Date: Thu, 26 Oct 2006 11:38:16 +0300 From: Kostik Belousov <kostikbel@gmail.com> To: Micah <micahjon@ywave.com> Cc: FreeBSD Hackers <freebsd-hackers@freebsd.org> Subject: Re: System panic under load (additional information) Message-ID: <20061026083816.GS45605@deviant.kiev.zoral.com.ua> In-Reply-To: <453F98C4.2060402@ywave.com> References: <453F882B.2040009@ywave.com> <453F98C4.2060402@ywave.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--Po3hG7FLjYU3tiSY
Content-Type: text/plain; charset=koi8-r
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Wed, Oct 25, 2006 at 10:03:00AM -0700, Micah wrote:
> Okay, I was reading the developer's handbook and trying stuff. The=20
> following may be helpful:
>=20
> (kgdb) up 7
> #7 0xc0593d34 in vfs_hash_get (mp=3D0xc5a53000, hash=3D5347783, flags=3D=
2,
> td=3D0xc5ef9d80, vpp=3D0xf02ca99c, fn=3D0, arg=3D0x0)
> at /usr/src/sys/kern/vfs_hash.c:73
> 73 if (vp->v_hash !=3D hash)
> (kgdb) list *0xc0593d34
> 0xc0593d34 is in vfs_hash_get (/usr/src/sys/kern/vfs_hash.c:73).
> 64 int
> 65 vfs_hash_get(struct mount *mp, u_int hash, int flags, struct=20
> thread *td, struct vnode **vpp, vfs_hash_cmp_t *fn, void *arg)
> 66 {
> 67 struct vnode *vp;
> 68 int error;
> 69
> 70 while (1) {
> 71 mtx_lock(&vfs_hash_mtx);
> 72 LIST_FOREACH(vp, vfs_hash_index(mp, hash),=20
> v_hashlist) {
> 73 if (vp->v_hash !=3D hash)
> 74 continue;
> 75 if (vp->v_mount !=3D mp)
> 76 continue;
> 77 if (fn !=3D NULL && fn(vp, arg))
> (kgdb) print vp
> $1 =3D (struct vnode *) 0xffffffff
>=20
> I'm no expert but that doesn't look like a valid address.... I was able=
=20
> to get another crashdump, but kgdb locked up while trying to read it.
I saw several similar reports.
Please, submit me the output of the "print *mp" in the same frame.
Also, I'm interested in kernel config.=20
Is the problem reproducible ?
>=20
> Micah wrote:
> >Can anyone help me in deciphering what this crashdump is telling me? My=
=20
> >i386 6.1p3 system is panicking under heavy IO load and I'm trying to=20
> >isolate the cause. I've never debugged a crashdump before, so if there's=
=20
> >more information I can milk from the core file, let me know.
> >
> >Thanks,
> >Micah
> >
> >trisha# kgdb kernel.debug /home/crash/vmcore.0
> >[GDB will not be able to debug user-mode threads:=20
> >/usr/lib/libthread_db.so: Undefined symbol "ps_pglobal_lookup"]
> >GNU gdb 6.1.1 [FreeBSD]
> >Copyright 2004 Free Software Foundation, Inc.
> >GDB is free software, covered by the GNU General Public License, and you=
=20
> >are
> >welcome to change it and/or distribute copies of it under certain=20
> >conditions.
> >Type "show copying" to see the conditions.
> >There is absolutely no warranty for GDB. Type "show warranty" for detai=
ls.
> >This GDB was configured as "i386-marcel-freebsd".
> >
> >Unread portion of the kernel message buffer:
> >
> >
> >Fatal trap 12: page fault while in kernel mode
> >fault virtual address =3D 0x27
> >fault code =3D supervisor read, page not present
> >instruction pointer =3D 0x20:0xc0593d34
> >stack pointer =3D 0x28:0xf02ca89c
> >frame pointer =3D 0x28:0xf02ca8bc
> >code segment =3D base 0x0, limit 0xfffff, type 0x1b
> > =3D DPL 0, pres 1, def32 1, gran 1
> >processor eflags =3D interrupt enabled, resume, IOPL =3D 0
> >current process =3D 24805 (perl5.8.8)
> >trap number =3D 12
> >panic: page fault
> >Uptime: 13h16m1s
> >Dumping 1534 MB (2 chunks)
> > chunk 0: 1MB (159 pages) ... ok
> > chunk 1: 1534MB (392672 pages) 1518 1502 1486 1470 1454 1438 1422 1406=
=20
> >1390 1374 1358 1342 1326 1310 1294 1278 1262 1246 1230 1214 1198 1182=20
> >1166 1150 1134 1118 1102 1086 1070 1054 1038 1022 1006 990 974 958 942=
=20
> >926 910 894 878 862 846 830 814 798 782 766 750 734 718 702 686 670 654=
=20
> >638 622 606 590 574 558 542 526 510 494 478 462 446 430 414 398 382 366=
=20
> >350 334 318 302 286 270 254 238 222 206 190 174 158 142 126 110 94 78 62=
=20
> >46 30 14
> >
> >#0 doadump () at pcpu.h:165
> >165 __asm __volatile("movl %%fs:0,%0" : "=3Dr" (td));
> >(kgdb) bt
> >#0 doadump () at pcpu.h:165
> >#1 0xc0535a3f in boot (howto=3D260) at /usr/src/sys/kern/kern_shutdown.=
c:402
> >#2 0xc0535d66 in panic (fmt=3D0xc0711e06 "%s")
> > at /usr/src/sys/kern/kern_shutdown.c:558
> >#3 0xc06ecf2c in trap_fatal (frame=3D0xf02ca85c, eva=3D0)
> > at /usr/src/sys/i386/i386/trap.c:836
> >#4 0xc06ecc32 in trap_pfault (frame=3D0xf02ca85c, usermode=3D0, eva=3D3=
9)
> > at /usr/src/sys/i386/i386/trap.c:744
> >#5 0xc06ec7fd in trap (frame=3D
> > {tf_fs =3D 8, tf_es =3D 40, tf_ds =3D 40, tf_edi =3D 4, tf_esi =3D=
4, tf_ebp=20
> >=3D -265508676, tf_isp =3D -265508728, tf_ebx =3D -1, tf_edx =3D -980369=
408,=20
> >tf_ecx =3D -979030016, tf_eax =3D 5347783, tf_trapno =3D 12, tf_err =3D =
0,=20
> >tf_eip =3D -1067893452, tf_cs =3D 32, tf_eflags =3D 66182, tf_esp =3D=20
> >-979030016, tf_ss =3D 5347783})
> > at /usr/src/sys/i386/i386/trap.c:434
> >#6 0xc06d9e2a in calltrap () at /usr/src/sys/i386/i386/exception.s:139
> >#7 0xc0593d34 in vfs_hash_get (mp=3D0xc5a53000, hash=3D5347783, flags=
=3D2,
> > td=3D0xc5ef9d80, vpp=3D0xf02ca99c, fn=3D0, arg=3D0x0)
> > at /usr/src/sys/kern/vfs_hash.c:73
> >#8 0xc067af59 in ffs_vget (mp=3D0xc5a53000, ino=3D5347783, flags=3D2,
> > vpp=3D0xf02ca99c) at pcpu.h:162
> >#9 0xc0683353 in ufs_lookup (ap=3D0xf02caa40)
> > at /usr/src/sys/ufs/ufs/ufs_lookup.c:572
> >#10 0xc0700f03 in VOP_CACHEDLOOKUP_APV (vop=3D0x5199c7, a=3D0xc590c000)
> > at vnode_if.c:150
> >#11 0xc059006a in vfs_cache_lookup (ap=3D0x5199c7) at vnode_if.h:82
> >#12 0xc0700e78 in VOP_LOOKUP_APV (vop=3D0xc0764f20, a=3D0xf02caaec)
> > at vnode_if.c:99
> >#13 0xc059547b in lookup (ndp=3D0xf02cabf4) at vnode_if.h:56
> >#14 0xc0594c08 in namei (ndp=3D0xf02cabf4) at=20
> >/usr/src/sys/kern/vfs_lookup.c:203
> >#15 0xc05a672d in kern_stat (td=3D0xc5ef9d80,
> > path=3D0xc590c000 "=9C\033\210? B\215?0???\020?Z?\020?\211?0\003\237=
?PU0?",
> > pathseg=3D3314597888, sbp=3D0x5199c7) at=20
> >/usr/src/sys/kern/vfs_syscalls.c:2076
> >#16 0xc05a66bf in stat (td=3D0x5199c7, uap=3D0xf02cad04)
> > at /usr/src/sys/kern/vfs_syscalls.c:2061
> >#17 0xc06ed302 in syscall (frame=3D
> > {tf_fs =3D 59, tf_es =3D 59, tf_ds =3D 59, tf_edi =3D 1209537912, =
tf_esi =3D=20
> >140130588, tf_ebp =3D -1077941096, tf_isp =3D -265507484, tf_ebx =3D=20
> >1209530852, tf_edx =3D 68, tf_ecx =3D 0, tf_eax =3D 188, tf_trapno =3D 1=
2,=20
> >tf_err =3D 2, tf_eip =3D 1210540343, tf_cs =3D 51, tf_eflags =3D 582, tf=
_esp =3D=20
> >-1077941140, tf_ss =3D 59})
> > at /usr/src/sys/i386/i386/trap.c:981
> >#18 0xc06d9e7f in Xint0x80_syscall () at=20
> >/usr/src/sys/i386/i386/exception.s:200
> >---Type <return> to continue, or q <return> to quit---
> >#19 0x00000033 in ?? ()
> >Previous frame inner to this frame (corrupt stack?)
> >_______________________________________________
> >freebsd-hackers@freebsd.org mailing list
> >http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
> >To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.or=
g"
>=20
> _______________________________________________
> freebsd-hackers@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
> To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org"
--Po3hG7FLjYU3tiSY
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.5 (FreeBSD)
iD8DBQFFQHP3C3+MBN1Mb4gRAo/cAJ4hKUa0spNekUDK2bfrg2eAA9mzOwCfYeWW
01UsJX7jBRFj/nFIm4+Y+KM=
=J6LK
-----END PGP SIGNATURE-----
--Po3hG7FLjYU3tiSY--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20061026083816.GS45605>