使用zabbix监控磁盘是否只读

由于环境上主机资源紧张，vm对资源争抢严重，导致时常会出现文件系统只读的情况。

1. 在zabbix-agent上：

mkdir -p /usr/local/zabbix/scripts
cd /usr/local/zabbix/scripts
cat >> disk_health_check.py <<EOF
#!/usr/bin/python
# -*- coding: utf-8 -*-
#磁盘只读检测脚本正常0，异常1
import time
try:
    fileDisk = open ( '/usr/local/zabbix/scripts/disk_health_check.log', 'w' )
    old = str(time.time())
    fileDisk.write(old)
    fileDisk = open ( '/usr/local/zabbix/scripts/disk_health_check.log' )
    new=fileDisk.read()
    if (old==new):
        print '0'
    else:
        print '1'
    fileDisk.close()
except:
    print '1'
EOF
chmod +x disk_health_check.py
cd /etc/zabbix/zabbix_agentd.d/
echo "UserParameter=disk.health.check,/usr/bin/python /usr/local/zabbix/scripts/disk_health_check.py" > disk.conf
chown -R zabbix:zabbix /usr/local/zabbix/
sed -i "s/SELINUX=enforcing/SELINUX=disabled/g" /etc/sysconfig/selinux
sed -i "s/SELINUX=enforcing/SELINUX=disabled/g" /etc/selinux/config
setenforce 0
systemctl restart zabbix-agent

2. 把下面的模板在zabbix上面导入（配置-模板-导入）：

<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
    <version>4.2</version>
    <date>2019-05-21T02:13:55Z</date>
    <groups>
        <group>
            <name>Template-Hardware</name>
        </group>
    </groups>
    <templates>
        <template>
            <template>DiskHealth-Check</template>
            <name>DiskHealth-Check</name>
            <description>磁盘写入输出状态0正常，1异常</description>
            <groups>
                <group>
                    <name>Template-Hardware</name>
                </group>
            </groups>
            <applications>
                <application>
                    <name>diskHealth</name>
                </application>
            </applications>
            <items>
                <item>
                    <name>文件系统read-only检查</name>
                    <type>0</type>
                    <snmp_community/>
                    <snmp_oid/>
                    <key>disk.health.check</key>
                    <delay>120</delay>
                    <history>90d</history>
                    <trends>365d</trends>
                    <status>0</status>
                    <value_type>3</value_type>
                    <allowed_hosts/>
                    <units/>
                    <snmpv3_contextname/>
                    <snmpv3_securityname/>
                    <snmpv3_securitylevel>0</snmpv3_securitylevel>
                    <snmpv3_authprotocol>0</snmpv3_authprotocol>
                    <snmpv3_authpassphrase/>
                    <snmpv3_privprotocol>0</snmpv3_privprotocol>
                    <snmpv3_privpassphrase/>
                    <params/>
                    <ipmi_sensor/>
                    <authtype>0</authtype>
                    <username/>
                    <password/>
                    <publickey/>
                    <privatekey/>
                    <port/>
                    <description/>
                    <inventory_link>0</inventory_link>
                    <applications>
                        <application>
                            <name>diskHealth</name>
                        </application>
                    </applications>
                    <valuemap/>
                    <logtimefmt/>
                    <preprocessing/>
                    <jmx_endpoint/>
                    <timeout>3s</timeout>
                    <url/>
                    <query_fields/>
                    <posts/>
                    <status_codes>200</status_codes>
                    <follow_redirects>1</follow_redirects>
                    <post_type>0</post_type>
                    <http_proxy/>
                    <headers/>
                    <retrieve_mode>0</retrieve_mode>
                    <request_method>0</request_method>
                    <output_format>0</output_format>
                    <allow_traps>0</allow_traps>
                    <ssl_cert_file/>
                    <ssl_key_file/>
                    <ssl_key_password/>
                    <verify_peer>0</verify_peer>
                    <verify_host>0</verify_host>
                    <master_item/>
                </item>
            </items>
            <discovery_rules/>
            <httptests/>
            <macros/>
            <templates/>
            <screens/>
            <tags/>
        </template>
    </templates>
    <triggers>
        <trigger>
            <expression>{DiskHealth-Check:disk.health.check.count(#2,1,&quot;eq&quot;)}&gt;1</expression>
            <recovery_mode>0</recovery_mode>
            <recovery_expression/>
            <name>文件系统read-only</name>
            <correlation_mode>0</correlation_mode>
            <correlation_tag/>
            <url/>
            <status>0</status>
            <priority>5</priority>
            <description>2次内触发器等于1的次数大于1（等于2）次就会告警，判断两次都异常即告警</description>
            <type>0</type>
            <manual_close>0</manual_close>
            <dependencies/>
            <tags/>
        </trigger>
    </triggers>
    <graphs>
        <graph>
            <name>文件系统read-only检查</name>
            <width>900</width>
            <height>200</height>
            <yaxismin>0.0000</yaxismin>
            <yaxismax>100.0000</yaxismax>
            <show_work_period>1</show_work_period>
            <show_triggers>1</show_triggers>
            <type>0</type>
            <show_legend>1</show_legend>
            <show_3d>0</show_3d>
            <percent_left>0.0000</percent_left>
            <percent_right>0.0000</percent_right>
            <ymin_type_1>0</ymin_type_1>
            <ymax_type_1>0</ymax_type_1>
            <ymin_item_1>0</ymin_item_1>
            <ymax_item_1>0</ymax_item_1>
            <graph_items>
                <graph_item>
                    <sortorder>0</sortorder>
                    <drawtype>3</drawtype>
                    <color>00C800</color>
                    <yaxisside>0</yaxisside>
                    <calc_fnc>7</calc_fnc>
                    <type>0</type>
                    <item>
                        <host>DiskHealth-Check</host>
                        <key>disk.health.check</key>
                    </item>
                </graph_item>
            </graph_items>
        </graph>
    </graphs>
</zabbix_export>

3. 可以在zabbix-server上先测试一下：

[root@0f3c27f24c08 alertscripts]# zabbix_get -s 172.16.6.24 -k disk.health.check
0

4. 主机链接新创建的模板