09-22-2015 10:34 AM - edited 03-08-2019 01:54 AM
When I check the CPU utilization on my cisco 3750,this is what I see (Following graphs) I am confused, when I check the processor utilization for 5 min it is less 6% but it jumps up to 90 % in last 72 hours. Is this consider as high CPU utilization ?
11111
555555555555666665555566666666665555555555555556666677777555
100
90
80
70
60
50
40
30
20 *****
10 **********************************************************
0....5....1....1....2....2....3....3....4....4....5....5....6
0 5 0 5 0 5 0 5 0 5 0
CPU% per second (last 60 seconds)
1111111111111111111111 1311111111111111111111111111111111111
613666136677285257645677216186666657687576376763766677776535
100
90
80
70
60
50
40
30 *
20 * *** **** ** *** ** ** * ************** **** **********
10 ##########################################################
0....5....1....1....2....2....3....3....4....4....5....5....6
0 5 0 5 0 5 0 5 0 5 0
CPU% per minute (last 60 minutes)
* = maximum CPU% # = average CPU%
100
90 *
80 *
70 * * * * *
60 * * * * * * ** * * * ** * * ** * *
50 * * *** * ** * *** ** *** * *** *** ** * ** ** * * * **** *
40 ************** ************** ******** ************** ************ **
30 **********************************************************************
20 **********************************************************************
10 ######################################################################
0....5....1....1....2....2....3....3....4....4....5....5....6....6....7..
0 5 0 5 0 5 0 5 0 5 0 5 0
CPU% per hour (last 72 hours)
s01#show processes cpu sorted
CPU utilization for five seconds: 5%/0%; one minute: 6%; five minutes: 6%
PID Runtime(ms) Invoked uSecs 5Sec 1Min 5Min TTY Process
s01#show processes cpu extended
################################################################################
Global Statistics
-----------------
5 sec CPU util 5%/0% Timestamp 7w1d
Queue Statistics
----------------
Exec Count Total CPU Response Time Queue Length
(avg/max) (avg/max)
Critical 1 0 0/0 1/1
High 365 0 0/0 1/3
Normal 1520 8 0/8 2/11
Low 8 0 0/0 1/1
Common Process Information
-------------------------------
PID Name Prio Style
-------------------------------
167 Hulc LED Process H New
CPU Intensive processes
-------------------------------------------------------------------------------
PID Total Exec Quant Burst Burst size Schedcall Schedcall
CPUms Count avg/max Count avg/max(ms) Count Per avg/max
-------------------------------------------------------------------------------
Priority Suspends
------------------------------------
PID Exec Count Prio-Susps
------------------------------------
167 153 28
Latencies
-------------------------
PID Exec Count Latency
avg/max
-------------------------
09-22-2015 10:56 AM
Hi,
The CPU utilisaiton for the 72 hour graph is a little different from the per second graph in that it shows the average and the maximum utilisation. If you notice, while the maximum went to 90% the average is still showing up to 10%.
You can see CPU spikes for all sorts of reasons e.g., CLI output, SNMP processing etc., and so this is probably not worrying.
I just checked against a switch in my lab that's doing next to nothing and it also shows 90% maximum utilisation.
Regards
Discover and save your favorite ideas. Come back to expert answers, step-by-step guides, recent topics, and more.
New here? Get started with these tips. How to use Community New member guide