Description

This article describes the commands to check the CPU utilization of a Satellite device from both the Aggregation and Satellite device. It explains how to verify if LCMD is reporting the correct CPU utilization to the Aggregation Device (AD).


Symptoms

In the Junos Fusion Environment, an LCMD daemon similar to chassisd is responsible for managing FRUs. It monitors and reports environmental details of the satellite devices; LCMD is responsible for reporting CPU utilization of the Satellite device to the Aggregation Device (AD).


 

Solution

 

From the AD, run the following command to check the CPU Utilization of a  Satellite Node

Step 1: To view the CPU utilization of a particular satellite device : - 

show chassis routing-engine satellite slot-id <>

Example :

labroot@AD> show chassis routing-engine satellite slot-id 202
Routing Engine status:
Slot 202:
Temperature 50 degrees C / 122 degrees F
CPU temperature 50 degrees C / 122 degrees F
DRAM 3619
Memory utilization 8 percent
CPU utilization:
User 5 percent
Background 0 percent
Kernel 2 percent
Interrupt 0 percent
Idle 94 percent
Model QFX5100-96S-8Q
Serial ID VB3715060116
Start time 2016-09-28 20:54:28 UTC
Uptime 7 days, 18 hours, 44 minutes, 6 seconds
Last reboot reason Software Reset
Load averages: 1 minute 5 minute 15 minute
0.14 0.16 0.20

Step 2.  To view the CPU stats by login into the Satellite Device, use the following method:

Log in to the respective Satellite Device:

labroot@AD> request chassis satellite login fpc-slot 202
Warning: Permanently added '172.16.0.202' (ECDSA) to the list of known hosts.

Last login: Thu Oct 6 15:38:53 2016 from 172.16.255.1

sd202:~$
sd202:~$ cli <<< press enter twice


> d localhost

localhost# show lcmd sys_stat
{
"sys_s": {
         "krn_ut": "1.30", <<<<<< Kernel
         "up_t": "672529",
         "id_ut": "93.90", <<<<<< Idle
         "bkg_ut": "0.00", <<<<<< Background
         "bt_t": "1475096069",
         "re_te": 50,
         "usr_ut": "4.90", <<<<<< User
         "buf_ut": "7.66", <<<<<< Memory utilization
         "in_te": 50,
         "av_rn": [
                  "0.27",
                  "0.20",
                  "0.21"
                       ],
         "int_ut": "0.00" <<<<<< Interrupt
        }
}

[Press Ctrl+c to exit]

Here are other commands that can be used to check the real time CPU utilization on the satellite device:

  • top : This command will provide real time cpu & memory utilization per ~3 seconds.
  • sar -u 2 : This command will display average CPU utilization every seconds till the time command is aborted.
  • sar -u 2 5 : This command will display average cpu utilization every 2 sounds for 5 such occurrence.
  • mpstat –P All : This command will display cpu utilization of individual physical CPU’s and average of all CPU.
  • mpstat -P ALL 2 5 : This command will display same output every 2 seconds for 5 times.

Example : 

sd202:~$ mpstat -P ALL
Linux 3.10.62-ltsi-WR6.0.0.21_standard (sd202) 10/06/16 _x86_64_ (4 CPU)

16:44:02 CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
16:44:02 all 4.21 0.00 1.47 0.03 0.00 0.00 0.00 0.00 0.00 94.29
16:44:02 0 5.37 0.00 1.62 0.05 0.00 0.01 0.00 0.00 0.00 92.96
16:44:02 1 2.06 0.00 1.28 0.01 0.00 0.00 0.00 0.00 0.00 96.66
16:44:02 2 5.51 0.00 1.56 0.06 0.00 0.00 0.00 0.00 0.00 92.86
16:44:02 3 3.94 0.00 1.40 0.00 0.00 0.00 0.00 0.00 0.00 94.66