Receive EVENTLIB-3-CPUHOG occasionally - What does it mean?

[Reiner Will]

Hi,

We see occasionally these EVENTLIB-3-CPUHOG messages in our log of one of our switches, and we have no idea where it comes from. Even after Google search we only found other EVENTLIB messages but not this one in the box below:

Nov 27 01:44:03.243: %EVENTLIB-3-CPUHOG: Switch 1 R0/0: cmand: undefined: 1272ms, Traceback=1#5ff4e90bb1848a3ab4ffe3d13199bbad linux-vdso:7F7B8BF000+510 c:7F73CFA000+BAAA0 c:7F73CFA000+6B148 c:7F73CFA000+6B2AC c:7F73CFA000+5F97C :400000+98AB4 :400000+98D64 evlib:7F7A17C000+8534 evlib:7F7A17C000+8DD8 orchestrator_lib:7F74EE5000+CBC0 luajit:7F7419F000+66B40
Nov 30 12:14:29.082: %EVENTLIB-3-CPUHOG: Switch 1 R0/0: cmand: undefined: 1348ms, Traceback=1#5ff4e90bb1848a3ab4ffe3d13199bbad linux-vdso:7F7B8BF000+510 c:7F73CFA000+BAAA0 c:7F73CFA000+6B148 c:7F73CFA000+6B2AC c:7F73CFA000+5F97C :400000+98AB4 :400000+98D64 evlib:7F7A17C000+8534 evlib:7F7A17C000+8DD8 orchestrator_lib:7F74EE5000+CBC0 luajit:7F7419F000+66B40
Dec 2 02:14:42.276: %EVENTLIB-3-CPUHOG: Switch 1 R0/0: cmand: undefined: 1028ms, Traceback=1#5ff4e90bb1848a3ab4ffe3d13199bbad linux-vdso:7F7B8BF000+510 c:7F73CFA000+BAAA0 c:7F73CFA000+6B148 c:7F73CFA000+6B2AC c:7F73CFA000+5F97C :400000+98AB4 :400000+98D64 evlib:7F7A17C000+8534 evlib:7F7A17C000+8DD8 orchestrator_lib:7F74EE5000+CBC0 luajit:7F7419F000+66B40
Dec 2 02:44:43.602: %EVENTLIB-3-CPUHOG: Switch 1 R0/0: cmand: undefined: 1180ms, Traceback=1#5ff4e90bb1848a3ab4ffe3d13199bbad linux-vdso:7F7B8BF000+510 c:7F73CFA000+BAAA0 c:7F73CFA000+6B148 c:7F73CFA000+6B2AC c:7F73CFA000+5F97C :400000+98AB4 :400000+98D64 evlib:7F7A17C000+8534 evlib:7F7A17C000+8DD8 orchestrator_lib:7F74EE5000+CBC0 luajit:7F7419F000+66B40
Dec 2 09:14:46.486: %EVENTLIB-3-CPUHOG: Switch 1 R0/0: cmand: undefined: 1132ms, Traceback=1#5ff4e90bb1848a3ab4ffe3d13199bbad linux-vdso:7F7B8BF000+510 c:7F73CFA000+BAAA0 c:7F73CFA000+6B148 c:7F73CFA000+6B2AC c:7F73CFA000+5F97C :400000+98AB4 :400000+98D64 evlib:7F7A17C000+8534 evlib:7F7A17C000+8DD8 orchestrator_lib:7F74EE5000+CBC0 luajit:7F7419F000+66B40

Device: C9200L-48T-4X

IOS Version 16.9.4

Any help would be appreciated.

Regards,
Reiner Will

[balaji.bandi]

is this single switch or stack ?

follow below troubleshooting tips :

https://www.cisco.com/c/en/us/support/docs/ios-nx-os-software/ios-xe-16/213549-troubleshoot-high-cpu-usage-in-catalyst.html

Also worth upgrade to latest code 17.6.X or 17.9.X and check

[Reiner Will]

It's not a stack, and the link was not helpful, sorry. I don't think the message belongs to high cpu usage, but I may be wrong. Here is the current usage:

#show processes cpu sort | ex 0.00
CPU utilization for five seconds: 6%/5%; one minute: 9%; five minutes: 9%
 PID Runtime(ms)     Invoked      uSecs   5Sec   1Min   5Min TTY Process
 214  1194314048  1765369211        676  1.35%  1.47%  1.45%   0 IP Input
 524    18764892   238971395         78  0.15%  0.06%  0.05%   0 IP SNMP
 121    68659444   829814371         82  0.07%  0.03%  0.02%   0 IOSXE-RP Punt Se
  23    70155116   550317213        127  0.07%  0.09%  0.08%   0 ARP Input

And this history output:

#sho proc cpu hist



      111          11111               11111               11111
      444444444444433333555556666644444555555555566666555550000055
  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)




      131123253223223113312123333213223421223433221221311412333211
      547697519764618958265722153047371089832311206328036562324798
  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%




      455666554465556564555544454544644554554546555645554445555565654655454455
      516155917592250004479380413195858048236250822176769810042463044164717488
  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)
                  * = maximum CPU%   # = average CPU%

RW

[Reiner Will]

No it's not a stack, just a single node.

#show processes cpu sort | ex 0.00
CPU utilization for five seconds: 6%/5%; one minute: 9%; five minutes: 9%
 PID Runtime(ms)     Invoked      uSecs   5Sec   1Min   5Min TTY Process
 214  1194314048  1765369211        676  1.35%  1.47%  1.45%   0 IP Input
 524    18764892   238971395         78  0.15%  0.06%  0.05%   0 IP SNMP
 121    68659444   829814371         82  0.07%  0.03%  0.02%   0 IOSXE-RP Punt Se
  23    70155116   550317213        127  0.07%  0.09%  0.08%   0 ARP Input

I don't think it's because of high CPU load, but I may be wrong. The history show high load peaks occasionally up to 70%. I think this is not a problem, or should not be a problem:

# sho proc cpu hist

      111          11111               11111               11111
      444444444444433333555556666644444555555555566666555550000055
  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)

      131123253223223113312123333213223421223433221221311412333211
      547697519764618958265722153047371089832311206328036562324798
  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%

     455666554465556564555544454544644554554546555645554445555565654655454455
      516155917592250004479380413195858048236250822176769810042463044164717488
  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)
                  * = maximum CPU%   # = average CPU%

Reiner

[balaji.bandi]

there may be small spikes that required some investigation- But  if that is only Log and not effecting performance - i will igore as cosmetic. when get chance upgrade to latest code as i suggested.