On Mon, 7 Apr 2008, Dan Williams wrote: > On Mon, Apr 7, 2008 at 8:22 AM, dean gaudet <dean@xxxxxxxxxx> wrote: > > while my system was doing its monthly check (debian) i bumped into > > soft-lockups in the raid5 code. i must mention this is a rather mature > > system, the disks are 3.5 years old at this point... so i'm not surprised > > that the check will find some bad sectors which will take the > > device/driver a while to read/correct. > > > > all SMART events in this log are on disks which are part of /dev/md4 which > > is a raid5. the controller is a 3ware 7508, the disks are seagate > > ST3400832A. > > > > apparently no errors propagated all the way up to raid5, but based on the > > SMART events i'm pretty sure several sectors took a long time to finish > > being read and were probably corrected by the drive itself. > > > > this is debian kernel image 2.6.24-1-686 version 2.6.24-4 which contains > > upstream 2.6.24.2. > > > > -dean > > > > root@neemlark:~# cat /sys/block/md4/md/mismatch_cnt > > 0 > > > > This does not look like the hang that is set to be fixed in 2.6.24.5. > Does /proc/mdstat show that the resync is progressing, or does it > appear to be stalled? oh it finished, sorry i should have said that :) there were just those various soft lockup warnings... as a wild stab in the dark -- does the "faulty" test mode support delaying reads or writes for a very long time? (or is there some other fake block device we can inject long delays with?) -dean -- 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
