nagios监控squid的脚本

r囧r小猫 2022-01-10 23:57 181阅读 0赞

最近一直都在忙工作上的事情，没有时间来写点东西了，公司用的cache是squid，之前有过监控，但是nagios中看不到squid的命中率，于是就写了这么一个脚本来通过pnp4nagios查看squid的一些图。下面是脚本：

1.  \#!/bin/bash
2.  \# 这个脚本主要是检测squid的每分钟http的请求熟、cpu的使用率、可用的文件描述符、5min的请求命中率、5min的内存请求命中率和5min的硬盘请求命中率。
3.  \# 并且可以通过pnp4nagios画图。
4.  
5.  PROGNAME=\`basename $0\`
6.  VERSION="Version 1.1"
7.  AUTHOR="zhhmj (tgariltg@gmail.com)"
8.  
9.  \#DEFINES
10. ST\_OK=0
11. ST\_WR=1
12. ST\_CR=2
13. ST\_UK=3
14. \#VARS
15. hostname="localhost"
16. port=8001
17. running=0
18. warn\_descriptors=100
19. crit\_descriptors=30
20. warn\_hits=70
21. crit\_hits=50
22. 
23. print\_version() \{
24. echo "$PROGNAME $VERSION $AUTHOR"
25. \}
26. 
27. print\_help() \{
28. echo ""
29. print\_version
30. echo ""
31. echo "Description:"
32. echo "Gets percentage of hits for a squid reverse proxy"
33. echo "Options:"
34. echo " -h|--help"
35. echo " Print help info."
36. echo " -H|--hostname)"
37. echo " Sets the hostname, default is localhost"
38. echo " -P|--port)"
39. echo " Sets the port, default is 8001"
40. echo " -wd)"
41. echo " Sets the number of available file descriptors to warn at, default 100"
42. echo " -cd)"
43. echo " Sets the number of available file descriptors to go critical at, default 30"
44. echo " -wh)"
45. echo " Sets the percentage of hits to warn at, default 70"
46. echo " -ch)"
47. echo " Sets the percentage of hits to go critical at, default 50"
48. echo ""
49. echo "Example:"
50. echo " ./check\_squid -H 127.0.0.1 -P 8001 -wd 100 -cd 30 -wh 70 -ch 50"
51. echo " WARNING - Squid is serving an average of 7.2 per minute since start with 655349 file descriptors left and 0.04 percent of CPU use and Hits as 64% of all requests"
52. exit $ST\_UK
53. \}
54. 
55. \#获取squid的信息
56. get\_status\_text() \{
57. status\_text=$(squidclient -h $\{hostname\} -p $\{port\} mgr:info 2>&1)
58. \}
59. 
60. \#确保服务器回复正常
61. is\_replying() \{
62. case "$status\_text" in
63. \*Denied.\*)
64. echo "Error gettings metrics.(Access control on squid?)"
65. exit $ST\_CR
66. ;;
67. \*ERROR\*)
68. echo "Error connecting to host"
69. exit $ST\_CR
70. ;;
71. esac
72. \}
73. 
74. \#下面是获取有用的信息：
75. \#Available file descriptors
76. \#CPU Usage
77. \#Average HTTP requests per minute
78. \#Hits as % of all requests by 5min
79. \#Memory hits as % of hit requests by 5min
80. \#Disk hits as % of hit requests by 5min
81. get\_statistics() \{
82. available\_descriptors=$(echo "$\{status\_text\}" | grep "Available number of file descriptors" | cut -d: -f 2 | sed -e 's/^\[ \\t\]\*//')
83. cpu\_usage=$(echo "$\{status\_text\}" | grep "CPU Usage:" | cut -d: -f2 | cut -d% -f 1 | sed -e 's/^\[ \\t\]\*//')
84. avg\_http\_requests=$(echo "$\{status\_text\}" | grep "Average HTTP requests per minute since start" | cut -d: -f2 | cut -d% -f 1 | sed -e 's/^\[ \\t\]\*//')
85. all\_requests\_hits=$(echo "$\{status\_text\}" | grep "Hits as % of all requests" | awk '\{print $8\}' | awk -F\\. '\{print $1\}')
86. memory\_hits=$(echo "$\{status\_text\}" | grep "Memory hits as % of hit requests" | awk '\{print $9\}' | awk -F\\. '\{print $1\}')
87. disk\_hits=$(echo "$\{status\_text\}" | grep "Disk hits as % of hit requests" | awk '\{print $9\}' | awk -F\\. '\{print $1\}')
88. \#buid perfdata string
89. perfdata="'avail\_descriptors'=$available\_descriptors 'cpu\_usage'=$cpu\_usage 'avg\_http\_requests'=$avg\_http\_requests 'all\_requests\_hits'=$all\_requests\_hits% 'memory\_hits'=$memory\_hits% 'disk\_hits'=$disk\_hits%"
90. \}
91. 
92. \#报警对比的判断
93. build\_output() \{
94. out="Squid is serving an average of $avg\_http\_requests per minute since start with $available\_descriptors file descriptors left and $cpu\_usage percent of CPU use and Hits as $all\_requests\_hits% of all requests"
95. if \[ $available\_descriptors -le $crit\_descriptors \] || \[ $all\_requests\_hits -le $crit\_hits \]
96. then
97. echo "CRITICAL - $\{out\} | $\{perfdata\}"
98. exit $ST\_CR
99. elif \[ $available\_descriptors -le $warn\_descriptors \] || \[ $all\_requests\_hits -le $warn\_hits \]
100. then
101. echo "WARNING - $\{out\} | $\{perfdata\}"
102. exit $ST\_WR
103. else
104. echo "OK - $\{out\} | $\{perfdata\}"
105. exit $ST\_OK
106. fi
107. \}
108. 
109. \#主程序
110. \#获取参数
111. while test -n "$1"; do
112. case "$1" in
113. \--help|-h)
114. print\_help
115. exit $ST\_UK
116. ;;
117. \--version|-v)
118. print\_version
119. exit $ST\_UK
120. ;;
121. \--hostname|-H)
122. hostname=$2
123. shift
124. ;;
125. \--port|-P)
126. port=$2
127. shift
128. ;;
129. \-wd)
130. warn\_descriptors=$2
131. shift
132. ;;
133. \-cd)
134. crit\_descriptors=$2
135. shift
136. ;;
137. \-wh)
138. warn\_hits=$2
139. shift
140. ;;
141. \-ch)
142. crit\_hits=$2
143. shift
144. ;;
145. \*)
146. echo "Unknown argument: $1"
147. print\_help
148. exit $ST\_UK
149. ;;
150. esac
151. shift
152. done
153. 
154. \#sanity
155. if \[ $warn\_descriptors -lt $crit\_descriptors \] || \[ $warn\_hits -lt $crit\_hits \]
156. then
157. echo "Warn descriptors must not be lower than critical and crit hits must not be lower than warn hits!"
158. print\_help
159. fi
160. 
161. get\_status\_text
162. is\_replying
163. get\_statistics
164. build\_output

转载于:https://blog.51cto.com/zhhmj/1100511