aic94xx: failing under heavy load

From: Patrick LeBoutillier
Date: Wed Jun 25 2008 - 13:44:49 EST


Hi,

I'm using the aic94xx driver with a AIC-9410W controller (w/6 Seagate
Cheetah SAS drives) and am getting the following errors under heavy
load:

kernel: aic94xx: escb_tasklet_complete: REQ_TASK_ABORT, reason=0x10
kernel: sas: command 0xffff81083c893700, task 0xffff81083c4459c0,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff8108381b8580, task 0xffff81083d054200,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083e64c080, task 0xffff81083c42a240,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c4f5e40, task 0xffff810836417540,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff8108381b8bc0, task 0xffff81083d054980,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff8108381b8d00, task 0xffff81083c42a840,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c4f5580, task 0xffff81083d054500,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff8108381b8800, task 0xffff810838808080,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff8108381b8a80, task 0xffff81083d054e00,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c893200, task 0xffff810838808c80,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c4d16c0, task 0xffff81083d054680,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c70d5c0, task 0xffff8108376d3b40,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c4d1580, task 0xffff81083c42a9c0,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083e64c940, task 0xffff8108376d3cc0,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c8830c0, task 0xffff810836424e00,
timed out: EH_NOT_HANDLED
kernel: sas: command 0xffff81083c4d1e40, task 0xffff8108364170c0,
timed out: EH_NOT_HANDLED
kernel: sas: Enter sas_scsi_recover_host
kernel: sas: trying to find task 0xffff81083c4459c0
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083c4459c0
kernel: aic94xx: tmf tasklet complete
kernel: aic94xx: tmf resp tasklet
kernel: aic94xx: tmf came back
kernel: aic94xx: task not done, clearing nexus
kernel: aic94xx: asd_clear_nexus_tag: PRE
kernel: aic94xx: asd_clear_nexus_tag: POST
kernel: aic94xx: asd_clear_nexus_tag: clear nexus posted, waiting...
kernel: aic94xx: task 0xffff81083c4459c0 done with opcode 0x23 resp
0x0 stat 0x8d but aborted by upper layer!
kernel: aic94xx: asd_clear_nexus_tasklet_complete: here
kernel: aic94xx: asd_clear_nexus_tasklet_complete: opcode: 0x0
kernel: aic94xx: task 0xffff81083d054200 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083c42a240 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff810836417540 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083d054980 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083c42a840 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083d054500 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff810838808080 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083d054e00 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff810838808c80 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083d054680 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff8108376d3b40 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff81083c42a9c0 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff8108376d3cc0 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff810836424e00 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: task 0xffff8108364170c0 done with opcode 0x0 resp 0x0
stat 0x0 but aborted by upper layer!
kernel: aic94xx: came back from clear nexus
kernel: aic94xx: task 0xffff81083c4459c0 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083c4459c0 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083c4459c0 is done
kernel: sas: trying to find task 0xffff81083d054200
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083d054200
kernel: aic94xx: asd_abort_task: task 0xffff81083d054200 done
kernel: aic94xx: task 0xffff81083d054200 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083d054200 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083d054200 is done
kernel: sas: trying to find task 0xffff81083c42a240
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083c42a240
kernel: aic94xx: asd_abort_task: task 0xffff81083c42a240 done
kernel: aic94xx: task 0xffff81083c42a240 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083c42a240 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083c42a240 is done
kernel: sas: trying to find task 0xffff810836417540
kernel: sas: sas_scsi_find_task: aborting task 0xffff810836417540
kernel: aic94xx: asd_abort_task: task 0xffff810836417540 done
kernel: aic94xx: task 0xffff810836417540 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff810836417540 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff810836417540 is done
kernel: sas: trying to find task 0xffff81083d054980
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083d054980
kernel: aic94xx: asd_abort_task: task 0xffff81083d054980 done
kernel: aic94xx: task 0xffff81083d054980 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083d054980 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083d054980 is done
kernel: sas: trying to find task 0xffff81083c42a840
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083c42a840
kernel: aic94xx: asd_abort_task: task 0xffff81083c42a840 done
kernel: aic94xx: task 0xffff81083c42a840 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083c42a840 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083c42a840 is done
kernel: sas: trying to find task 0xffff81083d054500
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083d054500
kernel: aic94xx: asd_abort_task: task 0xffff81083d054500 done
kernel: aic94xx: task 0xffff81083d054500 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083d054500 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083d054500 is done
kernel: sas: trying to find task 0xffff810838808080
kernel: sas: sas_scsi_find_task: aborting task 0xffff810838808080
kernel: aic94xx: asd_abort_task: task 0xffff810838808080 done
kernel: aic94xx: task 0xffff810838808080 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff810838808080 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff810838808080 is done
kernel: sas: trying to find task 0xffff81083d054e00
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083d054e00
kernel: aic94xx: asd_abort_task: task 0xffff81083d054e00 done
kernel: aic94xx: task 0xffff81083d054e00 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083d054e00 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083d054e00 is done
kernel: sas: trying to find task 0xffff810838808c80
kernel: sas: sas_scsi_find_task: aborting task 0xffff810838808c80
kernel: aic94xx: asd_abort_task: task 0xffff810838808c80 done
kernel: aic94xx: task 0xffff810838808c80 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff810838808c80 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff810838808c80 is done
kernel: sas: trying to find task 0xffff81083d054680
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083d054680
kernel: aic94xx: asd_abort_task: task 0xffff81083d054680 done
kernel: aic94xx: task 0xffff81083d054680 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083d054680 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083d054680 is done
kernel: sas: trying to find task 0xffff8108376d3b40
kernel: sas: sas_scsi_find_task: aborting task 0xffff8108376d3b40
kernel: aic94xx: asd_abort_task: task 0xffff8108376d3b40 done
kernel: aic94xx: task 0xffff8108376d3b40 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff8108376d3b40 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff8108376d3b40 is done
kernel: sas: trying to find task 0xffff81083c42a9c0
kernel: sas: sas_scsi_find_task: aborting task 0xffff81083c42a9c0
kernel: aic94xx: asd_abort_task: task 0xffff81083c42a9c0 done
kernel: aic94xx: task 0xffff81083c42a9c0 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff81083c42a9c0 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff81083c42a9c0 is done
kernel: sas: trying to find task 0xffff8108376d3cc0
kernel: sas: sas_scsi_find_task: aborting task 0xffff8108376d3cc0
kernel: aic94xx: asd_abort_task: task 0xffff8108376d3cc0 done
kernel: aic94xx: task 0xffff8108376d3cc0 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff8108376d3cc0 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff8108376d3cc0 is done
kernel: sas: trying to find task 0xffff810836424e00
kernel: sas: sas_scsi_find_task: aborting task 0xffff810836424e00
kernel: aic94xx: asd_abort_task: task 0xffff810836424e00 done
kernel: aic94xx: task 0xffff810836424e00 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff810836424e00 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff810836424e00 is done
kernel: sas: trying to find task 0xffff8108364170c0
kernel: sas: sas_scsi_find_task: aborting task 0xffff8108364170c0
kernel: aic94xx: asd_abort_task: task 0xffff8108364170c0 done
kernel: aic94xx: task 0xffff8108364170c0 aborted, res: 0x0
kernel: sas: sas_scsi_find_task: task 0xffff8108364170c0 is done
kernel: sas: sas_eh_handle_sas_errors: task 0xffff8108364170c0 is done
kernel: sas: --- Exit sas_scsi_recover_host


I am running kernel 2.6.25.8.
Controller firmware (/lib/firmware/aic94xx-seq.fw) is V30.

I have seen a few threads in the mailing list regarding similar errors
but none seem to lead to any kind of solution.

Does anyone have any leads I can follow? I'll be happy to try out
patches if anybody has anything.


Thanks a lot,

Patrick

--
=====================
Patrick LeBoutillier
Laval, Québec, Canada
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/