Hi,
I'm currently testing cache tier on ceph 0.94.2 - I've set up an erasure
coded pool with a cache pool on SSD drives, the cache mode is set to
writeback. I tried to fill the cache and see how it will flush objects
but the cache pool is full and I can't flush-evict any objects.. and
there are some requests blocked.
I tried to restart osd daemon that is blocked but it didn't help. And
when a issue command: rados -p cache cache-flush-evict-all - the command
just hangs.
How can I fix this?
Here's my setup:
root@cf01:~# ceph -s
cluster 999ed979-3837-4919-bd41-9929f9d44548
health HEALTH_ERR
4 requests are blocked > 32 sec
1 full osd(s)
2 near full osd(s)
monmap e1: 1 mons at {cf01=10.4.10.211:6789/0}
election epoch 1, quorum 0 cf01
osdmap e951: 14 osds: 14 up, 14 in
flags full
pgmap v32829: 768 pgs, 3 pools, 612 GB data, 153 kobjects
1054 GB used, 55615 GB / 56670 GB avail
768 active+clean
root@cf01:~# ceph osd df
ID WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR
10 1.00000 1.00000 204G 179G 25917M 87.64 47.09
11 1.00000 1.00000 204G 182G 22827M 89.12 47.88
12 1.00000 1.00000 204G 147G 58599M 72.06 38.72
13 1.00000 1.00000 204G 195G 9784M 95.34 51.22
0 1.00000 1.00000 5585G 33104M 5552G 0.58 0.31
1 1.00000 1.00000 5585G 25250M 5560G 0.44 0.24
2 1.00000 1.00000 5585G 31215M 5554G 0.55 0.29
3 1.00000 1.00000 5585G 43265M 5542G 0.76 0.41
4 1.00000 1.00000 5585G 46252M 5539G 0.81 0.43
5 1.00000 1.00000 5585G 30239M 5555G 0.53 0.28
6 1.00000 1.00000 5585G 32174M 5553G 0.56 0.30
7 1.00000 1.00000 5585G 27162M 5558G 0.47 0.26
9 1.00000 1.00000 5585G 47511M 5538G 0.83 0.45
8 1.00000 1.00000 5585G 42006M 5544G 0.73 0.39
TOTAL 56670G 1054G 55615G 1.86
MIN/MAX VAR: 0.24/51.22 STDDEV: 45.24
root@cf02:~# ceph osd pool ls detail
pool 4 'rbd' replicated size 2 min_size 1 crush_ruleset 0 object_hash
rjenkins pg_num 256 pgp_num 256 last_change 189 lfor 188 flags
hashpspool stripe_width 0
pool 7 'cache' replicated size 2 min_size 1 crush_ruleset 1 object_hash
rjenkins pg_num 256 pgp_num 256 last_change 873 flags
hashpspool,incomplete_clones tier_of 8 cache_mode writeback target_bytes
440234147840 target_objects 1000000 hit_set
bloom{false_positive_probability: 0.05, target_size: 0, seed: 0} 3600s
x1 stripe_width 0
removed_snaps [1~1]
pool 8 'ecpool' erasure size 4 min_size 3 crush_ruleset 2 object_hash
rjenkins pg_num 256 pgp_num 256 last_change 705 lfor 701 flags
hashpspool tiers 7 read_tier 7 write_tier 7 stripe_width 4128
removed_snaps [1~1]
root@cf01:~# ceph daemon osd.10 dump_ops_in_flight
{
"ops": [
{
"description": "osd_op(client.32158.0:2
rb.0.7c12.238e1f29.00000001591a [cache-flush] 7.cc760000
ack+read+ignore_cache+ignore_overlay+known_if_redirected e932)",
"initiated_at": "2015-07-04 15:42:09.361984",
"age": 574.793637,
"duration": 0.000235,
"type_data": [
"delayed",
{
"client": "client.32158",
"tid": 2
},
[
{
"time": "2015-07-04 15:42:09.361984",
"event": "initiated"
},
{
"time": "2015-07-04 15:42:09.362197",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:42:09.362219",
"event": "waiting for blocked object"
}
]
]
},
{
"description": "osd_op(client.32169.0:2
rb.0.7c12.238e1f29.00000001591a [cache-flush] 7.cc760000
ack+read+ignore_cache+ignore_overlay+known_if_redirected e951)",
"initiated_at": "2015-07-04 15:49:28.302955",
"age": 135.852667,
"duration": 0.000304,
"type_data": [
"delayed",
{
"client": "client.32169",
"tid": 2
},
[
{
"time": "2015-07-04 15:49:28.302955",
"event": "initiated"
},
{
"time": "2015-07-04 15:49:28.303211",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:49:28.303258",
"event": "waiting for blocked object"
}
]
]
},
{
"description": "osd_op(client.32151.0:1
rb.0.7c12.238e1f29.00000001591a [cache-flush] 7.cc760000 RETRY=1
ack+retry+read+ignore_cache+ignore_overlay+known_if_redirected e923)",
"initiated_at": "2015-07-04 15:41:24.216643",
"age": 619.938979,
"duration": 0.441889,
"type_data": [
"started",
{
"client": "client.32151",
"tid": 1
},
[
{
"time": "2015-07-04 15:41:24.216643",
"event": "initiated"
},
{
"time": "2015-07-04 15:41:24.269935",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:41:24.334561",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:41:24.604050",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:41:24.658221",
"event": "reached_pg"
},
{
"time": "2015-07-04 15:41:24.658532",
"event": "started"
}
]
]
}
],
"num_ops": 3
}
# begin crush map
tunable choose_local_tries 0
tunable choose_local_fallback_tries 0
tunable choose_total_tries 50
tunable chooseleaf_descend_once 1
# devices
device 0 osd.0
device 1 osd.1
device 2 osd.2
device 3 osd.3
device 4 osd.4
device 5 osd.5
device 6 osd.6
device 7 osd.7
device 8 osd.8
device 9 osd.9
device 10 osd.10
device 11 osd.11
device 12 osd.12
device 13 osd.13
# types
type 0 osd
type 1 host
type 2 chassis
type 3 rack
type 4 row
type 5 pdu
type 6 pod
type 7 room
type 8 datacenter
type 9 region
type 10 root
# buckets
host cf01 {
id -2 # do not change unnecessarily
# weight 3.000
alg straw
hash 0 # rjenkins1
item osd.0 weight 1.000
item osd.1 weight 1.000
item osd.2 weight 1.000
}
host cf02 {
id -3 # do not change unnecessarily
# weight 2.000
alg straw
hash 0 # rjenkins1
item osd.3 weight 1.000
item osd.4 weight 1.000
}
host cf03 {
id -4 # do not change unnecessarily
# weight 3.000
alg straw
hash 0 # rjenkins1
item osd.5 weight 1.000
item osd.6 weight 1.000
item osd.7 weight 1.000
}
host cf04 {
id -5 # do not change unnecessarily
# weight 2.000
alg straw
hash 0 # rjenkins1
item osd.9 weight 1.000
item osd.8 weight 1.000
}
root default {
id -1 # do not change unnecessarily
# weight 10.000
alg straw
hash 0 # rjenkins1
item cf01 weight 3.000
item cf02 weight 2.000
item cf03 weight 3.000
item cf04 weight 2.000
}
host ssd01 {
id -6 # do not change unnecessarily
# weight 1.000
alg straw
hash 0 # rjenkins1
item osd.10 weight 1.000
}
host ssd02 {
id -7 # do not change unnecessarily
# weight 1.000
alg straw
hash 0 # rjenkins1
item osd.11 weight 1.000
}
host ssd03 {
id -8 # do not change unnecessarily
# weight 1.000
alg straw
hash 0 # rjenkins1
item osd.12 weight 1.000
}
host ssd04 {
id -9 # do not change unnecessarily
# weight 1.000
alg straw
hash 0 # rjenkins1
item osd.13 weight 1.000
}
root ssd {
id -10 # do not change unnecessarily
# weight 8.000
alg straw
hash 0 # rjenkins1
item ssd01 weight 2.000
item ssd02 weight 2.000
item ssd03 weight 2.000
item ssd04 weight 2.000
}
# rules
rule default {
ruleset 0
type replicated
min_size 1
max_size 10
step take default
step chooseleaf firstn 0 type host
step emit
}
rule cache {
ruleset 1
type replicated
min_size 1
max_size 10
step take ssd
step chooseleaf firstn 0 type host
step emit
}
rule ecpool {
ruleset 2
type erasure
min_size 3
max_size 4
step set_chooseleaf_tries 5
step set_choose_tries 100
step take default
step chooseleaf indep 0 type host
step emit
}
# end crush map
--
Jacek Jarosiewicz
Administrator Systemów Informatycznych
----------------------------------------------------------------------------------------
SUPERMEDIA Sp. z o.o. z siedzibą w Warszawie
ul. Senatorska 13/15, 00-075 Warszawa
Sąd Rejonowy dla m.st.Warszawy, XII Wydział Gospodarczy Krajowego
Rejestru Sądowego,
nr KRS 0000029537; kapitał zakładowy 42.756.000 zł
NIP: 957-05-49-503
Adres korespondencyjny: ul. Jubilerska 10, 04-190 Warszawa
----------------------------------------------------------------------------------------
SUPERMEDIA -> http://www.supermedia.pl
dostep do internetu - hosting - kolokacja - lacza - telefonia
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
