check_mssql_health

cherish2004

有些话不好说，看图吧

这只是一个例子，有好多SQL是没问题，但是这样测试就有问题，真是百思不得其姐。

r2007

官网上的例子，试试有木有好使的

1. nagios$ check_oracle_health --connect bba --mode tnsping
   
2. OK - connection established to bba.
   
3. 
   
4. nagios$ check_oracle_health --mode connection-time
   
5. OK - 0.17 seconds to connect  |
   
6.   connection_time=0.1740;1;5
   
7. 
   
8. nagios$ check_oracle_health --mode sga-data-buffer-hit-ratio
   
9. CRITICAL - SGA data buffer hit ratio 0.99%  |
   
10.   sga_data_buffer_hit_ratio=0.99%;98:;95:
    
11. 
    
12. nagios$ check_oracle_health --mode sga-library-cache-hit-ratio
    
13. OK - SGA library cache hit ratio 98.75%  |
    
14.   sga_library_cache_hit_ratio=98.75%;98:;95:
    
15. 
    
16. nagios$ check_oracle_health --mode sga-latches-hit-ratio
    
17. OK - SGA latches hit ratio 100.00%  |
    
18.   sga_latches_hit_ratio=100.00%;98:;95:
    
19. 
    
20. nagios$ check_oracle_health --mode sga-shared-pool-reloads
    
21. OK - SGA shared pool reloads 0.28%  |
    
22.   sga_shared_pool_reloads=0.28%;1;10
    
23. 
    
24. nagios$ check_oracle_health --mode sga-shared-pool-free
    
25. WARNING - SGA shared pool free 8.91%  |
    
26.   sga_shared_pool_free=8.91%;10:;5:
    
27. 
    
28. nagios$ check_oracle_health --mode pga-in-memory-sort-ratio
    
29. OK - PGA in-memory sort ratio 100.00%  |
    
30.   pga_in_memory_sort_ratio=100.00;99:;90:
    
31. 
    
32. nagios$ check_oracle_health --mode invalid-objects
    
33. OK - no invalid objects found  |
    
34.   invalid_ind_partitions=0 invalid_indexes=0
    
35.   invalid_objects=0 unrecoverable_datafiles=0
    
36. 
    
37. nagios$ check_oracle_health --mode switch-interval
    
38. OK - Last redo log file switch interval was 18 minutes |
    
39.     redo_log_file_switch_interval=1090s;600:;60:
    
40. 
    
41. nagios$ check_oracle_health --mode switch-interval --connect rac1
    
42. OK - Last redo log file switch interval was 32 minutes (thread 1)|
    
43.     redo_log_file_switch_interval=1938s;600:;60:
    
44. 
    
45. nagios$ check_oracle_health --mode tablespace-usage
    
46. CRITICAL - tbs SYSTEM usage is 99.33%
    
47. tbs SYSAUX usage is 93.73%
    
48. tbs USERS usage is 8.75%
    
49. tbs UNDOTBS1 usage is 6.65% | 'tbs_users_usage_pct'=8%;90;98
    
50. 'tbs_users_usage'=0MB;4;4;0;5
    
51. 'tbs_undotbs1_usage_pct'=6%;90;98
    
52. 'tbs_undotbs1_usage'=11MB;153;166;0;170
    
53. 'tbs_system_usage_pct'=99%;90;98
    
54. 'tbs_system_usage'=695MB;630;686;0;700
    
55. 'tbs_sysaux_usage_pct'=93%;90;98
    
56. 'tbs_sysaux_usage'=802MB;770;839;0;856
    
57. 
    
58. nagios$ check_oracle_health --mode tablespace-usage
    
59.     --tablespace USERS
    
60. OK - tbs USERS usage is 8.75% |
    
61.   'tbs_users_usage_pct'=8%;90;98
    
62.   'tbs_users_usage'=0MB;4;4;0;5
    
63. 
    
64. nagios$ check_oracle_health --mode tablespace-usage
    
65.     --name USERS
    
66. OK - tbs USERS usage is 8.75% |
    
67.   'tbs_users_usage_pct'=8%;90;98
    
68.   'tbs_users_usage'=0MB;4;4;0;5
    
69. 
    
70. nagios$ check_oracle_health --mode tablespace-free
    
71.     --name TEST
    
72. OK - tbs TEST has 97.91% free space left |
    
73.     'tbs_test_free_pct'=97.91%;5:;2:
    
74.     'tbs_test_free'=32083MB;1638.40:;655.36:;0.00;32767.98
    
75. 
    
76. nagios$ check_oracle_health --mode tablespace-free
    
77.     --name TEST --units MB --warning 100: --critical 50:
    
78. OK - tbs TEST has 32083.61MB free space left |
    
79.     'tbs_test_free_pct'=97.91%;0.31:;0.15:
    
80.     'tbs_test_free'=32083.61MB;100.00:;50.00:;0;32767.98
    
81. 
    
82. nagios$ check_oracle_health --mode tablespace-free
    
83.     --name TEST --warning 10: --critical 5:
    
84. OK - tbs TEST has 97.91% free space left |
    
85.     'tbs_test_free_pct'=97.91%;10:;5:
    
86.     'tbs_test_free'=32083MB;3276.80:;1638.40:;0.00;32767.98
    
87. 
    
88. nagios$ check_oracle_health --mode tablespace-remaining-time
    
89.     --tablespace ARUSERS --lookback 7
    
90. WARNING - tablespace ARUSERS will be full in 78 days |
    
91.   'tbs_arusers_days_until_full'=78;90:;30:
    
92. 
    
93. nagios$ check_oracle_health --mode flash-recovery-area-free
    
94. OK - flra /u00/app/oracle/flash_recovery_area has 100.00% free space left |
    
95.     'flra_free_pct'=100.00%;5:;2:
    
96.     'flra_free'=2048MB;102.40:;40.96:;0;2048.00
    
97. 
    
98. nagios$ check_oracle_health --mode flash-recovery-area-free
    
99.     --units KB --warning 1000: --critical 500:
    
100. OK - flra /u00/app/oracle/flash_recovery_area has 2097152.00KB free space left |     'flra_free_pct'=100.00%;0.05:;0.02:
     
101.     'flra_free'=2097152.00KB;1000.00:;500.00:;0;2097152.00
     
102. 
     
103. nagios$ check_oracle_health --mode datafile-io-traffic
     
104.   --datafile users01.dbf
     
105. WARNING - users01.dbf: 1049.83 IO Operations per Second |
     
106.   'dbf_users01.dbf_io_total_per_sec'=1049.83;1000;5000
     
107. 
     
108. nagios$ check_oracle_health --mode latch-contention
     
109.   --name 214
     
110. OK - SGA latch library cache (214) contention 0.08% |
     
111. 'latch_214_contention'=0.08%;1;2
     
112. 'latch_214_sleep_share'=0.00% 'latch_214_gets'=49995
     
113. 
     
114. nagios$ check_oracle_health --mode latch-contention
     
115.   --name 'library cache'
     
116. OK - SGA latch library cache (214) contention 0.08% |
     
117. 'latch_214_contention'=0.08%;1;2
     
118. 'latch_214_sleep_share'=0.00% 'latch_214_gets'=49937
     
119. 
     
120. nagios$ check_oracle_health --mode enqueue-contention --name TC
     
121. CRITICAL - enqueue TC: 19.90% of the requests must wait |
     
122. 'TC_contention'=19.90%;1;10
     
123. 'TC_requests'=2015 'TC_waits'=401
     
124. 
     
125. nagios$ check_oracle_health --mode latch-contention
     
126.   --name 'messages'
     
127. OK - SGA latch messages (17) contention 0.02% |
     
128. 'latch_17_contention'=0.02%;1;2 'latch_17_gets'=4867
     
129. 
     
130. nagios$ check_oracle_health --mode latch-waiting
     
131.   --name 'user lock'
     
132. OK - SGA latch user lock (205) sleeping 0.000841% of the time |
     
133. 'latch_205_sleep_share'=0.000841%
     
134. 
     
135. nagios$ check_oracle_health --mode event-waits
     
136.   --name 'log file sync'
     
137. OK - log file sync : 1.839511 waits/sec |
     
138. 'log file sync_waits_per_sec'=1.839511;10;100
     
139. 
     
140. nagios$ check_oracle_health --mode event-waiting
     
141.   --name 'Log file parallel write'
     
142. OK - log file parallel write waits 0.045843% of the time |
     
143. rarr 'log file parallel write_percent_waited'=0.045843%;0.1;0.5
     
144. 
     
145. nagios$ check_oracle_health --mode sysstat
     
146.   --name 'transaction rollbacks'
     
147. OK - 0.000003 transaction rollbacks/sec |
     
148. 'transaction rollbacks_per_sec'=0.000003;10;100
     
149. 'transaction rollbacks'=4
     
150. 
     
151. nagios$ check_oracle_health --mode sql
     
152.   --name 'select count(*) from v$session' --name2 sessions
     
153. CRITICAL - sessions: 21 | 'sessions'=21;1;5
     
154. 
     
155. nagios$ check_oracle_health --mode sql
     
156.   --name 'select 12 from dual' --name2 twelve --units MB
     
157. CRITICAL - twelfe: 12MB | 'twelfe'=12MB;1;5
     
158. 
     
159. nagios$ check_oracle_health --mode sql
     
160.   --name 'select 200,300,1000 from dual'
     
161.   --name2 'kaspar melchior balthasar'
     
162.   --warning 180 --critical 500
     
163. WARNING - kaspar melchior balthasar: 200 300 1000 |
     
164. 'kaspar'=200;180;500 'melchior'=300;; 'balthasar'=1000;;
     
165. 
     
166. nagios$ check_oracle_health --mode sql
     
167.   --name "select 'abc123' from dual" --name2 \\d
     
168.   --regexp
     
169. OK - output abc123 matches pattern \d

复制代码

cherish2004

回复 2# r2007


    这些例子是固定的，我想自定义sql。其实我大概知道原因了，得到的结果要数值型的，如10，12.3等等，但是像dbversion=select * from v$version这种就不好办了。

r2007

回复 3# cherish2004

倒数第5个例子不就是你想测的那个吗？

1. nagios$ check_oracle_health --mode sql
   
2.   --name 'select count(*) from v$session' --name2 sessions
   
3. CRITICAL - sessions: 21 | 'sessions'=21;1;5

复制代码

r2007

明白你的意思了，没有数值无法确定状态。

r2007

mode=sql的用法

1. Result of any SQL-Statement that returns a number. The statement itself is passed over with the parameter –name. A Label for the performance data output can be passed over with the parameter –name2.

复制代码

cherish2004

回复 6# r2007


    是这样的，可是我现在想得到一些字符串类型的结果，不过我发现你给的代码最后一个例子好像是得到字符串，不太明白用法。

1. 
   
2. [oracle@oraclerhel libexec]$ ./check_oracle_health --connect=prod --username=system --password=oracle --mode=sql --name="select%20%27abc123%27%20from%20dual" --name2=r--name2 \\d --regexp
   
3. OK - output abc123 matches pattern \d
   

复制代码

r2007

用name2的正则匹配select的结果，如果匹配成功就ok，不成功估计会显示CRITICAL