Date: Sun, 29 Sep 2013 01:45:01 +0300 From: Konstantin Belousov <kostikbel@gmail.com> To: jfv@freebsd.org Cc: net@freebsd.org Subject: Re: igb(4) panic: already enqueue Message-ID: <20130928224501.GX41229@kib.kiev.ua> In-Reply-To: <20130928213038.GT41229@kib.kiev.ua> References: <20130928213038.GT41229@kib.kiev.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
--XRLv71ZoqfThaM/0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sun, Sep 29, 2013 at 12:30:38AM +0300, Konstantin Belousov wrote: > On a relatively old test machine, dual-socket X7DWU supermicro, Xeon > X5272, with on-board 82575EB igb controllers, running the stress2 > udp blast test immediately causes the following >=20 > panic: buf=3D0xfffff8001aa5c800 already enqueue at 1445 prod=3D1315 cons= =3D1445 > cpuid =3D 3 > KDB: stack backtrace: > db_trace_self_wrapper() at 0xffffffff802839ab =3D db_trace_self_wrapper+0= x2b/frame 0xfffffe0123570600 > vpanic() at 0xffffffff8033bd96 =3D vpanic+0x126/frame 0xfffffe0123570640 > panic() at 0xffffffff8033be23 =3D panic+0x43/frame 0xfffffe01235706a0 > igb_mq_start() at 0xffffffff80bcb228 =3D igb_mq_start+0xb8/frame 0xfffffe= 0123570710 =20 > ether_output() at 0xffffffff804072a8 =3D ether_output+0x5c8/frame 0xfffff= e0123570780 =20 > ip_output() at 0xffffffff80430be1 =3D ip_output+0xe91/frame 0xfffffe01235= 70860 > udp_send() at 0xffffffff804a5fc4 =3D udp_send+0x834/frame 0xfffffe0123570= 910 > sosend_dgram() at 0xffffffff803b517b =3D sosend_dgram+0x36b/frame 0xfffff= e0123570990 =20 > soo_write() at 0xffffffff8039dbb9 =3D soo_write+0x49/frame 0xfffffe012357= 09d0 > dofilewrite() at 0xffffffff803956c5 =3D dofilewrite+0x85/frame 0xfffffe01= 23570a20 > kern_writev() at 0xffffffff803953d5 =3D kern_writev+0x65/frame 0xfffffe01= 23570a70 > sys_write() at 0xffffffff80395363 =3D sys_write+0x63/frame 0xfffffe012357= 0ac0 > amd64_syscall() at 0xffffffff8053ae7d =3D amd64_syscall+0x28d/frame 0xfff= ffe0123570bf0 >=20 > Test is available at > svn:base/user/pho/stress2/testcases/udp, invocation line is > BLASTHOST=3D192.168.5.1 ./udp -t 10m -i 50 -h -v > Substitute the BLASTHOST with the ip address of a scratch box. >=20 > This is on the yesterday HEAD. Could you, please, fix this ? I also tested on i350 adapters, there the issue is harder to reproduce, but it still panics under the test. Also, I saw the following: Expensive timeout(9) function: 0xffffffff809c7d60(0xfffffe0001864000) 1.929= 7931s Expensive timeout(9) function: 0xffffffff809c7d60(0xfffffe0001864000) 9.966= 9852s db> x/i 0xffffffff809c7d60 0xffffffff809c7d60 =3D igb_local_timer: pushq %rbp --XRLv71ZoqfThaM/0 Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.21 (FreeBSD) iQIbBAEBAgAGBQJSR1vsAAoJEJDCuSvBvK1BTCUP+P79Xa3gbBhomSQUboyqW/hZ 1isDKCguScJo6hOW/R1iltnkbn3RMCJNBQS9MBM9dWdiVGI0orBolsk/XKKKCT8l W2pPWjlInN0jUPqoBDj+flF1eM9d0EDnuJVMKIlESMD5cuY+bpMm+OLZo6u8qqwR 6O1Db2kUt4kgqhbjyrjTj65Isdrll0Pa5vSMGMQe1/Y9UI3aBJQVxmJdsgBE8IbZ h3x4Vus6fgzBHjikrYQGer8pUCnc32BfpsJfNiiyKB5ki3ix6mXn6BfAj197r1H+ N++nJ4g6UvHl9YfNoSxRae981FDuqwYod1PfYm1RkMQh9UaB6l+hkihhDI+ncqdS 8NjC4tDaF+NGtuKFc/sX6PTxbrJ4Y5uxUU6Rc3xdcW9wb+7ZHwnDfh/kBumtzh2w sFEVsclx5XgCZfU6PjHLhHs3KawB37jRiiS/5k/98P9ohkOQvRQyuAZMqsghkvyL upRrFl+MtA7koyoZBMvGPqvdA3/ROXW2njUiQitlLPuj/s6KJVUKF9uqGL+hbVjW F2Y9mMM1N7BfsiuEkW0pDXENWquBiu4LcKGo+c3WnsJH5JDkxPblSkYiwvg2LAdj ozf2GmP+6Ug5DEsDfZpMm6PDp5TqPI8rfLmMU6h+FjfCe8TqGQt76x3gCBoAtixt z7gMtMRV1XhQEqkXu44= =c29f -----END PGP SIGNATURE----- --XRLv71ZoqfThaM/0--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20130928224501.GX41229>