监控zookeeper来自网上，大家一搜就可搜到了，只是zabbix版本和zookeeper有点出入，自行修改一下就可以了。
zookeeper监控要点
系统监控 这个监控linux系统以及修改linux服务器参数即可
内存使用量 ZooKeeper应当完全运行在内存中，不能使用到SWAP。Java Heap大小不能超过可用内存。
Swap使用量 使用Swap会降低ZooKeeper的性能，设置vm.swappiness = 0
网络带宽占用 如果发现ZooKeeper性能降低关注下网络带宽占用情况和丢包情况，通常情况下ZooKeeper是20%写入80%读入
磁盘使用量 ZooKeeper数据目录使用情况需要注意
磁盘I/O ZooKeeper的磁盘写入是异步的，所以不会存在很大的I/O请求，如果ZooKeeper和其他I/O密集型服务公用应该关注下磁盘I/O情况
ZooKeeper监控
zk_avg/min/max_latency 响应一个客户端请求的时间，建议这个时间大于10个Tick就报警 平均延迟/最小延迟/最大延迟
zk_outstanding_requests 排队请求的数量，当ZooKeeper超过了它的处理能力时，这个值会增大，建议设置报警阀值为10 堆积请求数
zk_packets_received 接收到客户端请求的包数量 收包数
zk_packets_sent 发送给客户单的包数量，主要是响应和通知 发包数
zk_max_file_descriptor_count 最大允许打开的文件数，由ulimit控制 最大文件描述符数量
zk_open_file_descriptor_count 打开文件数量，当这个值大于允许值得85%时报警 打开的文件描述符数量
Mode 运行的角色，如果没有加入集群就是standalone,加入集群式follower或者leader
zk_followers leader角色才会有这个输出,集合中follower的个数。正常的值应该是集合成员的数量减1 follower数量
zk_pending_syncs leader角色才会有这个输出，pending syncs的数量 准备同步数
zk_znode_count znodes的数量 znode数量
zk_watch_count watches的数量 watch数量
Java Heap Size ZooKeeper Java进程的安装依赖包
yum install -y nc
yum install -y zabbix-sender找到zabbix-sender安装的话，可以尝试一下
yum list all|grep zabbix-sender
监控原理描述
[root@test-mq03 ~]# echo ruok|nc 127.0.0.1 2181
imok
[root@test-mq03 ~]# echo mntr|nc 127.0.0.1 2181
zk_version 3.4.10-39d3a4f269333c922ed3db283be479f9deacaa0f, built on 03/23/2017 10:13 GMT
zk_avg_latency 0
zk_max_latency 13254
zk_min_latency 0
zk_packets_received 3440389
zk_packets_sent 3502224
zk_num_alive_connections 2
zk_outstanding_requests 0
zk_server_state follower
zk_znode_count 203
zk_watch_count 100
zk_ephemerals_count 83
zk_approximate_data_size 46378
zk_open_file_descriptor_count 33
zk_max_file_descriptor_count 4096
[root@test-mq03 ~]# echo srvr|nc 127.0.0.1 2181
Zookeeper version: 3.4.10-39d3a4f269333c922ed3db283be479f9deacaa0f, built on 03/23/2017 10:13 GMT
Latency min/avg/max: 0/0/13254
Received: 3440393
Sent: 3502228
Connections: 2
Outstanding: 0
Zxid: 0x2000b2629
Mode: follower
Node count: 203zookeeper监控脚本
/etc/zabbix/script/zookeeper/check_zookeeper.py
#!/usr/bin/python
""" Check Zookeeper Cluster
zookeeper version should be newer than 3.4.x
# echo mntr|nc 127.0.0.1 2181
zk_version 3.4.6-1569965, built on 02/20/2014 09:09 GMT
zk_avg_latency 0
zk_max_latency 4
zk_min_latency 0
zk_packets_received 84467
zk_packets_sent 84466
zk_num_alive_connections 3
zk_outstanding_requests 0
zk_server_state follower
zk_znode_count 17159
zk_watch_count 2
zk_ephemerals_count 1
zk_approximate_data_size 6666471
zk_open_file_descriptor_count 29
zk_max_file_descriptor_count 102400
# echo ruok|nc 127.0.0.1 2181
imok
"""
import sys
import socket
import re
import subprocess
from StringIO import StringIO
import os
zabbix_sender = '/usr/bin/zabbix_sender'
zabbix_conf = '/etc/zabbix/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 """
data_mntr = self._send_cmd('mntr')
data_ruok = self._send_cmd('ruok')
if data_mntr:
result_mntr = self._parse(data_mntr)
if data_ruok:
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):
""" 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):
""" 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):
try:
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}' '''
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[" + 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)
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 == '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
添加zabbix-agent配置文件
/etc/zabbix/zabbix_agentd.d/check_zookeeper.conf
UserParameter=zookeeper.status[*],/usr/bin/python /etc/zabbix/script/zookeeper/check_zookeeper.py $1zabbix-web添加zookeeper模板
zbx_export_templates.xml
3.4
2018-02-02T06:22:07Z
Templates
Template ZooKeeper
Template ZooKeeper
Templates
ZooKeeper Status
-
zookeeper pid
0
zookeeper.status[all]
30
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper approximate data size
2
zookeeper.status[zk_approximate_data_size]
0
90d
365d
0
3
B
0
0
0
0
0
ZooKeeper Status
-
zookeeper average latency
2
zookeeper.status[zk_avg_latency]
0
90d
365d
0
3
tick
0
0
0
0
0
ZooKeeper Status
-
zookeeper ephemerals count
2
zookeeper.status[zk_ephemerals_count]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper leader's followers
2
zookeeper.status[zk_followers]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper max file descriptor count
2
zookeeper.status[zk_max_file_descriptor_count]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper max latency
2
zookeeper.status[zk_max_latency]
0
90d
365d
0
3
tick
0
0
0
0
0
ZooKeeper Status
-
zookeeper min latency
2
zookeeper.status[zk_min_latency]
0
90d
365d
0
3
tick
0
0
0
0
0
ZooKeeper Status
-
zookeeper alive connections
2
zookeeper.status[zk_num_alive_connections]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper opened file descriptor count
2
zookeeper.status[zk_open_file_descriptor_count]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper outstanding requests
2
zookeeper.status[zk_outstanding_requests]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper packages received
2
zookeeper.status[zk_packets_received]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper packages sent
2
zookeeper.status[zk_packets_sent]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper leader's pending syncs
2
zookeeper.status[zk_pending_syncs]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper response checking
2
zookeeper.status[zk_server_ruok]
0
90d
0
0
1
0
0
0
0
0
ZooKeeper Status
-
zookeeper state role
2
zookeeper.status[zk_server_state]
0
90d
0
0
1
0
0
0
0
0
ZooKeeper Status
-
zookeeper leader's synced followers
2
zookeeper.status[zk_synced_followers]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper version
2
zookeeper.status[zk_version]
0
90d
0
0
1
0
0
0
0
0
ZooKeeper Status
-
zookeeper watches count
2
zookeeper.status[zk_watch_count]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
-
zookeeper znodes count
2
zookeeper.status[zk_znode_count]
0
90d
365d
0
3
0
0
0
0
0
ZooKeeper Status
{Template ZooKeeper:zookeeper.status[zk_outstanding_requests].last()}>10
0
big outstanding requests number
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[zk_pending_syncs].last()}>10
0
big pending syncs
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[zk_avg_latency].last()}>10
0
large average latency
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[zk_open_file_descriptor_count].last()} > {Template ZooKeeper:zookeeper.status[zk_max_file_descriptor_count].last()}*0.85
0
large file descriptor used
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[zk_server_ruok].str(imok)}<>1
0
zookeeper is abnormal
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[all].last()}=0
0
zookeeper is not running
0
0
4
0
0
{Template ZooKeeper:zookeeper.status[zk_server_state].abschange()}>0
0
zookeeper state role has been changed
0
0
2
0
0
ZooKeeper Alive Connections
900
200
0.0000
100.0000
1
1
1
1
0
0.0000
0.0000
0
0
0
0
0
0
00DDDD
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_num_alive_connections]
ZooKeeper Data Size
900
200
0.0000
100.0000
1
1
1
1
0
0.0000
0.0000
0
0
0
0
0
0
00C800
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_approximate_data_size]
ZooKeeper Latency
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
2
00C800
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_avg_latency]
1
2
C80000
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_min_latency]
2
2
0000C8
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_max_latency]
ZooKeeper Packages Received/Sent
900
200
0.0000
100.0000
1
1
1
1
0
0.0000
0.0000
0
0
0
0
0
0
FF3333
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_packets_sent]
1
0
00C800
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_packets_received]
ZooKeeper Watches Count
900
200
0.0000
100.0000
1
1
1
1
0
0.0000
0.0000
0
0
0
0
0
0
660066
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_watch_count]
ZooKeeper Znodes Count
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
1
FFCCFF
0
2
0
-
Template ZooKeeper
zookeeper.status[zk_znode_count]
上面导出的xml有个地方不太明白，<> 不等号 变成了≷>，官网并没有说明这种用法。
重启zabbix-agent
service zabbix-agent restart由于这个是使用zabbix-sender发送，在服务器端使用zabbix-get获取不了数据，不知道网友是否可以使用zabbix-get获取数据呢？
