Re: mpt2sas + raid10 goes boom

2013-04-09 Thread Matthias Prager
Hello everyone, an update: I was able to reproduce the problem on my testing machine (at least sort of) and confirmed that c8dc9c6 md: raid1,10: Handle REQ_WRITE_SAME flag in write bios fixes things. Also applied c8dc9c6 to the main system's 3.8.6 kernel. Working without any issues. One interes

Re: mpt2sas + raid10 goes boom

2013-04-09 Thread Matthias Prager
Thanks for your insights Baruch. The crc count did not increase any further - so this was probably just small oddity (was zero before when the write-same issue already happened). The real issue however does persist. I found a way to reliably trigger the log messages. Using a program called checksum

Re: mpt2sas + raid10 goes boom

2013-04-08 Thread NeilBrown
On Tue, 9 Apr 2013 12:22:29 +1000 Chris Dunlop wrote: > > Neil -- should c8dc9c6 go to stable? > > I think it definitely should. Without it you can't create a > raid10 and it looks like you have a controller issue! It is too late for 3.7, but it probably makes sense for 3.8. I suggest you ask

Re: mpt2sas + raid10 goes boom

2013-04-08 Thread Chris Dunlop
On Mon, Apr 08, 2013 at 09:32:42AM -0400, Joe Lawrence wrote: > On Mon, 8 Apr 2013 03:53:51 -0400 > "Chris Dunlop" wrote: > >> Upon reflection, given this smells like a controller issue, this >> may be better addressed to linux-scsi@vger.kernel.org... >> >> On Mon, Apr 08, 2013 at 05:18:34PM +10

Re: mpt2sas + raid10 goes boom

2013-04-08 Thread Joe Lawrence
On Mon, 8 Apr 2013 03:53:51 -0400 "Chris Dunlop" wrote: > Upon reflection, given this smells like a controller issue, this > may be better addressed to linux-scsi@vger.kernel.org... > > On Mon, Apr 08, 2013 at 05:18:34PM +1000, Chris Dunlop wrote: [... snip ...] > Apr 8 15:08:53 b4 kernel: [ 4

Re: mpt2sas + raid10 goes boom

2013-04-08 Thread Baruch Even
> Apr 8 15:08:41 b4 kernel: [ 436.346595] mpt2sas0: log_info(0x31120320): > originator(PL), code(0x12), sub_code(0x0320) This log_info error code means a bad TX SGE, I don't know the code to point to the issue but it seems like there is a problem in the driver or the higher layers that provided

Re: mpt2sas + raid10 goes boom

2013-04-08 Thread Chris Dunlop
Upon reflection, given this smells like a controller issue, this may be better addressed to linux-scsi@vger.kernel.org... On Mon, Apr 08, 2013 at 05:18:34PM +1000, Chris Dunlop wrote: > G'day, > > On a LSI 9211-8i controller with IT firmware, when I use mdadm > to create a 4-disk raid10 and mount