On Tue, 14 Mar 2006, Neil Brown wrote:

On Monday March 13, patrik@ucolick.org wrote:

quoted

Hi all,

I just experienced some kind of lockup accessing my 8-drive raid5
(2.6.16-rc4-mm2). The system has been up for 16 days running fine, but
now processes that try to read the md device hang. ps tells me they are
all sleeping in get_active_stripe. There is nothing in the syslog, and I
can read from the individual drives fine with dd. mdadm says the state
is "active".

Hmmm... That's sad. That's going to be very hard to track down.

If you could
  echo t > /proc/sysrq-trigger

and send me the dump that appears in the kernel log, I would
appreciate it.  I doubt it will be very helpful, but it is the best
bet I can come up with.

i seem to be running into this as well... it has happenned several times 
in the past three weeks.  i attached the kernel log output...

it's a debian 2.6.16 kernel, which is based mostly on 2.6.16.10.

md4 : active raid5 sdd1[0] sde1[5](S) sdh1[4] sdg1[3] sdf1[2] sdc1[1]
      1562834944 blocks level 5, 128k chunk, algorithm 2 [5/5] [UUUUU]
      bitmap: 3/187 pages [12KB], 1024KB chunk

those drives are on 3w-xxxx (7508 controller).  i'm using lvm2 and
xfs as the filesystem (although i'm pretty sure an ext3 fs on another lv
is hanging too -- but i forgot to check before i unwedged it).

let me know if anything else is useful and i can try to catch it next
time.

You could try increasing the size of the stripe cache
  echo 512 > /sys/block/mdX/md/stripe_cache_size
(choose and appropriate 'X').

yeah that got things going again -- it took a minute or so maybe, i
wasn't paying attention as to how fast things cleared up.

Maybe check the content of
         /sys/block/mdX/md/stripe_cache_active
as well.

next time i'll check this before i increase stripe_cache_size... it's
0 now, but the raid5 is working again...

-dean