZF9G5Eabl..maZ_9tsWhBZrIuzsEwOQxss xV7yDlTEKkBqhU.e0lImGSKKk0VvYT27GtNqmyQrl_5C5D7C2ovQxdjdO7.z CYoFyLN.CIHKse_HNvlbjbE9Triu2X6.40t.kpW_fYTI4eZUeaS2omKav5z_ satnmBxjm5LPFdh1XhcF_V_zmsa8ie3_Tt37lNresTIgNfLDsz2b1Fb4l9BK l7jWENeSWELQO0uPERkyIg6UGDJOFs.ktmJ5FtdxZhkakCLdgxa2P4sCFUiv aUGrQdQoYK9.pbgvdHccnLBevOP1Sq8G3kjruQ4cIBh8l7eSrBvfnuESm3Zl H.9YNZxXiHYvd4fzogctOYz_wPzUB8jYCURdWxVKFRNxCvZ6qI5fjiRBlA_8 - X-Yahoo-SMTP: iMEfVeSswBC.EZkJ4kuORkNsxQ-- From: Hrishikesh Keremane Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Subject: GPL issues around OFED code in FreeBSD 9.1 Message-Id: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> Date: Mon, 31 Aug 2015 09:34:14 -0700 To: hackers@freebsd.org, net@freebsd.org Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) X-Mailer: Apple Mail (2.2104) X-Mailman-Approved-At: Mon, 31 Aug 2015 17:07:12 +0000 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 31 Aug 2015 16:39:57 -0000 [Sorry for cross posting] Hi, We are working on a product(FreeBSD based) that would require RDMA over = iWARP and are considering using the OFED stack in FreeBSD 9.1. We will be making some changes to the OFED stack to customize it to our = requirements. The concern is regarding the implications of GPL licensing of OFED on = our code base. Has anyone worked with OFED in FreeBSD and/or is aware of the licensing = issues around it? Thanks in advance for your help. Please include me in your replies as I am not subscribed to these lists. Thanks, Hrishi From owner-freebsd-net@freebsd.org Mon Aug 31 17:25:41 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id DD6189C65DE for ; Mon, 31 Aug 2015 17:25:41 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id BC80C1F67 for ; Mon, 31 Aug 2015 17:25:41 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id B7D639C65DC; Mon, 31 Aug 2015 17:25:41 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B70C39C65DA; Mon, 31 Aug 2015 17:25:41 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: from mail-pa0-x232.google.com (mail-pa0-x232.google.com [IPv6:2607:f8b0:400e:c03::232]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 896C11F60; Mon, 31 Aug 2015 17:25:41 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: by pacdd16 with SMTP id dd16so145587817pac.2; Mon, 31 Aug 2015 10:25:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=jOTVo3W8EXIHBTFTkCjiuk+ZQ2HXpXWR7JBmfIB0KMU=; b=ZNtwoZ8uoWzP3vCdypBTSrgt4vzF5MEG152zqj3hygQuZYReIrN7FVbV2u+xvi9cXc Xkki1Gj7A9TdpeZ4vBNqaoFeyH0H18BhQCMv4j8PwhKKU5TdSerz+8hUR+Tgh9ckMbSb qV9P/qE3/feyWZUbHI/TsZbIGvjAQ6rCdn9MwRwskI2zfmkg4LAcstlPLwX67Lb2maP8 8aGAHbbS0Wfxuu/Vd6Jb9tzjuHo7AEQAWuNtSd+iLi637Hk6GLRtgO6Pu+AKbscXSYlY DJ9BjSNdJ05QqCpJyphUqfRpfrANcIaKjXaZrXC0GVIv+GZbDcDxO0u3fe466AjZe/ut VEMg== X-Received: by 10.66.144.165 with SMTP id sn5mr15514864pab.122.1441041941099; Mon, 31 Aug 2015 10:25:41 -0700 (PDT) Received: from ?IPv6:2601:601:800:126d:fdd2:9111:6c01:3040? ([2601:601:800:126d:fdd2:9111:6c01:3040]) by smtp.gmail.com with ESMTPSA id jd12sm11642675pbd.44.2015.08.31.10.25.40 (version=TLSv1/SSLv3 cipher=OTHER); Mon, 31 Aug 2015 10:25:40 -0700 (PDT) Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (1.0) Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: Garrett Cooper X-Mailer: iPhone Mail (12H321) In-Reply-To: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> Date: Mon, 31 Aug 2015 10:25:39 -0700 Cc: "hackers@freebsd.org" , "net@freebsd.org" Content-Transfer-Encoding: quoted-printable Message-Id: References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> To: Hrishikesh Keremane X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 31 Aug 2015 17:25:42 -0000 > On Aug 31, 2015, at 09:34, Hrishikesh Keremane via freebsd-hackers wrote: >=20 > [Sorry for cross posting] >=20 > Hi, >=20 > We are working on a product(FreeBSD based) that would require RDMA over iW= ARP and are considering using the OFED stack in FreeBSD 9.1. > We will be making some changes to the OFED stack to customize it to our re= quirements. >=20 > The concern is regarding the implications of GPL licensing of OFED on our c= ode base. > Has anyone worked with OFED in FreeBSD and/or is aware of the licensing is= sues around it? >=20 > Thanks in advance for your help. >=20 > Please include me in your replies as I am not subscribed to these lists. The OFED stack is BSD/GPLv2 dual licensed IIRC. the Mellanox import might ha= ve made it 100% BSD licensed though. There's FreeBSD-infiniband@freebsd.org as well. It's a low traffic list, but= it might hit a better target audience in the future. Cheers, -NGie= From owner-freebsd-net@freebsd.org Tue Sep 1 06:40:11 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 021DA9C8A07 for ; Tue, 1 Sep 2015 06:40:11 +0000 (UTC) (envelope-from njwilliams@swin.edu.au) Received: from gpo1.cc.swin.edu.au (gpo1.cc.swin.edu.au [136.186.1.30]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7C371C85 for ; Tue, 1 Sep 2015 06:40:10 +0000 (UTC) (envelope-from njwilliams@swin.edu.au) Received: from [136.186.242.243] (vpn242-243.cc.swin.edu.au [136.186.242.243]) by gpo1.cc.swin.edu.au (8.14.3/8.14.3) with ESMTP id t816e6Ce032735 for ; Tue, 1 Sep 2015 16:40:07 +1000 To: freebsd-net@freebsd.org From: Nigel Williams Subject: Multipath TCP for FreeBSD v0.5 Message-ID: <55E54846.4020504@swin.edu.au> Date: Tue, 1 Sep 2015 16:40:06 +1000 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.2.0 MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 06:40:11 -0000 Hi, A new mptcp v0.5 patch is available at http://caia.swin.edu.au/urp/newtcp/mptcp/tools.html. This release represents a near-complete rewrite of the v0.4 implementation and as such there have been a large number of changes (see [1] and [2]). The patch applies against r285254 of HEAD. Current functionality is slightly advanced of the previous patch, though the new code base should allow for an increased rate of improvement over the next few months. I'm hoping to keep to release incremental updates on a more regular basis over this time period. Along with the patch there are also pre-configured VMs and a pre-built kernel binary available for download, for those who want to try it out without going through the patching/building process. There is also a set of scripts that demonstrate some basic multi-path connections. The patch is still under heavy development and testing so consider this release code to be of alpha quality (expect bugs/panics etc). Currently it supports MPTCP for FreeBSD-to-FreeBSD connections only. Feedback re bugs encountered or suggestions on code/design improvements is welcome. To come in the near future: - A public-facing source repository - A report that details the design of the current implementation This work has been made possible in part by grants from the FreeBSD Foundation, and The Cisco University Research Program Fund at Community Foundation Silicon Valley. cheers, nigel [1] http://caia.swin.edu.au/urp/newtcp/mptcp/tools/v05/mptcp-readme-v0.5.txt [2] http://caia.swin.edu.au/urp/newtcp/mptcp/tools/v05/mptcp-changelog-v0.5.txt From owner-freebsd-net@freebsd.org Tue Sep 1 11:20:53 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 764FD9C6888 for ; Tue, 1 Sep 2015 11:20:53 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 5BAC280D for ; Tue, 1 Sep 2015 11:20:53 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: by mailman.ysv.freebsd.org (Postfix) id 5B2559C6886; Tue, 1 Sep 2015 11:20:53 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 40C669C6882 for ; Tue, 1 Sep 2015 11:20:53 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (glebius.int.ru [81.19.69.10]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "cell.glebius.int.ru", Issuer "cell.glebius.int.ru" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id B933F80C; Tue, 1 Sep 2015 11:20:51 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (localhost [127.0.0.1]) by cell.glebius.int.ru (8.15.2/8.15.2) with ESMTPS id t81BKhuo001416 (version=TLSv1.2 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Tue, 1 Sep 2015 14:20:43 +0300 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.glebius.int.ru (8.15.2/8.15.2/Submit) id t81BKhSu001415; Tue, 1 Sep 2015 14:20:43 +0300 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.glebius.int.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Tue, 1 Sep 2015 14:20:43 +0300 From: Gleb Smirnoff To: adrian@FreeBSD.org, Andriy Voskoboinyk , lstewart@FreeBSD.org Cc: net@FreeBSD.org Subject: mbufq-less iwn(4) Message-ID: <20150901112043.GB1023@glebius.int.ru> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="wRRV7LY7NUeQGEoC" Content-Disposition: inline User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 11:20:53 -0000 --wRRV7LY7NUeQGEoC Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Hi, Adrian and Andriy! One of the fundamental things that me and Lawrence want to bring to FreeBSD 12 (probably won't be in time with 11), is the NIC TX exhaustion notification to the stack, also named as "network stack backpressure". The problem is that when NICs TX queue is full we start to lose packets, just as if they were lost somewhere in a wire, outside of our control. Of course TCP engine copes with that and does necessary retransmitting. The idea is that we can make TCP perform much better, is we report the TX problem to it via ENOBUFS and DO NOT free the mbuf, since protocol may have better idea on its destiny. In the projects/ifnet branch, I already put this idea into the code. In the branch drivers if_transmit doesn't free. I also put this idea into the recent net80211 changes. New ic_transmit doesn't free. However, due to most drivers have software queues as historical artifact, this new semantic of ic_transmit is degenerated. So, the long term plan is to slowly get rid of software mbuf queues in drivers. The protocols should care about queueing (for example ARP already does :)). We probably won't be able to get rid of software queues everywhere before Lawrence does the needed work to TCP, since now software queues are smoothing transmission for drivers that have very small hardware queues. Speaking particularly about iwn(4). Looks like the hardware has enough descriptors to run w/o software queue. Right now writing this email through WiFi connection with patched driver. Didn't notice any issues with download/upload speed. Any objections on checking it in? -- Totus tuus, Glebius. --wRRV7LY7NUeQGEoC Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="iwn-queueless.diff" Index: if_iwn.c =================================================================== --- if_iwn.c (revision 287348) +++ if_iwn.c (working copy) @@ -231,7 +231,6 @@ static void iwn_xmit_task(void *arg0, int pending) static int iwn_raw_xmit(struct ieee80211_node *, struct mbuf *, const struct ieee80211_bpf_params *); static int iwn_transmit(struct ieee80211com *, struct mbuf *); -static void iwn_start_locked(struct iwn_softc *); static void iwn_watchdog(void *); static int iwn_ioctl(struct ieee80211com *, u_long , void *); static void iwn_parent(struct ieee80211com *); @@ -471,7 +470,6 @@ iwn_attach(device_t dev) } IWN_LOCK_INIT(sc); - mbufq_init(&sc->sc_snd, ifqmaxlen); /* Read hardware revision and attach. */ sc->hw_type = (IWN_READ(sc, IWN_HW_REV) >> IWN_HW_REV_TYPE_SHIFT) @@ -1409,8 +1407,6 @@ iwn_detach(device_t dev) ieee80211_ifdetach(&sc->sc_ic); } - mbufq_drain(&sc->sc_snd); - /* Uninstall interrupt handler. */ if (sc->irq != NULL) { bus_teardown_intr(dev, sc->irq, sc->sc_ih); @@ -3597,14 +3593,10 @@ iwn_tx_done(struct iwn_softc *sc, struct iwn_rx_de (status & IWN_TX_FAIL) != 0); sc->sc_tx_timer = 0; - if (--ring->queued < IWN_TX_RING_LOMARK) { + if (--ring->queued < IWN_TX_RING_LOMARK) sc->qfullmsk &= ~(1 << ring->qid); - if (sc->qfullmsk == 0) - iwn_start_locked(sc); - } DPRINTF(sc, IWN_DEBUG_TRACE, "->%s: end\n",__func__); - } /* @@ -3781,14 +3773,10 @@ iwn_ampdu_tx_done(struct iwn_softc *sc, int qid, i } sc->sc_tx_timer = 0; - if (ring->queued < IWN_TX_RING_LOMARK) { + if (ring->queued < IWN_TX_RING_LOMARK) sc->qfullmsk &= ~(1 << ring->qid); - if (sc->qfullmsk == 0) - iwn_start_locked(sc); - } DPRINTF(sc, IWN_DEBUG_TRACE, "->%s: end\n",__func__); - } /* @@ -4948,57 +4936,33 @@ iwn_raw_xmit(struct ieee80211_node *ni, struct mbu static int iwn_transmit(struct ieee80211com *ic, struct mbuf *m) { - struct iwn_softc *sc; + struct iwn_softc *sc = ic->ic_softc; + struct ieee80211_node *ni; int error; - sc = ic->ic_softc; - IWN_LOCK(sc); - if ((sc->sc_flags & IWN_FLAG_RUNNING) == 0) { + if ((sc->sc_flags & IWN_FLAG_RUNNING) == 0 || sc->sc_beacon_wait) { IWN_UNLOCK(sc); return (ENXIO); } - error = mbufq_enqueue(&sc->sc_snd, m); - if (error) { + + if (sc->qfullmsk) { IWN_UNLOCK(sc); - return (error); + return (ENOBUFS); } - iwn_start_locked(sc); + + ni = (struct ieee80211_node *)m->m_pkthdr.rcvif; + error = iwn_tx_data(sc, m, ni); + if (error) { + if_inc_counter(ni->ni_vap->iv_ifp, IFCOUNTER_OERRORS, 1); + ieee80211_free_node(ni); + } else + sc->sc_tx_timer = 5; IWN_UNLOCK(sc); - return (0); + return (error); } static void -iwn_start_locked(struct iwn_softc *sc) -{ - struct ieee80211_node *ni; - struct mbuf *m; - - IWN_LOCK_ASSERT(sc); - - /* - * If we're waiting for a beacon, we can just exit out here - * and wait for the taskqueue to be kicked. - */ - if (sc->sc_beacon_wait) { - return; - } - - DPRINTF(sc, IWN_DEBUG_XMIT, "%s: called\n", __func__); - while (sc->qfullmsk == 0 && - (m = mbufq_dequeue(&sc->sc_snd)) != NULL) { - ni = (struct ieee80211_node *)m->m_pkthdr.rcvif; - if (iwn_tx_data(sc, m, ni) != 0) { - if_inc_counter(ni->ni_vap->iv_ifp, - IFCOUNTER_OERRORS, 1); - ieee80211_free_node(ni); - } else - sc->sc_tx_timer = 5; - } - DPRINTF(sc, IWN_DEBUG_XMIT, "%s: done\n", __func__); -} - -static void iwn_watchdog(void *arg) { struct iwn_softc *sc = arg; @@ -8731,9 +8695,6 @@ iwn_panicked(void *arg0, int pending) "%s: could not move to run state\n", __func__); } - /* Only run start once the NIC is in a useful state, like associated */ - iwn_start_locked(sc); - IWN_UNLOCK(sc); } Index: if_iwnvar.h =================================================================== --- if_iwnvar.h (revision 287348) +++ if_iwnvar.h (working copy) @@ -238,7 +238,6 @@ struct iwn_softc { struct cdev *sc_cdev; struct mtx sc_mtx; struct ieee80211com sc_ic; - struct mbufq sc_snd; u_int sc_flags; #define IWN_FLAG_HAS_OTPROM (1 << 1) --wRRV7LY7NUeQGEoC-- From owner-freebsd-net@freebsd.org Tue Sep 1 12:34:41 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 92F0D9C67FD for ; Tue, 1 Sep 2015 12:34:41 +0000 (UTC) (envelope-from john.cannon@perfora.net) Received: from mout.kundenserver.de (mout.kundenserver.de [212.227.126.130]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "mout.kundenserver.de", Issuer "TeleSec ServerPass DE-2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4E04E10EB for ; Tue, 1 Sep 2015 12:34:40 +0000 (UTC) (envelope-from john.cannon@perfora.net) Received: from icpu2311.kundenserver.de (infong476.lxa.perfora.net [74.208.16.19]) by mrelayeu.kundenserver.de (node=mreue006) with ESMTP (Nemesis) id 0MG3wg-1ZRp0I0Pig-00Ex1w; Tue, 01 Sep 2015 14:29:20 +0200 Received: from 194.69.193.111 (IP may be forged by CGI script) by icpu2311.kundenserver.de with HTTP id 00dkfY-1Z1neJ1d44-00dl6z; Tue, 01 Sep 2015 14:29:19 +0200 X-Sender-Info: <189087788@icpu2311.kundenserver.de> Precedence: bulk To: freebsd-net@freebsd.org Subject: Notice to appear in Court #00206902 Date: Tue, 1 Sep 2015 14:29:19 +0200 From: "County Court" Reply-To: "County Court" Message-ID: X-Priority: 3 MIME-Version: 1.0 X-Provags-ID: V02:K0:CmLzurwFnMiOHGexLLaIMrXORYO9MxH2wDsI0bmio6j mpOlIj9RfvIWohR11M2ZaBDxTliuwp907kAMwYznzpEoMpwAh3 UgiyBytfWExBQ3bjckX4j4KgTVHky+zwGNogiRRVkLauTK9uX5 bal0YB8AzU10a06CqOAN3ynw7wBkd/Xf7axNPInIBVBT8uq1Zr GkU4m2DwdhT2ZN8U2BrTLmf6ABa/zh8ZwFkMaY8kS7acDXKLUv JW8NDhR4m+WramSmQ1GItjCDeWmfxHEEDXgduvrmwKaoowxiJp 3u1AN4YoXFw9aRXD4R+r8KcVEwn1H0VrxTWOEKnVofOYITVBgx 3Eg8rSJzAonYxneqClRr3Syqz0SlYV+sgkMui3E5GYB2xz9IPa +aKRD0E+kcgDj/cIT8KK4r5YKPJtcTAi30= X-UI-Out-Filterresults: notjunk:1;V01:K0:lt/GvurTlY0=:88RdCL5obq5NYmXP8BWgPi sJmuDX8yES55uzh+zcSa9MaU/qxHMkc1MF52/fugqz4gmTacRao+KROb2Odbbx42WnENVgknI SREGGDbL6okcFtZe1cs8jtJIFH6LpGW1oCbQoZsqjcMQRNqw+QrwaQB2C3ekJP64SozoUnLan 9T6ePSiXCM5NpZU9XU7QQ6rIrZdAb5tKygDEn08sbAL+ZiCNWzGSUCxtTm3+2GQeXvKOEPzZ1 O91oLlQ5A2kRS5F Content-Type: text/plain; charset=us-ascii X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 01 Sep 2015 12:34:41 -0000 Notice to Appear, This is to inform you to appear in the Court on the September 06 for your case hearing. You are kindly asked to prepare and bring the documents relating to the case to Court on the specified date. Note: If you do not come, the case will be heard in your absence. The copy of Court Notice is attached to this email. Kind regards, John Cannon, Clerk of Court. From owner-freebsd-net@freebsd.org Tue Sep 1 17:41:17 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B561C9C883D for ; Tue, 1 Sep 2015 17:41:17 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A226E13DA for ; Tue, 1 Sep 2015 17:41:17 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81HfHLx033266 for ; Tue, 1 Sep 2015 17:41:17 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202691] race condition in if_lagg.c Date: Tue, 01 Sep 2015 17:41:17 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: linimon@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 17:41:17 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202691 Mark Linimon changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-bugs@FreeBSD.org |freebsd-net@FreeBSD.org -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 17:42:03 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 3B2799C89A1 for ; Tue, 1 Sep 2015 17:42:03 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 276E917C5 for ; Tue, 1 Sep 2015 17:42:03 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81Hg3VI035682 for ; Tue, 1 Sep 2015 17:42:03 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Tue, 01 Sep 2015 17:42:02 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: linimon@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 17:42:03 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 Mark Linimon changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-bugs@FreeBSD.org |freebsd-net@FreeBSD.org -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 17:42:25 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 2A1869C8A11 for ; Tue, 1 Sep 2015 17:42:25 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 16EC318CC for ; Tue, 1 Sep 2015 17:42:25 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81HgOjZ036023 for ; Tue, 1 Sep 2015 17:42:24 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202667] ipsec broken on i386 Date: Tue, 01 Sep 2015 17:42:25 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: linimon@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 17:42:25 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202667 Mark Linimon changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-bugs@FreeBSD.org |freebsd-net@FreeBSD.org -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 18:27:40 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A2F849C83BB for ; Tue, 1 Sep 2015 18:27:40 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8EEC315DF for ; Tue, 1 Sep 2015 18:27:40 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81IReTL055627 for ; Tue, 1 Sep 2015 18:27:40 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Tue, 01 Sep 2015 18:27:40 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: KOT@MATPOCKuH.Ru X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: attachments.created Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 18:27:40 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 --- Comment #5 from Dmitry Afanasiev --- Created attachment 160604 --> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=160604&action=edit pciconf -lvbc output -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 18:28:11 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id BAD4B9C8427 for ; Tue, 1 Sep 2015 18:28:11 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A6BAF17C0 for ; Tue, 1 Sep 2015 18:28:11 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81ISBM4056145 for ; Tue, 1 Sep 2015 18:28:11 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Tue, 01 Sep 2015 18:28:11 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: KOT@MATPOCKuH.Ru X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: attachments.created Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 18:28:11 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 --- Comment #6 from Dmitry Afanasiev --- Created attachment 160605 --> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=160605&action=edit boot -v output -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 18:37:33 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id BFA5D9C89AF for ; Tue, 1 Sep 2015 18:37:33 +0000 (UTC) (envelope-from melifaro@ipfw.ru) Received: from forward20h.cmail.yandex.net (forward20h.cmail.yandex.net [IPv6:2a02:6b8:0:f35::a5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "forwards.mail.yandex.net", Issuer "Certum Level IV CA" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 7BBF41DAC for ; Tue, 1 Sep 2015 18:37:33 +0000 (UTC) (envelope-from melifaro@ipfw.ru) Received: from web19h.yandex.ru (web19h.yandex.ru [IPv6:2a02:6b8:0:f05::29]) by forward20h.cmail.yandex.net (Yandex) with ESMTP id DCB0221850; Tue, 1 Sep 2015 21:37:11 +0300 (MSK) Received: from 127.0.0.1 (localhost [127.0.0.1]) by web19h.yandex.ru (Yandex) with ESMTP id 583212E00D78; Tue, 1 Sep 2015 21:37:11 +0300 (MSK) Received: by web19h.yandex.ru with HTTP; Tue, 01 Sep 2015 21:37:10 +0300 From: Alexander V. Chernikov Envelope-From: melifaro@ipfw.ru To: Nigel Williams , "freebsd-net@freebsd.org" In-Reply-To: <55E54846.4020504@swin.edu.au> References: null <55E54846.4020504@swin.edu.au> Subject: Re: Multipath TCP for FreeBSD v0.5 MIME-Version: 1.0 Message-Id: <1951081441132630@web19h.yandex.ru> X-Mailer: Yamail [ http://yandex.ru ] 5.0 Date: Tue, 01 Sep 2015 21:37:10 +0300 Content-Transfer-Encoding: 7bit Content-Type: text/plain X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 18:37:33 -0000 01.09.2015, 09:50, "Nigel Williams" : > Hi, > > A new mptcp v0.5 patch is available at > http://caia.swin.edu.au/urp/newtcp/mptcp/tools.html. This release > represents a near-complete rewrite of the v0.4 implementation and as > such there have been a large number of changes (see [1] and [2]). The > patch applies against r285254 of HEAD. Hi Nigel, If not early enough, I'd like to discuss mptcp<>routing interaction. It is stated in the readme that "In future releases, routing will involve using multiple FIBs and and route management within the MP connection". My question is - how route management is planned to work: e.g. if we have fibs 1 and 2 w/ default route, what will instruct connection to use given fibs? application? kernel itself? if we have multiple default routes in fib 0 (and we're using single fib), what will make connection utilize both routes? what kind of kernel interfaces might be needed for that case? e.g. my current understanding is that you need - the ability to get number of nexthops (routes) to particular destination at the session setup - the ability to select particular nexthop in ip[6]_output routines - the ability to track nexthop changes for particular destination (route addition/removals) What's you vision on this? > > Current functionality is slightly advanced of the previous patch, though > the new code base should allow for an increased rate of improvement over > the next few months. I'm hoping to keep to release incremental updates > on a more regular basis over this time period. > > Along with the patch there are also pre-configured VMs and a pre-built > kernel binary available for download, for those who want to try it out > without going through the patching/building process. There is also a set > of scripts that demonstrate some basic multi-path connections. > > The patch is still under heavy development and testing so consider this > release code to be of alpha quality (expect bugs/panics etc). Currently > it supports MPTCP for FreeBSD-to-FreeBSD connections only. Feedback re > bugs encountered or suggestions on code/design improvements is welcome. > > To come in the near future: > - A public-facing source repository > - A report that details the design of the current implementation > > This work has been made possible in part by grants from the FreeBSD > Foundation, and The Cisco University Research Program Fund at Community > Foundation Silicon Valley. > > cheers, > nigel > > [1] http://caia.swin.edu.au/urp/newtcp/mptcp/tools/v05/mptcp-readme-v0.5.txt > [2] > http://caia.swin.edu.au/urp/newtcp/mptcp/tools/v05/mptcp-changelog-v0.5.txt > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://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 Sep 1 18:42:50 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id CDE7D9C8CB9 for ; Tue, 1 Sep 2015 18:42:50 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id B830B169 for ; Tue, 1 Sep 2015 18:42:50 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81IgooU081674 for ; Tue, 1 Sep 2015 18:42:50 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Tue, 01 Sep 2015 18:42:49 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: KOT@MATPOCKuH.Ru X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 18:42:50 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 --- Comment #7 from Dmitry Afanasiev --- (In reply to Sean Bruno from comment #4) "pciconf -lvbc" output and dmesg.boot from "boot -v" attached. I'm not sure that the problem is similar to PR196980, because I have no "Allocation of PCI resources failed" problems and all four interfaces in my Sun Fire X4100 working. Also... I think problem with data corruption exists in 9-STABLE too... I tried to scp from another host to 9.3-STABLE r274181 on another X4100 server and got: Corrupted MAC on input. Disconnecting: Packet corrupt lost connection -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 19:04:36 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A45E19C774C for ; Tue, 1 Sep 2015 19:04:36 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 905961440 for ; Tue, 1 Sep 2015 19:04:36 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81J4a52046275 for ; Tue, 1 Sep 2015 19:04:36 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202351] [ip6] [panic] Kernel panic in ip6_forward (different from 128247, 131038) Date: Tue, 01 Sep 2015 19:04:36 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: commit-hook@freebsd.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 19:04:36 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202351 --- Comment #4 from commit-hook@freebsd.org --- A commit references this bug: Author: kp Date: Tue Sep 1 19:04:05 UTC 2015 New revision: 287376 URL: https://svnweb.freebsd.org/changeset/base/287376 Log: pf: Fix misdetection of forwarding when net.link.bridge.pfil_bridge is set If net.link.bridge.pfil_bridge is set we can end up thinking we're forwarding in pf_test6() because the rcvif and the ifp (output interface) are different. In that case we're bridging though, and the rcvif the the bridge member on which the packet was received and ifp is the bridge itself. If we'd set dir to PF_FWD we'd end up calling ip6_forward() which is incorrect. Instead check if the rcvif is a member of the ifp bridge. (In other words, the if_bridge is the ifp's softc). If that's the case we're not forwarding but bridging. PR: 202351 Reviewed by: eri Differential Revision: https://reviews.freebsd.org/D3534 Changes: head/sys/netpfil/pf/pf.c -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 19:07:34 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B5E2D9C7889 for ; Tue, 1 Sep 2015 19:07:34 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A180C157F for ; Tue, 1 Sep 2015 19:07:34 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t81J7YrK048648 for ; Tue, 1 Sep 2015 19:07:34 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202351] [ip6] [panic] Kernel panic in ip6_forward (different from 128247, 131038) Date: Tue, 01 Sep 2015 19:07:34 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: kp@freebsd.org X-Bugzilla-Status: Closed X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: kp@freebsd.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: bug_status assigned_to resolution Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 19:07:34 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202351 Kristof Provost changed: What |Removed |Added ---------------------------------------------------------------------------- Status|New |Closed Assignee|freebsd-net@FreeBSD.org |kp@freebsd.org Resolution|--- |FIXED --- Comment #5 from Kristof Provost --- The panic should be fixed as of r287376. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Tue Sep 1 19:33:54 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 0B00B9C88D0 for ; Tue, 1 Sep 2015 19:33:54 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id E023761D for ; Tue, 1 Sep 2015 19:33:53 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id DFAC59C88CF; Tue, 1 Sep 2015 19:33:53 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id C65549C88CE for ; Tue, 1 Sep 2015 19:33:53 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-ig0-x22e.google.com (mail-ig0-x22e.google.com [IPv6:2607:f8b0:4001:c05::22e]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 937F461B; Tue, 1 Sep 2015 19:33:53 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by igbkq10 with SMTP id kq10so9301539igb.0; Tue, 01 Sep 2015 12:33:53 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=icz93U7dNDpzHD2lqvklPvfn3sf/Q/mxcgPukggS5Cw=; b=KT497+vWTOnDEMpevCJGpnyFfgRHQPuig92FJ4hzXjobAS/KH+ypKpNfp7hm5CPWio RdV1p8Y2Mcl+m1QfXDgW+bFa05FwPeOBVw+9oKIZlGkO/+AAe4MP5i2zYrl0w0hw1AY3 vVdnXavkDPaBDK6VYRFFTHEMwHO4tnXRTVlfPYEP8VIX/vJDIEoknW6Qr0xCQ3lnCric uz49M9Ep6jpUcgKcHbkw4Fr9M/5Fz+FuOvAe1W/GIfGcnmjBF/Pghxil4GiwvbWo/y8o v53X+2mxhRrUpomhUlhp4hJd/my+MEpiw78Sn8ECo9UXK6dmuv8PP+fcaOGkdii/q0my Cyag== MIME-Version: 1.0 X-Received: by 10.50.73.97 with SMTP id k1mr3842431igv.61.1441136033098; Tue, 01 Sep 2015 12:33:53 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.36.28.208 with HTTP; Tue, 1 Sep 2015 12:33:53 -0700 (PDT) In-Reply-To: <20150901112043.GB1023@glebius.int.ru> References: <20150901112043.GB1023@glebius.int.ru> Date: Tue, 1 Sep 2015 12:33:53 -0700 X-Google-Sender-Auth: dP9sBKxjgSLqMMDT2dj0MiPyoKE Message-ID: Subject: Re: mbufq-less iwn(4) From: Adrian Chadd To: Gleb Smirnoff Cc: Andriy Voskoboinyk , Lawrence Stewart , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 19:33:54 -0000 hi, We have to do mbuf queues in drivers for wifi, because of 11n aggregation. So on one hand we want to have if_transmit() apply backpressure through the stack, but there's also going to be some buffering. :P I'd like to see that for ic_transmit(). Other thing - ic_transmit() also needs to handle fragments, like I do with ath. Ie, handing it a list of packets is actually a list of 802.11 fragments, rather than separate MPDUs. Another thing - we're modifying the mbufs (adding 802.11 data to it) before we pass them to the driver, and if the driver fails to transmit, we can't just pass it back up the net80211 stack to the tcp or udp layer.. -adrian On 1 September 2015 at 04:20, Gleb Smirnoff wrote: > Hi, Adrian and Andriy! > > One of the fundamental things that me and Lawrence want to bring to > FreeBSD 12 (probably won't be in time with 11), is the NIC TX exhaustion > notification to the stack, also named as "network stack backpressure". > > The problem is that when NICs TX queue is full we start to lose packets, > just as if they were lost somewhere in a wire, outside of our control. > Of course TCP engine copes with that and does necessary retransmitting. > > The idea is that we can make TCP perform much better, is we report the > TX problem to it via ENOBUFS and DO NOT free the mbuf, since protocol > may have better idea on its destiny. > > In the projects/ifnet branch, I already put this idea into the code. > In the branch drivers if_transmit doesn't free. I also put this idea > into the recent net80211 changes. New ic_transmit doesn't free. However, > due to most drivers have software queues as historical artifact, this > new semantic of ic_transmit is degenerated. > > So, the long term plan is to slowly get rid of software mbuf queues > in drivers. The protocols should care about queueing (for example > ARP already does :)). We probably won't be able to get rid of software > queues everywhere before Lawrence does the needed work to TCP, since > now software queues are smoothing transmission for drivers that have > very small hardware queues. > > Speaking particularly about iwn(4). Looks like the hardware has > enough descriptors to run w/o software queue. Right now writing > this email through WiFi connection with patched driver. Didn't > notice any issues with download/upload speed. > > Any objections on checking it in? > > -- > Totus tuus, Glebius. From owner-freebsd-net@freebsd.org Tue Sep 1 22:20:31 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 071D69C8E5C for ; Tue, 1 Sep 2015 22:20:31 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id E0CE7C54 for ; Tue, 1 Sep 2015 22:20:30 +0000 (UTC) (envelope-from rpaulo@me.com) Received: by mailman.ysv.freebsd.org (Postfix) id DFDB99C8E5A; Tue, 1 Sep 2015 22:20:30 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id DF7E49C8E59 for ; Tue, 1 Sep 2015 22:20:30 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from mr11p00im-asmtp001.me.com (mr11p00im-asmtp001.me.com [17.110.69.252]) (using TLSv1.2 with cipher DHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id B87CEC52; Tue, 1 Sep 2015 22:20:30 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from akita.local (c-73-162-13-215.hsd1.ca.comcast.net [73.162.13.215]) by mr11p00im-asmtp001.me.com (Oracle Communications Messaging Server 7.0.5.35.0 64bit (built Mar 31 2015)) with ESMTPSA id <0NU0005RARDX0N20@mr11p00im-asmtp001.me.com>; Tue, 01 Sep 2015 22:20:23 +0000 (GMT) X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2015-09-01_09:,, signatures=0 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=2 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1412110000 definitions=main-1509010332 Message-id: <1441146021.1183.8.camel@me.com> Subject: Re: mbufq-less iwn(4) From: Rui Paulo To: Adrian Chadd , Gleb Smirnoff Cc: Lawrence Stewart , Andriy Voskoboinyk , "net@freebsd.org" Date: Tue, 01 Sep 2015 15:20:21 -0700 In-reply-to: References: <20150901112043.GB1023@glebius.int.ru> Content-type: text/plain; charset=UTF-8 X-Mailer: Evolution 3.16.4 FreeBSD GNOME Team Port MIME-version: 1.0 Content-transfer-encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 01 Sep 2015 22:20:31 -0000 On Tue, 2015-09-01 at 12:33 -0700, Adrian Chadd wrote: > hi, > > We have to do mbuf queues in drivers for wifi, because of 11n > aggregation. So on one hand we want to have if_transmit() apply > backpressure through the stack, but there's also going to be some > buffering. :P net80211 also has an ageq which was added to hold mbufs while the mesh peer link was being established. -- Rui Paulo From owner-freebsd-net@freebsd.org Wed Sep 2 01:20:00 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 838609C63CE for ; Wed, 2 Sep 2015 01:20:00 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: from mail-yk0-x22d.google.com (mail-yk0-x22d.google.com [IPv6:2607:f8b0:4002:c07::22d]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4C262CFC for ; Wed, 2 Sep 2015 01:20:00 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: by ykax124 with SMTP id x124so8688677yka.2 for ; Tue, 01 Sep 2015 18:19:58 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:date:message-id:subject:from:to:cc:content-type; bh=z70ejiOXmW+5wlp485NfJcGgX76PGfSsNiG+DQGEwHE=; b=cVhpJJswxYuD949rMAfslj+/lZYiKZtyhA0isE7tRpraslDx8kuwcGwch4V4dTP+zX udSggG9MKhUIV8T0DVlIpR1btxexP1rCnDV99UHY9Y6/GvR9RfN2zdTt6UiezoHk/2+q hq8xHH5wpeBu4g93JZbNmEw/lUQbU0c4efP1sYjurrwEtJ8jbnLx1uUBcGCcI+OjEKYe EElEfrdMf5FN4jRvDdvDmQJhnMq00YEWFs8u6kIiBKRILuYVIrOPkXhP2R9rmWfDpVbj 9HjYuxuOWJnEyt2rdBnhjDY3jSQiE6vw9t9atD3hOzgcnEjNhqYrtG3PO1XaIU7FO3l3 W70Q== MIME-Version: 1.0 X-Received: by 10.13.197.132 with SMTP id h126mr32145905ywd.140.1441156798769; Tue, 01 Sep 2015 18:19:58 -0700 (PDT) Sender: pkelsey@gmail.com Received: by 10.129.24.212 with HTTP; Tue, 1 Sep 2015 18:19:58 -0700 (PDT) Date: Tue, 1 Sep 2015 21:19:58 -0400 X-Google-Sender-Auth: wMlpG8gtn3mf0AWdYOZQj7Jo1lY Message-ID: Subject: TCP Fast Open (RFC7413) for FreeBSD From: Patrick Kelsey To: "freebsd-net@freebsd.org" Cc: sara@sinodun.com, jones@sdf.org Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 01:20:00 -0000 Hi, About two weeks from now, I will be starting work on server-side TCP Fast Open (TFO) support for FreeBSD head and stable/10, with the intention of having patches up for review by November. This message is an attempt to uncover any existing work on TFO for FreeBSD, as the existence of such work may change my plans. Copying Sara Dickinson and Tom Jones due to this thread: https://lists.freebsd.org/pipermail/freebsd-net/2015-January/040910.html. -Patrick From owner-freebsd-net@freebsd.org Wed Sep 2 04:50:36 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id AEF179C8F44 for ; Wed, 2 Sep 2015 04:50:36 +0000 (UTC) (envelope-from truckman@FreeBSD.org) Received: from gw.catspoiler.org (unknown [IPv6:2602:304:b010:ef20::f2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "gw.catspoiler.org", Issuer "gw.catspoiler.org" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 90C79E2D for ; Wed, 2 Sep 2015 04:50:36 +0000 (UTC) (envelope-from truckman@FreeBSD.org) Received: from FreeBSD.org (mousie.catspoiler.org [192.168.101.2]) by gw.catspoiler.org (8.15.2/8.15.2) with ESMTP id t824oTKP057556 for ; Tue, 1 Sep 2015 21:50:33 -0700 (PDT) (envelope-from truckman@FreeBSD.org) Message-Id: <201509020450.t824oTKP057556@gw.catspoiler.org> Date: Tue, 1 Sep 2015 21:50:29 -0700 (PDT) From: Don Lewis Subject: CoDel and ECN questions To: freebsd-net@FreeBSD.org MIME-Version: 1.0 Content-Type: TEXT/plain; charset=us-ascii X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 04:50:36 -0000 Bufferbloat on my DSL link to the outside world has been bugging me lately. I was considering adding an OpenWrt box between my DSL modem and my FreeBSD firewall in order to get CoDel, when I discovered that CoDel had been quietly added to FreeBSD 11. Unfortunately the documentation is severely lacking. The ALTQ(4) man page mentions CoDel and points to pfctl(8) and pf.conf(5) for details, but pf.conf(5) discusses cbq, priq, hfsc, and red, but not codel. I'm currently using ipfw and not pf, but it looks like ipfw can connect to altq, so I'm good there. I need to limit bandwidth in both directions, but altq only controls outbound traffic on an interface, which makes sense. If this box was just forwarding packets between two interfaces, I could also use altq on the inward-facing interface to limit download bandwidth to control the queue depth on the ISP side of my DSL link. The problem is that some of the inbound traffic terminates on the firewall box itself, and in the future I may have more than one inside interface. Dummynet is able to control bandwidth in both directions, but it only implements RED and gRED but not CoDel (or at least it's not documented). The OpenWrt implementation can account for extra per-packet overhead in its bandwidth calculations. That could be significant for me because of the additional PPPoE and ATM overhead, which is pretty large for small packets. Do we have anything similar? Can we combine ECN with CoDel? Pf.conf(5) says that ECN implies RED. I'm using 6rd and gif(4) for IPv6 connectivity. Does gif copy the ECN bits when encapsulating and decapsulating packets? According to , Apple has announced that OS X 10.11 and iOS 9 will enable ECN by default. Have we given any thought to changing our default? Linux can control ECN separately for incoming and outgoing connections. It sounds like the default is now to accepting ECN for incoming connections, but not request it for outgoing connections. From owner-freebsd-net@freebsd.org Wed Sep 2 04:54:08 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 30DD99C814B for ; Wed, 2 Sep 2015 04:54:08 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from mr11p00im-asmtp001.me.com (mr11p00im-asmtp001.me.com [17.110.69.252]) (using TLSv1.2 with cipher DHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0A7FB108; Wed, 2 Sep 2015 04:54:08 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from akita.local (c-73-162-13-215.hsd1.ca.comcast.net [73.162.13.215]) by mr11p00im-asmtp001.me.com (Oracle Communications Messaging Server 7.0.5.35.0 64bit (built Mar 31 2015)) with ESMTPSA id <0NU100JQ79M3SA30@mr11p00im-asmtp001.me.com>; Wed, 02 Sep 2015 04:54:06 +0000 (GMT) X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2015-09-02_03:,, signatures=0 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=2 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1412110000 definitions=main-1509020088 Message-id: <1441169643.1183.12.camel@me.com> Subject: Re: TCP Fast Open (RFC7413) for FreeBSD From: Rui Paulo To: Patrick Kelsey , "freebsd-net@freebsd.org" Cc: jones@sdf.org, sara@sinodun.com Date: Tue, 01 Sep 2015 21:54:03 -0700 In-reply-to: References: Content-type: text/plain; charset=UTF-8 X-Mailer: Evolution 3.16.4 FreeBSD GNOME Team Port MIME-version: 1.0 Content-transfer-encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 04:54:08 -0000 On Tue, 2015-09-01 at 21:19 -0400, Patrick Kelsey wrote: > Hi, > > About two weeks from now, I will be starting work on server-side TCP > Fast > Open (TFO) support for FreeBSD head and stable/10, with the intention > of > having patches up for review by November. This message is an attempt > to > uncover any existing work on TFO for FreeBSD, as the existence of > such work > may change my plans. > > Copying Sara Dickinson and Tom Jones due to this thread: > https://lists.freebsd.org/pipermail/freebsd-net/2015 > -January/040910.html. Have you performed any measurements on the likelihood that stateful packet inspectors (firewalls, NATs, etc.) will allow a SYN or a SYN/ACK to pass with data in it? How would this interact with our syncache? Does it just need to store the cookie? -- Rui Paulo From owner-freebsd-net@freebsd.org Wed Sep 2 05:30:50 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id D85329C847F for ; Wed, 2 Sep 2015 05:30:50 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: from mail-qg0-x22f.google.com (mail-qg0-x22f.google.com [IPv6:2607:f8b0:400d:c04::22f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 92B2C1B1 for ; Wed, 2 Sep 2015 05:30:50 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: by qgx61 with SMTP id 61so11711278qgx.3 for ; Tue, 01 Sep 2015 22:30:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=9s/Aq34FOOMGQcKWfSSZEr3aB6M0DUdM8V57v2/i1RU=; b=IOrXE21pMwNI8P+iw1s/7rDVKGxkT24XiMjXwp6K6Ni0lQja9HCyd52egF+/ecckZ3 Qz5FFWaYw4laCRKcNFAx+kmGh08Vkg+hYidG72pz/eDUrXArq/akW1LWRjsvA1YhCH1T 1BXhJH0uk5oeqV8psGYkOG6Q7tgWjzENjrhCnEY53IQv5V0RLxv4mL66BGPQdrifXEqF PtjlmMKOsfdRwS/A2amFI2aEC7QOuvzyy/QZW7zZAv/Z3jm5bkAV04G9pMlfiRULShab 6vQuYHtXCluZJJNsGvpRH/raE+WLjQPCPJwbrn2BHF3j30DyblPQb+oeUjSUJcpKy/Eq MmZQ== X-Received: by 10.140.194.145 with SMTP id p139mr57385884qha.84.1441171849694; Tue, 01 Sep 2015 22:30:49 -0700 (PDT) Received: from [10.218.90.20] ([166.170.28.215]) by smtp.gmail.com with ESMTPSA id x4sm2905649qha.24.2015.09.01.22.30.49 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 01 Sep 2015 22:30:49 -0700 (PDT) Sender: Patrick Kelsey Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (1.0) Subject: Re: TCP Fast Open (RFC7413) for FreeBSD From: Patrick Kelsey X-Mailer: iPhone Mail (12F70) In-Reply-To: <1441169643.1183.12.camel@me.com> Date: Wed, 2 Sep 2015 01:30:48 -0400 Cc: "freebsd-net@freebsd.org" , "jones@sdf.org" , "sara@sinodun.com" Content-Transfer-Encoding: quoted-printable Message-Id: References: <1441169643.1183.12.camel@me.com> To: Rui Paulo X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 05:30:50 -0000 > On Sep 2, 2015, at 12:54 AM, Rui Paulo wrote: >=20 >> On Tue, 2015-09-01 at 21:19 -0400, Patrick Kelsey wrote: >> Hi, >>=20 >> About two weeks from now, I will be starting work on server-side TCP=20 >> Fast >> Open (TFO) support for FreeBSD head and stable/10, with the intention=20 >> of >> having patches up for review by November. This message is an attempt=20 >> to >> uncover any existing work on TFO for FreeBSD, as the existence of=20 >> such work >> may change my plans. >>=20 >> Copying Sara Dickinson and Tom Jones due to this thread: >> https://lists.freebsd.org/pipermail/freebsd-net/2015 >> -January/040910.html. >=20 > Have you performed any measurements on the likelihood that stateful > packet inspectors (firewalls, NATs, etc.) will allow a SYN or a SYN/ACK > to pass with data in it? I have not performed any such measurements. This issue is discussed in sect= ion 7.1 of the RFC, which cites such studies and summarizes the finding as b= eing that 6% of the probed internet paths dropped SYN packets with data or w= ith unknown TCP options. >=20 > How would this interact with our syncache? Does it just need to store > the cookie? >=20 The exact interaction with the syncache is still TBD, but I do not expect to= be storing TFO cookies in the syncache as the cookies are per client-server= IP pair and not per-connection. -Patrick= From owner-freebsd-net@freebsd.org Wed Sep 2 05:46:22 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id F1A6A9C8CD0 for ; Wed, 2 Sep 2015 05:46:22 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E0030B9A; Wed, 2 Sep 2015 05:46:22 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id CD6A8CCAF0; Tue, 1 Sep 2015 22:46:15 -0700 (PDT) Date: Tue, 1 Sep 2015 22:46:15 -0700 From: hiren panchasara To: Patrick Kelsey Cc: "freebsd-net@freebsd.org" , jones@sdf.org, sara@sinodun.com Subject: Re: TCP Fast Open (RFC7413) for FreeBSD Message-ID: <20150902054615.GG68814@strugglingcoder.info> References: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="NPukt5Otb9an/u20" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 05:46:23 -0000 --NPukt5Otb9an/u20 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 09/01/15 at 09:19P, Patrick Kelsey wrote: > Hi, >=20 > About two weeks from now, I will be starting work on server-side TCP Fast > Open (TFO) support for FreeBSD head and stable/10, with the intention of > having patches up for review by November. Awesome! Looking forward to it. Cheers, Hiren --NPukt5Otb9an/u20 Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJV5o0nXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/loVQIAKdvCZm6akhEHdl/HwaQOt/b I8JOGk3Eiq9uc+y2IGxVm8EgzfbBrTQdWQXI9CG02dYu8CN/9KFz2vmpbpDMn2fP oYR+cwY/C8JvG6wS+ARiPh0EEgkPJ6Kg2mhbKVjLD6i4zHbZVQ0PmxgRDlSCJDNr Hynvbeww4thuOdaz30n6vsSddsGBrnvlwzJa+UX0M1Be0h0A9gampSkMY4gTOgYo ZmKBpG3QYTuM7ph7zZ93u6/6huQ6hjnuUhxqPBjSD8I2gmCRc7QoL8LeVYSdkX37 +/0CiYEcpqQu/nTgG3zOZMkGlXQBPEEQvYOBMsHdECCxFazoD1dY1xwzNS2JvRY= =gx5E -----END PGP SIGNATURE----- --NPukt5Otb9an/u20-- From owner-freebsd-net@freebsd.org Wed Sep 2 06:03:29 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id BE7CA9C7956 for ; Wed, 2 Sep 2015 06:03:29 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id A3DE0912 for ; Wed, 2 Sep 2015 06:03:29 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: by mailman.ysv.freebsd.org (Postfix) id A30779C7955; Wed, 2 Sep 2015 06:03:29 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A2A5E9C7954 for ; Wed, 2 Sep 2015 06:03:29 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (glebius.int.ru [81.19.69.10]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "cell.glebius.int.ru", Issuer "cell.glebius.int.ru" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 298FE910; Wed, 2 Sep 2015 06:03:27 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (localhost [127.0.0.1]) by cell.glebius.int.ru (8.15.2/8.15.2) with ESMTPS id t8263OTt006925 (version=TLSv1.2 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Wed, 2 Sep 2015 09:03:24 +0300 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.glebius.int.ru (8.15.2/8.15.2/Submit) id t8263ONP006924; Wed, 2 Sep 2015 09:03:24 +0300 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.glebius.int.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Wed, 2 Sep 2015 09:03:24 +0300 From: Gleb Smirnoff To: Adrian Chadd Cc: Andriy Voskoboinyk , Lawrence Stewart , "net@freebsd.org" Subject: Re: mbufq-less iwn(4) Message-ID: <20150902060324.GF1023@glebius.int.ru> References: <20150901112043.GB1023@glebius.int.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 06:03:29 -0000 Adrian, On Tue, Sep 01, 2015 at 12:33:53PM -0700, Adrian Chadd wrote: A> We have to do mbuf queues in drivers for wifi, because of 11n A> aggregation. So on one hand we want to have if_transmit() apply A> backpressure through the stack, but there's also going to be some A> buffering. :P No, that's not because of 11n aggregation. That's a remnant of ifnet ifqueue. Note that I'm speaking about queueing in drivers, not in net80211 stack. Look at the iwn patch, it doesn't remove any functionality except of enqueueing and dequeueing. Look at your own ath(4) - there is no software queue there already :) A> I'd like to see that for ic_transmit(). A> A> Other thing - ic_transmit() also needs to handle fragments, like I do A> with ath. Ie, handing it a list of packets is actually a list of A> 802.11 fragments, rather than separate MPDUs. A> A> Another thing - we're modifying the mbufs (adding 802.11 data to it) A> before we pass them to the driver, and if the driver fails to A> transmit, we can't just pass it back up the net80211 stack to the tcp A> or udp layer.. Sure, stack probably would need to strip the data. Anyway, that's a future task. -- Totus tuus, Glebius. From owner-freebsd-net@freebsd.org Wed Sep 2 08:10:53 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 20D2E9C6364 for ; Wed, 2 Sep 2015 08:10:53 +0000 (UTC) (envelope-from sara@sinodun.com) Received: from shcp01.hosting.zen.net.uk (shcp01.hosting.zen.net.uk [88.98.24.67]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id D5EDBE9B; Wed, 2 Sep 2015 08:10:52 +0000 (UTC) (envelope-from sara@sinodun.com) Received: from 82-68-8-206.dsl.in-addr.zen.co.uk ([82.68.8.206]:61836 helo=[192.168.100.27]) by shcp01.hosting.zen.net.uk with esmtpsa (TLSv1:DHE-RSA-AES256-SHA:256) (Exim 4.85) (envelope-from ) id 1ZX2EL-0001lO-Ir; Wed, 02 Sep 2015 08:13:14 +0100 Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) Subject: Re: TCP Fast Open (RFC7413) for FreeBSD From: sara In-Reply-To: Date: Wed, 2 Sep 2015 08:13:15 +0100 Cc: "freebsd-net@freebsd.org" , jones@sdf.org Message-Id: <893D25B9-B0A4-417E-A018-67F7B01C1112@sinodun.com> References: To: Patrick Kelsey X-Mailer: Apple Mail (2.2104) X-OutGoing-Spam-Status: No, score=-1.0 X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - shcp01.hosting.zen.net.uk X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - sinodun.com X-Get-Message-Sender-Via: shcp01.hosting.zen.net.uk: authenticated_id: sara+sinodun.com/only user confirmed/virtual account not confirmed Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 08:10:53 -0000 > On 2 Sep 2015, at 02:19, Patrick Kelsey wrote: >=20 > Hi, >=20 > About two weeks from now, I will be starting work on server-side TCP = Fast Open (TFO) support for FreeBSD head and stable/10, with the = intention of having patches up for review by November. This message is = an attempt to uncover any existing work on TFO for FreeBSD, as the = existence of such work may change my plans. >=20 > Copying Sara Dickinson and Tom Jones due to this thread: = https://lists.freebsd.org/pipermail/freebsd-net/2015-January/040910.html = = . Patrick,=20 This is great news - many thanks for keeping me updated.=20 Sara.=20 From owner-freebsd-net@freebsd.org Wed Sep 2 11:44:21 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 2803D9C9082 for ; Wed, 2 Sep 2015 11:44:21 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 14FF67B4 for ; Wed, 2 Sep 2015 11:44:21 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82BiKeh052989 for ; Wed, 2 Sep 2015 11:44:20 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202667] ipsec broken on i386 Date: Wed, 02 Sep 2015 11:44:20 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: ae@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: ae@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 11:44:21 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202667 Andrey V. Elsukov changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-net@FreeBSD.org |ae@FreeBSD.org --- Comment #1 from Andrey V. Elsukov --- Take it. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Wed Sep 2 15:15:25 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id DC9A99C9287 for ; Wed, 2 Sep 2015 15:15:25 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id BD30D7E0 for ; Wed, 2 Sep 2015 15:15:25 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id BAC139C9286; Wed, 2 Sep 2015 15:15:25 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B96569C9285 for ; Wed, 2 Sep 2015 15:15:25 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-io0-x22f.google.com (mail-io0-x22f.google.com [IPv6:2607:f8b0:4001:c06::22f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 886047DC; Wed, 2 Sep 2015 15:15:25 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by ioiz6 with SMTP id z6so23728558ioi.2; Wed, 02 Sep 2015 08:15:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=aPrusJ+iyOWR/oXozqks2ymenTpYxpj1b0lTM8GnaJ4=; b=xQlCrzxFJWFarlhfte7lAoNGVVFa+J3Wh4GQ6eHrg1ea4xfTrzQ/SUj2C1L5oSVso/ cN+BRBI1mZKMpviFV6FrTVwlXrtja2jhUreNi2iFiltAu8l/egf56qGlF74eUpIY15Vl i5QQYOqNqaFzWcvoT/kyj9x9Aq3hltogNgUVPOCl4jCe46gDYoKfcNh5kkMm4NqcI9LH qdXOnxQZZfgU+QVTfNfyzEnD/5mh2c8+UR+NV+9yoE2rzc6/tprvIbsrz3YHqnDNPvcf v+Ki5KGvQRlQG1eYY7CAF5C+wjghaVwSLEuLLd3GQbM5aw4LUJOKXj4koBtXRqWrEJ7d s6Vw== MIME-Version: 1.0 X-Received: by 10.107.154.212 with SMTP id c203mr14891570ioe.123.1441206924819; Wed, 02 Sep 2015 08:15:24 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.36.28.208 with HTTP; Wed, 2 Sep 2015 08:15:24 -0700 (PDT) In-Reply-To: <20150902060324.GF1023@glebius.int.ru> References: <20150901112043.GB1023@glebius.int.ru> <20150902060324.GF1023@glebius.int.ru> Date: Wed, 2 Sep 2015 08:15:24 -0700 X-Google-Sender-Auth: j2zcv6OqyCAjuzzliCDg_BPlRPI Message-ID: Subject: Re: mbufq-less iwn(4) From: Adrian Chadd To: Gleb Smirnoff Cc: Andriy Voskoboinyk , Lawrence Stewart , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 15:15:26 -0000 oh, remove the mbufq from each driver? Absolutely - go ahead and nuke them all. We need to do that anyway - using an mbufq breaks fragments and leaks mbufs. -a From owner-freebsd-net@freebsd.org Wed Sep 2 16:21:06 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 7E6239C90A4 for ; Wed, 2 Sep 2015 16:21:06 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 6552F949 for ; Wed, 2 Sep 2015 16:21:06 +0000 (UTC) (envelope-from rpaulo@me.com) Received: by mailman.ysv.freebsd.org (Postfix) id 620C29C90A3; Wed, 2 Sep 2015 16:21:06 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 619D09C90A2 for ; Wed, 2 Sep 2015 16:21:06 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from mr11p00im-asmtp001.me.com (mr11p00im-asmtp001.me.com [17.110.69.252]) (using TLSv1.2 with cipher DHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 3DCEE948; Wed, 2 Sep 2015 16:21:06 +0000 (UTC) (envelope-from rpaulo@me.com) Received: from akita.local (c-73-162-13-215.hsd1.ca.comcast.net [73.162.13.215]) by mr11p00im-asmtp001.me.com (Oracle Communications Messaging Server 7.0.5.35.0 64bit (built Mar 31 2015)) with ESMTPSA id <0NU2005US5F2U730@mr11p00im-asmtp001.me.com>; Wed, 02 Sep 2015 16:21:05 +0000 (GMT) X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2015-09-02_06:,, signatures=0 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=2 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1412110000 definitions=main-1509020253 Message-id: <1441210862.1183.14.camel@me.com> Subject: Re: TCP Fast Open (RFC7413) for FreeBSD From: Rui Paulo To: Patrick Kelsey , net@freebsd.org Date: Wed, 02 Sep 2015 09:21:02 -0700 In-reply-to: References: <1441169643.1183.12.camel@me.com> Content-type: text/plain; charset=UTF-8 X-Mailer: Evolution 3.16.4 FreeBSD GNOME Team Port MIME-version: 1.0 Content-transfer-encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 16:21:06 -0000 On Wed, 2015-09-02 at 01:30 -0400, Patrick Kelsey wrote: > > > > > On Sep 2, 2015, at 12:54 AM, Rui Paulo wrote: > > > > > On Tue, 2015-09-01 at 21:19 -0400, Patrick Kelsey wrote: > > > Hi, > > > > > > About two weeks from now, I will be starting work on server-side > > > TCP > > > Fast > > > Open (TFO) support for FreeBSD head and stable/10, with the > > > intention > > > of > > > having patches up for review by November. This message is an > > > attempt > > > to > > > uncover any existing work on TFO for FreeBSD, as the existence of > > > such work > > > may change my plans. > > > > > > Copying Sara Dickinson and Tom Jones due to this thread: > > > https://lists.freebsd.org/pipermail/freebsd-net/2015 > > > -January/040910.html. > > > > Have you performed any measurements on the likelihood that stateful > > packet inspectors (firewalls, NATs, etc.) will allow a SYN or a > > SYN/ACK > > to pass with data in it? > > I have not performed any such measurements. This issue is discussed > in section 7.1 of the RFC, which cites such studies and summarizes > the finding as being that 6% of the probed internet paths dropped SYN > packets with data or with unknown TCP options. > > > > > > How would this interact with our syncache? Does it just need to > > store > > the cookie? > > > > The exact interaction with the syncache is still TBD, but I do not > expect to be storing TFO cookies in the syncache as the cookies are > per client-server IP pair and not per-connection. > OK. The only request I have is to be conservative and leave it disabled for a while. The RFC is pretty much experimental for a good reason and we don't want to repeat the T/TCP mistake. -- Rui Paulo From owner-freebsd-net@freebsd.org Wed Sep 2 16:24:06 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 369EC9C92D0 for ; Wed, 2 Sep 2015 16:24:06 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 14397B72 for ; Wed, 2 Sep 2015 16:24:06 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id 135189C92CF; Wed, 2 Sep 2015 16:24:06 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id EEA019C92CE for ; Wed, 2 Sep 2015 16:24:05 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: from mail-qg0-x236.google.com (mail-qg0-x236.google.com [IPv6:2607:f8b0:400d:c04::236]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id BA07EB71 for ; Wed, 2 Sep 2015 16:24:05 +0000 (UTC) (envelope-from pkelsey@gmail.com) Received: by qgt47 with SMTP id 47so8769350qgt.2 for ; Wed, 02 Sep 2015 09:24:04 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=YZkT/7Vo1DUAV6MfGNCptyexfKFC6emjkXCk7446H8g=; b=tJRnzJKth/wAdeR9/mjEZi85EQrm8RCDi9QD4plE7I/88rp7eV3vdMxlXwM6yq/PG6 De4ljnhdhL6gRD5MZb7wrJi5pYTM6un2RukrGr/9AZSWcn/CprlHLZ7nmk9MIkUZO0m6 NRTX3ti5eA9cinLw/+27qX5ZoEuiiXJFk2ge+QUUQ6HLF3NtATU04WVNHegYLG/W/WZn dWzNsk+T5JpCFIIzkZAK9wFTAm6uaWPf7bUiLc4WJXeYD2UlW0eIsODLMqMnNloHFImy 0x2Rp0AUL4KHVjH4NOTj+JDMHOO6+6D93RaDKhZ01sUlOfScIKYoX12PtIddw72alF9t W2ow== X-Received: by 10.140.238.3 with SMTP id j3mr61672699qhc.14.1441211044601; Wed, 02 Sep 2015 09:24:04 -0700 (PDT) Received: from [10.117.73.93] (mobile-166-171-057-239.mycingular.net. [166.171.57.239]) by smtp.gmail.com with ESMTPSA id h78sm13007567qhc.47.2015.09.02.09.24.03 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Wed, 02 Sep 2015 09:24:04 -0700 (PDT) Sender: Patrick Kelsey Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (1.0) Subject: Re: TCP Fast Open (RFC7413) for FreeBSD From: Patrick Kelsey X-Mailer: iPhone Mail (12F70) In-Reply-To: <1441210862.1183.14.camel@me.com> Date: Wed, 2 Sep 2015 12:24:02 -0400 Cc: "net@freebsd.org" Content-Transfer-Encoding: quoted-printable Message-Id: <1D272A8E-C411-4FE1-A8C7-6E6FBDE23DC8@freebsd.org> References: <1441169643.1183.12.camel@me.com> <1441210862.1183.14.camel@me.com> To: Rui Paulo X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 16:24:06 -0000 > On Sep 2, 2015, at 12:21 PM, Rui Paulo wrote: >=20 >> On Wed, 2015-09-02 at 01:30 -0400, Patrick Kelsey wrote: >>=20 >>=20 >>=20 >>>> On Sep 2, 2015, at 12:54 AM, Rui Paulo wrote: >>>>=20 >>>> On Tue, 2015-09-01 at 21:19 -0400, Patrick Kelsey wrote: >>>> Hi, >>>>=20 >>>> About two weeks from now, I will be starting work on server-side=20 >>>> TCP=20 >>>> Fast >>>> Open (TFO) support for FreeBSD head and stable/10, with the=20 >>>> intention=20 >>>> of >>>> having patches up for review by November. This message is an=20 >>>> attempt=20 >>>> to >>>> uncover any existing work on TFO for FreeBSD, as the existence of=20 >>>> such work >>>> may change my plans. >>>>=20 >>>> Copying Sara Dickinson and Tom Jones due to this thread: >>>> https://lists.freebsd.org/pipermail/freebsd-net/2015 >>>> -January/040910.html. >>>=20 >>> Have you performed any measurements on the likelihood that stateful >>> packet inspectors (firewalls, NATs, etc.) will allow a SYN or a=20 >>> SYN/ACK >>> to pass with data in it? >>=20 >> I have not performed any such measurements. This issue is discussed=20 >> in section 7.1 of the RFC, which cites such studies and summarizes=20 >> the finding as being that 6% of the probed internet paths dropped SYN=20 >> packets with data or with unknown TCP options. >>=20 >>=20 >>>=20 >>> How would this interact with our syncache? Does it just need to=20 >>> store >>> the cookie? >>=20 >> The exact interaction with the syncache is still TBD, but I do not=20 >> expect to be storing TFO cookies in the syncache as the cookies are=20 >> per client-server IP pair and not per-connection. >=20 > OK. The only request I have is to be conservative and leave it > disabled for a while. The RFC is pretty much experimental for a good > reason and we don't want to repeat the T/TCP mistake. >=20 I agree completely. This feature will be guarded with an #ifdef, default di= sabled. -Patrick= From owner-freebsd-net@freebsd.org Wed Sep 2 16:33:57 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id D91219C9834 for ; Wed, 2 Sep 2015 16:33:57 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C5C38124C for ; Wed, 2 Sep 2015 16:33:57 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82GXvk8000995 for ; Wed, 2 Sep 2015 16:33:57 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 200221] em0 watchdog timeout under load Date: Wed, 02 Sep 2015 16:33:58 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.1-RELEASE X-Bugzilla-Keywords: IntelNetworking, needs-qa, patch X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: sbruno@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 16:33:57 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=200221 --- Comment #16 from Sean Bruno --- You'll need this one as well to avoid a panic: https://svnweb.freebsd.org/base?view=revision&revision=287330 -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Wed Sep 2 16:35:46 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 8547F9C9929 for ; Wed, 2 Sep 2015 16:35:46 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7226F132D for ; Wed, 2 Sep 2015 16:35:46 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82GZk9C002653 for ; Wed, 2 Sep 2015 16:35:46 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Wed, 02 Sep 2015 16:35:45 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: sbruno@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 16:35:46 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 --- Comment #8 from Sean Bruno --- Can you try to apply three changesets from head and see if the condition still exists? https://svnweb.freebsd.org/base?view=revision&revision=286831 https://svnweb.freebsd.org/base?view=revision&revision=285879 https://svnweb.freebsd.org/base?view=revision&revision=287330 -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Wed Sep 2 16:36:32 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 1F6DC9C9981 for ; Wed, 2 Sep 2015 16:36:32 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0C4B413CC for ; Wed, 2 Sep 2015 16:36:32 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82GaVZJ003386 for ; Wed, 2 Sep 2015 16:36:31 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202680] Silent data corruption on em(4) interfaces Date: Wed, 02 Sep 2015 16:36:32 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.2-STABLE X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: sbruno@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 16:36:32 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202680 --- Comment #9 from Sean Bruno --- (In reply to Sean Bruno from comment #8) wait ... never mind. This is a lem(4) device not a em(4) device so those patches are not applicable. I'll think more. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Wed Sep 2 19:14:11 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id BF4819C9B3F for ; Wed, 2 Sep 2015 19:14:11 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id ABB5C1000 for ; Wed, 2 Sep 2015 19:14:11 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82JEBX8078685 for ; Wed, 2 Sep 2015 19:14:11 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 200221] em0 watchdog timeout under load Date: Wed, 02 Sep 2015 19:14:11 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.1-RELEASE X-Bugzilla-Keywords: IntelNetworking, needs-qa, patch X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: anthony@ury.org.uk X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: attachments.created Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 19:14:11 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=200221 --- Comment #17 from anthony@ury.org.uk --- Created attachment 160662 --> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=160662&action=edit svn di svn://svn0.eu.freebsd.org/base/stable/10/sys/dev/e1000 sys/dev/e1000 -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Wed Sep 2 19:16:40 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 333AF9C9CEC for ; Wed, 2 Sep 2015 19:16:40 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 067EF694 for ; Wed, 2 Sep 2015 19:16:40 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t82JGdm5081758 for ; Wed, 2 Sep 2015 19:16:39 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 200221] em0 watchdog timeout under load Date: Wed, 02 Sep 2015 19:16:40 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.1-RELEASE X-Bugzilla-Keywords: IntelNetworking, needs-qa, patch X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: anthony@ury.org.uk X-Bugzilla-Status: In Progress X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 02 Sep 2015 19:16:40 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=200221 --- Comment #18 from anthony@ury.org.uk --- Unfortunately, the server experienced a watchdog timeout this morning : Sep 2 07:39:49 urybsod kernel: em0: Watchdog timeout Queue[0]-- resetting Sep 2 07:39:49 urybsod kernel: Interface is RUNNING and ACTIVE Sep 2 07:39:49 urybsod kernel: em0: TX Queue 0 ------ Sep 2 07:39:49 urybsod kernel: em0: hw tdh = 247, hw tdt = 495 Sep 2 07:39:49 urybsod kernel: em0: Tx Queue Status = -2147483648 Sep 2 07:39:49 urybsod kernel: em0: TX descriptors avail = 771 Sep 2 07:39:49 urybsod kernel: em0: Tx Descriptors avail failure = 237 Sep 2 07:39:49 urybsod kernel: em0: RX Queue 0 ------ Sep 2 07:39:49 urybsod kernel: em0: hw rdh = 344, hw rdt = 343 Sep 2 07:39:49 urybsod kernel: em0: RX discarded packets = 0 Sep 2 07:39:49 urybsod kernel: em0: RX Next to Check = 344 Sep 2 07:39:49 urybsod kernel: em0: RX Next to Refresh = 343 Sep 2 07:39:49 urybsod kernel: em0: Link is Down Sep 2 07:39:49 urybsod kernel: em0: link state changed to DOWN Sep 2 07:39:53 urybsod kernel: em0: Link is up 1000 Mbps Full Duplex Sep 2 07:39:53 urybsod kernel: em0: link state changed to UP Sep 2 07:39:53 urybsod devd: Executing '/etc/rc.d/dhclient quietstart em0' So these patches appear to be improving stability, as this is the only occurrence in 13 days of uptime, compared to nearly every day previously. I should reiterate what state this kernel is in : sys/dev/e1000 is at 10-STABLE@HEAD with CURRENT@286381, CURRENT@285879 patched. This required some manual patching. Diff of e1000 to 10-STABLE attached. Merged r274043 and r274704 from 10-STABLE. I've not yet encountered a panic, but I'll apply 287330 to be on the safe side. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Thu Sep 3 00:54:07 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 09DA79C8B95 for ; Thu, 3 Sep 2015 00:54:07 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id EF1F21E5C for ; Thu, 3 Sep 2015 00:54:06 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id E2EEFCC514 for ; Wed, 2 Sep 2015 17:54:05 -0700 (PDT) Date: Wed, 2 Sep 2015 17:54:05 -0700 From: hiren panchasara To: freebsd-net@FreeBSD.org Subject: Value of congestion window (cwnd) when loss is detected Message-ID: <20150903005405.GN68814@strugglingcoder.info> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="/UvyDgxjlFfP/4zZ" Content-Disposition: inline User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 00:54:07 -0000 --/UvyDgxjlFfP/4zZ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline I am failing to understand the reason behind this behavior. What should the congestion window (snd_cwnd) be set to when we hit loss? It seems that we set it to 1 segment right now. https://svnweb.freebsd.org/base/head/sys/netinet/tcp_input.c?revision=286227&view=markup#l2531 I also see that in the simulations I did. Sender side pcap can be found at: https://people.freebsd.org/~hiren/pcaps/single_packet_loss.pcap Trying to send 50kb of data from freebsd 10.2 server to freebsd client. Initial cwnd is 10 so we blast out 10 packets but 1 packet gets dropped: seq 2897:4345. We get 3 dupacks and we retransmit it. But as soon as we detect this loss, we reduce cwnd to 1 segment. In fact, we could've used data in SACK to see how much we could send on the n/w, imo. 3rd dup ack (which triggered the retransmit) looks like this: IP 192.168.11.10.41674 > 192.168.10.10.http: Flags [.], ack 2897, win 12579, options [nop,nop,TS val 4236220288 ecr 3905376863,nop,nop,sack 1 {4345:10137}], length 0 And the retransmit: IP 192.168.10.10.http > 192.168.11.10.41674: Flags [.], seq 2897:4345, ack 172, win 12579, options [nop,nop,TS val 3905376894 ecr 4236220288], length 1448 At this point in time, sender knows that it has sent 23169 bytes (last packet server sent was seq 21721:23169) and received ack for 10137 bytes minus a missing packet = 8689 bytes. i.e. 6 packets. So, there is at least that much room on n/w at that point in time. We can go conservative and halve that. i.e. 3 packets. That is still better than going down to 1 packet. Is there something basic I am missing here? Any insights would be helpful. Cheers, Hiren --/UvyDgxjlFfP/4zZ Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJV55otXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/l5YUH/06EVmLj18+NgLRZb8qmvbZZ RTSQm8jK37ha1CjXS4VJItXo3FImTEiJd/NMqnYUFlKrn9DymVZt03q+9H3E2hl4 ZtZ9mBkfvklwk0euaE0N5Ip7RVVS6cE5sYRCmNUe1IEomjBKpv8sOVZsHQ4+ajfX qS/3rbHvIl83VHq7jE7bZmXrjc75Ckd0Wm7gSNDAfoDOpDjMAXg6rjx6TH+KH/Eh uoesRscqm1XpQKJk8zx2xrF71as+n6TeXICneoCpdzNOWnctf8jA1F/cjNAHbScJ /mhg67GjtFAmPCV/g2F7clTL+3xSVaBscbEyY0EjFRnkbCpE1M0D5vQZ9qKh6Ko= =Trgd -----END PGP SIGNATURE----- --/UvyDgxjlFfP/4zZ-- From owner-freebsd-net@freebsd.org Thu Sep 3 00:55:15 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B44FA9C8C49 for ; Thu, 3 Sep 2015 00:55:15 +0000 (UTC) (envelope-from freebsd-net@m.gmane.org) Received: from plane.gmane.org (plane.gmane.org [80.91.229.3]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 717261EFF for ; Thu, 3 Sep 2015 00:55:15 +0000 (UTC) (envelope-from freebsd-net@m.gmane.org) Received: from list by plane.gmane.org with local (Exim 4.69) (envelope-from ) id 1ZXInx-00041l-Gd for freebsd-net@freebsd.org; Thu, 03 Sep 2015 02:55:05 +0200 Received: from 2-230-230-148.ip204.fastwebnet.it ([2.230.230.148]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 03 Sep 2015 02:55:05 +0200 Received: from c0redump by 2-230-230-148.ip204.fastwebnet.it with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Thu, 03 Sep 2015 02:55:05 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-net@freebsd.org From: C0ReDuMP Subject: Re: Poor high-PPS performance of the 10G ixgbe(9) NIC/driver in FreeBSD 10.1 Date: Wed, 2 Sep 2015 02:27:52 +0000 (UTC) Lines: 37 Message-ID: References: <77171439377164@web21h.yandex.ru> <55CB2F18.40902@FreeBSD.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@ger.gmane.org X-Gmane-NNTP-Posting-Host: sea.gmane.org User-Agent: Loom/3.14 (http://gmane.org/) X-Loom-IP: 2.230.230.148 (Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 00:55:15 -0000 Maxim Sobolev sippysoft.com> writes: > > Yes, we've confirmed it's IXGBE_FDIR. That's good it comes disabled in 10.2. > > Thanks everyone for constructive input! > > -Max > _______________________________________________ > freebsd-net freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe freebsd.org" > > Hello Maxim, after disabling FDIR what's the pps rate you are getting from you 24 core system? You made a lot of tuning of the network driver while searching a solution to this problem. Could you share all the relevant settings of the ixgbe driver from /boot/loader.conf and /etc/sysctl.conf? I'm trying to fine tune the settings on a 16 core system but I have some doubt so I'd like to compare my settings with yours. I'm working on a high PPS router and I'm also interested to Luigi Rizzo's netmap code. I tried netmap with click for forwarding but unfortunately I'm facing some problem with route pushing from quagga. I had also to understand if is possible to link aggregate two ixgbe with netmap (using lacp). Thanks in Advance, Davide From owner-freebsd-net@freebsd.org Thu Sep 3 11:13:59 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 62FBA9C9B8B for ; Thu, 3 Sep 2015 11:13:59 +0000 (UTC) (envelope-from lstewart@freebsd.org) Received: from lauren.room52.net (lauren.room52.net [210.50.193.198]) by mx1.freebsd.org (Postfix) with ESMTP id 29EA3106A for ; Thu, 3 Sep 2015 11:13:58 +0000 (UTC) (envelope-from lstewart@freebsd.org) Received: from lgwl-lstewart2.corp.netflix.com (c110-22-60-167.eburwd6.vic.optusnet.com.au [110.22.60.167]) by lauren.room52.net (Postfix) with ESMTPSA id A8B407E81E; Thu, 3 Sep 2015 21:13:48 +1000 (EST) Message-ID: <55E82B59.6000202@freebsd.org> Date: Thu, 03 Sep 2015 21:13:29 +1000 From: Lawrence Stewart User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:31.0) Gecko/20100101 Thunderbird/31.5.0 MIME-Version: 1.0 To: hiren panchasara , freebsd-net@freebsd.org Subject: Re: Value of congestion window (cwnd) when loss is detected References: <20150903005405.GN68814@strugglingcoder.info> In-Reply-To: <20150903005405.GN68814@strugglingcoder.info> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=2.4 required=5.0 tests=DNS_FROM_AHBL_RHSBL, UNPARSEABLE_RELAY autolearn=no version=3.3.2 X-Spam-Level: ** X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on lauren.room52.net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 11:13:59 -0000 On 09/03/15 10:54, hiren panchasara wrote: > I am failing to understand the reason behind this behavior. > > What should the congestion window (snd_cwnd) be set to when we hit loss? > It seems that we set it to 1 segment right now. > https://svnweb.freebsd.org/base/head/sys/netinet/tcp_input.c?revision=286227&view=markup#l2531 > > I also see that in the simulations I did. Sender side pcap can be found > at: https://people.freebsd.org/~hiren/pcaps/single_packet_loss.pcap > > Trying to send 50kb of data from freebsd 10.2 server to freebsd client. > Initial cwnd is 10 so we blast out 10 packets but 1 packet gets dropped: > seq 2897:4345. We get 3 dupacks and we retransmit it. But as soon as we > detect this loss, we reduce cwnd to 1 segment. In fact, we could've used > data in SACK to see how much we could send on the n/w, imo. > > 3rd dup ack (which triggered the retransmit) looks like this: > IP 192.168.11.10.41674 > 192.168.10.10.http: Flags [.], ack 2897, win > 12579, options [nop,nop,TS val 4236220288 ecr 3905376863,nop,nop,sack 1 > {4345:10137}], length 0 > > And the retransmit: > IP 192.168.10.10.http > 192.168.11.10.41674: Flags [.], seq 2897:4345, > ack 172, win 12579, options [nop,nop,TS val 3905376894 ecr 4236220288], > length 1448 > > At this point in time, sender knows that it has sent 23169 bytes (last > packet server sent was seq 21721:23169) and received ack for 10137 > bytes minus a missing packet = 8689 bytes. i.e. 6 packets. So, there is > at least that much room on n/w at that point in time. We can go > conservative and halve that. i.e. 3 packets. That is still better than > going down to 1 packet. > > Is there something basic I am missing here? > Any insights would be helpful. You want to read up about window inflation during fast recovery in RFC 5681 followed by 3782, and then consult Stevens vol 2 to understand how variables are used for different purposes depending on connection state and which code path was taken (something I greatly dislike and would love to change one day). Cheers, Lawrence From owner-freebsd-net@freebsd.org Thu Sep 3 13:41:11 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 3C2D89C9E09 for ; Thu, 3 Sep 2015 13:41:11 +0000 (UTC) (envelope-from julian@freebsd.org) Received: from vps1.elischer.org (vps1.elischer.org [204.109.63.16]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "vps1.elischer.org", Issuer "CA Cert Signing Authority" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id F0F35B59 for ; Thu, 3 Sep 2015 13:41:10 +0000 (UTC) (envelope-from julian@freebsd.org) Received: from Julian-MBP3.local (ppp121-45-243-143.lns20.per4.internode.on.net [121.45.243.143]) (authenticated bits=0) by vps1.elischer.org (8.15.2/8.15.2) with ESMTPSA id t83Dex5b001309 (version=TLSv1.2 cipher=DHE-RSA-AES128-SHA bits=128 verify=NO) for ; Thu, 3 Sep 2015 06:41:03 -0700 (PDT) (envelope-from julian@freebsd.org) Subject: Re: Value of congestion window (cwnd) when loss is detected To: freebsd-net@freebsd.org References: <20150903005405.GN68814@strugglingcoder.info> <55E82B59.6000202@freebsd.org> From: Julian Elischer Message-ID: <55E84DE5.6000008@freebsd.org> Date: Thu, 3 Sep 2015 21:40:53 +0800 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:38.0) Gecko/20100101 Thunderbird/38.2.0 MIME-Version: 1.0 In-Reply-To: <55E82B59.6000202@freebsd.org> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 13:41:11 -0000 On 9/3/15 7:13 PM, Lawrence Stewart wrote: > On 09/03/15 10:54, hiren panchasara wrote: >> I am failing to understand the reason behind this behavior. >> >> What should the congestion window (snd_cwnd) be set to when we hit loss? >> It seems that we set it to 1 segment right now. >> https://svnweb.freebsd.org/base/head/sys/netinet/tcp_input.c?revision=286227&view=markup#l2531 >> >> I also see that in the simulations I did. Sender side pcap can be found >> at: https://people.freebsd.org/~hiren/pcaps/single_packet_loss.pcap >> >> Trying to send 50kb of data from freebsd 10.2 server to freebsd client. >> Initial cwnd is 10 so we blast out 10 packets but 1 packet gets dropped: >> seq 2897:4345. We get 3 dupacks and we retransmit it. But as soon as we >> detect this loss, we reduce cwnd to 1 segment. In fact, we could've used >> data in SACK to see how much we could send on the n/w, imo. >> >> 3rd dup ack (which triggered the retransmit) looks like this: >> IP 192.168.11.10.41674 > 192.168.10.10.http: Flags [.], ack 2897, win >> 12579, options [nop,nop,TS val 4236220288 ecr 3905376863,nop,nop,sack 1 >> {4345:10137}], length 0 >> >> And the retransmit: >> IP 192.168.10.10.http > 192.168.11.10.41674: Flags [.], seq 2897:4345, >> ack 172, win 12579, options [nop,nop,TS val 3905376894 ecr 4236220288], >> length 1448 >> >> At this point in time, sender knows that it has sent 23169 bytes (last >> packet server sent was seq 21721:23169) and received ack for 10137 >> bytes minus a missing packet = 8689 bytes. i.e. 6 packets. So, there is >> at least that much room on n/w at that point in time. We can go >> conservative and halve that. i.e. 3 packets. That is still better than >> going down to 1 packet. >> >> Is there something basic I am missing here? >> Any insights would be helpful. > You want to read up about window inflation during fast recovery in RFC > 5681 followed by 3782, and then consult Stevens vol 2 to understand how > variables are used for different purposes depending on connection state > and which code path was taken (something I greatly dislike and would > love to change one day). how about today? > > Cheers, > Lawrence > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > From owner-freebsd-net@freebsd.org Thu Sep 3 14:11:32 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id AB1DE9C9B89 for ; Thu, 3 Sep 2015 14:11:32 +0000 (UTC) (envelope-from s3erios@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 893631C3D for ; Thu, 3 Sep 2015 14:11:32 +0000 (UTC) (envelope-from s3erios@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id 862A29C9B88; Thu, 3 Sep 2015 14:11:32 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 85C459C9B87 for ; Thu, 3 Sep 2015 14:11:32 +0000 (UTC) (envelope-from s3erios@gmail.com) Received: from mail-wi0-x231.google.com (mail-wi0-x231.google.com [IPv6:2a00:1450:400c:c05::231]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 2D0641C3C; Thu, 3 Sep 2015 14:11:32 +0000 (UTC) (envelope-from s3erios@gmail.com) Received: by wibz8 with SMTP id z8so100496781wib.1; Thu, 03 Sep 2015 07:11:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=content-type:to:cc:subject:references:date:mime-version :content-transfer-encoding:from:message-id:in-reply-to:user-agent; bh=CqRLcYZMgES5BX9I92noyYk8ghnMFFHCLl6p56UGtL4=; b=IfOQsvDgBN4HNnX3peUuAFI1TdCYQ1s3EBhAvuBVkzZP/9JjDFbmvPc3DcNHxnrMuO VWATxoHLShU30a2NqrlfVOJGLKJX1aJFJA7ugd7nrtLTPOH5BRA2rP+WXAIZU6UsHglp 0PBJtFIGfIxbiwJSYQZjgB0BzoHMxbm6wWm5fnxp0fBioQiknGjwPMrD80rbfahcm9/W DwDXly72Mxz/3N+D2XJeZWLDpxroqgxN6pc2kMeEfiNQbyStWqMXPDqX1G6NyreFB4Si lVeeyCHNp0jbjDOI4mlChFmE+62MMzBcj44ytF7oLMdS1U8gAFqUOkDtXhFYzB3aY9AJ vZaQ== X-Received: by 10.194.110.132 with SMTP id ia4mr51540073wjb.103.1441289490419; Thu, 03 Sep 2015 07:11:30 -0700 (PDT) Received: from localhost (host-176-37-109-22.la.net.ua. [176.37.109.22]) by smtp.gmail.com with ESMTPSA id ej5sm38010495wjd.22.2015.09.03.07.11.29 (version=TLSv1 cipher=RC4-SHA bits=128/128); Thu, 03 Sep 2015 07:11:29 -0700 (PDT) Content-Type: text/plain; charset=utf-8; format=flowed; delsp=yes To: "Gleb Smirnoff" Cc: "Lawrence Stewart" , "Adrian Chadd" , "net@freebsd.org" Subject: Re: mbufq-less iwn(4) References: <20150901112043.GB1023@glebius.int.ru> <20150902060324.GF1023@glebius.int.ru> Date: Thu, 03 Sep 2015 17:11:27 +0300 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: "Andriy Voskoboinyk" Message-ID: In-Reply-To: <20150902060324.GF1023@glebius.int.ru> User-Agent: Opera Mail/12.16 (FreeBSD) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 14:11:32 -0000 > Adrian, > > On Tue, Sep 01, 2015 at 12:33:53PM -0700, Adrian Chadd wrote: > A> We have to do mbuf queues in drivers for wifi, because of 11n > A> aggregation. So on one hand we want to have if_transmit() apply > A> backpressure through the stack, but there's also going to be some > A> buffering. :P > > No, that's not because of 11n aggregation. That's a remnant of > ifnet ifqueue. Note that I'm speaking about queueing in drivers, > not in net80211 stack. Look at the iwn patch, it doesn't remove > any functionality except of enqueueing and dequeueing. > > Look at your own ath(4) - there is no software queue there already :) > > A> I'd like to see that for ic_transmit(). > A> > A> Other thing - ic_transmit() also needs to handle fragments, like I do > A> with ath. Ie, handing it a list of packets is actually a list of > A> 802.11 fragments, rather than separate MPDUs. > A> > A> Another thing - we're modifying the mbufs (adding 802.11 data to it) > A> before we pass them to the driver, and if the driver fails to > A> transmit, we can't just pass it back up the net80211 stack to the tcp > A> or udp layer.. > > Sure, stack probably would need to strip the data. Anyway, that's > a future task. > What about https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=193569 ? From owner-freebsd-net@freebsd.org Thu Sep 3 15:00:46 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 7293B99E094 for ; Thu, 3 Sep 2015 15:00:46 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 55FEE991 for ; Thu, 3 Sep 2015 15:00:46 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: by mailman.ysv.freebsd.org (Postfix) id 52F5099E091; Thu, 3 Sep 2015 15:00:46 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 5288399E090 for ; Thu, 3 Sep 2015 15:00:46 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (glebius.int.ru [81.19.69.10]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "cell.glebius.int.ru", Issuer "cell.glebius.int.ru" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id CDACB98D; Thu, 3 Sep 2015 15:00:44 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (localhost [127.0.0.1]) by cell.glebius.int.ru (8.15.2/8.15.2) with ESMTPS id t83F0f1H016240 (version=TLSv1.2 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Thu, 3 Sep 2015 18:00:41 +0300 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.glebius.int.ru (8.15.2/8.15.2/Submit) id t83F0fmm016239; Thu, 3 Sep 2015 18:00:41 +0300 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.glebius.int.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Thu, 3 Sep 2015 18:00:41 +0300 From: Gleb Smirnoff To: Andriy Voskoboinyk , Adrian Chadd Cc: "net@freebsd.org" Subject: Re: mbufq-less iwn(4) Message-ID: <20150903150041.GR1023@glebius.int.ru> References: <20150901112043.GB1023@glebius.int.ru> <20150902060324.GF1023@glebius.int.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 15:00:46 -0000 On Thu, Sep 03, 2015 at 05:11:27PM +0300, Andriy Voskoboinyk wrote: A> > A> Other thing - ic_transmit() also needs to handle fragments, like I do A> > A> with ath. Ie, handing it a list of packets is actually a list of A> > A> 802.11 fragments, rather than separate MPDUs. A> > A> A> > A> Another thing - we're modifying the mbufs (adding 802.11 data to it) A> > A> before we pass them to the driver, and if the driver fails to A> > A> transmit, we can't just pass it back up the net80211 stack to the tcp A> > A> or udp layer.. A> > A> > Sure, stack probably would need to strip the data. Anyway, that's A> > a future task. A> > A> A> What about https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=193569 ? I'd leave that to you, guys :) I don't want to go knee deep into the 802.11, I'm just working on a "tiny" project of opaque struct ifnet :) -- Totus tuus, Glebius. From owner-freebsd-net@freebsd.org Thu Sep 3 16:16:58 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 330DB9C8555 for ; Thu, 3 Sep 2015 16:16:58 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 15DE5D19; Thu, 3 Sep 2015 16:16:57 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id 3B7CFCC2A2; Thu, 3 Sep 2015 09:16:51 -0700 (PDT) Date: Thu, 3 Sep 2015 09:16:51 -0700 From: hiren panchasara To: Lawrence Stewart Cc: freebsd-net@freebsd.org Subject: Re: Value of congestion window (cwnd) when loss is detected Message-ID: <20150903161651.GQ68814@strugglingcoder.info> References: <20150903005405.GN68814@strugglingcoder.info> <55E82B59.6000202@freebsd.org> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="X35wERi4JU/f1kly" Content-Disposition: inline In-Reply-To: <55E82B59.6000202@freebsd.org> User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 16:16:58 -0000 --X35wERi4JU/f1kly Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 09/03/15 at 09:13P, Lawrence Stewart wrote: > On 09/03/15 10:54, hiren panchasara wrote: > > I am failing to understand the reason behind this behavior. > >=20 > > What should the congestion window (snd_cwnd) be set to when we hit loss? > > It seems that we set it to 1 segment right now. > > https://svnweb.freebsd.org/base/head/sys/netinet/tcp_input.c?revision= =3D286227&view=3Dmarkup#l2531 > >=20 > > I also see that in the simulations I did. Sender side pcap can be found > > at: https://people.freebsd.org/~hiren/pcaps/single_packet_loss.pcap > >=20 > > Trying to send 50kb of data from freebsd 10.2 server to freebsd client. > > Initial cwnd is 10 so we blast out 10 packets but 1 packet gets dropped: > > seq 2897:4345. We get 3 dupacks and we retransmit it. But as soon as we > > detect this loss, we reduce cwnd to 1 segment. In fact, we could've used > > data in SACK to see how much we could send on the n/w, imo. > >=20 > > 3rd dup ack (which triggered the retransmit) looks like this: > > IP 192.168.11.10.41674 > 192.168.10.10.http: Flags [.], ack 2897, win > > 12579, options [nop,nop,TS val 4236220288 ecr 3905376863,nop,nop,sack 1 > > {4345:10137}], length 0 > >=20 > > And the retransmit: > > IP 192.168.10.10.http > 192.168.11.10.41674: Flags [.], seq 2897:4345, > > ack 172, win 12579, options [nop,nop,TS val 3905376894 ecr 4236220288], > > length 1448 > >=20 > > At this point in time, sender knows that it has sent 23169 bytes (last > > packet server sent was seq 21721:23169) and received ack for 10137 > > bytes minus a missing packet =3D 8689 bytes. i.e. 6 packets. So, there = is > > at least that much room on n/w at that point in time. We can go > > conservative and halve that. i.e. 3 packets. That is still better than > > going down to 1 packet. > >=20 > > Is there something basic I am missing here? > > Any insights would be helpful. >=20 > You want to read up about window inflation during fast recovery in RFC > 5681 followed by 3782, and then consult Stevens vol 2 to understand how > variables are used for different purposes depending on connection state > and which code path was taken (something I greatly dislike and would > love to change one day). Thanks Lawrence for the pointers. From what I could see in the code (as I pointed above in original email) as soon as we get 3rd dup ack in tcp_do_segment() insdie 'else if (tp->t_dupacks =3D=3D tcprexmtthresh)' we check if we could do SACK with 'if (tp->t_flags & TF_SACK_PERMIT)' and we set 'tp->snd_cwnd =3D tp->t_maxseg;' before calling tcp_output(). And I've seen this behavior on many situations. So wanted to confirm if others are also seeing this. FWIW, I am using cubic cc. But as far as I can see, snd_cwnd setting for FreeBSD is outside of any cc algos' scope. i.e. We override whatever is being set. I'll do the necessary readings. Cheers, Hiren --X35wERi4JU/f1kly Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJV6HJyXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lPaQH/3Hj5kIgPEfPESvpxfoXk3mT wXXKOW/fHoNBHO5tdkqH2pJGQKh5XZmU6dpzZp8gR+Sfg+wDu7lAbZwiwH2NzXQX KWcoOltJtaYnSUzA8afAlt98GBmUu7176zkbHdWa/+20mr6MA2VgRLCPDuBpqmSH yFGa3W+hRu+0MEXD1rC8sd+zlx6k0S9zykBEv1xaPL+bn/6HHjwcRwj2TqD1VREE Hu207WEQckBP82aolqy5hYsv5hc2cuH/iE/USt9yRm49LzhsqZVxVLB8faExkSIz +cEgVf4bMI+uQb87bZ3CjqSR6YE1woJHPJTtbFnkM6wKcCMolGamoZTal7Nbrfs= =Ghkx -----END PGP SIGNATURE----- --X35wERi4JU/f1kly-- From owner-freebsd-net@freebsd.org Thu Sep 3 17:33:53 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 0DEB69CAFA2 for ; Thu, 3 Sep 2015 17:33:53 +0000 (UTC) (envelope-from vijju.singh@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id E19F3E30 for ; Thu, 3 Sep 2015 17:33:52 +0000 (UTC) (envelope-from vijju.singh@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id DED289CAFA1; Thu, 3 Sep 2015 17:33:52 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id DE3709CAF9F; Thu, 3 Sep 2015 17:33:52 +0000 (UTC) (envelope-from vijju.singh@gmail.com) Received: from mail-ig0-x22f.google.com (mail-ig0-x22f.google.com [IPv6:2607:f8b0:4001:c05::22f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id A9847E2F; Thu, 3 Sep 2015 17:33:52 +0000 (UTC) (envelope-from vijju.singh@gmail.com) Received: by igbkq10 with SMTP id kq10so54537459igb.0; Thu, 03 Sep 2015 10:33:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=wDM0p1h+Ph65B/lfjdxxKkE3U6VA4luo6krKOe9wuV0=; b=CLtXGOucJfoyDzavZzBbZBO5t16cNSv2gn9M0oyxVY4AefpoL1HYEqwy5NAhk5Pp6q bg6GWbnU9Lf7Ffft72EXn5AsNW3KG7SaGqChRsMYqTXvPJ1VjPnbFNIVETpwEZ5I39Cw p1Yu+8BUlTAjq9ExaYz43epb9ySeNsIBHagDwbgTMUAOKN1ivsuthuptnAyMjlotPUVF qaeDtI4NPQtkVuvCN4sAYuGrW3/FQmt6ntiak/f7YKpyi6NIjHkdddJYIMdzr+tHg47U wOJA4Fi/KAo+RR0x2OOaFOGTQUgwhEn3iR0ZeA4ObYi5U5XZ1n0d9i7w8Yi+8GN01s3K Ymfw== MIME-Version: 1.0 X-Received: by 10.50.30.106 with SMTP id r10mr15592090igh.69.1441301631865; Thu, 03 Sep 2015 10:33:51 -0700 (PDT) Received: by 10.107.137.233 with HTTP; Thu, 3 Sep 2015 10:33:51 -0700 (PDT) In-Reply-To: References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> Date: Thu, 3 Sep 2015 10:33:51 -0700 Message-ID: Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: Vijay Singh To: Garrett Cooper Cc: Hrishikesh Keremane , "hackers@freebsd.org" , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 17:33:53 -0000 Someone told me that once the OFED code hit kernel.org the GPL is the only license that applies. Does anyone have insights about that? On Mon, Aug 31, 2015 at 10:25 AM, Garrett Cooper wrote: > > > On Aug 31, 2015, at 09:34, Hrishikesh Keremane via freebsd-hackers < > freebsd-hackers@freebsd.org> wrote: > > > > [Sorry for cross posting] > > > > Hi, > > > > We are working on a product(FreeBSD based) that would require RDMA over > iWARP and are considering using the OFED stack in FreeBSD 9.1. > > We will be making some changes to the OFED stack to customize it to our > requirements. > > > > The concern is regarding the implications of GPL licensing of OFED on > our code base. > > Has anyone worked with OFED in FreeBSD and/or is aware of the licensing > issues around it? > > > > Thanks in advance for your help. > > > > Please include me in your replies as I am not subscribed to these lists. > > The OFED stack is BSD/GPLv2 dual licensed IIRC. the Mellanox import might > have made it 100% BSD licensed though. > > There's FreeBSD-infiniband@freebsd.org as well. It's a low traffic list, > but it might hit a better target audience in the future. > > Cheers, > -NGie > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > From owner-freebsd-net@freebsd.org Thu Sep 3 17:53:14 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A624F9C9A29 for ; Thu, 3 Sep 2015 17:53:14 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 89BA3F0; Thu, 3 Sep 2015 17:53:14 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id 727C3CCAC6; Thu, 3 Sep 2015 10:53:13 -0700 (PDT) Date: Thu, 3 Sep 2015 10:53:13 -0700 From: hiren panchasara To: Lawrence Stewart Cc: freebsd-net@freebsd.org Subject: Re: Value of congestion window (cwnd) when loss is detected Message-ID: <20150903175313.GS68814@strugglingcoder.info> References: <20150903005405.GN68814@strugglingcoder.info> <55E82B59.6000202@freebsd.org> <20150903161651.GQ68814@strugglingcoder.info> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="H5pgEA8DvTwLpheO" Content-Disposition: inline In-Reply-To: <20150903161651.GQ68814@strugglingcoder.info> User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 17:53:14 -0000 --H5pgEA8DvTwLpheO Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 09/03/15 at 09:16P, hiren panchasara wrote: > On 09/03/15 at 09:13P, Lawrence Stewart wrote: [skip] > >=20 > > You want to read up about window inflation during fast recovery in RFC > > 5681 followed by 3782, and then consult Stevens vol 2 to understand how > > variables are used for different purposes depending on connection state > > and which code path was taken (something I greatly dislike and would > > love to change one day). Here is my understanding of these rfcs: RFC 5681: 3.2. Fast Retransmit/Fast Recovery When we detect loss: 2. When the third duplicate ACK is received, a TCP MUST set ssthresh to no more than the value given in equation (4). When [RFC3042]is in use, additional data sent in limited transmit MUST NOT be included in this calculation. ssthresh =3D max (FlightSize / 2, 2*SMSS) <-- equation (4). In my example, ssthresh =3D max (14480 / 2, 2*1448) =3D 7240. i.e. 5 packets 3. The lost segment starting at SND.UNA MUST be retransmitted and cwnd set to ssthresh plus 3*SMSS. This artificially "inflates" the congestion window by the number of segments (three) that haveleft the network and which the receiver has buffered. cwnd =3D (ssthresh + 3*SMSS) In my example, cwnd =3D 7240 + 3*1448 =3D 11584, i,e, 8 packets RFC 3782: We either do sack based recovery *or* newreno based recovery. And we do sack based when TF_SACK_PERMIT is present. So I don't think this comes into play. Please correct me if that is not the case. Stevens vol 2: sshthresh: "When t_dupacks reaches 3 ( tcprexmtthresh ), the value of snd_nxt is saved in onxt and the slow start threshold ( ssthresh ) is set to one-half the current congestion window, with a minimum value of two segments." snd_cwnd: The congestion window is set to the slow start threshold plus the number of segments that the other end has cached. By cached we mean the number of out-of-order segments that the other end has received and generated duplicate ACKs for. These cannot be passed to the process at the other end until the missing segment (which was just sent) is received. So, according to this, sshthresh itself is set pretty high i.e. cwnd/2. And, snd_cwnd =3D sshthresh + cached packets at the other end. In my example, when server realizes loss, cwnd is 17377 i.e. 12 packets. Half of that is 6 packets. And cached packets is 2 because the dup acks we got were for 'ack 2897'. So, according to stevens, snd_cwnd should have been 6+2 =3D 8 packets. Which matches up to what RFC 5681 suggests. Does this look reasonable? Cheers, Hiren --H5pgEA8DvTwLpheO Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJV6IkIXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lKxkH/Al/p8UkvNMD6jzWMPlP57I+ 6d6u5kAe+gPnvDxAqQtuYgmirCb60YkXLBw7c+xoa39ThMsNx+R336ftRWYIhw8B Jjvwih8f6ZLZmvr+BQg5Hkywt1V9PO8bOtKMZ+kcLuGB75RWxuKljp51TGLFf6lZ N+/u0zPgTTyReWQNV3OI3EK5E8T9udBpyUWU6uYUDODaatvyMSOZJBKQAsvE0WEh kBAyh2p2XOGv+eCHGxszvHp65JnLZ3kSQK46ZhLaNRa2wnfpqKwSdFaqDFZG4DUm AJBhfMHUEHPkwkCDxnc+lCOCpWsfLkbYRpPMj2DlH71vukwjDVAFRsGDTCQkt1Q= =K0QQ -----END PGP SIGNATURE----- --H5pgEA8DvTwLpheO-- From owner-freebsd-net@freebsd.org Thu Sep 3 19:07:40 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id D8F219C9919 for ; Thu, 3 Sep 2015 19:07:40 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id B596C76A for ; Thu, 3 Sep 2015 19:07:40 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id B2DC09C9917; Thu, 3 Sep 2015 19:07:40 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B1EFD9C9914; Thu, 3 Sep 2015 19:07:40 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-ig0-x234.google.com (mail-ig0-x234.google.com [IPv6:2607:f8b0:4001:c05::234]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 7A3B4766; Thu, 3 Sep 2015 19:07:40 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: by igbni9 with SMTP id ni9so47902278igb.0; Thu, 03 Sep 2015 12:07:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=GtkR/W04jW8i6faDWNdN1sRyq3J4jM8/X3ST1W+jG78=; b=snqLyDxKXbRznv7mYPW3ZKtdJcoFgT5njc9R1ToqBIu8YfQBCbTXBcwsmC2lw95RDv kKH0mzCppGxTlWTNyQ6oIpo6jU8A0mkf+MWQJrzX7gnzPPIEr7qow47BQ9YV7TWoAKuM SllQa7oHd3jXVO+ecb2RfemkSpw/zS02vtb5KktHaIy9v2sLcH4FQQzxcUFEljZv+Yqz exhd7v0E9Z1CP0Lr69IrEEbn6ovTHhpMOwFZT8UE4L2EGJK4P3UwYCPBNe4K/Nnahj9S LB+tjgfOYZDX6aTwpTbaZIoZ+aZAVVa9sWkufvAW/DGWxE/ph58Cm0maXnK389zT6RfJ EJYg== MIME-Version: 1.0 X-Received: by 10.50.87.98 with SMTP id w2mr16626352igz.60.1441307259856; Thu, 03 Sep 2015 12:07:39 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.36.30.202 with HTTP; Thu, 3 Sep 2015 12:07:39 -0700 (PDT) Received: by 10.36.30.202 with HTTP; Thu, 3 Sep 2015 12:07:39 -0700 (PDT) In-Reply-To: References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> Date: Thu, 3 Sep 2015 12:07:39 -0700 X-Google-Sender-Auth: e57jsptXKKUbU8MDBY1KCyuYGec Message-ID: Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: "K. Macy" To: Vijay Singh Cc: Hrishikesh Keremane , "hackers@freebsd.org" , Garrett Cooper , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 19:07:40 -0000 On Sep 3, 2015 10:33 AM, "Vijay Singh" wrote: > > Someone told me that once the OFED code hit kernel.org the GPL is the only > license that applies. Does anyone have insights about that? That sounds bizarre since mellanox wrote the code and explicitly dual licensed. The problem you *do* run in to is code creep. The Linux internal interfaces are almost certainly totally undocumented, so a clean room reimplementation as they change or bugs get fixed - changing behaviors - is not possible. Over time the tendency is to copy and paste from Linux to OFED or the shim layer creating real ambiguity about provenance. In practice it's not so much of a problem because Linus tends to adhere to an interpretation of the GPLv2 that is not vendor unfriendly the way some of his lieutenants would prefer (see Greg's efforts to call closed source drivers derived works). Nonetheless, if you're paranoid an audit is in order. Cheers. > > On Mon, Aug 31, 2015 at 10:25 AM, Garrett Cooper > wrote: > > > > > > On Aug 31, 2015, at 09:34, Hrishikesh Keremane via freebsd-hackers < > > freebsd-hackers@freebsd.org> wrote: > > > > > > [Sorry for cross posting] > > > > > > Hi, > > > > > > We are working on a product(FreeBSD based) that would require RDMA over > > iWARP and are considering using the OFED stack in FreeBSD 9.1. > > > We will be making some changes to the OFED stack to customize it to our > > requirements. > > > > > > The concern is regarding the implications of GPL licensing of OFED on > > our code base. > > > Has anyone worked with OFED in FreeBSD and/or is aware of the licensing > > issues around it? > > > > > > Thanks in advance for your help. > > > > > > Please include me in your replies as I am not subscribed to these lists. > > > > The OFED stack is BSD/GPLv2 dual licensed IIRC. the Mellanox import might > > have made it 100% BSD licensed though. > > > > There's FreeBSD-infiniband@freebsd.org as well. It's a low traffic list, > > but it might hit a better target audience in the future. > > > > Cheers, > > -NGie > > _______________________________________________ > > freebsd-net@freebsd.org mailing list > > https://lists.freebsd.org/mailman/listinfo/freebsd-net > > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > > > _______________________________________________ > freebsd-hackers@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-hackers > To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org" From owner-freebsd-net@freebsd.org Thu Sep 3 20:07:05 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 4ADE29C92E3 for ; Thu, 3 Sep 2015 20:07:05 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 279D018D3 for ; Thu, 3 Sep 2015 20:07:05 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id 2250B9C92DD; Thu, 3 Sep 2015 20:07:05 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 219309C92DA; Thu, 3 Sep 2015 20:07:05 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: from mail-wi0-x232.google.com (mail-wi0-x232.google.com [IPv6:2a00:1450:400c:c05::232]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id A2FDF18CC; Thu, 3 Sep 2015 20:07:04 +0000 (UTC) (envelope-from jfvogel@gmail.com) Received: by wicge5 with SMTP id ge5so85334225wic.0; Thu, 03 Sep 2015 13:07:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=cQouZsnwV7/aSzxQCC7bDuq6DHZisqUj8LiLLoh0PeA=; b=dSS3Y1dPtCH5TSOI5TuRGE7054DMDHbhWsTrTLpfbieQ3LQboxZgkxjytjvcv1vx79 ZP6xUbU8zDr6v+Hsj2U8U+0h+ZYPQ1MhW1MMv03gXj8TPGkA4nameYRco4pd1Cs6ASiW ZvU/pbP2RI6jxJEn5gnaKVdG1pGzcLqRYY0RLqcKhzA7NUbcjdwEEy3ImLfTPbfcOWq3 Lv+LfKez/RuTf9sOB6Lb7EkAgunBdHsE3XDx87/ppsbT1l+G7VbHqvbR83V4dPK6Ydsu LLfdXfuoX1i1dpHmol1pHr1JRela9MocoirdSmeJvRllv1NQZaSEx+IeLLrNRMJ0LinV DQwQ== MIME-Version: 1.0 X-Received: by 10.194.104.39 with SMTP id gb7mr54433357wjb.150.1441310823083; Thu, 03 Sep 2015 13:07:03 -0700 (PDT) Received: by 10.194.158.101 with HTTP; Thu, 3 Sep 2015 13:07:03 -0700 (PDT) In-Reply-To: References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> Date: Thu, 3 Sep 2015 13:07:03 -0700 Message-ID: Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: Jack Vogel To: "K. Macy" Cc: Vijay Singh , Hrishikesh Keremane , "hackers@freebsd.org" , Garrett Cooper , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 20:07:05 -0000 We (meaning Intel when I was still there) raised this issue with George a long time ago, I'm not sure what the resolution was. If Mellanox is the owner then they should have released the code somewhere without any GPL license in it, as Intel does with code they multi-license. Jack On Thu, Sep 3, 2015 at 12:07 PM, K. Macy wrote: > On Sep 3, 2015 10:33 AM, "Vijay Singh" wrote: > > > > Someone told me that once the OFED code hit kernel.org the GPL is the > only > > license that applies. Does anyone have insights about that? > > That sounds bizarre since mellanox wrote the code and explicitly dual > licensed. > > The problem you *do* run in to is code creep. The Linux internal interfaces > are almost certainly totally undocumented, so a clean room reimplementation > as they change or bugs get fixed - changing behaviors - is not possible. > Over time the tendency is to copy and paste from Linux to OFED or the shim > layer creating real ambiguity about provenance. In practice it's not so > much of a problem because Linus tends to adhere to an interpretation of the > GPLv2 that is not vendor unfriendly the way some of his lieutenants would > prefer (see Greg's efforts to call closed source drivers derived works). > > Nonetheless, if you're paranoid an audit is in order. > > Cheers. > > > > > On Mon, Aug 31, 2015 at 10:25 AM, Garrett Cooper > > wrote: > > > > > > > > > On Aug 31, 2015, at 09:34, Hrishikesh Keremane via freebsd-hackers < > > > freebsd-hackers@freebsd.org> wrote: > > > > > > > > [Sorry for cross posting] > > > > > > > > Hi, > > > > > > > > We are working on a product(FreeBSD based) that would require RDMA > over > > > iWARP and are considering using the OFED stack in FreeBSD 9.1. > > > > We will be making some changes to the OFED stack to customize it to > our > > > requirements. > > > > > > > > The concern is regarding the implications of GPL licensing of OFED on > > > our code base. > > > > Has anyone worked with OFED in FreeBSD and/or is aware of the > licensing > > > issues around it? > > > > > > > > Thanks in advance for your help. > > > > > > > > Please include me in your replies as I am not subscribed to these > lists. > > > > > > The OFED stack is BSD/GPLv2 dual licensed IIRC. the Mellanox import > might > > > have made it 100% BSD licensed though. > > > > > > There's FreeBSD-infiniband@freebsd.org as well. It's a low traffic > list, > > > but it might hit a better target audience in the future. > > > > > > Cheers, > > > -NGie > > > _______________________________________________ > > > freebsd-net@freebsd.org mailing list > > > https://lists.freebsd.org/mailman/listinfo/freebsd-net > > > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > > > > > _______________________________________________ > > freebsd-hackers@freebsd.org mailing list > > https://lists.freebsd.org/mailman/listinfo/freebsd-hackers > > To unsubscribe, send any mail to " > freebsd-hackers-unsubscribe@freebsd.org" > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > From owner-freebsd-net@freebsd.org Thu Sep 3 20:25:28 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 1B4739C9C15 for ; Thu, 3 Sep 2015 20:25:28 +0000 (UTC) (envelope-from jeffm@frob.org) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id F33EE279 for ; Thu, 3 Sep 2015 20:25:27 +0000 (UTC) (envelope-from jeffm@frob.org) Received: by mailman.ysv.freebsd.org (Postfix) id EDCD29C9C11; Thu, 3 Sep 2015 20:25:27 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id D41CD9C9C0E for ; Thu, 3 Sep 2015 20:25:27 +0000 (UTC) (envelope-from jeffm@frob.org) Received: from server283.com (server283.com [64.14.68.91]) by mx1.freebsd.org (Postfix) with ESMTP id 8DF87276 for ; Thu, 3 Sep 2015 20:25:27 +0000 (UTC) (envelope-from jeffm@frob.org) Received: (qmail 28369 invoked by uid 503); 3 Sep 2015 20:18:46 -0000 Received: from unknown (HELO ?192.168.100.131?) (jeffm@98.203.199.57) by server283.com with ESMTPA; 3 Sep 2015 20:18:46 -0000 Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: Jeff Meegan In-Reply-To: Date: Thu, 3 Sep 2015 13:18:32 -0700 Cc: "K. Macy" , "net@freebsd.org" , Hrishikesh Keremane , "hackers@freebsd.org" , Garrett Cooper , Vijay Singh Message-Id: <7FF6BFC8-0031-4E40-AB38-75B5FD4EF466@frob.org> References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> To: Jack Vogel X-Mailer: Apple Mail (2.2104) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 20:25:28 -0000 According to their EULA, it is BSD licensed. http://www.mellanox.com/page/mlnx_ofed_eula?mtag=3Dlinux_sw_drivers = =E2=80=94j > On Sep 3, 2015, at 1:07 PM, Jack Vogel wrote: >=20 > We (meaning Intel when I was still there) raised this issue with = George a > long time ago, I'm not sure > what the resolution was. >=20 > If Mellanox is the owner then they should have released the code = somewhere > without any > GPL license in it, as Intel does with code they multi-license. >=20 > Jack >=20 >=20 > On Thu, Sep 3, 2015 at 12:07 PM, K. Macy wrote: >=20 >> On Sep 3, 2015 10:33 AM, "Vijay Singh" wrote: >>>=20 >>> Someone told me that once the OFED code hit kernel.org the GPL is = the >> only >>> license that applies. Does anyone have insights about that? >>=20 >> That sounds bizarre since mellanox wrote the code and explicitly dual >> licensed. >>=20 >> The problem you *do* run in to is code creep. The Linux internal = interfaces >> are almost certainly totally undocumented, so a clean room = reimplementation >> as they change or bugs get fixed - changing behaviors - is not = possible. >> Over time the tendency is to copy and paste from Linux to OFED or the = shim >> layer creating real ambiguity about provenance. In practice it's not = so >> much of a problem because Linus tends to adhere to an interpretation = of the >> GPLv2 that is not vendor unfriendly the way some of his lieutenants = would >> prefer (see Greg's efforts to call closed source drivers derived = works). >>=20 >> Nonetheless, if you're paranoid an audit is in order. >>=20 >> Cheers. >>=20 >>>=20 >>> On Mon, Aug 31, 2015 at 10:25 AM, Garrett Cooper = >>> wrote: >>>=20 >>>>=20 >>>>> On Aug 31, 2015, at 09:34, Hrishikesh Keremane via freebsd-hackers = < >>>> freebsd-hackers@freebsd.org> wrote: >>>>>=20 >>>>> [Sorry for cross posting] >>>>>=20 >>>>> Hi, >>>>>=20 >>>>> We are working on a product(FreeBSD based) that would require RDMA >> over >>>> iWARP and are considering using the OFED stack in FreeBSD 9.1. >>>>> We will be making some changes to the OFED stack to customize it = to >> our >>>> requirements. >>>>>=20 >>>>> The concern is regarding the implications of GPL licensing of OFED = on >>>> our code base. >>>>> Has anyone worked with OFED in FreeBSD and/or is aware of the >> licensing >>>> issues around it? >>>>>=20 >>>>> Thanks in advance for your help. >>>>>=20 >>>>> Please include me in your replies as I am not subscribed to these >> lists. >>>>=20 >>>> The OFED stack is BSD/GPLv2 dual licensed IIRC. the Mellanox import >> might >>>> have made it 100% BSD licensed though. >>>>=20 >>>> There's FreeBSD-infiniband@freebsd.org as well. It's a low traffic >> list, >>>> but it might hit a better target audience in the future. >>>>=20 >>>> Cheers, >>>> -NGie >>>> _______________________________________________ >>>> freebsd-net@freebsd.org mailing list >>>> https://lists.freebsd.org/mailman/listinfo/freebsd-net >>>> To unsubscribe, send any mail to = "freebsd-net-unsubscribe@freebsd.org" >>>>=20 >>> _______________________________________________ >>> freebsd-hackers@freebsd.org mailing list >>> https://lists.freebsd.org/mailman/listinfo/freebsd-hackers >>> To unsubscribe, send any mail to " >> freebsd-hackers-unsubscribe@freebsd.org" >> _______________________________________________ >> freebsd-net@freebsd.org mailing list >> https://lists.freebsd.org/mailman/listinfo/freebsd-net >> To unsubscribe, send any mail to = "freebsd-net-unsubscribe@freebsd.org" >>=20 > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@freebsd.org Thu Sep 3 21:42:46 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id EE92B9C9E64 for ; Thu, 3 Sep 2015 21:42:45 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id CF4C3D33 for ; Thu, 3 Sep 2015 21:42:45 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id CE21B9C9E63; Thu, 3 Sep 2015 21:42:45 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id CDB2E9C9E62 for ; Thu, 3 Sep 2015 21:42:45 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-ig0-x230.google.com (mail-ig0-x230.google.com [IPv6:2607:f8b0:4001:c05::230]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 9A56FD32; Thu, 3 Sep 2015 21:42:45 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by igcrk20 with SMTP id rk20so1504445igc.1; Thu, 03 Sep 2015 14:42:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=o8MTDSc9N9CYKDVbTP83qJfwW0Xe9j9kncckSVTb1VQ=; b=Yv/KsjbkuTdoDka+zh7Ua6svciGqNzBBulKLBQSpasZu1d88aI8jTSgYU4x5sa6+Q7 oUgy002VDBFo25kTXtLE+pOxC26sBefdNYfIGN2vB2sVcVZzwx4htA9EGbyyNAZU08dH jd6sZGdKH2MBevKra32jPElddR1IDB3XNij942szokTAcPTg+M4sq1nXq4KM7f7F7QAZ VE6sreWe2KJy7Bhb9RdvymMJ2dx3ga6Up6UE51vbaGWN4HR5a95/WUP8z0Dz27RUxzZT SoNC8K1tCRyVboTPCJEyjPoKV5bqYYaqKGPEpnAYxb0fshvUESjS8DciS4o6BPYzT1aH LoTw== MIME-Version: 1.0 X-Received: by 10.50.49.101 with SMTP id t5mr639070ign.61.1441316565067; Thu, 03 Sep 2015 14:42:45 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.36.28.208 with HTTP; Thu, 3 Sep 2015 14:42:45 -0700 (PDT) In-Reply-To: References: <20150901112043.GB1023@glebius.int.ru> <20150902060324.GF1023@glebius.int.ru> Date: Thu, 3 Sep 2015 14:42:45 -0700 X-Google-Sender-Auth: Sps5yrZOqoqVs2WXb7VrAzPaomg Message-ID: Subject: Re: mbufq-less iwn(4) From: Adrian Chadd To: Andriy Voskoboinyk Cc: Gleb Smirnoff , Lawrence Stewart , "net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 21:42:46 -0000 It's fixed in -head. I should close that. -a On 3 September 2015 at 07:11, Andriy Voskoboinyk wrote: >> Adrian, >> >> On Tue, Sep 01, 2015 at 12:33:53PM -0700, Adrian Chadd wrote: >> A> We have to do mbuf queues in drivers for wifi, because of 11n >> A> aggregation. So on one hand we want to have if_transmit() apply >> A> backpressure through the stack, but there's also going to be some >> A> buffering. :P >> >> No, that's not because of 11n aggregation. That's a remnant of >> ifnet ifqueue. Note that I'm speaking about queueing in drivers, >> not in net80211 stack. Look at the iwn patch, it doesn't remove >> any functionality except of enqueueing and dequeueing. >> >> Look at your own ath(4) - there is no software queue there already :) >> >> A> I'd like to see that for ic_transmit(). >> A> >> A> Other thing - ic_transmit() also needs to handle fragments, like I do >> A> with ath. Ie, handing it a list of packets is actually a list of >> A> 802.11 fragments, rather than separate MPDUs. >> A> >> A> Another thing - we're modifying the mbufs (adding 802.11 data to it) >> A> before we pass them to the driver, and if the driver fails to >> A> transmit, we can't just pass it back up the net80211 stack to the tcp >> A> or udp layer.. >> >> Sure, stack probably would need to strip the data. Anyway, that's >> a future task. >> > > What about https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=193569 ? From owner-freebsd-net@freebsd.org Thu Sep 3 23:08:31 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 9F51C9CA4FA for ; Thu, 3 Sep 2015 23:08:31 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: from mailman.ysv.freebsd.org (mailman.ysv.freebsd.org [IPv6:2001:1900:2254:206a::50:5]) by mx1.freebsd.org (Postfix) with ESMTP id 60360117E for ; Thu, 3 Sep 2015 23:08:31 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: by mailman.ysv.freebsd.org (Postfix) id 5D2089CA4F9; Thu, 3 Sep 2015 23:08:31 +0000 (UTC) Delivered-To: net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 42C519CA4F7; Thu, 3 Sep 2015 23:08:31 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: from mail-pa0-x22e.google.com (mail-pa0-x22e.google.com [IPv6:2607:f8b0:400e:c03::22e]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 0F674117D; Thu, 3 Sep 2015 23:08:31 +0000 (UTC) (envelope-from yaneurabeya@gmail.com) Received: by pacex6 with SMTP id ex6so4223053pac.0; Thu, 03 Sep 2015 16:08:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=YjXKeJVvXBjsZYIiq4e+ipdI5KoJmu4L8DS62OHxAzs=; b=Qi7USCpL2YEhJOH4q2FS2ztBhQ7mmaHkAHs0T7DnqdUGasEK2f0Sp0I0ZVBSLF+rer 5TLWDn5ndyuhO3ZZBCkkpxfCc8EzzkDksFkz1BcdR1DQL1s2HzNxYA2ywZ5sI30/FFnN GgoquXoCARvFQvGMhvxQfzE8ckmzg4WGpFsZ6/M+tVzJLkC9LL8dqHmg8P32wn0RxXFj imR3HZOzUkmH1wZkTSAZmknkjt/QgfBtZTpdBoyij0pEYzyxKFarohM37+douaiCyrcg 7XLVYKy4tdxPnr4ewe07GLbT+ln7uE1CFTUN9KA673AOvQcyVAFxsdM/mPcXhkFBNmJr qCyw== X-Received: by 10.68.69.70 with SMTP id c6mr1007082pbu.28.1441321710382; Thu, 03 Sep 2015 16:08:30 -0700 (PDT) Received: from [33.167.141.194] ([172.56.33.24]) by smtp.gmail.com with ESMTPSA id dh9sm206055pdb.67.2015.09.03.16.08.29 (version=TLSv1/SSLv3 cipher=OTHER); Thu, 03 Sep 2015 16:08:29 -0700 (PDT) Mime-Version: 1.0 (1.0) Subject: Re: GPL issues around OFED code in FreeBSD 9.1 From: Garrett Cooper X-Mailer: iPhone Mail (12H321) In-Reply-To: <7FF6BFC8-0031-4E40-AB38-75B5FD4EF466@frob.org> Date: Thu, 3 Sep 2015 16:08:28 -0700 Cc: Jack Vogel , "K. Macy" , "net@freebsd.org" , Hrishikesh Keremane , "hackers@freebsd.org" , Vijay Singh Message-Id: References: <5BFB9010-159A-44EE-BB9A-A4E445383AA2@yahoo.com> <7FF6BFC8-0031-4E40-AB38-75B5FD4EF466@frob.org> To: Jeff Meegan Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 23:08:31 -0000 > On Sep 3, 2015, at 13:18, Jeff Meegan wrote: > > According to their EULA, it is BSD licensed. > > http://www.mellanox.com/page/mlnx_ofed_eula?mtag=linux_sw_drivers Yes, but the 9.1 version wasn't strictly from Mellanox.. I don't know if I'd use the pre-Mellanox version though, tbh. Thanks, -NGie From owner-freebsd-net@freebsd.org Thu Sep 3 23:32:31 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 1080B9CAF13 for ; Thu, 3 Sep 2015 23:32:31 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E7EAF18C; Thu, 3 Sep 2015 23:32:30 +0000 (UTC) (envelope-from hiren@strugglingcoder.info) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id 9F542CCD45; Thu, 3 Sep 2015 16:32:29 -0700 (PDT) Date: Thu, 3 Sep 2015 16:32:29 -0700 From: hiren panchasara To: Lawrence Stewart Cc: freebsd-net@freebsd.org Subject: Re: Value of congestion window (cwnd) when loss is detected Message-ID: <20150903233229.GT68814@strugglingcoder.info> References: <20150903005405.GN68814@strugglingcoder.info> <55E82B59.6000202@freebsd.org> <20150903161651.GQ68814@strugglingcoder.info> <20150903175313.GS68814@strugglingcoder.info> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="U8v/hV883cEE9JJG" Content-Disposition: inline In-Reply-To: <20150903175313.GS68814@strugglingcoder.info> User-Agent: Mutt/1.5.23 (2014-03-12) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 03 Sep 2015 23:32:31 -0000 --U8v/hV883cEE9JJG Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 09/03/15 at 10:53P, hiren panchasara wrote: > On 09/03/15 at 09:16P, hiren panchasara wrote: > > On 09/03/15 at 09:13P, Lawrence Stewart wrote: > [skip] > > >=20 > > > You want to read up about window inflation during fast recovery in RFC > > > 5681 followed by 3782, and then consult Stevens vol 2 to understand h= ow > > > variables are used for different purposes depending on connection sta= te > > > and which code path was taken (something I greatly dislike and would > > > love to change one day). >=20 > Here is my understanding of these rfcs: > RFC 5681: > 3.2. Fast Retransmit/Fast Recovery > When we detect loss: > 2. When the third duplicate ACK is received, a TCP MUST set ssthresh to > no more than the value given in equation (4). When [RFC3042]is in use, > additional data sent in limited transmit MUST NOT be included in this > calculation. >=20 > ssthresh =3D max (FlightSize / 2, 2*SMSS) <-- equation (4). > In my example, > ssthresh =3D max (14480 / 2, 2*1448) =3D 7240. i.e. 5 packets >=20 > 3. The lost segment starting at SND.UNA MUST be retransmitted and cwnd > set to ssthresh plus 3*SMSS. This artificially "inflates" the > congestion window by the number of segments (three) that haveleft the > network and which the receiver has buffered. >=20 > cwnd =3D (ssthresh + 3*SMSS) > In my example, > cwnd =3D 7240 + 3*1448 =3D 11584, i,e, 8 packets >=20 > RFC 3782: > We either do sack based recovery *or* newreno based recovery. And we do > sack based when TF_SACK_PERMIT is present. > So I don't think this comes into play. Please correct me if that is not t= he > case. >=20 > Stevens vol 2: >=20 > sshthresh: > "When t_dupacks reaches 3 ( tcprexmtthresh ), the value of snd_nxt is > saved in onxt and the slow start threshold ( ssthresh ) is set to one-half > the current congestion window, with a minimum value of two segments." >=20 > snd_cwnd: > The congestion window is set to the slow start threshold plus the number > of segments that the other end has cached. By cached we mean the number > of out-of-order segments that the other end has received and generated > duplicate ACKs for. These cannot be passed to the process at the other > end until the missing segment (which was just sent) is received. >=20 > So, according to this, sshthresh itself is set pretty high i.e. cwnd/2. > And, snd_cwnd =3D sshthresh + cached packets at the other end. >=20 > In my example, when server realizes loss, cwnd is 17377 i.e. 12 packets. > Half of that is 6 packets. And cached packets is 2 because the dup acks > we got were for 'ack 2897'. So, according to stevens, snd_cwnd should > have been 6+2 =3D 8 packets. Which matches up to what RFC 5681 suggests. My interpretation of cached packets is wrong here. It should be the packets that receiver *cannot* send up the stack. Receiver told us via SACK (sack 1 {4345:10137}) that it has got at least up to 10137, i.e. 7 packets. And cumulative ack is 2897, i.e. 2 packets. So cached packets at the receiver that it cannot send up comes out to be 5 packets. According to this, the snd_cwnd should be 6(ssthresh) + 5(cached) =3D 11 pa= ckets. Cheers, Hiren --U8v/hV883cEE9JJG Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJV6NiNXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lTkAH/1wSoKTNbrFEcuZnbWVM/w+D FXeSG/7J/+WuOclkxNHVM2eDG4UBPYB0ANke/E8Cs4+MJ51AotSosprI76bJ58QO wq43P5oWCn22JPq/vEfMQCSF2AF710io2yz8XlTpuiyXpoF5SGbbkSXaaO0CcThX jv52DAtSV+TqQJ86YV2m8GbyEFhxH7bThuA018/WVpLbpk3zdiTPO+ynvw/5Vev/ 0KkBtvqAsTLtcoPDeBf1QbvF0SOGKW5B6oMyHHB3uWdCBU/soDvdXd5/EZJRIIU+ KJa5xE7DECTuuLDgMSZdFDn2LeROeSyXA6RvLx6KnOqRRXheijYhrcrh8w5l0co= =fRAN -----END PGP SIGNATURE----- --U8v/hV883cEE9JJG-- From owner-freebsd-net@freebsd.org Fri Sep 4 10:43:41 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 83C5E9CA2B1 for ; Fri, 4 Sep 2015 10:43:41 +0000 (UTC) (envelope-from noname.esst@yahoo.com) Received: from nm4-vm1.bullet.mail.ne1.yahoo.com (nm4-vm1.bullet.mail.ne1.yahoo.com [98.138.91.44]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 53F8B8AB for ; Fri, 4 Sep 2015 10:43:40 +0000 (UTC) (envelope-from noname.esst@yahoo.com) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1441363052; bh=3YXjyDVxosqhgiKrw6+4y5eHt9KyXAmAlUfvAcYn3Cs=; h=Date:From:Reply-To:To:Subject:From:Subject; b=QGxbJtmXPih7VwMd/5YqigktekAjDp3zSbQXQUddZfV5XIIbqGKpJ3CDLke9dDCK7gTfHOs6s5kNHDIsmS7yxwrAdTZ33JXSs+A78To1xqCjhIjH9LKAo91+xYoQVkAVo1ZtSzCKRT8ZU/Z0YGkBt3eeZFQqH2stIhp4i9kzXIcrOvAh3uL+X7qpDQpdlL2eSu2NNr5ZQFnfHGsHCVmGbHFGACIZD9nAz+ekp9R1FZ21MlPnWnMeSdmpZE0nany9JqbrvY3HemOavRLWPf2KLcuxJeF8NLrx39TlDqYo63CQ0nnur08NrQspTO/VZyqwUmhsGhqqaoFxRUOZXYnU5g== Received: from [98.138.101.132] by nm4.bullet.mail.ne1.yahoo.com with NNFMP; 04 Sep 2015 10:37:32 -0000 Received: from [98.138.87.5] by tm20.bullet.mail.ne1.yahoo.com with NNFMP; 04 Sep 2015 10:37:32 -0000 Received: from [127.0.0.1] by omp1005.mail.ne1.yahoo.com with NNFMP; 04 Sep 2015 10:37:32 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 176579.64844.bm@omp1005.mail.ne1.yahoo.com X-YMail-OSG: ymxtVEQVM1np.37CbZ1Ys8NXXC.st3CmV2qBc76lqrg9.U2higFhK2ljyok.1D0 b8wcF__acyeVBBlSe_ENxkMVXbz481jQ2esW48lCnCmL2DbjVXlj9vP2rZNWs6u8Sb9AXoOD5GiM phPuGTKwUqwhpSjQrvkSlef8MUzBhl_tSTpq_j5rr7_WApXRpLgKyAvjRv1nGr4tY.OscrreIdXz ViprMdG9cqiwU7CR9exkmBrGzHVr6lrln3Pml87EdiTrh2FqkOAtuqDx_cNz72pJyEd3rHt.bS4F QwyEwO.LnaEW69SA.pmgZIVqm7H2n0LKr1PQ5k6NA_CYkO5gd3GpHNh8bQF1O7suOkYOq7ubgOW1 XKHDLLBTFkXQ5QEKfrWLc_tUt4ZKA3pRd.oLhV_fsLoRNPTFDAUaziztDofahY11WErSx8X8E.rL Wj9b9mSnzcQyWtef7pjox3aE16RhWmckoGR0Ugx51nWi6qsSHMi6kA34- Received: by 98.138.105.193; Fri, 04 Sep 2015 10:37:31 +0000 Date: Fri, 4 Sep 2015 10:37:31 +0000 (UTC) From: Nomad Esst Reply-To: Nomad Esst To: "freebsd-drivers@freebsd.org" , FreeBSD Net , Freebsd Hackers List Message-ID: <740628555.1564144.1441363051289.JavaMail.yahoo@mail.yahoo.com> Subject: FreeBSD em, igb driver question MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 04 Sep 2015 10:43:41 -0000 Hi allDuring some performance tests, we found out some weird problems. We u= se a shell script that do the following : do from 1 to 10Shutdown em/igb interfacesleep 3Bring em/igb interface uptcp= replay -i em0 -l ospf_hello.pcap=C2=A0sleep3end By running this shell on one side we expect 10 ospf hello packets to get ar= rived at the other side, but tcpdump (on the other side) shows 4, sometimes= 8 and etc ... (not all 10 packets are arrived at the other side).We test t= his scenario with a Cisco router, and all packets are received at the Cisco= side. What causes this packet loss in FreeBSD (maybe in em or igb drivers)= ?I know that this scenario may not have any use in the real world, but I'm = curious, why Cisco don't have such behavior.Thanks in advance. Regards. From owner-freebsd-net@freebsd.org Fri Sep 4 22:24:19 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 9F4849CAE00 for ; Fri, 4 Sep 2015 22:24:19 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8B1BA669 for ; Fri, 4 Sep 2015 22:24:19 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t84MOJ5d034703 for ; Fri, 4 Sep 2015 22:24:19 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 123330] [nsswitch.conf] Enabling samba wins in nsswitch.conf causes sshd, ftpd, etc services to die Date: Fri, 04 Sep 2015 22:24:19 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: conf X-Bugzilla-Version: unspecified X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: timur@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 04 Sep 2015 22:24:19 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=123330 --- Comment #3 from Timur I. Bakeyev --- Is this still relevant? Any tries with recent Samba versions? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sat Sep 5 00:42:09 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id AD65B9CA8CD for ; Sat, 5 Sep 2015 00:42:09 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-io0-x22a.google.com (mail-io0-x22a.google.com [IPv6:2607:f8b0:4001:c06::22a]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 8666C19A8 for ; Sat, 5 Sep 2015 00:42:09 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: by ioiz6 with SMTP id z6so41090417ioi.2 for ; Fri, 04 Sep 2015 17:42:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:date:message-id:subject:from:to:content-type; bh=cFz4j6Vpg93W3KpgttbEY1dQJR4TaMoZePaamRfJiWs=; b=Sfdkgz4UwRdOZQmyFpJXZ6IAgolgPmbid0qHz10JXqF1gAr1GoWCm5qFplz2mzmVo2 I3+2EveCBf42nkKOhcb6L9XYnILIEgPcuD+hFIAbDl1ySHKpP35ACUika1xxwQid7Ep4 lmu7c+qT25Jz9Zoff4Gb0ermJrkDFY4+mw2G/UTNvpomPoPnxZgbKAjKnPx12HYWos1k zedPuUmvV7gqZ0o+fr8yYZ/BAop7Ir2dIsePC0vKVcloS8v8vlli0dkApyZRTXu7+NmY MqvynFn8h8aq0U8SySZJXkQbudQA8zTEEQKH/0z3Lken917Sf8NDCnzkus5poFgKuXV2 RReA== MIME-Version: 1.0 X-Received: by 10.107.167.136 with SMTP id q130mr11849174ioe.2.1441413728559; Fri, 04 Sep 2015 17:42:08 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.36.30.202 with HTTP; Fri, 4 Sep 2015 17:42:08 -0700 (PDT) Date: Fri, 4 Sep 2015 17:42:08 -0700 X-Google-Sender-Auth: HWt4lkl8YzaIeCUkDOkC3dQ-3gc Message-ID: Subject: default ECN settings From: "K. Macy" To: "freebsd-net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 00:42:09 -0000 By default ECN is completely disabled on FreeBSD. On Linux the default is to disable it outbound (not request it) but enable it inbound (accept new connections asking for it). Is there a good reason to only set ECN_PERMIT on inbound connections if the system is doing ECN on outbound connections? From owner-freebsd-net@freebsd.org Sat Sep 5 00:53:52 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 0EEF69CAF19 for ; Sat, 5 Sep 2015 00:53:52 +0000 (UTC) (envelope-from truckman@FreeBSD.org) Received: from gw.catspoiler.org (unknown [IPv6:2602:304:b010:ef20::f2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "gw.catspoiler.org", Issuer "gw.catspoiler.org" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id CC10A1E0B; Sat, 5 Sep 2015 00:53:51 +0000 (UTC) (envelope-from truckman@FreeBSD.org) Received: from FreeBSD.org (mousie.catspoiler.org [192.168.101.2]) by gw.catspoiler.org (8.15.2/8.15.2) with ESMTP id t850rh9P071595; Fri, 4 Sep 2015 17:53:47 -0700 (PDT) (envelope-from truckman@FreeBSD.org) Message-Id: <201509050053.t850rh9P071595@gw.catspoiler.org> Date: Fri, 4 Sep 2015 17:53:43 -0700 (PDT) From: Don Lewis Subject: Re: default ECN settings To: kmacy@freebsd.org cc: freebsd-net@freebsd.org In-Reply-To: MIME-Version: 1.0 Content-Type: TEXT/plain; charset=us-ascii X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 00:53:52 -0000 On 4 Sep, K. Macy wrote: > By default ECN is completely disabled on FreeBSD. On Linux the default > is to disable it outbound (not request it) but enable it inbound > (accept new connections asking for it). Is there a good reason to only > set ECN_PERMIT on inbound connections if the system is doing ECN on > outbound connections? Not that I can think of. The risk in enabling ECN for outbound connections is that some connection attempts can fail, especially if you are attempting to connect to some old and oddball device. That should not be a risk for inbound connections since those devices won't be requesting ECN. Seems like we should be defaulting ECN on for inbound connections, though we currently can't control the two directions separately. From owner-freebsd-net@freebsd.org Sat Sep 5 01:05:38 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id C4BA49CB473 for ; Sat, 5 Sep 2015 01:05:38 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: from mail-ig0-x22f.google.com (mail-ig0-x22f.google.com [IPv6:2607:f8b0:4001:c05::22f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 9208F834; Sat, 5 Sep 2015 01:05:38 +0000 (UTC) (envelope-from kmacybsd@gmail.com) Received: by igbut12 with SMTP id ut12so25823046igb.1; Fri, 04 Sep 2015 18:05:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=MeHXChYAY5pCa1EPbq3IZuXo4941O6GJla42YlKkwAQ=; b=rEGuxCwJy4s3LjT7AxbdKqO6J7vqUMZ6SfX3DAmuHd2EdRvsqYraGzzwAjHjMzpjgT kHphu9W9GLbQK5AZVNjtujjXb+QpiyuPrhUi6zHG6B1G6CX54mVMVfNL/bQnEhQMq6Cw Fo4gVp+DdDL+nqcIYEKDaLauIdQ9E+GQ7tbmz8VtLJWpGZ38qIc0CKkcoWoPur9ZSDXs P/G5p6gpl3CWazj/PGfRamPneu/WqiyuJMKQjP00kj4HfMqvOtzZyRGSY7Qkp+O5GRoz loaLEeJwtVM5hcON4hbnS2RVNNziVDqTZaGt4ta6mciBBNw6TokAfueE+VUuvKz9ZiM5 s6Qw== MIME-Version: 1.0 X-Received: by 10.50.33.68 with SMTP id p4mr8754337igi.60.1441415138006; Fri, 04 Sep 2015 18:05:38 -0700 (PDT) Sender: kmacybsd@gmail.com Received: by 10.36.30.202 with HTTP; Fri, 4 Sep 2015 18:05:37 -0700 (PDT) In-Reply-To: <201509050053.t850rh9P071595@gw.catspoiler.org> References: <201509050053.t850rh9P071595@gw.catspoiler.org> Date: Fri, 4 Sep 2015 18:05:37 -0700 X-Google-Sender-Auth: QrGs-2nOedZQ9brgDLTGs-z0scM Message-ID: Subject: Re: default ECN settings From: "K. Macy" To: Don Lewis Cc: "freebsd-net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 01:05:38 -0000 On Fri, Sep 4, 2015 at 5:53 PM, Don Lewis wrote: > On 4 Sep, K. Macy wrote: >> By default ECN is completely disabled on FreeBSD. On Linux the default >> is to disable it outbound (not request it) but enable it inbound >> (accept new connections asking for it). Is there a good reason to only >> set ECN_PERMIT on inbound connections if the system is doing ECN on >> outbound connections? > > Not that I can think of. The risk in enabling ECN for outbound > connections is that some connection attempts can fail, especially if you > are attempting to connect to some old and oddball device. That should > not be a risk for inbound connections since those devices won't be > requesting ECN. Even with 'oddball' devices the stack is configured to retry ECN n times where n defaults to 1 and then revert to not requesting ECN support. Thus connections would take longer on 'oddball' devices. The solution that *I* would choose for that would be to track ECN support in the host cache. The first connection to a new host would always try ECN and in the event that that failed all subsequent connection attempts would not try ECN. To me this seems like the most robust compromise. However, I don't yet have enough information to say how much benefit this would confer. > Seems like we should be defaulting ECN on for inbound connections, > though we currently can't control the two directions separately. That is a straightforward change. Cheers. From owner-freebsd-net@freebsd.org Sat Sep 5 01:57:53 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 7FF479CABBB for ; Sat, 5 Sep 2015 01:57:53 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 6CA1519C3 for ; Sat, 5 Sep 2015 01:57:53 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t851vrf6073444 for ; Sat, 5 Sep 2015 01:57:53 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202885] IPsec performance problems with fragmented ESP and packet loss Date: Sat, 05 Sep 2015 01:57:53 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: linimon@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 01:57:53 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202885 Mark Linimon changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-bugs@FreeBSD.org |freebsd-net@FreeBSD.org -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sat Sep 5 02:02:25 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 17C269CAFA7 for ; Sat, 5 Sep 2015 02:02:25 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 03FFA1ECB for ; Sat, 5 Sep 2015 02:02:25 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t8522OBl016103 for ; Sat, 5 Sep 2015 02:02:24 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202875] ixv driver in 11.0-CURRENT doesn't pass traffic using KVM hypervisor Date: Sat, 05 Sep 2015 02:02:25 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: linimon@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc keywords assigned_to Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 02:02:25 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202875 Mark Linimon changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |sbruno@FreeBSD.org Keywords| |IntelNetworking Assignee|freebsd-bugs@FreeBSD.org |freebsd-net@FreeBSD.org --- Comment #1 from Mark Linimon --- Reassign and add possibly interested party to Cc: . -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sat Sep 5 14:47:55 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 2CCAF9CA1A1 for ; Sat, 5 Sep 2015 14:47:55 +0000 (UTC) (envelope-from noname.esst@yahoo.com) Received: from nm14.bullet.mail.ne1.yahoo.com (nm14.bullet.mail.ne1.yahoo.com [98.138.90.77]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id F1E501CB3 for ; Sat, 5 Sep 2015 14:47:54 +0000 (UTC) (envelope-from noname.esst@yahoo.com) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1441464278; bh=f9IlInt5sRz1yn7AMCZFKJl3wsnvaKfyz+TKfkW/g9M=; h=Date:From:Reply-To:To:Subject:From:Subject; b=RyC8k2ztRn5SFUQLLMt2tJDBXz93Q4vfhshgD0fMu+/UROiWa/iI5FKtuY3ipQSzqZRYeo1MmQ79of8UjtxAybWPPtrhI3MhYAia+VGhZM2fx0JBhix4EJyjZfQZHCXBRaJDBQZPX2jbL7PJaxdmNf38J2eCfu2brTxLhEiDfay341jZzLmdZQYvqevCdpuWyR/VCqG84S2duBSHnxWd8Lo5JrHmV4foto3eARpq2MmDOhTA5231Wa8cDy+zb5564oUkabab30hnC9yQBt57rWRUUnp9C1uH4uoG1nzOujIIWqxAUqVlR3FPCCgpQ2GRJnF7k5klhHFb2puC0V+Epw== Received: from [98.138.101.129] by nm14.bullet.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 14:44:38 -0000 Received: from [98.138.89.163] by tm17.bullet.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 14:44:38 -0000 Received: from [127.0.0.1] by omp1019.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 14:44:38 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 61978.59642.bm@omp1019.mail.ne1.yahoo.com X-YMail-OSG: RXdlbEsVM1kqLA52r8UyrcHxNQkGm2hCOCfWMPdhI6bw96c1sf3lmRiddP7Dp1D p_FXyKErLncLk3ClAkR7z8tpWu4XqDSvvHK8REzwr5OEXoGp1bOARsMH6L74Dg4eTBVUHmg4_jN. ZA_nZZajvDoRkOCekb77Nn47.hiuy8nGZYROd4J5gk2V038ORAUrM0EiAOB95mnCH_JTksU7nqKE Au2cEyewRtDK4GEsPf4eWrqIkNymX3m4_VUuQWZluZM7_BiNPLcvF_nNdIE5LkUNrI7NDwOxF3Ob L4IcWhj5ChY64EiXmw5Lqzp1o2xEM_KE8kvvWLTG4KGkiLsyRlyl6IhCZUEfYUdyzjjdWcO0S2Cp PD75Vz61vWDFOD66aQO96LRx0R55kMP.3TznYLPCLWO_LftEjutpj_NWZg6ZYxk2Iey9JLnWK3si _nW9kd58NhoHKPHTTLGgGVAzGMNo5YAg1hZOx3gzaPU8usyYMhJhUOwU- Received: by 98.138.105.199; Sat, 05 Sep 2015 14:44:37 +0000 Date: Sat, 5 Sep 2015 14:44:37 +0000 (UTC) From: Nomad Esst Reply-To: Nomad Esst To: FreeBSD Net Message-ID: <912205684.2111325.1441464277341.JavaMail.yahoo@mail.yahoo.com> Subject: em, igb performance test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 14:47:55 -0000 Hi allDuring some performance tests, we found out some weird problems. We u= se a shell script that do the following : do from 1 to 10Shutdown em/igb interfacesleep 3Bring em/igb interface uptcp= replay -i em0 -l ospf_hello.pcap=C2=A0sleep3end By running this shell on one side we expect 10 ospf hello packets to get ar= rived at the other side, but tcpdump (on the other side) shows 4, sometimes= 8 and etc ... (not all 10 packets are arrived at the other side). We test this scenario with a Cisco router, and all packets are received at = the Cisco side. What causes this packet loss in FreeBSD (maybe in em or igb= drivers)? I know that this scenario may not have any use in the real world, but I'm c= urious, why Cisco don't have such behavior. Thanks in advance. Regards. From owner-freebsd-net@freebsd.org Sat Sep 5 16:48:02 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 162019CB71F for ; Sat, 5 Sep 2015 16:48:02 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0196C18CB for ; Sat, 5 Sep 2015 16:48:02 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t85Gm1ds020016 for ; Sat, 5 Sep 2015 16:48:01 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202875] ixv driver in 11.0-CURRENT doesn't pass traffic using KVM hypervisor Date: Sat, 05 Sep 2015 16:48:02 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: pkelsey@freebsd.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 16:48:02 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202875 --- Comment #2 from Patrick Kelsey --- (In reply to Jeff Pieper from comment #0) What are the results when you only attach an 11.0-CURRENT guest in step 3 of your reproduction steps? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sat Sep 5 17:45:36 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 9CA499CB381 for ; Sat, 5 Sep 2015 17:45:36 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 6ECD11B33 for ; Sat, 5 Sep 2015 17:45:36 +0000 (UTC) (envelope-from bugzilla-noreply@freebsd.org) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.15.2/8.15.2) with ESMTP id t85HjaC0044457 for ; Sat, 5 Sep 2015 17:45:36 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 202875] ixv driver in 11.0-CURRENT doesn't pass traffic using KVM hypervisor Date: Sat, 05 Sep 2015 17:45:36 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: IntelNetworking X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: pkelsey@freebsd.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 17:45:36 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=202875 --- Comment #3 from Patrick Kelsey --- (In reply to Jeff Pieper from comment #0) Some additional thoughts: 1. In the reported configuration, the Linux ixgbe driver in the host is running the PF, and the FreeBSD ixgbe driver(s)s in the guest(s) are running the respective VFs. The VF drivers communicate with the PF driver via the mailbox, so disagreements among the PF and VF driver implementations as to how the mailbox messaging works could in general be an issue. 2. Why do you feel r285590 is the likely culprit? Have you built a kernel prior to that revision and shown it to be working? r285590 does change the interpretation of a mailbox message and the generation of the response to that message in the FreeBSD PF driver, but the VF driver only uses the result for a printf() - that is, disagreement over that message between PF and VF won't bother the VF. You mention other changes being made "around that time", but since you are comparing the behavior of 10.2-RELEASE to 11.0-CURRENT, the set of changes to look at is all the differences between the code in 10.2-RELEASE and 11.0-CURRENT, and the code in 10.2-RELEASE is not the code that was in 11.0-CURRENT around the time 10.2-RELEASE was made, it's older. Looking at the diffs between the two, there are substantial ixv-related changes between 10.2-RELEASE and 11.0-CURRENT that pre-date r285590. 3. Have you checked whether any packets make it to the wire from the 11.0-CURRENT guest? That is, is this only an rx problem, or is it a tx and rx problem? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@freebsd.org Sat Sep 5 20:35:04 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id D1DBA9CBB85 for ; Sat, 5 Sep 2015 20:35:04 +0000 (UTC) (envelope-from bored_to_death85@yahoo.com) Received: from nm49-vm9.bullet.mail.ne1.yahoo.com (nm49-vm9.bullet.mail.ne1.yahoo.com [98.138.121.137]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 936ACBD5 for ; Sat, 5 Sep 2015 20:35:04 +0000 (UTC) (envelope-from bored_to_death85@yahoo.com) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1441485298; bh=qKm8pL9FjWhTQh1mVgPdsLT0S7J0DGKKnTBDeRA7k3k=; h=Date:From:Subject:To:From:Subject; b=jrV8uz+xEuX+yR1QTFa01AYpGCmf6y4IQxNd1+XBcNW1Lq+WH8xThCL32H2+ucj1sC52ZeXmmpQm0+GvgZwds1Yb6w4opSvHeaGz6Vl8EuQRRSGk/hdh7q88D0wiigI1GkpJ1tROlb2raX74u16nkHsRi5PJS90lg2vxI0WCpkIkXoWa3Hrx7httnAJMJwTRe+oOZrIEpLMTGs/T5DRazbLCRfDXc6UHd0Vpx5t8z54Og9DsrQDtL9AWAl5qLKR+UKI/Hql6JkSOi+8sC1Tnk4tHJQEkAXIMmWn0OvczlqivxeUUl0df7hAC5yQpAutLnsn1ljBzCzpwk++f7use3A== Received: from [127.0.0.1] by nm49.bullet.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 20:34:58 -0000 Received: from [98.138.100.102] by nm49.bullet.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 20:32:12 -0000 Received: from [66.196.81.172] by tm101.bullet.mail.ne1.yahoo.com with NNFMP; 05 Sep 2015 20:32:12 -0000 Received: from [98.139.212.210] by tm18.bullet.mail.bf1.yahoo.com with NNFMP; 05 Sep 2015 20:32:12 -0000 Received: from [127.0.0.1] by omp1019.mail.bf1.yahoo.com with NNFMP; 05 Sep 2015 20:32:12 -0000 X-Yahoo-Newman-Property: ymail-4 X-Yahoo-Newman-Id: 379359.59597.bm@omp1019.mail.bf1.yahoo.com Received: (qmail 59056 invoked by uid 60001); 5 Sep 2015 20:32:12 -0000 X-YMail-OSG: N8BS8oUVM1kZGw_HgVGoA83bsu9aD2DQs8tkHJ8PpHe_Lcp Tc8mbsrZa3fZmuRlur0VwN2nMASly4k5Ksb6X2FyUwmsIjq32qVDcKPdz.pB irUeWhktzWsX9uaAtjqbqM2qe2S1nOGS3rxya4gb2JB2eGmUanWGPsp4nXFF 2wslN1ztC.7fUkKVKsciIL7PVbMCSb4Lib8sO.NmOciS4SOZCRinUCQ0UuAb 1VuPfCaMPh9hH9nLT7dw3.QAeE69VJn40c4Nem0_ryQ3lvK4GCQZ7JYhQWRU vLYkDs3PgBRVyVDJ7CN4T2v4mTjITipZIaGFIz93XAhVcSf.30Y4tnjClV0L Ew6ytJ.njqkfdfVG6obX4It4kZy9fbMqniVj9W7HpHSs_4NC5JbUVTFy0Far dsWqokRl_1FJTmPdFXU1uyaqb4.Vt4dB.sS3q0dhHGc7x4PatJhDolfsKAZ_ sctXJTVyGreCRDlfIh6nU7IdWwtRjhWilbQFESQ.DAacttmycOgbTTUcy4Xg SMW97vTqY2rizgWAm66u4pMZdaWQ.GazyH4f64hv7JVgsCzRVdrbCYggQlyo HX8Ue0p.Zx.GfRYqSyPc0jbSwYZToxknR Received: from [151.238.53.33] by web165005.mail.bf1.yahoo.com via HTTP; Sat, 05 Sep 2015 13:32:12 PDT X-Rocket-MIMEInfo: 002.001, SGksDQoNCk91ciBwcm9kdWN0IGlzIGJlaW5nIHRlc3RlZCB3aXRoIFNwaXJlbnQgVGVzdENlbnRlciwgYW5kIHdlJ3JlIGZhY2luZyBhbiB1bnVzdWFsIHByb2JsZW0gd2l0aCB0aGUgdGVzdHMuDQpXZSB1c2UgTklDcyB3aXRoIGludGVsIDgyNTc0IGFuZCA4MjU3NiBvbiBGcmVlQlNEIDkuMiB3aXRoIGxhdGVzdCBlbSBhbmQgaWdiIGRyaXZlcnMgKHdlIGFsc28gdGVzdGVkIHRoaXMgb24gRnJlZUJTRC0xMC4xKSBJdCBzZWVtcyB3aGF0IFNwaXJlbnQgVGVzdENlbnRlciBkb2VzIHRvIHN0YXJ0IGFueSBpbmQBMAEBAQE- X-Mailer: YahooMailBasic/651 YahooMailWebService/0.8.203.813 Message-ID: <1441485132.75285.YahooMailBasic@web165005.mail.bf1.yahoo.com> Date: Sat, 5 Sep 2015 13:32:12 -0700 From: "M. V." Subject: Problem with receiving packets right after remote-interface is up To: freebsd-net@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 20:35:05 -0000 Hi, Our product is being tested with Spirent TestCenter, and we're facing an unusual problem with the tests. We use NICs with intel 82574 and 82576 on FreeBSD 9.2 with latest em and igb drivers (we also tested this on FreeBSD-10.1) It seems what Spirent TestCenter does to start any individual test is, it disables its own interface, and at the beginning of the new test, it suddenly "up"s its interface and sends test packet right after that without any delay. This is where we have problem, and we don't receive this first packets most of the time (result is vary, in 100 tests, we lose about 60~70% of this "first" packets on each test, so we FAIL most of tests because apparently we need about 0.5~1 seconds after setup and renegotiation before we can receive packets) we checked both em and igb drivers and both have this problem. this is how we reproduce the problem: - connect sender-system's first port to receiver-system's first port. - In sender-system: -- ifconfig em0 down -- sleep 5 -- ifconfig em0 up && tcpreplay -l 1 -i em0 one_packet.pcap We checked, and even though sender sends packet successfully (tx led blinks), in receiver even driver doesn't receive it (rx led doesn't blink, and "rxeof" function in "if_em" tells us no new packet is received) we removed optional interface options like msix, tso, rxcsum, ... but no luck. So, does anyone know any solution for this problem? or any suggestions on where we should look or what we should do that might solve it and prevent our tests from being failed? Thank you guys. From owner-freebsd-net@freebsd.org Sat Sep 5 21:44:37 2015 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id A05FD9C9B92 for ; Sat, 5 Sep 2015 21:44:37 +0000 (UTC) (envelope-from rizzo.unipi@gmail.com) Received: from mail-lb0-x233.google.com (mail-lb0-x233.google.com [IPv6:2a00:1450:4010:c04::233]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 2005EBF4 for ; Sat, 5 Sep 2015 21:44:37 +0000 (UTC) (envelope-from rizzo.unipi@gmail.com) Received: by lbcjc2 with SMTP id jc2so25597013lbc.0 for ; Sat, 05 Sep 2015 14:44:33 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=mwrVXGJLP+F3pZNvyNzQ9pZmD/4ZroiR3E6EVjGY3K4=; b=cCwOyKjNuXiN/ivEaaXqbXqis7RcKv+jTili6bVsoSC1x61Z2eB0PBokTlCRbiIpXQ cCsvYaO9PjrFvPXJR6X6PxQobbmT4QGYCn5NcuSdCSzTs9qZjBoNyf/hTRh1YwnvnM1k iJlNw9u9m4LeVpDJS2TzUqzlg5U2NHk6/braW7f78r6lndl49i/N0FOAGxdYDKRhLUyH tDdcCJvc4r2EA4VmLioz0SagmCbgqfSwnFLxoPEaz+XL1XuZO5v/4jreYaQdQANZiXKP U4bTT0tlforyl0s7Eq8pPAS3BOhIn61MynDeE0/lvU8zAGeSjQAnOaxCyuvA0fyXUJo3 Y5Eg== MIME-Version: 1.0 X-Received: by 10.152.27.134 with SMTP id t6mr10245246lag.100.1441489473626; Sat, 05 Sep 2015 14:44:33 -0700 (PDT) Sender: rizzo.unipi@gmail.com Received: by 10.114.96.168 with HTTP; Sat, 5 Sep 2015 14:44:33 -0700 (PDT) In-Reply-To: <1441485132.75285.YahooMailBasic@web165005.mail.bf1.yahoo.com> References: <1441485132.75285.YahooMailBasic@web165005.mail.bf1.yahoo.com> Date: Sat, 5 Sep 2015 23:44:33 +0200 X-Google-Sender-Auth: tWFa-gPgy9OMdvVlj5l_fnS_xhI Message-ID: Subject: Re: Problem with receiving packets right after remote-interface is up From: Luigi Rizzo To: "M. V." Cc: "freebsd-net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 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, 05 Sep 2015 21:44:37 -0000 You may be able to avoid the issue if you avoid autonegotiation and manually set the media type, speed and duplex. Cheers Luigi On Saturday, September 5, 2015, M. V. via freebsd-net < freebsd-net@freebsd.org> wrote: > Hi, > > Our product is being tested with Spirent TestCenter, and we're facing an > unusual problem with the tests. > We use NICs with intel 82574 and 82576 on FreeBSD 9.2 with latest em and > igb drivers (we also tested this on FreeBSD-10.1) It seems what Spirent > TestCenter does to start any individual test is, it disables its own > interface, and at the beginning of the new test, it suddenly "up"s its > interface and sends test packet right after that without any delay. This is > where we have problem, and we don't receive this first packets most of the > time (result is vary, in 100 tests, we lose about 60~70% of this "first" > packets on each test, so we FAIL most of tests because apparently we need > about 0.5~1 seconds after setup and renegotiation before we can receive > packets) > we checked both em and igb drivers and both have this problem. > this is how we reproduce the problem: > - connect sender-system's first port to receiver-system's first port. > - In sender-system: > -- ifconfig em0 down > -- sleep 5 > -- ifconfig em0 up && tcpreplay -l 1 -i em0 one_packet.pcap > > We checked, and even though sender sends packet successfully (tx led > blinks), in receiver even driver doesn't receive it (rx led doesn't blink, > and "rxeof" function in "if_em" tells us no new packet is received) > we removed optional interface options like msix, tso, rxcsum, ... but no > luck. > > So, does anyone know any solution for this problem? or any suggestions on > where we should look or what we should do that might solve it and prevent > our tests from being failed? > > Thank you guys. > _______________________________________________ > freebsd-net@freebsd.org mailing list > https://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org > " > -- -----------------------------------------+------------------------------- Prof. Luigi RIZZO, rizzo@iet.unipi.it . Dip. di Ing. dell'Informazione http://www.iet.unipi.it/~luigi/ . Universita` di Pisa TEL +39-050-2217533 . via Diotisalvi 2 Mobile +39-338-6809875 . 56122 PISA (Italy) -----------------------------------------+-------------------------------