On Mon, Apr 08, 2013 at 09:32:42AM -0400, Joe Lawrence wrote: > On Mon, 8 Apr 2013 03:53:51 -0400 > "Chris Dunlop" <chris@xxxxxxxxxxxx> wrote: > >> Upon reflection, given this smells like a controller issue, this >> may be better addressed to linux-scsi@xxxxxxxxxxxxxxx... >> >> On Mon, Apr 08, 2013 at 05:18:34PM +1000, Chris Dunlop wrote: > [... snip ...] >> Apr 8 15:08:53 b4 kernel: [ 448.657142] md4: WRITE SAME failed. >> Manually zeroing. > > Hi Chris, > > WRITE SAME was broken in MD RAID 1/10 up until: > > c8dc9c6 md: raid1,10: Handle REQ_WRITE_SAME flag in write bios > > and should be present in any kernel that includes the block layer WRITE > SAME changes: > > 4363ac7 block: Implement support for WRITE SAME > 579e8f3 block: Make blkdev_issue_zeroout use WRITE SAME Aha! That did it. My kernels, 3.7.3 and 3.7.10, include the latter two changes but not the former. A cherry-pick of c8dc9c6 fixed the issue for me. > 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! Thanks Joe, and to all who took an interest in my problem! Cheers, Chris. -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
