From owner-freebsd-net@FreeBSD.ORG Wed Oct 31 09:48:19 2012 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 668B1108; Wed, 31 Oct 2012 09:48:19 +0000 (UTC) (envelope-from remi.pauchet@netasq.com) Received: from work.netasq.com (gwlille.netasq.com [91.212.116.1]) by mx1.freebsd.org (Postfix) with ESMTP id EC7BE8FC14; Wed, 31 Oct 2012 09:48:18 +0000 (UTC) Received: from [10.2.9.2] (unknown [91.212.116.2]) by work.netasq.com (Postfix) with ESMTPSA id AAE0327057D1; Wed, 31 Oct 2012 10:48:17 +0100 (CET) Subject: Re: panic ixgbevf / SMP under high network load Mime-Version: 1.0 (Apple Message framework v1283) Content-Type: multipart/signed; boundary="Apple-Mail=_E52DEB8F-A706-41F2-A7F2-A8D0A5885E2B"; protocol="application/pkcs7-signature"; micalg=sha1 From: =?iso-8859-1?Q?R=E9mi_Pauchet?= In-Reply-To: <20121026103006.GB70741@glebius.int.ru> Date: Wed, 31 Oct 2012 10:47:59 +0100 Message-Id: <7E43156D-C927-4C18-AD3A-200582C81C65@netasq.com> References: <20121025164031.GA70741@FreeBSD.org> <20121026103006.GB70741@glebius.int.ru> To: Gleb Smirnoff X-Mailer: Apple Mail (2.1283) X-Content-Filtered-By: Mailman/MimeDel 2.1.14 Cc: freebsd-net@FreeBSD.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.14 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, 31 Oct 2012 09:48:19 -0000 --Apple-Mail=_E52DEB8F-A706-41F2-A7F2-A8D0A5885E2B Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=iso-8859-1 Hi, from a svn checkout r242392: #0 doadump (textdump=3D1) at /usr/svn/head/sys/kern/kern_shutdown.c:266 #1 0xffffffff808d3b72 in kern_reboot (howto=3D260) at = /usr/svn/head/sys/kern/kern_shutdown.c:449 #2 0xffffffff808d359a in panic (fmt=3D0x0) at = /usr/svn/head/sys/kern/kern_shutdown.c:637 #3 0xffffffff8033f737 in db_panic (addr=3DVariable "addr" is not = available. ) at /usr/svn/head/sys/ddb/db_command.c:482 #4 0xffffffff8033fbe1 in db_command (last_cmdp=3D0xffffffff812eb1e0, = cmd_table=3DVariable "cmd_table" is not available. ) at /usr/svn/head/sys/ddb/db_command.c:449 #5 0xffffffff8033fe30 in db_command_loop () at = /usr/svn/head/sys/ddb/db_command.c:502 #6 0xffffffff80341f89 in db_trap (type=3DVariable "type" is not = available. ) at /usr/svn/head/sys/ddb/db_main.c:231 #7 0xffffffff8090c388 in kdb_trap (type=3D12, code=3D0, = tf=3D0xffffff80003739c0) at /usr/svn/head/sys/kern/subr_kdb.c:654 #8 0xffffffff80c61dcd in trap_fatal (frame=3D0xffffff80003739c0, = eva=3DVariable "eva" is not available. ) at /usr/svn/head/sys/amd64/amd64/trap.c:867 #9 0xffffffff80c61f8a in trap_pfault (frame=3D0xffffff80003739c0, = usermode=3D0) at /usr/svn/head/sys/amd64/amd64/trap.c:789 #10 0xffffffff80c626ca in trap (frame=3D0xffffff80003739c0) at = /usr/svn/head/sys/amd64/amd64/trap.c:463 #11 0xffffffff80c4bdb3 in calltrap () at = /usr/svn/head/sys/amd64/amd64/exception.S:228 #12 0xffffffff805a5fbf in ixv_rxeof (que=3D0xfffffe000220cd00, = count=3D118) at /usr/svn/head/sys/dev/ixgbe/ixv.c:3438 #13 0xffffffff805aac91 in ixv_handle_que (context=3DVariable "context" = is not available. ) at /usr/svn/head/sys/dev/ixgbe/ixv.c:980 #14 0xffffffff80919df3 in taskqueue_run_locked = (queue=3D0xfffffe000221a900) at = /usr/svn/head/sys/kern/subr_taskqueue.c:308 #15 0xffffffff8091a89e in taskqueue_thread_loop (arg=3DVariable "arg" is = not available. ) at /usr/svn/head/sys/kern/subr_taskqueue.c:497 #16 0xffffffff808a3e45 in fork_exit (callout=3D0xffffffff8091a860 = , arg=3D0xfffffe000220cd58,=20 frame=3D0xffffff8000373c00) at = /usr/svn/head/sys/kern/kern_fork.c:995 #17 0xffffffff80c4c2de in fork_trampoline () at = /usr/svn/head/sys/amd64/amd64/exception.S:602 Regards, R=E9mi Le 26 oct. 2012 =E0 12:30, Gleb Smirnoff a =E9crit : > On Fri, Oct 26, 2012 at 11:09:20AM +0200, R?mi Pauchet wrote: > R> Hi > R>=20 > R> I have the same crash with FreeBSD 10-current > R>=20 > R> FreeBSD freebsd10 10.0-CURRENT FreeBSD 10.0-CURRENT #4 r241761: Sat = Oct 20 07:40:33 UTC 2012 = root@kaos.glenbarber.us:/usr/obj/usr/src/sys/GENERIC amd64 > R>=20 > R> Sorry for the screenshots: panic doesn't dump the memory to the = swap, I can't figure out why > R>=20 > R> I use udp frames (size 700) so this load is not supposed to produce = ip fragmentation. > R>=20 > R> And again, the panic happens with 4 vcpus, no issue with 1 vcpu. >=20 > r241761 predates conversion of the IPv4 stack to net byte order, which = happened > in r241913. >=20 > Can you please try out your test on head r242077 or later? >=20 > --=20 > Totus tuus, Glebius. --Apple-Mail=_E52DEB8F-A706-41F2-A7F2-A8D0A5885E2B--