Hi,cephers
some osd has high latency in theoutput of ceph osd perf,but I have
setting the reweight of these osd in crushmap tp 0.0
and I use iostat to check these disk,no load.
so how does command `ceph osd perf` work?
root@node-67:~# ceph osd perf
osdid fs_commit_latency(ms) fs_apply_latency(ms)
0 9819 10204
1 1 2
2 1 2
3 9126 9496
4 2 3
5 2 3
6 0 0
7 0 1
8 1 2
9 32960 33953
10 2 3
11 1 31
12 23450 24324
13 0 1
14 1 2
15 18882 19622
16 2 4
17 1 2
18 3 46
root@node-67:~# ceph osd tree
# id weight type name up/down reweight
-1 103.7 root default
-2 8.19 host node-65
18 2.73 osd.18 up 1
21 0 osd.21 up 1
24 2.73 osd.24 up 1
27 2.73 osd.27 up 1
30 0 osd.30 up 1
33 0 osd.33 up 1
0 0 osd.0 up 1
3 0 osd.3 up 1
6 0 osd.6 down 0
9 0 osd.9 up 1
12 0 osd.12 up 1
15 0 osd.15 up 1
root@node-65:~# iostat -xm 1 -p sdd,sde,sdf,sdg
Linux 3.11.0-26-generic (node-65) 03/30/2016 _x86_64_ (40 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
3.34 0.00 0.61 2.60 0.00 93.45
Device: rrqm/s wrqm/s r/s w/s rMB/s wMB/s
avgrq-sz avgqu-sz await r_await w_await svctm %util
sdd 0.00 0.05 0.08 0.16 0.00 0.01
64.48 0.01 29.11 4.21 42.09 1.70 0.04
sdd1 0.00 0.05 0.08 0.16 0.00 0.01
64.54 0.01 29.14 4.22 42.09 1.71 0.04
sde 0.00 0.00 0.04 0.00 0.00 0.00
15.59 0.00 4.00 4.00 0.85 3.86 0.01
sde1 0.00 0.00 0.04 0.00 0.00 0.00
15.62 0.00 4.01 4.02 0.85 3.88 0.01
sdf 0.00 0.04 0.39 0.31 0.04 0.01
148.58 0.01 13.58 2.61 27.50 1.17 0.08
sdf1 0.00 0.04 0.39 0.31 0.04 0.01
148.63 0.01 13.59 2.61 27.50 1.17 0.08
sdg 0.00 0.06 0.22 0.24 0.02 0.02
162.41 0.01 23.64 2.85 42.89 1.49 0.07
sdg1 0.00 0.06 0.22 0.24 0.02 0.02
162.49 0.01 23.65 2.86 42.89 1.49 0.07
root@node-65:~# top
top - 11:16:34 up 11 days, 19:26, 4 users, load average: 4.46, 4.73, 3.66
Tasks: 588 total, 1 running, 587 sleeping, 0 stopped, 0 zombie
Cpu(s): 3.6%us, 0.6%sy, 0.0%ni, 93.5%id, 2.1%wa, 0.0%hi, 0.1%si, 0.0%st
Mem: 131998604k total, 69814800k used, 62183804k free, 216612k buffers
Swap: 3999740k total, 0k used, 3999740k free, 14093896k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
17000 libvirt- 20 0 39.7g 32g 12m S 109 25.7 18417:09 qemu-system-x86
8852 root 20 0 2116m 854m 9896 S 20 0.7 303:24.39 ceph-osd
9319 root 20 0 2285m 974m 12m S 16 0.8 385:24.69 ceph-osd
8797 root 20 0 2298m 929m 10m S 10 0.7 298:14.61 ceph-osd
17001 root 20 0 0 0 0 S 4 0.0 384:38.16 vhost-17000
24241 nova 20 0 148m 64m 4908 S 2 0.1 89:47.86 nova-network
24189 nova 20 0 125m 37m 4880 S 1 0.0 49:48.06 nova-api
1 root 20 0 24720 2644 1376 S 0 0.0 4:35.38 init
50 root 20 0 0 0 0 S 0 0.0 46:32.66 rcu_sched
52 root 20 0 0 0 0 S 0 0.0 1:21.29 rcuos/1
64 root 20 0 0 0 0 S 0 0.0 4:34.05 rcuos/13
67 root 20 0 0 0 0 S 0 0.0 3:06.16 rcuos/16
68 root 20 0 0 0 0 S 0 0.0 2:45.34 rcuos/17
4732 root 20 0 1650m 807m 15m S 0 0.6 3:24.89 ceph-osd
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
