Massive sense key & IO errors and eventual crashing. R900 with Perc 6i

Chris Trainor ctrainor at quickhit.com
Mon May 24 13:34:36 CDT 2010


Hi all,

Just wanted to report in that replacing the SAS cable between the R900 & MD1120 seems to have done the trick.   Also interesting that the new cable I got from Dell was quite a bit 'thicker' then the one I replaced.  I wonder if we just received a low-quality cable from Dell the first time around.

--Chris


-----Original Message-----
From: linux-poweredge-bounces at dell.com [mailto:linux-poweredge-bounces at dell.com] On Behalf Of Tino Schwarze
Sent: Wednesday, May 12, 2010 3:27 AM
To: linux-poweredge at dell.com
Subject: Re: Massive sense key & IO errors and eventual crashing. R900 with Perc 6i

If I'm interpreting the sense keys correctly (according to
http://docs.hp.com/en/A5159-96003/apas01.html ), 
> Sense: b/4b/04

means: 
b = Aborted command
4b = Data phase error

I smell some cabling issue...

HTH,

Tino.

On Tue, May 11, 2010 at 01:44:29PM -0700, Chris Trainor wrote:
> Here's the last 50 lines of the external adapters event log.  Unfortunately it looks like one of the admins here cleared the log on the other controller. :(   Tho I'm sure in the next few days I'll have something there. :)
> 
> Adapter: 0 - Number of events : 8791
> 
> 
> 
> seqNum: 0x00446483
> Time: Tue May 11 11:59:23 2010
> 
> Code: 0x0000001e
> Class: 0
> Locale: 0x20
> Event Description: Event log cleared
> Event Data:
> ===========
> None
> 
> 
> seqNum: 0x00446484
> Time: Tue May 11 11:59:24 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 23(e0x11/s5) Path 5000c5000beae891, CDB: 28 00 05 83 44 67 00 00 19 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 35
> Enclosure Index: 17
> Slot Number: 5
> CDB Length: 10
> CDB Data:
> 0028 0000 0005 0083 0044 0067 0000 0000 0019 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0005 0083 0044 0078 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 00
> 00 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000
>  0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 
> 
> seqNum: 0x00446485
> Time: Tue May 11 11:59:24 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 27(e0x11/s9) Path 5000c5000beae6f9, CDB: 28 00 07 9c 4a 00 00 00 17 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 39
> Enclosure Index: 17
> Slot Number: 9
> CDB Length: 10
> CDB Data:
> 0028 0000 0007 009c 004a 0000 0000 0000 0017 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0007 009c 004a 0013 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 00
> 00 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000
>  0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 
> 
> seqNum: 0x00446486
> Time: Tue May 11 11:59:26 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 27(e0x11/s9) Path 5000c5000beae6f9, CDB: 28 00 06 01 bc 0f 00 00 20 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 39
> Enclosure Index: 17
> Slot Number: 9
> CDB Length: 10
> CDB Data:
> 0028 0000 0006 0001 00bc 000f 0000 0000 0020 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0006 0001 00bc 0022 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 00
> 00 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000
>  0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 
> 
> seqNum: 0x00446487
> Time: Tue May 11 11:59:26 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 15(e0x11/s13) Path 5000c5000bead7d9, CDB: 28 00 01 0d d6 17 00 00 20 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 21
> Enclosure Index: 17
> Slot Number: 13
> CDB Length: 10
> CDB Data:
> 0028 0000 0001 000d 00d6 0017 0000 0000 0020 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> [root at mackey MegaCli]# tail -50 AdpEvt-a0.log 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 15(e0x11/s13) Path 5000c5000bead7d9, CDB: 28 00 07 5e be c7 00 00 20 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 21
> Enclosure Index: 17
> Slot Number: 13
> CDB Length: 10
> CDB Data:
> 0028 0000 0007 005e 00be 00c7 0000 0000 0020 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0007 005e 00be 00e0 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 
> 
> seqNum: 0x004486d9
> Time: Tue May 11 17:41:01 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 27(e0x11/s9) Path 5000c5000beae6f9, CDB: 28 00 06 be 00 07 00 00 20 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 39
> Enclosure Index: 17
> Slot Number: 9
> CDB Length: 10
> CDB Data:
> 0028 0000 0006 00be 0000 0007 0000 0000 0020 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0006 00be 0000 0022 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 
> 
> seqNum: 0x004486da
> Time: Tue May 11 17:41:26 2010
> 
> Code: 0x00000071
> Class: 0
> Locale: 0x02
> Event Description: Unexpected sense: PD 1e(e0x11/s2) Path 5000c5000beae7cd, CDB: 28 00 00 84 81 00 00 00 07 00, Sense: b/4b/04
> Event Data:
> ===========
> Device ID: 30
> Enclosure Index: 17
> Slot Number: 2
> CDB Length: 10
> CDB Data:
> 0028 0000 0000 0084 0081 0000 0000 0000 0007 0000 0000 0000 0000 0000 0000 0000 Sense Length: 18
> Sense Data:
> 00f0 0000 000b 0000 0084 0081 0003 000a 0000 0000 0000 0000 004b 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000
> 
> 
> 
> --Chris
> 
> 
> 
> 
> -----Original Message-----
> From: David Miller [mailto:dmiller at sofi.org.uk] 
> Sent: Tuesday, May 11, 2010 4:33 PM
> To: Chris Trainor
> Cc: linux-poweredge at dell.com
> Subject: Re: Massive sense key & IO errors and eventual crashing. R900 with Perc 6i
> 
> Sense key B/4B/4 is a buffer overflow error going by the tool I have here:
> Full KCQ Dump
> KCQ: B4B04
> 
> Sense Key:Volume Overflow:
> Indicates a buffered peripheral device has reached the end of medium 
> partition and data remains in the buffer that has not been written to 
> the medium.
> Key Code:KCQ code unknown
> 
> Could the IO errors be coming from the Perc6E for the storage?
> 
> It would be interesting to see a controller log (use megacli to get the 
> controller logs for the internal and external controllers assuming a 
> perc internal controller as well).
> 
> David.
> 
> _______________________________________________
> Linux-PowerEdge mailing list
> Linux-PowerEdge at dell.com
> https://lists.us.dell.com/mailman/listinfo/linux-poweredge
> Please read the FAQ at http://lists.us.dell.com/faq

-- 
"What we nourish flourishes." - "Was wir nähren erblüht."

www.lichtkreis-chemnitz.de
www.tisc.de

_______________________________________________
Linux-PowerEdge mailing list
Linux-PowerEdge at dell.com
https://lists.us.dell.com/mailman/listinfo/linux-poweredge
Please read the FAQ at http://lists.us.dell.com/faq



More information about the Linux-PowerEdge mailing list