[stgt] help tgt segfault

FUJITA Tomonori fujita.tomonori at lab.ntt.co.jp
Fri Feb 6 17:03:20 CET 2009


On Fri, 06 Feb 2009 11:16:56 +0100
Tomasz Chmielewski <mangoo at wpkg.org> wrote:

> FUJITA Tomonori schrieb:
> > On Tue, 03 Feb 2009 12:51:45 +0100
> > Tomasz Chmielewski <mangoo at wpkg.org> wrote:
> > 
> >> FUJITA Tomonori schrieb:
> >>
> >> (...)
> >>
> >>> Can you try this patch with 0.9.3 and send the log of 0.9.3? Please
> >>> test it with one target and one initiator with a slow link.
> >>>
> >>> I'll try to reproduce the problem with the same configuration.
> >> Feb  3 12:45:44 superthecus tgtd: Target daemon logger with pid=3022 started!
> >> Feb  3 12:45:45 superthecus tgtd: main(391) the main daemon (0.9.3) started
> >> Feb  3 12:48:50 superthecus tgtd: conn_close(99) connection closed, 0x9b420b4 26
> >> Feb  3 12:48:50 superthecus tgtd: conn_close(105) sesson 0x9b422d0 1
> >> Feb  3 12:48:50 superthecus tgtd: conn_close(146) Forcing release of rx task 0x9b49260 48
> >> Feb  3 12:49:35 superthecus kernel: tgtd[3021]: segfault at 28 ip 0805832f sp 77d454c0 error 4 in tgtd[8048000+24000]
> >> Feb  3 12:49:35 superthecus tgtd: conn_close(99) connection closed, 0x9b49264 28
> >> Feb  3 12:49:35 superthecus tgtd: conn_close(105) sesson 0x9ba56b0 1
> >> Feb  3 12:49:35 superthecus tgtd: conn_close(128) Forcing release of tx task 0x9c19478 10000003 1
> >> Feb  3 12:49:35 superthecus tgtd: conn_close(128) Forcing release of tx task 0x9c196b0 10000004 1
> > 
> > Can you try this patch?
> 
> I didn't have a segfault,

That's good news.

> but device had I/O errors pretty fast instead.

Hmm, this patch just fixes tgt to clean up the resource when tgt
closes a connection.

> Note that iscsid didn't drop the connection (it recovers from timeouts).

Looks like the log says that iscsid dropped a connection? I guess that
it would be better to ask Mike.


> On tgtd side, there were no IO errors.
> 
> 
> Feb  6 11:06:05 syn2 kernel: kjournald starting.  Commit interval 5 seconds
> Feb  6 11:06:05 syn2 kernel: EXT3 FS on sdav, internal journal
> Feb  6 11:06:05 syn2 kernel: EXT3-fs: recovery complete.
> Feb  6 11:06:05 syn2 kernel: EXT3-fs: mounted filesystem with ordered data mode.
> Feb  6 11:07:46 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33074933, last ping 33075933, now 33077433
> Feb  6 11:07:46 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:07:46 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:07:59 syn2 iscsid: connection47:0 is operational after recovery (1 attempts)
> Feb  6 11:08:44 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33080798, last ping 33081798, now 33083298
> Feb  6 11:08:44 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:08:45 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:08:48 syn2 iscsid: connection47:0 is operational after recovery (1 attempts)
> Feb  6 11:09:12 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33083630, last ping 33084630, now 33086130
> Feb  6 11:09:12 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:09:13 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:09:30 syn2 iscsid: connection47:0 is operational after recovery (1 attempts)
> Feb  6 11:10:15 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33089875, last ping 33090875, now 33092375
> Feb  6 11:10:15 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:10:16 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:10:19 syn2 iscsid: connection47:0 is operational after recovery (1 attempts)
> Feb  6 11:10:43 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33092657, last ping 33093658, now 33095158
> Feb  6 11:10:43 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:10:44 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:10:58 syn2 iscsid: connection47:0 is operational after recovery (1 attempts)
> Feb  6 11:11:23 syn2 kernel:  connection47:0: ping timeout of 15 secs expired, last rx 33096653, last ping 33097653, now 33099153
> Feb  6 11:11:23 syn2 kernel:  connection47:0: detected conn error (1011)
> Feb  6 11:11:23 syn2 iscsid: Kernel reported iSCSI connection 47:0 error (1011) state (3)
> Feb  6 11:11:37 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:37 syn2 kernel: end_request: I/O error, dev sdav, sector 2528
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 316
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 317
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 318
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 319
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 320
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 321
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 322
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 323
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 324
> Feb  6 11:11:37 syn2 kernel: Buffer I/O error on device sdav, logical block 325
> Feb  6 11:11:37 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:37 syn2 kernel: end_request: I/O error, dev sdav, sector 820360
> Feb  6 11:11:37 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 819336
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 818408
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 817384
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 816360
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 815464
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 814904
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 814016
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> Feb  6 11:11:38 syn2 kernel: end_request: I/O error, dev sdav, sector 813576
> Feb  6 11:11:38 syn2 kernel: sd 48:0:0:1: SCSI error: return code = 0x00020000
> (...)
> 
> 
> -- 
> Tomasz Chmielewski
> http://wpkg.org
> --
> To unsubscribe from this list: send the line "unsubscribe stgt" in
> the body of a message to majordomo at vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe stgt" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html



More information about the stgt mailing list