Le dispositif SD-WAN Gateway est une architecture de pipeline qui traite les rafales de trafic et des rafales de CPU élevées sont attendues. La passerelle doit être surveillée pour les cœurs de CPU qui tournent à 100 %.

Vous trouverez ci-dessous un exemple de script Python pour la surveillance de l'utilisation du CPU :

#! /usr/bin/env python
"""
Check for CPUs spinning at 100%
"""
import re
import collections
import time
import sys
import json
import os
import subprocess
re_cpu = re.compile(r"^cpu\d+\s")
CPUStat = collections.namedtuple('CPUStat', ['user', 'nice', 'sys', 'idle'])
def get_stats():
        stats = open("/proc/stat").readlines()
        ret = {}
        for s in stats:
                if not re_cpu.search(s): continue
                s = s.split()
                ret[s[0]] = CPUStat(*[ int(v) for v in s[1:5]])
        return ret
def verify_dpdk_support():
    if os.path.isfile('/opt/vc/etc/dpdk.json'):
       with open("/opt/vc/etc/dpdk.json") as data:
           d=json.loads((data.read()))
       if "status" in  d.keys():
           return True if d['status'] is "Supported" else False
    else:
       return False
def another_verify_dpdk_support():
    if os.path.isfile('/opt/vc/bin/debug.py'):
        f=subprocess.check_output(["/opt/vc/bin/debug.py","--dpdk_ports_dump"])
        x=[r.split() for r in f.split('\n')]
	if len(x) <= 1:
		return False
	else:
                return True
    else:
	return False
dpdk_status=verify_dpdk_support() or another_verify_dpdk_support()
if __name__ == "__main__":
        try:
                stat1 = get_stats()
                time.sleep(3)
                stat2 = get_stats()
        except:
                print "UKNOWN - failed to get CPU stat: %s" % str(sys.exc_info()[1])
                sys.exit(3)
        busy_cpu_set = [ cpu for cpu in stat1 if (stat2[cpu].idle - stat1[cpu].idle)==0 ]
        if not busy_cpu_set:
                        print "OK - no spinning CPUs"
                        sys.exit(0)
        if dpdk_status == True:
           if "cpu1" in busy_cpu_set and len(busy_cpu_set) == 1:
                        print "OK - no spinning CPUs"
                        sys.exit(0)
           elif "cpu1" in busy_cpu_set:
                        busy_cpu_set.remove('cpu1')
                        print "CRITICAL - %s is at 100%%" % (",".join(busy_cpu_set))
                        sys.exit(2)
           else:
                        print busy_cpu_set,1
                        print "CRITICAL - %s is at 100%%" % (",".join(busy_cpu_set))
                        sys.exit(2)
        else:
                        print "CRITICAL - %s is at 100%%" % (",".join(busy_cpu_set))
                        sys.exit(2)