0

I'm tinkering with an Embedded Linux device that is utilizing an ARM6 CPU (single core) that seems to be experiencing high CPU Load averages.

This is what I am seeing after 10 minutes of being powered on

Load average: 5.00 5.00 4.84 1/58 669

The 1 process that is running (from the 58) is top. Most everything else is sleeping.

    Mem: 52064K used, 6788K free, 0K shrd, 0K buff, 25916K cached
CPU:   0% usr   0% sys   0% nic  98% idle   0% io   0% irq   0% sirq
Load average: 5.00 5.00 4.85 1/57 669
  PID  PPID USER     STAT   VSZ %VSZ CPU %CPU COMMAND
  653   652 root     R     2964   5%   0   1% top
  552   432 root     S     5396   9%   0   0% ./lld
  650   546 root     S     4636   8%   0   0% sshd: root@ttyp0
  610   552 root     S    67600 114%   0   0% /croc/cr715 --root-dir /croc/
  605   552 root     S    16080  27%   0   0% /croc/media_daemon --log -1 --rec 0 --play 0
  546     1 root     S     4636   8%   0   0% /usr/sbin/sshd
  432     1 root     S     3812   6%   0   0% {rcS} /bin/sh /etc/init.d/rcS
  652   650 root     S     3284   6%   0   0% -bash
    1     0 root     S     2960   5%   0   0% init
  635   610 99       S     2016   3%   0   0% dns-proxy
  431     2 root     SWN      0   0%   0   0% [jffs2_gcd_mtd7]
  123     2 root     SW       0   0%   0   0% [pdflush]
    5     2 root     SW<      0   0%   0   0% [khelper]
  396     2 root     SW<      0   0%   0   0% [SPI]
    4     2 root     SW<      0   0%   0   0% [events/0]
  426     2 root     SW<      0   0%   0   0% [croc715fb]
  524     2 root     DW       0   0%   0   0% [hwthread]
    2     0 root     SW<      0   0%   0   0% [kthreadd]
    3     2 root     SW<      0   0%   0   0% [ksoftirqd/0]
   17     2 root     SW       0   0%   0   0% [bcmring_ddrvpmp]
   45     2 root     SW       0   0%   0   0% [knllog]
   76     2 root     SW<      0   0%   0   0% [kblockd/0]
   79     2 root     SW       0   0%   0   0% [perfpoll]
   80     2 root     SW<      0   0%   0   0% [hosticp]
   88     2 root     SW<      0   0%   0   0% [ksuspend_usbd]
   94     2 root     SW<      0   0%   0   0% [khubd]
   98     2 root     SW<      0   0%   0   0% [kmmcd]
  104     2 root     SW<      0   0%   0   0% [btaddconn]
  105     2 root     SW<      0   0%   0   0% [btdelconn]
  122     2 root     SW       0   0%   0   0% [pdflush]
  124     2 root     SW<      0   0%   0   0% [kswapd0]
  125     2 root     SW<      0   0%   0   0% [aio/0]
  126     2 root     SW<      0   0%   0   0% [nfsiod]
  127     2 root     SW       0   0%   0   0% [crypto]
  128     2 root     SW       0   0%   0   0% [crypto_ret]
  334     2 root     SW<      0   0%   0   0% [GE_THREAD]
  338     2 root     SW<      0   0%   0   0% [vpm_power_queue]
  369     2 root     SW<      0   0%   0   0% [mtdblockd]
  410     2 root     SWN      0   0%   0   0% [keypad: hook po]
  420     2 root     SW<      0   0%   0   0% [krfcommd]
  421     2 root     SW<      0   0%   0   0% [rpciod/0]
  525     2 root     DW       0   0%   0   0% [hausioctl]
  526     2 root     SW<      0   0%   0   0% [frameProfiler]

There is a hwthread and some other processes that are in a DW state. Could the items that are DW be the culprits?

  • Could it be thrashing because pid 610 is using so much memory? – RonJohn Jun 6 at 18:39
  • This could come from important IO as well, try yo look at iotop. – Kiwy Jun 7 at 12:22
  • @RonJohn I'll take a look more in it as thrashing and see. – Onyxdragun Jun 7 at 15:41
  • @Kiwy I did not know about iotop, I'll take a look and see if i can compile it for the target. Thanks – Onyxdragun Jun 7 at 15:42
  • Try reading this but be sure to read the comment at the end ... – Murray Jensen Jun 9 at 12:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.