Anomalous peaks of CPU consumption in debian


Warning: count(): Parameter must be an array or an object that implements Countable in /home/styllloz/code-flow.club/qa-theme/donut-theme/qa-donut-layer.php on line 274
0 like 0 dislike
16 views
The server has debian lenny with kernel 2.6.26-2-amd64. The problem is that I can't diagnose that periodically causes it to be 4%, so that it becomes inaccessible from the outside. Does not respond even on ARP. After a certain period of time it "allows" on their own.

Graficki (according to /proc/stat, 3rd figure) show that some kind of system consumes (by the way, that this is what ONOS? core?):

Graficki (large, therefore a link): CPU user/system | CPU system/io/irq | load avg for 1 minute and 5 minutes

As I said, the network the machine is unavailable at this time. So at this point, the list of processes to look impossible. Tried to collect and periodically analyze the old and ps', the process suddenly increases the overall TIME after blunt missing.

Plz tell me what this could be or at least remotely to diagnose/where to dig?
by | 16 views

3 Answers

0 like 0 dislike
top-b > file
by
0 like 0 dislike
dmesg|syslog at the time lags. Possible problems with the iron.
by
0 like 0 dislike
Somewhere I've seen it only there a debian was like. A problem closer to hardware I guess. Iron, wood, core. And what a percent is? You can do a dmesg attached stick. :)
by

Related questions

0 like 0 dislike
7 answers
0 like 0 dislike
4 answers
asked May 10, 2019 by grinch_asd
0 like 0 dislike
3 answers
0 like 0 dislike
2 answers
asked May 20, 2019 by PavelBelyaev
0 like 0 dislike
2 answers
110,608 questions
257,186 answers
0 comments
22,471 users