enbd+raid5 problem
Hoffmann Christian <[email protected]>
| Newsgroups | gmane.linux.enbd.general |
|---|---|
| Message-ID | <512FA669CAABD711AFC000047581AD0932AA@FORD-PREFECT> |
hi!
I am new to the mailing list and have a problem with enbd+raid5.
My system is debian sarge kernel 2.6.8-2-smp on all clients and servers.
I have 4 enbd-server providing 4 devices for enbd. (backened1, backend2
backend3, backend4)
On the client side I mount 4 devices (/dev/nda,/dev/ndb,/dev/ndc,/dev/ndd)
which works quite fine I guess. Here is the output of /proc/nbdinfo:
Device a: Open
[a] State: verify, rw, enabled, validated, show_errs, last error 0,
lives 5, bp 0
[a] Queued: +0R/0W curr (check 0R/0W) +252R/1W max
[a] Buffersize: 262144 (sectors=512, blocks=64)
[a] Blocksize: 4096 (log=12)
[a] Size: 2008092KB
[a] Blocks: 502023
[a] Sockets: 2 (*) (+)
[a] Requested: 490.28K (245K) (245K) 490.2KR/5W max 1
[a] Despatched: 490.28K (245K) (245K) 490.2KR/5W md5 0W (0 eq, 0 ne,
0 dn)
[a] Errored: 3 (0) (0) 0+3
[a] Pending: 0 (0) (0) 0R/0W+0R/0W
[a] B/s now: 0 (0R+0W)
[a] B/s ave: 216K (216KR+0W)
[a] B/s max: 2.79G (2.78GR+4.88MW)
[a] Spectrum: 99%1
[a] Kthreads: 0 (0 waiting/0 running/2 max)
[a] Cthreads: 2 (+) (+)
[a] Cpids: 2 (7029) (7030)
Device b: Open
[b] State: verify, rw, enabled, validated, show_errs, last error 0,
lives 5, bp 0
[b] Queued: +0R/0W curr (check 0R/0W) +252R/1W max
[b] Buffersize: 262144 (sectors=512, blocks=64)
[b] Blocksize: 4096 (log=12)
[b] Size: 2008092KB
[b] Blocks: 502023
[b] Sockets: 2 (+) (*)
[b] Requested: 490.28K (245K) (245K) 490.2KR/4W max 1
[b] Despatched: 490.28K (245K) (245K) 490.2KR/4W md5 0W (0 eq, 0 ne,
0 dn)
[b] Errored: 3 (0) (0) 0+3
[b] Pending: 0 (0) (0) 0R/0W+0R/0W
[b] B/s now: 0 (0R+0W)
[b] B/s ave: 216K (216KR+0W)
[b] B/s max: 2.79G (2.79GR+3.90MW)
[b] Spectrum: 99%1
[b] Kthreads: 0 (0 waiting/0 running/2 max)
[b] Cthreads: 2 (+) (+)
[b] Cpids: 2 (7033) (7034)
Device c: Open
[c] State: verify, rw, enabled, validated, show_errs, last error 0,
lives 5, bp 0
[c] Queued: +0R/0W curr (check 0R/0W) +20R/157W max
[c] Buffersize: 262144 (sectors=512, blocks=64)
[c] Blocksize: 4096 (log=12)
[c] Size: 2008092KB
[c] Blocks: 502023
[c] Sockets: 2 (+) (*)
[c] Requested: 490.26K (245K) (245K) 29R/490.2KW max 1
[c] Despatched: 490.26K (245K) (245K) 29R/490.2KW md5 137KW (133K eq,
3.88K ne, 0 dn)
[c] Errored: 0 (0) (0) 0+0
[c] Pending: 0 (0) (0) 0R/0W+0R/0W
[c] B/s now: 0 (0R+0W)
[c] B/s ave: 216K (0R+216KW)
[c] B/s max: 3.10G (109MR+2.99GW)
[c] Spectrum: 99%1
[c] Kthreads: 0 (0 waiting/0 running/1 max)
[c] Cthreads: 2 (+) (+)
[c] Cpids: 2 (7031) (7032)
Device d: Open
[d] State: verify, rw, enabled, validated, show_errs, last error 0,
lives 6, bp 0
[d] Queued: +0R/0W curr (check 0R/0W) +1R/1W max
[d] Buffersize: 262144 (sectors=512, blocks=64)
[d] Blocksize: 4096 (log=12)
[d] Size: 2008092KB
[d] Blocks: 502023
[d] Sockets: 2 (+) (*)
[d] Requested: 9 (3) (6) 9R/0W max 1
[d] Despatched: 9 (3) (6) 9R/0W md5 0W (0 eq, 0 ne, 0 dn)
[d] Errored: 0 (0) (0) 0+0
[d] Pending: 0 (0) (0) 0R/0W+0R/0W
[d] B/s now: 0 (0R+0W)
[d] B/s ave: 0 (0R+0W)
[d] B/s max: 8.78M (8.78MR+0W)
[d] Spectrum: 40%0 60%1
[d] Kthreads: 0 (0 waiting/0 running/1 max)
[d] Cthreads: 2 (+) (+)
[d] Cpids: 2 (7035) (7036)
Device e-p: Closed
On top of the enbd-devices I try to run raid5 using mdadm:
mdadm --create /dev/md0 --level=5 --raid-devices=4 /dev/nda /dev/ndb
/dev/ndc /dev/ndd
The array is build and shows following output:
Personalities : [raid5]
md0 : active raid5 nda[0] ndc[2] ndb[1] ndd[3]
4016000 blocks level 5, 64k chunk, algorithm 2 [4/4] [UUUU]
unused devices: <none>
The problem starts when I remove one enbd-server. The raid array does not
recognize that one device is missing and still marks all devices online!!
I am using the raid module provided by the kernel. Do I have to compile a
new kernel with another raid module?
Did anybody have the same problem already? I could´nt find it anywhere...
Thanks,
Chris