Not sure if this is normal behaviour or not, but on a recent RELENG_11
r321624, I noticed something odd about rand_harvestq.
While doing some disk stress testing of zfs, I was creating a bunch of
random files.
eg
dd if=/dev/urandom > /tmp/junk2 bs=1m count=10000
If I create enough of them, rand_harvestq seems to get pegged at 100% on
one of my CPUs
last pid: 1014; load averages: 1.36, 0.96, 0.65
up 0+00:17:00 14:22:45
49 processes: 3 running, 45 sleeping, 1 waiting
CPU: 0.0% user, 0.0% nice, 24.8% system, 0.0% interrupt, 75.2% idle
Mem: 24M Active, 4140K Inact, 12G Wired, 4001M Free
ARC: 11G Total, 3144K MFU, 11G MRU, 64K Anon, 19M Header, 1224K Other
11G Compressed, 11G Uncompressed, 1.00:1 Ratio
Swap: 40G Total, 40G Free
PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU
COMMAND
11 root 4 155 ki31 0K 64K CPU0 0 55:37 302.56% idle
16 root 1 -16 - 0K 16K CPU3 3 10:39 105.60%
rand_harvestq
1014 root 1 20 0 7892K 2668K CPU2 2 0:00 0.03% top
And it stays there
# ps auxwS | head -5
USER PID %CPU %MEM VSZ RSS TT STAT STARTED TIME COMMAND
root 11 295.2 0.0 0 64 - RL 14:05 59:05.25 [idle]
root 16 100.0 0.0 0 16 - RL 14:05 11:48.24
[rand_harvestq]
root 0 0.0 0.1 0 8400 - DLs 14:05 0:08.96 [kernel]
root 1 0.0 0.0 5408 588 - ILs 14:05 0:00.84 /sbin/init
Any idea whats going on ? The box is pretty standard
CPU: Intel(R) Xeon(R) CPU E3-1220 v3 @ 3.10GHz (3092.90-MHz K8-class CPU)
11.1-STABLE FreeBSD 11.1-STABLE #1 r321624 AMD64
KERNEL is non generic, but it just has a bunch of ethernet drivers
removed and pf and pflog added.
---Mike
--
--
-------------------
Mike Tancsa, tel +1 519 651 3400
Sentex Communications, mike at sentex.net
Providing Internet services since 1994 www.sentex.net
Cambridge, Ontario Canada http://www.tancsa.com/