I/O errors in PowerEdge 2900 with Megaraid SAS

[L.P.H. van Belle]

Hi, 

To help a bit, 

Im running on my PE2900 with 2x E5345 CPU, Bios 2.0.1, Latest Perc firmware
also
and kernel 2.6.18-5-i686 . And no problems at all. ( no 64 Bit )

Louis


>-----Oorspronkelijk bericht-----
>Van: linux-poweredge-bounces at dell.com 
>[mailto:linux-poweredge-bounces at dell.com] Namens Robert Goley
>Verzonden: dinsdag 18 december 2007 21:36
>Aan: linux-poweredge at dell.com
>Onderwerp: Re: I/O errors in PowerEdge 2900 with Megaraid SAS
>
>I have experienced issues with 2970s and recently a 2900 with 
>a RAID 5 arrays 
>on the PERC5 controller.  I have upgraded all of the kernels 
>to backports.org 
>2.6.21 or 2.6.22 kernels.  The problems seem to have went away.  I saw 
>additional communication errors and the filesystems were 
>mounted readonly 
>automatically because of the errors.  I am using Debian Etch 
>(AMD64).  The 
>problems I saw took from hours to days to appear.  All machines worked 
>properly after reboot with the 2.6.18 kernel.  I have used the 
>2.6.18 kernel 
>with Debian Sarge on the 2900 machines for a long time now without any 
>trouble.  It has something to do with Etch or 64 bit.  I am 
>not sure past 
>that.  Your particular errors may also be related to cache on 
>the controller.  
>
>Robert
>
>On Tuesday 18 December 2007 14:54, Victor Olalla wrote:
>> Hi to all,
>>
>> I'm having problems with a Power Edge 2900 machine.
>>
>> I have configured a Raid5 with three SAS disks and I
>> have installed a Linux Debian etch with 2.6.18 kernel.
>>
>> After 2 months of perfect work, the system is throwing
>> a lot of error messages about I/O, also mounts the
>> filesystem in read_only. Here is a little fragment
>> from dmesg:
>>
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> end_request: I/O error, dev sda, sector 24786199
>> Buffer I/O error on device sda3, logical block 2554073
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> lost page write due to I/O error on sda3
>> end_request: I/O error, dev sda, sector 24786343
>> Buffer I/O error on device sda3, logical block 2554091
>> lost page write due to I/O error on sda3
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> end_request: I/O error, dev sda, sector 24786399
>> end_request: I/O error, dev sda, sector 8024063
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> end_request: I/O error, dev sda, sector 8285991
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> end_request: I/O error, dev sda, sector 9858639
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>> driverbyte=DRIVER_OK,SUGGEST_OK
>> end_request: I/O error, dev sda, sector 9858679
>> sd 0:2:0:0: [sda] Result: hostbyte=DID_BAD_TARGET
>>
>> After a reboot, the system works fine, without any
>> error about the filesystems. But after few hours,
>> (sometimes 3 hours and sometimes 30 hours) the I/O
>> errors return.
>>
>> I have changed the kernel, using a 2.6.22 kernel the
>> problem persists.
>>
>> Has anyone some experience with this problem?
>>
>> Thanks a lot.
>>
>>
>>
>> ______________________________________________
>> ¿Chef por primera vez?
>> Sé un mejor Cocinillas.
>> http://es.answers.yahoo.com/info/welcome
>>
>> _______________________________________________
>> Linux-PowerEdge mailing list
>> Linux-PowerEdge at dell.com
>> http://lists.us.dell.com/mailman/listinfo/linux-poweredge
>> Please read the FAQ at http://lists.us.dell.com/faq
>
>_______________________________________________
>Linux-PowerEdge mailing list
>Linux-PowerEdge at dell.com
>http://lists.us.dell.com/mailman/listinfo/linux-poweredge
>Please read the FAQ at http://lists.us.dell.com/faq
>