Aug 242013
 

My ZFS system hits a high load average every week during its scrub. Here is what top looks like after I pressed i and then S:

last pid: 42049;  load averages:  3.78,  3.26,  3.42     up 18+13:47:14  11:43:01
220 processes: 3 running, 216 sleeping, 1 waiting
CPU:  7.5% user,  0.0% nice, 12.8% system,  1.2% interrupt, 78.5% idle
Mem: 765M Active, 236M Inact, 8667M Wired, 17M Cache, 3284M Buf, 22G Free
Swap: 8192M Total, 2404K Used, 8190M Free

  PID USERNAME  THR PRI NICE   SIZE    RES STATE   C   TIME   WCPU COMMAND
   11 root        8 155 ki31     0K   128K CPU7    7 3331.6 625.59% idle
    0 root      204  -8    0     0K  3264K -       4 105.6H 68.07% kernel
32775  10837      1  87    0 88584K 49864K CPU3    3   5:32 49.27% postgres
   12 root       31 -76    -     0K   496K WAIT    0 999:45  9.33% intr
   13 root        3  -8    -     0K    48K -       5 866:23  9.13% geom
    6 root        4  -8    -     0K    80K soldel  2 776:06  7.67% zfskern
32774 dan         1  23    0 27708K  4568K select  7   0:49  6.05% pg_restore
 8992  10837      1  22    0 75792K 45768K select  0   1:15  3.17% postgres
 8994  10837      1  20    0 75792K 13000K zio->i  5   0:14  0.20% postgres
42033 dan         1  52    0  6276K   720K wait    0   0:00  0.20% make
36815 dan         1  20    0 16560K  2920K CPU4    7   0:00  0.10% top
41840 dan         1  52    0  6276K   752K wait    0   0:00  0.10% make
42037 dan         1  52    0 14504K  1888K wait    7   0:00  0.10% sh
41841 dan         1  32    0 14504K  1892K wait    5   0:00  0.10% sh
42032 dan         1  32    0 14504K  1900K wait    3   0:00  0.10% sh
42049 dan         1  45    0 21724K  9860K zio->i  4   0:00  0.00% cc1plus
42048 dan         1  52    0  9916K  1536K wait    3   0:00  0.00% g++

There are a few other things going on. A Bacula regression test for one.

Website Pin Facebook Twitter Myspace Friendfeed Technorati del.icio.us Digg Google StumbleUpon Premium Responsive