Zabbix监控zookeeper
近期需求增加zookeeper监控到zabbix , 经过一番搜索, 确定通过 agentd端运行脚本的方式采集数据,传送给 zabbix-server端.
Zabbix_sender方式发送
将这些监控数据一次性使用zabbix_sender全部发送给zabbix.将监控项目汇集成一个字典，然后遍历这个字典，将字典中的key:value对通过zabbix_sender的-k和-o参数指定发送出去.
感谢博文：https://blog.csdn.net/reblue520/article/details/52352689
基本上参考了这篇博文的方法及python 脚本 . 模版文档.
经过修改及仔细查看, 该博文中的xml模版文件,发现 server 通过 调用 zookeeper.status[alive] 这个key值,来获取pid, 同时出发sender 发送给server 数据 . 无需配合计划任务, 可能是我初学python , 没有理解好用途. 总之没成功,但是经过修改后,可以 正确获取数据.
下面为修改后的 python代码
#!/usr/bin/python
"""{'zk_followers': 0,
'zk_outstanding_requests': 0,
'zk_approximate_data_size': 890971,
'zk_packets_sent': 5818488,
'zk_pending_syncs': 0,
'zk_avg_latency': 0,
'zk_version': '3.4.6-1569965, built on 02/20/2014 09:09 GMT',
'zk_watch_count': 1364,
'zk_packets_received': 5797681,
'zk_open_file_descriptor_count': 46,
'zk_server_ruok': 'imok',
'zk_server_state': 'follower',
'zk_synced_followers': 0,
'zk_max_latency': 400,
'zk_num_alive_connections': 18,
'zk_min_latency': 0,
'zk_ephemerals_count': 1112,
'zk_znode_count': 2207,
'zk_max_file_descriptor_count': 4096}
"""
import sys
import socket
import re
import subprocess
from StringIO import StringIO
import os
zabbix_sender = '/usr/local/zabbix/bin/zabbix_sender'
zabbix_conf = '/usr/local/zabbix/conf/zabbix_agentd.conf'
send_to_zabbix = 1
# get zookeeper server status
class ZooKeeperServer(object):
def __init__(self, host='localhost', port='2181', timeout=1):
self._address = (host, int(port))
self._timeout = timeout
self._result = {}
def _create_socket(self):
return socket.socket()
def _send_cmd(self, cmd):
""" Send a 4letter word command to the server """
s = self._create_socket()
s.settimeout(self._timeout)
s.connect(self._address)
s.send(cmd)
data = s.recv(2048)
s.close()
return data
def get_stats(self):
""" Get ZooKeeper server stats as a map """
"""zk_version 3.4.6-1569965, built on 02/20/2014 09:09 GMT
zk_avg_latency 0
zk_max_latency 94
zk_min_latency 0
zk_packets_received 1267904
zk_packets_sent 1317835
zk_num_alive_connections 12
zk_outstanding_requests 0
zk_server_state follower
zk_znode_count 1684
zk_watch_count 2757
zk_ephemerals_count 899
zk_approximate_data_size 728074
zk_open_file_descriptor_count 41
zk_max_file_descriptor_count 4096
"""
data_mntr = self._send_cmd('mntr')
data_ruok = self._send_cmd('ruok')
if data_mntr:
result_mntr = self._parse(data_mntr)
if data_ruok:
# {'zk_server_ruok': 'imok'}
result_ruok = self._parse_ruok(data_ruok)
self._result = dict(result_mntr.items() + result_ruok.items())
if not self._result.has_key('zk_followers') and not self._result.has_key('zk_synced_followers') and not self._result.has_key('zk_pending_syncs'):
# #### the tree metrics only exposed on leader role zookeeper server, we just set the followers' to 0
leader_only = {'zk_followers':0,'zk_synced_followers':0,'zk_pending_syncs':0}
self._result = dict(result_mntr.items() + result_ruok.items() + leader_only.items())
return self._result
def _parse(self, data):
"""
:param data: zk_outstanding_requests 0 zk_approximate_data_size 653931
:return: {'zk_outstanding_requests': '0', 'zk_approximate_data_size': '653931',}
"""
""" Parse the output from the 'mntr' 4letter word command """
h = StringIO(data)
result = {}
for line in h.readlines():
try:
key, value = self._parse_line(line)
result[key] = value
except ValueError:
pass # ignore broken lines
return result
def _parse_ruok(self, data):
"""
:param data: imok
:return: {'zk_server_ruok': 'imok'}
"""
""" Parse the output from the 'ruok' 4letter word command """
h = StringIO(data)
result = {}
ruok = h.readline()
if ruok:
result['zk_server_ruok'] = ruok
return result
def _parse_line(self, line):
# zk_watch_count 1482
try:
# zk_max_file_descriptor_count 65535
key, value = map(str.strip, line.split('\t'))
except ValueError:
raise ValueError('Found invalid line: %s' % line)
if not key:
raise ValueError('The key is mandatory and should not be empty')
try:
value = int(value)
except (TypeError, ValueError):
pass
return key, value
def get_pid(self):
# ps -ef|grep java|grep zookeeper|awk '{print $2}'
pidarg = '''ps -ef|grep java|grep zookeeper|grep -v grep|awk '{print $2}' ''' # 31022
pidout = subprocess.Popen(pidarg, shell=True, stdout=subprocess.PIPE)
pid = pidout.stdout.readline().strip('\n')
return pid
def send_to_zabbix(self, metric):
# key = zookeeper.status[zk_max_file_descriptor_count]
key = "zookeeper.status[" + metric + "]"
if send_to_zabbix > 0:
# print key + ":" + str(self._result[metric])
try:
subprocess.call([zabbix_sender, "-c", zabbix_conf, "-k", key, "-o", str(self._result[metric])], stdout=FNULL, stderr=FNULL, shell=False)
#print "send zabbix success"
except OSError, detail:
print "Something went wrong while exectuting zabbix_sender : ", detail
else:
print "Simulation: the following command would be execucted :\n", zabbix_sender, "-c", zabbix_conf, "-k", key, "-o", self._result[metric], "\n"
def usage():
"""Display program usage"""
print "\nUsage : ", sys.argv[0], " alive|all"
print "Modes : \n\talive : Return pid of running zookeeper\n\tall : Send zookeeper stats as well"
sys.exit(1)
accepted_modes = ['alive', 'all']
if len(sys.argv) == 2 and sys.argv[1] in accepted_modes:
mode = sys.argv[1]
else:
usage()
zk = ZooKeeperServer()
# print zk.get_stats()
pid = zk.get_pid()
if pid != "" and mode == 'alive':
zk.get_stats()
# print zk._result
FNULL = open(os.devnull, 'w')
for key in zk._result:
zk.send_to_zabbix(key)
FNULL.close()
print pid
下面为原代码的最后部分,同时贴出,对比下逻辑, 如果有我的方式有问题, 请留言指正, 新手感谢 .
if pid != "" and mode == 'all': zk.get_stats() # print zk._result FNULL = open(os.devnull, 'w') for key in zk._result: zk.send_to_zabbix(key) FNULL.close() print pid elif pid != "" and mode == "alive": print pid else: print 0
Zabbix_agentd获取
参考了上一种方式中的python脚本, 经过修改, 所有数据都通过agentd的方式获取数据.
一下为修改后的python脚本, 个人感觉shell实现很简单,但是 作为一个python初学者, 还是自己修改了下, 功能实现了.
#!/usr/bin/python
#monitor zookeeper
#by mo
import sys
import socket
import re
import subprocess
from StringIO import StringIO
import os
class ZooKeeperServer(object):
def __init__(self, host='localhost', port='2181', timeout=1):
self._address = (host, int(port))
self._timeout = timeout
self._result = {}
def _create_socket(self):
return socket.socket()
def _send_cmd(self, cmd):
""" Send a 4letter word command to the server """
s = self._create_socket()
s.settimeout(self._timeout)
s.connect(self._address)
s.send(cmd)
data = s.recv(2048)
s.close()
return data
def get_pid(self):
# ps -ef|grep java|grep zookeeper|awk '{print $2}'
pidarg = '''ps -ef|grep java|grep zookeeper|grep -v grep|awk '{print $2}' ''' # 31022
pidout = subprocess.Popen(pidarg, shell=True, stdout=subprocess.PIPE)
pid = pidout.stdout.readline().strip('\n')
return pid
def _parse(self, data):
"""
:param data: zk_outstanding_requests 0 zk_approximate_data_size 653931
:return: {'zk_outstanding_requests': '0', 'zk_approximate_data_size': '653931',}
"""
""" Parse the output from the 'mntr' 4letter word command """
h = StringIO(data)
result = {}
for line in h.readlines():
try:
key, value = self._parse_line(line)
result[key] = value
except ValueError:
pass # ignore broken lines
return result
def _parse_line(self, line):
# zk_watch_count 1482
try:
# zk_max_file_descriptor_count 65535
key, value = map(str.strip, line.split('\t'))
except ValueError:
raise ValueError('Found invalid line: %s' % line)
if not key:
raise ValueError('The key is mandatory and should not be empty')
try:
value = int(value)
except (TypeError, ValueError):
pass
return key, value
def get_stats(self):
""" Get ZooKeeper server stats as a map """
"""zk_version 3.4.6-1569965, built on 02/20/2014 09:09 GMT
zk_avg_latency 0
zk_max_latency 94
zk_min_latency 0
zk_packets_received 1267904
zk_packets_sent 1317835
zk_num_alive_connections 12
zk_outstanding_requests 0
zk_server_state follower
zk_znode_count 1684
zk_watch_count 2757
zk_ephemerals_count 899
zk_approximate_data_size 728074
zk_open_file_descriptor_count 41
zk_max_file_descriptor_count 4096
"""
data_mntr = self._send_cmd('mntr')
result_mntr = self._parse(data_mntr)
self._result = dict(result_mntr.items())
return self._result
zk = ZooKeeperServer()
pid = zk.get_pid()
accepted_modes = ['zk_server_ruok']
if sys.argv[1] in accepted_modes:
cmd = sys.argv[1]
data = zk._send_cmd(cmd)
print(data)
elif sys.argv[1] == 'alive':
print(pid)
elif sys.argv[1] == 'mntr':
cmd = sys.argv[1]
data = zk._send_cmd(cmd)
print(data)
else:
zk.get_stats()
key = sys.argv[1]
print(zk._result[key])
模版
参考博文中的模版
3.0 2017-12-11T08:02:58Z Zabbix servers Zookeeper Zookeeper Zabbix servers ZooKeeper Status zookeeper pid 2 0 zookeeper.status[alive] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper approximate data size 2 0 zookeeper.status[zk_approximate_data_size] 0 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper average latency 2 0 zookeeper.status[zk_avg_latency] 0 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper ephemerals count 2 0 zookeeper.status[zk_ephemerals_count] 0 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper leader's followers 2 0 zookeeper.status[zk_followers] 0 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper max file descriptor count 2 0 zookeeper.status[zk_max_file_descriptor_count] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper max latency 2 0 zookeeper.status[zk_max_latency] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper min latency 2 0 zookeeper.status[zk_min_latency] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper alive connections 2 0 zookeeper.status[zk_num_alive_connections] 0 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper opened file descriptor count 2 0 zookeeper.status[zk_open_file_descriptor_count] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper outstanding requests 2 0 zookeeper.status[zk_outstanding_requests] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper packages received 2 0 zookeeper.status[zk_packets_received] 10 90 365 0 3 0 0 0 0 1 0 0 收包数量 0 ZooKeeper Status zookeeper packages sent 2 0 zookeeper.status[zk_packets_sent] 10 90 365 0 3 0 0 0 0 1 0 0 发包数据量 0 ZooKeeper Status zookeeper leader's pending syncs 2 0 zookeeper.status[zk_pending_syncs] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper response checking 2 0 zookeeper.status[zk_server_ruok] 10 90 0 0 1 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper state role 2 0 zookeeper.status[zk_server_state] 10 90 0 0 1 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper leader's synced followers 2 0 zookeeper.status[zk_synced_followers] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper version 2 0 zookeeper.status[zk_version] 10 90 0 0 1 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper watches count 2 0 zookeeper.status[zk_watch_count] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status zookeeper znodes count 2 0 zookeeper.status[zk_znode_count] 10 90 365 0 3 0 0 0 0 1 0 0 0 ZooKeeper Status {Zookeeper:zookeeper.status[zk_outstanding_requests].last()}>10 big outstanding requests number 0 0 0 {Zookeeper:zookeeper.status[zk_pending_syncs].last()}>10 big pending syncs 0 0 0 {Zookeeper:zookeeper.status[zk_avg_latency].last()}>10 large average latency 0 0 0 {Zookeeper:zookeeper.status[zk_open_file_descriptor_count].last()} > {Zookeeper:zookeeper.status[zk_max_file_descriptor_count].last()}*0.85 large file descriptor used 0 0 0 {Zookeeper:zookeeper.status[zk_server_ruok].str(imok)}<>1 zookeeper is abnormal 0 4 0 {Zookeeper:zookeeper.status[alive].last()}=0 zookeeper is not running 0 4 0 {Zookeeper:zookeeper.status[zk_server_state].abschange()}>0 zookeeper state role has been changed 0 1 0 ZooKeeper Alive Connections 900 200 0.0000 100.0000 1 1 0 1 0 0.0000 0.0000 0 0 0 0 0 0 1A7C11 0 2 0 Zookeeper zookeeper.status[zk_num_alive_connections] ZooKeeper Latency 900 200 0.0000 100.0000 1 1 0 1 0 0.0000 0.0000 0 0 0 0 0 0 1A7C11 0 2 0 Zookeeper zookeeper.status[zk_avg_latency]
Zabbix_agentd配置
UserParameter=zookeeper.status[*],/usr/bin/python /usr/local/zabbix/scripts/zookeeper_monitor.py $1
###
注意: 给脚本执行权限