Hi all,
I'm running ASG/UTM 9.305-4.
Every few days, I see a spike in CPU usage caused by kswapd0:
top - 09:35:30 up 6 days, 12:29, 1 user, load average: 1.06, 1.03, 1.05
Tasks: 163 total, 2 running, 159 sleeping, 0 stopped, 2 zombie
Cpu(s): 0.0%us, 25.4%sy, 0.0%ni, 74.6%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 3792464k total, 3519572k used, 272892k free, 364348k buffers
Swap: 4190204k total, 27428k used, 4162776k free, 1637560k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
338 root 20 0 0 0 0 R 99 0.0 3587:29 kswapd0
1152 root 20 0 0 0 0 S 1 0.0 3:55.21 scsi_eh_1
13461 postgres 20 0 563m 9616 7936 S 1 0.3 0:00.46 postgres
16318 root 20 0 0 0 0 S 1 0.0 0:00.31 kworker/0:2
30871 postgres 20 0 562m 5888 4608 S 1 0.2 0:13.97 postgres
1 root 20 0 1916 572 516 S 0 0.0 0:02.47 init
2 root 20 0 0 0 0 S 0 0.0 0:00.02 kthreadd
3 root 20 0 0 0 0 S 0 0.0 0:11.24 ksoftirqd/0
5 root 0 -20 0 0 0 S 0 0.0 0:00.00 kworker/0:0H
7 root RT 0 0 0 0 S 0 0.0 0:00.27 migration/0
8 root 20 0 0 0 0 S 0 0.0 0:01.98 rcu_bh
9 root 20 0 0 0 0 S 0 0.0 1:31.84 rcu_sched
10 root RT 0 0 0 0 S 0 0.0 0:00.39 migration/1
11 root 20 0 0 0 0 S 0 0.0 0:02.81 ksoftirqd/1
13 root 0 -20 0 0 0 S 0 0.0 0:00.00 kworker/1:0H
14 root RT 0 0 0 0 S 0 0.0 0:00.30 migration/2
15 root 20 0 0 0 0 S 0 0.0 0:01.62 ksoftirqd/2
The CPU remains at this level until I restart the system. Has anyone else encountered this problem?
I've found that I can reduce the problem temporarily by using the following command to drop the kernel caches on the UTM:
echo 1 > /proc/sys/vm/drop_caches
which drops the CPU usage from kswapd0 down to zero for a while. Today, I noticed it was back. So I've put the command above in a cron job to run every hour for now, but I was wondering if there is another solution?
If it's of any help, the ASG/UTM runs on a Hypervisor (XenServer 6.5 build 90239c) with 4 CPUs and 4Gb of memory assigned to it.
Thanks,
Paulo
This thread was automatically locked due to age.
