Skip to Main Content

Infrastructure Software

Announcement

For appeals, questions and feedback about Oracle Forums, please email oracle-forums-moderators_us@oracle.com. Technical questions should be asked in the appropriate category. Thank you!

kswapd using 100% of CPU

1506714Aug 1 2016 — edited Aug 12 2016

Hi team,

One of our OEL box is showing some strange behaviour thoses last days. Randomly, after some hours, the kswapd process is eating up 100 % of the CPU.

Swap and memory level :

[oracle@Cah-Dump ~]$ free

             total       used       free     shared    buffers     cached

Mem:       3915152    3806080     109072          0       1408       5392

-/+ buffers/cache:    3799280     115872

Swap:      4063228      91596    3971632

Linux version :

[oracle@Cah-Dump ~]$ uname -a

Linux Cah-Dump.cahors.local 2.6.32-504.3.3.el6.x86_64 #1 SMP Tue Dec 16 12:12:30 PST 2014 x86_64 x86_64 x86_64 GNU/Linux

Extract of top :

top - 09:08:46 up 3 days, 15 min,  1 user,  load average: 3.02, 3.40, 3.47

Tasks: 111 total,   2 running, 107 sleeping,   0 stopped,   2 zombie

Cpu(s):  1.2%us, 82.1%sy,  0.0%ni, 14.6%id,  1.3%wa,  0.0%hi,  0.8%si,  0.0%st

Mem:   3915152k total,  3800636k used,   114516k free,      508k buffers

Swap:  4063228k total,    91836k used,  3971392k free,     3212k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND                                                                                      

   30 root      20   0     0    0    0 R 99.9  0.0   3494:23 kswapd0                                                                                       

    1 root      20   0 19356    4    4 S  0.0  0.0   0:01.05 init                                                                                          

    2 root      20   0     0    0    0 S  0.0  0.0   0:00.00 kthreadd                                                                                      

    3 root      RT   0     0    0    0 S  0.0  0.0   0:00.00 migration/0                                                                                   

    4 root      20   0     0    0    0 S  0.0  0.0   0:09.70 ksoftirqd/0                                                                                   

    5 root      RT   0     0    0    0 S  0.0  0.0   0:00.00 stopper/0                                                                                     

    6 root      RT   0     0    0    0 S  0.0  0.0   0:00.34 watchdog/0                                                                                    

    7 root      20   0     0    0    0 S  0.0  0.0   0:19.48 events/0                                                                                      

The only way I found to have the machine back to a normal state is a reboot... Do you know of a better way to handle this kind of situation ?

Thanks a lot.

Best regards.

--

Jérémy

This post has been answered by remzi.akyuz on Aug 3 2016
Jump to Answer
Comments
Locked Post
New comments cannot be posted to this locked post.
Post Details
Locked on Sep 9 2016
Added on Aug 1 2016
24 comments
7,030 views