Ganglia监控hadoop、hbase集群

1. 在主节点上安装ganglia-webfrontend和ganglia-monitor

1. sudo apt-get install ganglia-webfrontend ganglia-monitor

复制代码

在主节点上安装ganglia-webfrontend和ganglia-monitor。在其他监视节点上，只需要安装ganglia-monitor即可
将ganglia的文件链接到apache的默认目录下

1. sudo ln -s /usr/share/ganglia-webfrontend /var/www/ganglia

复制代码

2. 安装ganglia-monitor
在其他监视节点上，只需要安装ganglia-monitor

1. sudo apt-get install ganglia-monitor

复制代码

3. Ganglia配置
gmond.conf
在每个节点上都需要配置/etc/ganglia/gmond.conf,配置相同如下所示

1. sudo vim /etc/ganglia/gmond.conf

复制代码

修改后的/etc/ganglia/gmond.conf

1. globals {                    
   
2.   daemonize = yes  ##以后台的方式运行            
   
3.   setuid = yes             
   
4.   user = ganglia     #运行Ganglia的用户              
   
5.   debug_level = 0               
   
6.   max_udp_msg_len = 1472        
   
7.   mute = no             
   
8.   deaf = no             
   
9.   host_dmax = 0 /*secs */ 
   
10.   cleanup_threshold = 300 /*secs */ 
    
11.   gexec = no             
    
12.   send_metadata_interval = 10     #发送数据的时间间隔
    
13. } 
    
14. 
    
15. /* If a cluster attribute is specified, then all gmond hosts are wrapped inside 
    
16. * of a <CLUSTER> tag.  If you do not specify a cluster tag, then all <HOSTS> will 
    
17. * NOT be wrapped inside of a <CLUSTER> tag. */ 
    
18. cluster { 
    
19.   name = "hadoop-cluster"         #集群名称
    
20.   owner = "ganglia"               #运行Ganglia的用户
    
21.   latlong = "unspecified" 
    
22.   url = "unspecified" 
    
23. } 
    
24. 
    
25. /* The host section describes attributes of the host, like the location */ 
    
26. host { 
    
27.   location = "unspecified" 
    
28. } 
    
29. 
    
30. /* Feel free to specify as many udp_send_channels as you like.  Gmond 
    
31.    used to only support having a single channel */ 
    
32. udp_send_channel { 
    
33.   #mcast_join = 239.2.11.71     #注释掉组播
    
34.   host = master                 #发送给安装gmetad的机器
    
35.   port = 8649                   #监听端口
    
36.   ttl = 1 
    
37. } 
    
38. 
    
39. /* You can specify as many udp_recv_channels as you like as well. */ 
    
40. udp_recv_channel { 
    
41.   #mcast_join = 239.2.11.71     #注释掉组播
    
42.   port = 8649 
    
43.   #bind = 239.2.11.71 
    
44. } 
    
45. 
    
46. /* You can specify as many tcp_accept_channels as you like to share 
    
47.    an xml description of the state of the cluster */ 
    
48. tcp_accept_channel { 
    
49.   port = 8649 
    
50. }

复制代码

gmetad.conf
在主节点上还需要配置/etc/ganglia/gmetad.conf,这里面的名字hadoop-cluster和上面gmond.conf中name应该一致。　
/etc/ganglia/gmetad.conf

1. sudo vim /etc/ganglia/gmetad.conf

复制代码

修改为以下内容

1. data_source "hadoop-cluster" 10 master:8649 slave:8649
   
2. setuid_username "nobody"
   
3. rrd_rootdir "/var/lib/ganglia/rrds"
   
4. gridname "hadoop-cluster"
   
5. 注:master:8649 slave:8649为要监听的主机和端口,data_source中hadoop-cluster与gmond.conf中name一致

复制代码

4. Hadoop配置
在所有hadoop所在的节点，均需要配置hadoop-metrics2.properties，配置如下：

1. #   Licensed to the Apache Software Foundation (ASF) under one or more
   
2. #   contributor license agreements.  See the NOTICE file distributed with
   
3. #   this work for additional information regarding copyright ownership.
   
4. #   The ASF licenses this file to You under the Apache License, Version 2.0
   
5. #   (the "License"); you may not use this file except in compliance with
   
6. #   the License.  You may obtain a copy of the License at
   
7. #
   
8. #       http://www.apache.org/licenses/LICENSE-2.0
   
9. #
   
10. #   Unless required by applicable law or agreed to in writing, software
    
11. #   distributed under the License is distributed on an "AS IS" BASIS,
    
12. #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    
13. #   See the License for the specific language governing permissions and
    
14. #   limitations under the License.
    
15. #
    
16. 
    
17. # syntax: [prefix].[source|sink].[instance].[options]
    
18. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
    
19. 
    
20. #注释掉以前原有配置
    
21. 
    
22. #*.sink.file.class=org.apache.hadoop.metrics2.sink.FileSink
    
23. # default sampling period, in seconds
    
24. #*.period=10
    
25. 
    
26. # The namenode-metrics.out will contain metrics from all context
    
27. #namenode.sink.file.filename=namenode-metrics.out
    
28. # Specifying a special sampling period for namenode:
    
29. #namenode.sink.*.period=8
    
30. 
    
31. #datanode.sink.file.filename=datanode-metrics.out
    
32. 
    
33. # the following example split metrics of different
    
34. # context to different sinks (in this case files)
    
35. #jobtracker.sink.file_jvm.context=jvm
    
36. #jobtracker.sink.file_jvm.filename=jobtracker-jvm-metrics.out
    
37. #jobtracker.sink.file_mapred.context=mapred
    
38. #jobtracker.sink.file_mapred.filename=jobtracker-mapred-metrics.out
    
39. 
    
40. #tasktracker.sink.file.filename=tasktracker-metrics.out
    
41. 
    
42. #maptask.sink.file.filename=maptask-metrics.out
    
43. 
    
44. #reducetask.sink.file.filename=reducetask-metrics.out
    
45. 
    
46. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
    
47. *.sink.ganglia.period=10
    
48. 
    
49. *.sink.ganglia.slope=jvm.metrics.gcCount=zero,jvm.metrics.memHeapUsedM=both  
    
50. *.sink.ganglia.dmax=jvm.metrics.threadsBlocked=70,jvm.metrics.memHeapUsedM=40  
    
51. 
    
52. namenode.sink.ganglia.servers=master:8649  
    
53. resourcemanager.sink.ganglia.servers=master:8649  
    
54. 
    
55. datanode.sink.ganglia.servers=master:8649    
    
56. nodemanager.sink.ganglia.servers=master:8649    
    
57. 
    
58. 
    
59. maptask.sink.ganglia.servers=master:8649    
    
60. reducetask.sink.ganglia.servers=master:8649

复制代码

5. Hbase配置
在所有的hbase节点中均配置hadoop-metrics2-hbase.properties,配置如下:

1. # syntax: [prefix].[source|sink].[instance].[options]
   
2. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
   
3. 
   
4. #*.sink.file*.class=org.apache.hadoop.metrics2.sink.FileSink
   
5. # default sampling period
   
6. #*.period=10
   
7. 
   
8. # Below are some examples of sinks that could be used
   
9. # to monitor different hbase daemons.
   
10. 
    
11. # hbase.sink.file-all.class=org.apache.hadoop.metrics2.sink.FileSink
    
12. # hbase.sink.file-all.filename=all.metrics
    
13. 
    
14. # hbase.sink.file0.class=org.apache.hadoop.metrics2.sink.FileSink
    
15. # hbase.sink.file0.context=hmaster
    
16. # hbase.sink.file0.filename=master.metrics
    
17. 
    
18. # hbase.sink.file1.class=org.apache.hadoop.metrics2.sink.FileSink
    
19. # hbase.sink.file1.context=thrift-one
    
20. # hbase.sink.file1.filename=thrift-one.metrics
    
21. 
    
22. # hbase.sink.file2.class=org.apache.hadoop.metrics2.sink.FileSink
    
23. # hbase.sink.file2.context=thrift-two
    
24. # hbase.sink.file2.filename=thrift-one.metrics
    
25. 
    
26. # hbase.sink.file3.class=org.apache.hadoop.metrics2.sink.FileSink
    
27. # hbase.sink.file3.context=rest
    
28. # hbase.sink.file3.filename=rest.metrics
    
29. 
    
30. 
    
31. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
    
32. *.sink.ganglia.period=10  
    
33. 
    
34. hbase.sink.ganglia.period=10  
    
35. hbase.sink.ganglia.servers=master:8649

复制代码

6. 启动hadoop、hbase集群

1. start-dfs.sh
   
2. start-yarn.sh
   
3. start-hbase.sh

复制代码

7. 启动Ganglia
先需要重启hadoop和hbase 。在各个节点上启动gmond服务，主节点还需要启动gmetad服务。
使用apt-get方式安装的Ganglia，可以直接用service方式启动。

1. sudo service ganglia-monitor start（每台机器都需要启动）
   
2. 
   
3. sudo service gmetad start（在安装了ganglia-webfrontend的机器上启动）

复制代码

8. 检验
登录浏览器查看：http://master/ganglia，如果Hosts up为9即表示安装成功。
若安装不成功，有几个很有用的调试命令：
以调试模式启动gmetad：gmetad -d 9
查看gmetad收集到的XML文件：telnet master 8649


9. 截图

 


 


master节点gmetad.conf配置

1. # This is an example of a Ganglia Meta Daemon configuration file
   
2. #                http://ganglia.sourceforge.net/
   
3. #
   
4. #
   
5. #-------------------------------------------------------------------------------
   
6. # Setting the debug_level to 1 will keep daemon in the forground and
   
7. # show only error messages. Setting this value higher than 1 will make 
   
8. # gmetad output debugging information and stay in the foreground.
   
9. # default: 0
   
10. # debug_level 10
    
11. #
    
12. #-------------------------------------------------------------------------------
    
13. # What to monitor. The most important section of this file. 
    
14. #
    
15. # The data_source tag specifies either a cluster or a grid to
    
16. # monitor. If we detect the source is a cluster, we will maintain a complete
    
17. # set of RRD databases for it, which can be used to create historical 
    
18. # graphs of the metrics. If the source is a grid (it comes from another gmetad),
    
19. # we will only maintain summary RRDs for it.
    
20. #
    
21. # Format: 
    
22. # data_source "my cluster" [polling interval] address1:port addreses2:port ...
    
23. # 
    
24. # The keyword 'data_source' must immediately be followed by a unique
    
25. # string which identifies the source, then an optional polling interval in 
    
26. # seconds. The source will be polled at this interval on average. 
    
27. # If the polling interval is omitted, 15sec is asssumed. 
    
28. #
    
29. # If you choose to set the polling interval to something other than the default,
    
30. # note that the web frontend determines a host as down if its TN value is less
    
31. # than 4 * TMAX (20sec by default).  Therefore, if you set the polling interval
    
32. # to something around or greater than 80sec, this will cause the frontend to
    
33. # incorrectly display hosts as down even though they are not.
    
34. #
    
35. # A list of machines which service the data source follows, in the 
    
36. # format ip:port, or name:port. If a port is not specified then 8649
    
37. # (the default gmond port) is assumed.
    
38. # default: There is no default value
    
39. #
    
40. # data_source "my cluster" 10 localhost  my.machine.edu:8649  1.2.3.5:8655
    
41. # data_source "my grid" 50 1.3.4.7:8655 grid.org:8651 grid-backup.org:8651
    
42. # data_source "another source" 1.3.4.7:8655  1.3.4.8
    
43. 
    
44. data_source "hadoop-cluster" 10 master:8649 slave:8649
    
45. setuid_username "nobody"
    
46. rrd_rootdir "/var/lib/ganglia/rrds"
    
47. gridname "hadoop-cluster"
    
48. 
    
49. #
    
50. # Round-Robin Archives
    
51. # You can specify custom Round-Robin archives here (defaults are listed below)
    
52. #
    
53. # Old Default RRA: Keep 1 hour of metrics at 15 second resolution. 1 day at 6 minute
    
54. # RRAs "RRA:AVERAGE:0.5:1:244" "RRA:AVERAGE:0.5:24:244" "RRA:AVERAGE:0.5:168:244" "RRA:AVERAGE:0.5:672:244" \
    
55. #      "RRA:AVERAGE:0.5:5760:374"
    
56. # New Default RRA
    
57. # Keep 5856 data points at 15 second resolution assuming 15 second (default) polling. That's 1 day
    
58. # Two weeks of data points at 1 minute resolution (average)
    
59. #RRAs "RRA:AVERAGE:0.5:1:5856" "RRA:AVERAGE:0.5:4:20160" "RRA:AVERAGE:0.5:40:52704"
    
60. 
    
61. #
    
62. #-------------------------------------------------------------------------------
    
63. # Scalability mode. If on, we summarize over downstream grids, and respect
    
64. # authority tags. If off, we take on 2.5.0-era behavior: we do not wrap our output
    
65. # in <GRID></GRID> tags, we ignore all <GRID> tags we see, and always assume
    
66. # we are the "authority" on data source feeds. This approach does not scale to
    
67. # large groups of clusters, but is provided for backwards compatibility.
    
68. # default: on
    
69. # scalable off
    
70. #
    
71. #-------------------------------------------------------------------------------
    
72. # The name of this Grid. All the data sources above will be wrapped in a GRID
    
73. # tag with this name.
    
74. # default: unspecified
    
75. # gridname "MyGrid"
    
76. #
    
77. #-------------------------------------------------------------------------------
    
78. # The authority URL for this grid. Used by other gmetads to locate graphs
    
79. # for our data sources. Generally points to a ganglia/
    
80. # website on this machine.
    
81. # default: "http://hostname/ganglia/",
    
82. #   where hostname is the name of this machine, as defined by gethostname().
    
83. # authority "http://mycluster.org/newprefix/"
    
84. #
    
85. #-------------------------------------------------------------------------------
    
86. # List of machines this gmetad will share XML with. Localhost
    
87. # is always trusted. 
    
88. # default: There is no default value
    
89. # trusted_hosts 127.0.0.1 169.229.50.165 my.gmetad.org
    
90. #
    
91. #-------------------------------------------------------------------------------
    
92. # If you want any host which connects to the gmetad XML to receive
    
93. # data, then set this value to "on"
    
94. # default: off
    
95. # all_trusted on
    
96. #
    
97. #-------------------------------------------------------------------------------
    
98. # If you don't want gmetad to setuid then set this to off
    
99. # default: on
    
100. # setuid off
     
101. #
     
102. #-------------------------------------------------------------------------------
     
103. # User gmetad will setuid to (defaults to "nobody")
     
104. # default: "nobody"
     
105. # setuid_username "nobody"
     
106. #
     
107. #-------------------------------------------------------------------------------
     
108. # Umask to apply to created rrd files and grid directory structure
     
109. # default: 0 (files are public)
     
110. # umask 022
     
111. #
     
112. #-------------------------------------------------------------------------------
     
113. # The port gmetad will answer requests for XML
     
114. # default: 8651
     
115. # xml_port 8651
     
116. #
     
117. #-------------------------------------------------------------------------------
     
118. # The port gmetad will answer queries for XML. This facility allows
     
119. # simple subtree and summation views of the XML tree.
     
120. # default: 8652
     
121. # interactive_port 8652
     
122. #
     
123. #-------------------------------------------------------------------------------
     
124. # The number of threads answering XML requests
     
125. # default: 4
     
126. # server_threads 10
     
127. #
     
128. #-------------------------------------------------------------------------------
     
129. # Where gmetad stores its round-robin databases
     
130. # default: "/var/lib/ganglia/rrds"
     
131. # rrd_rootdir "/some/other/place"
     
132. #
     
133. #-------------------------------------------------------------------------------
     
134. # In earlier versions of gmetad, hostnames were handled in a case
     
135. # sensitive manner
     
136. # If your hostname directories have been renamed to lower case,
     
137. # set this option to 0 to disable backward compatibility.
     
138. # From version 3.2, backwards compatibility will be disabled by default.
     
139. # default: 1   (for gmetad < 3.2)
     
140. # default: 0   (for gmetad >= 3.2)
     
141. case_sensitive_hostnames 0
     
142. 
     
143. #-------------------------------------------------------------------------------
     
144. # It is now possible to export all the metrics collected by gmetad directly to
     
145. # graphite by setting the following attributes. 
     
146. #
     
147. # The hostname or IP address of the Graphite server
     
148. # default: unspecified
     
149. # carbon_server "my.graphite.box"
     
150. #
     
151. # The port on which Graphite is listening
     
152. # default: 2003
     
153. # carbon_port 2003
     
154. #
     
155. # A prefix to prepend to the metric names exported by gmetad. Graphite uses dot-
     
156. # separated paths to organize and refer to metrics. 
     
157. # default: unspecified
     
158. # graphite_prefix "datacenter1.gmetad"
     
159. #
     
160. # Number of milliseconds gmetad will wait for a response from the graphite server 
     
161. # default: 500
     
162. # carbon_timeout 500
     
163. #
     
164. master-gmond.conf.md Raw

复制代码

master节点gmond.conf配置

1. /* This configuration is as close to 2.5.x default behavior as possible 
   
2.    The values closely match ./gmond/metric.h definitions in 2.5.x */ 
   
3. globals {                    
   
4.   daemonize = yes              
   
5.   setuid = yes             
   
6.   user = ganglia              
   
7.   debug_level = 0               
   
8.   max_udp_msg_len = 1472        
   
9.   mute = no             
   
10.   deaf = no             
    
11.   host_dmax = 0 /*secs */ 
    
12.   cleanup_threshold = 300 /*secs */ 
    
13.   gexec = no             
    
14.   send_metadata_interval = 10 
    
15. } 
    
16. 
    
17. /* If a cluster attribute is specified, then all gmond hosts are wrapped inside 
    
18. * of a <CLUSTER> tag.  If you do not specify a cluster tag, then all <HOSTS> will 
    
19. * NOT be wrapped inside of a <CLUSTER> tag. */ 
    
20. cluster { 
    
21.   name = "hadoop-cluster" 
    
22.   owner = "ganglia" 
    
23.   latlong = "unspecified" 
    
24.   url = "unspecified" 
    
25. } 
    
26. 
    
27. /* The host section describes attributes of the host, like the location */ 
    
28. host { 
    
29.   location = "unspecified" 
    
30. } 
    
31. 
    
32. /* Feel free to specify as many udp_send_channels as you like.  Gmond 
    
33.    used to only support having a single channel */ 
    
34. udp_send_channel { 
    
35.   #mcast_join = 239.2.11.71 
    
36.   host = master
    
37.   port = 8649 
    
38.   ttl = 1 
    
39. } 
    
40. 
    
41. /* You can specify as many udp_recv_channels as you like as well. */ 
    
42. udp_recv_channel { 
    
43.   #mcast_join = 239.2.11.71 
    
44.   port = 8649 
    
45.   #bind = 239.2.11.71 
    
46. } 
    
47. 
    
48. /* You can specify as many tcp_accept_channels as you like to share 
    
49.    an xml description of the state of the cluster */ 
    
50. tcp_accept_channel { 
    
51.   port = 8649 
    
52. } 
    
53. 
    
54. /* Each metrics module that is referenced by gmond must be specified and 
    
55.    loaded. If the module has been statically linked with gmond, it does not 
    
56.    require a load path. However all dynamically loadable modules must include 
    
57.    a load path. */ 
    
58. modules { 
    
59.   module { 
    
60.     name = "core_metrics" 
    
61.   } 
    
62.   module { 
    
63.     name = "cpu_module" 
    
64.     path = "/usr/lib/ganglia/modcpu.so" 
    
65.   } 
    
66.   module { 
    
67.     name = "disk_module" 
    
68.     path = "/usr/lib/ganglia/moddisk.so" 
    
69.   } 
    
70.   module { 
    
71.     name = "load_module" 
    
72.     path = "/usr/lib/ganglia/modload.so" 
    
73.   } 
    
74.   module { 
    
75.     name = "mem_module" 
    
76.     path = "/usr/lib/ganglia/modmem.so" 
    
77.   } 
    
78.   module { 
    
79.     name = "net_module" 
    
80.     path = "/usr/lib/ganglia/modnet.so" 
    
81.   } 
    
82.   module { 
    
83.     name = "proc_module" 
    
84.     path = "/usr/lib/ganglia/modproc.so" 
    
85.   } 
    
86.   module { 
    
87.     name = "sys_module" 
    
88.     path = "/usr/lib/ganglia/modsys.so" 
    
89.   } 
    
90. } 
    
91. 
    
92. include ('/etc/ganglia/conf.d/*.conf') 
    
93. 
    
94. 
    
95. /* The old internal 2.5.x metric array has been replaced by the following 
    
96.    collection_group directives.  What follows is the default behavior for 
    
97.    collecting and sending metrics that is as close to 2.5.x behavior as 
    
98.    possible. */
    
99. 
    
100. /* This collection group will cause a heartbeat (or beacon) to be sent every 
     
101.    20 seconds.  In the heartbeat is the GMOND_STARTED data which expresses 
     
102.    the age of the running gmond. */ 
     
103. collection_group { 
     
104.   collect_once = yes 
     
105.   time_threshold = 20 
     
106.   metric { 
     
107.     name = "heartbeat" 
     
108.   } 
     
109. } 
     
110. 
     
111. /* This collection group will send general info about this host every 1200 secs. 
     
112.    This information doesn't change between reboots and is only collected once. */ 
     
113. collection_group { 
     
114.   collect_once = yes 
     
115.   time_threshold = 1200 
     
116.   metric { 
     
117.     name = "cpu_num" 
     
118.     title = "CPU Count" 
     
119.   } 
     
120.   metric { 
     
121.     name = "cpu_speed" 
     
122.     title = "CPU Speed" 
     
123.   } 
     
124.   metric { 
     
125.     name = "mem_total" 
     
126.     title = "Memory Total" 
     
127.   } 
     
128.   /* Should this be here? Swap can be added/removed between reboots. */ 
     
129.   metric { 
     
130.     name = "swap_total" 
     
131.     title = "Swap Space Total" 
     
132.   } 
     
133.   metric { 
     
134.     name = "boottime" 
     
135.     title = "Last Boot Time" 
     
136.   } 
     
137.   metric { 
     
138.     name = "machine_type" 
     
139.     title = "Machine Type" 
     
140.   } 
     
141.   metric { 
     
142.     name = "os_name" 
     
143.     title = "Operating System" 
     
144.   } 
     
145.   metric { 
     
146.     name = "os_release" 
     
147.     title = "Operating System Release" 
     
148.   } 
     
149.   metric { 
     
150.     name = "location" 
     
151.     title = "Location" 
     
152.   } 
     
153. } 
     
154. 
     
155. /* This collection group will send the status of gexecd for this host every 300 secs */
     
156. /* Unlike 2.5.x the default behavior is to report gexecd OFF.  */ 
     
157. collection_group { 
     
158.   collect_once = yes 
     
159.   time_threshold = 300 
     
160.   metric { 
     
161.     name = "gexec" 
     
162.     title = "Gexec Status" 
     
163.   } 
     
164. } 
     
165. 
     
166. /* This collection group will collect the CPU status info every 20 secs. 
     
167.    The time threshold is set to 90 seconds.  In honesty, this time_threshold could be 
     
168.    set significantly higher to reduce unneccessary network chatter. */ 
     
169. collection_group { 
     
170.   collect_every = 20 
     
171.   time_threshold = 90 
     
172.   /* CPU status */ 
     
173.   metric { 
     
174.     name = "cpu_user"  
     
175.     value_threshold = "1.0" 
     
176.     title = "CPU User" 
     
177.   } 
     
178.   metric { 
     
179.     name = "cpu_system"   
     
180.     value_threshold = "1.0" 
     
181.     title = "CPU System" 
     
182.   } 
     
183.   metric { 
     
184.     name = "cpu_idle"  
     
185.     value_threshold = "5.0" 
     
186.     title = "CPU Idle" 
     
187.   } 
     
188.   metric { 
     
189.     name = "cpu_nice"  
     
190.     value_threshold = "1.0" 
     
191.     title = "CPU Nice" 
     
192.   } 
     
193.   metric { 
     
194.     name = "cpu_aidle" 
     
195.     value_threshold = "5.0" 
     
196.     title = "CPU aidle" 
     
197.   } 
     
198.   metric { 
     
199.     name = "cpu_wio" 
     
200.     value_threshold = "1.0" 
     
201.     title = "CPU wio" 
     
202.   } 
     
203.   /* The next two metrics are optional if you want more detail... 
     
204.      ... since they are accounted for in cpu_system.  
     
205.   metric { 
     
206.     name = "cpu_intr" 
     
207.     value_threshold = "1.0" 
     
208.     title = "CPU intr" 
     
209.   } 
     
210.   metric { 
     
211.     name = "cpu_sintr" 
     
212.     value_threshold = "1.0" 
     
213.     title = "CPU sintr" 
     
214.   } 
     
215.   */ 
     
216. } 
     
217. 
     
218. collection_group { 
     
219.   collect_every = 20 
     
220.   time_threshold = 90 
     
221.   /* Load Averages */ 
     
222.   metric { 
     
223.     name = "load_one" 
     
224.     value_threshold = "1.0" 
     
225.     title = "One Minute Load Average" 
     
226.   } 
     
227.   metric { 
     
228.     name = "load_five" 
     
229.     value_threshold = "1.0" 
     
230.     title = "Five Minute Load Average" 
     
231.   } 
     
232.   metric { 
     
233.     name = "load_fifteen" 
     
234.     value_threshold = "1.0" 
     
235.     title = "Fifteen Minute Load Average" 
     
236.   }
     
237. } 
     
238. 
     
239. /* This group collects the number of running and total processes */ 
     
240. collection_group { 
     
241.   collect_every = 80 
     
242.   time_threshold = 950 
     
243.   metric { 
     
244.     name = "proc_run" 
     
245.     value_threshold = "1.0" 
     
246.     title = "Total Running Processes" 
     
247.   } 
     
248.   metric { 
     
249.     name = "proc_total" 
     
250.     value_threshold = "1.0" 
     
251.     title = "Total Processes" 
     
252.   } 
     
253. }
     
254. 
     
255. /* This collection group grabs the volatile memory metrics every 40 secs and 
     
256.    sends them at least every 180 secs.  This time_threshold can be increased 
     
257.    significantly to reduce unneeded network traffic. */ 
     
258. collection_group { 
     
259.   collect_every = 40 
     
260.   time_threshold = 180 
     
261.   metric { 
     
262.     name = "mem_free" 
     
263.     value_threshold = "1024.0" 
     
264.     title = "Free Memory" 
     
265.   } 
     
266.   metric { 
     
267.     name = "mem_shared" 
     
268.     value_threshold = "1024.0" 
     
269.     title = "Shared Memory" 
     
270.   } 
     
271.   metric { 
     
272.     name = "mem_buffers" 
     
273.     value_threshold = "1024.0" 
     
274.     title = "Memory Buffers" 
     
275.   } 
     
276.   metric { 
     
277.     name = "mem_cached" 
     
278.     value_threshold = "1024.0" 
     
279.     title = "Cached Memory" 
     
280.   } 
     
281.   metric { 
     
282.     name = "swap_free" 
     
283.     value_threshold = "1024.0" 
     
284.     title = "Free Swap Space" 
     
285.   } 
     
286. } 
     
287. 
     
288. collection_group { 
     
289.   collect_every = 40 
     
290.   time_threshold = 300 
     
291.   metric { 
     
292.     name = "bytes_out" 
     
293.     value_threshold = 4096 
     
294.     title = "Bytes Sent" 
     
295.   } 
     
296.   metric { 
     
297.     name = "bytes_in" 
     
298.     value_threshold = 4096 
     
299.     title = "Bytes Received" 
     
300.   } 
     
301.   metric { 
     
302.     name = "pkts_in" 
     
303.     value_threshold = 256 
     
304.     title = "Packets Received" 
     
305.   } 
     
306.   metric { 
     
307.     name = "pkts_out" 
     
308.     value_threshold = 256 
     
309.     title = "Packets Sent" 
     
310.   } 
     
311. }
     
312. 
     
313. /* Different than 2.5.x default since the old config made no sense */ 
     
314. collection_group { 
     
315.   collect_every = 1800 
     
316.   time_threshold = 3600 
     
317.   metric { 
     
318.     name = "disk_total" 
     
319.     value_threshold = 1.0 
     
320.     title = "Total Disk Space" 
     
321.   } 
     
322. }
     
323. 
     
324. collection_group { 
     
325.   collect_every = 40 
     
326.   time_threshold = 180 
     
327.   metric { 
     
328.     name = "disk_free" 
     
329.     value_threshold = 1.0 
     
330.     title = "Disk Space Available" 
     
331.   } 
     
332.   metric { 
     
333.     name = "part_max_used" 
     
334.     value_threshold = 1.0 
     
335.     title = "Maximum Disk Space Used" 
     
336.   } 
     
337. }
     
338. master-hadoop-metrics2-hbase.properties.md Raw
     
339. master节点hadoop-metrics2-hbase.properties配置
     
340. 
     
341. # syntax: [prefix].[source|sink].[instance].[options]
     
342. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
     
343. 
     
344. #*.sink.file*.class=org.apache.hadoop.metrics2.sink.FileSink
     
345. # default sampling period
     
346. #*.period=10
     
347. 
     
348. # Below are some examples of sinks that could be used
     
349. # to monitor different hbase daemons.
     
350. 
     
351. # hbase.sink.file-all.class=org.apache.hadoop.metrics2.sink.FileSink
     
352. # hbase.sink.file-all.filename=all.metrics
     
353. 
     
354. # hbase.sink.file0.class=org.apache.hadoop.metrics2.sink.FileSink
     
355. # hbase.sink.file0.context=hmaster
     
356. # hbase.sink.file0.filename=master.metrics
     
357. 
     
358. # hbase.sink.file1.class=org.apache.hadoop.metrics2.sink.FileSink
     
359. # hbase.sink.file1.context=thrift-one
     
360. # hbase.sink.file1.filename=thrift-one.metrics
     
361. 
     
362. # hbase.sink.file2.class=org.apache.hadoop.metrics2.sink.FileSink
     
363. # hbase.sink.file2.context=thrift-two
     
364. # hbase.sink.file2.filename=thrift-one.metrics
     
365. 
     
366. # hbase.sink.file3.class=org.apache.hadoop.metrics2.sink.FileSink
     
367. # hbase.sink.file3.context=rest
     
368. # hbase.sink.file3.filename=rest.metrics
     
369. 
     
370. 
     
371. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
     
372. *.sink.ganglia.period=10  
     
373. 
     
374. hbase.sink.ganglia.period=10  
     
375. hbase.sink.ganglia.servers=master:8649
     
376. master-hadoop-metrics2.properties.md Raw
     
377. master节点hadoop-metrics2.properties配置
     
378. 
     
379. #
     
380. #   Licensed to the Apache Software Foundation (ASF) under one or more
     
381. #   contributor license agreements.  See the NOTICE file distributed with
     
382. #   this work for additional information regarding copyright ownership.
     
383. #   The ASF licenses this file to You under the Apache License, Version 2.0
     
384. #   (the "License"); you may not use this file except in compliance with
     
385. #   the License.  You may obtain a copy of the License at
     
386. #
     
387. #       http://www.apache.org/licenses/LICENSE-2.0
     
388. #
     
389. #   Unless required by applicable law or agreed to in writing, software
     
390. #   distributed under the License is distributed on an "AS IS" BASIS,
     
391. #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     
392. #   See the License for the specific language governing permissions and
     
393. #   limitations under the License.
     
394. #
     
395. 
     
396. # syntax: [prefix].[source|sink].[instance].[options]
     
397. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
     
398. 
     
399. #*.sink.file.class=org.apache.hadoop.metrics2.sink.FileSink
     
400. # default sampling period, in seconds
     
401. #*.period=10
     
402. 
     
403. # The namenode-metrics.out will contain metrics from all context
     
404. #namenode.sink.file.filename=namenode-metrics.out
     
405. # Specifying a special sampling period for namenode:
     
406. #namenode.sink.*.period=8
     
407. 
     
408. #datanode.sink.file.filename=datanode-metrics.out
     
409. 
     
410. # the following example split metrics of different
     
411. # context to different sinks (in this case files)
     
412. #jobtracker.sink.file_jvm.context=jvm
     
413. #jobtracker.sink.file_jvm.filename=jobtracker-jvm-metrics.out
     
414. #jobtracker.sink.file_mapred.context=mapred
     
415. #jobtracker.sink.file_mapred.filename=jobtracker-mapred-metrics.out
     
416. 
     
417. #tasktracker.sink.file.filename=tasktracker-metrics.out
     
418. 
     
419. #maptask.sink.file.filename=maptask-metrics.out
     
420. 
     
421. #reducetask.sink.file.filename=reducetask-metrics.out
     
422. 
     
423. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
     
424. *.sink.ganglia.period=10
     
425. 
     
426. *.sink.ganglia.slope=jvm.metrics.gcCount=zero,jvm.metrics.memHeapUsedM=both  
     
427. *.sink.ganglia.dmax=jvm.metrics.threadsBlocked=70,jvm.metrics.memHeapUsedM=40  
     
428. 
     
429. namenode.sink.ganglia.servers=master:8649  
     
430. resourcemanager.sink.ganglia.servers=master:8649  
     
431. 
     
432. datanode.sink.ganglia.servers=master:8649    
     
433. nodemanager.sink.ganglia.servers=master:8649    
     
434. 
     
435. 
     
436. maptask.sink.ganglia.servers=master:8649    
     
437. reducetask.sink.ganglia.servers=master:8649
     
438. slave-gmond.conf.md Raw
     
439. slave节点gmond.conf配置
     
440. 
     
441. /* This configuration is as close to 2.5.x default behavior as possible 
     
442.    The values closely match ./gmond/metric.h definitions in 2.5.x */ 
     
443. globals {                    
     
444.   daemonize = yes              
     
445.   setuid = yes             
     
446.   user = ganglia              
     
447.   debug_level = 0               
     
448.   max_udp_msg_len = 1472        
     
449.   mute = no             
     
450.   deaf = no             
     
451.   host_dmax = 0 /*secs */ 
     
452.   cleanup_threshold = 300 /*secs */ 
     
453.   gexec = no             
     
454.   send_metadata_interval = 10     
     
455. } 
     
456. 
     
457. /* If a cluster attribute is specified, then all gmond hosts are wrapped inside 
     
458. * of a <CLUSTER> tag.  If you do not specify a cluster tag, then all <HOSTS> will 
     
459. * NOT be wrapped inside of a <CLUSTER> tag. */ 
     
460. cluster { 
     
461.   name = "hadoop-cluster" 
     
462.   owner = "ganglia" 
     
463.   latlong = "unspecified" 
     
464.   url = "unspecified" 
     
465. } 
     
466. 
     
467. /* The host section describes attributes of the host, like the location */ 
     
468. host { 
     
469.   location = "unspecified" 
     
470. } 
     
471. 
     
472. /* Feel free to specify as many udp_send_channels as you like.  Gmond 
     
473.    used to only support having a single channel */ 
     
474. udp_send_channel { 
     
475.   #mcast_join = 239.2.11.71
     
476.   host = master 
     
477.   port = 8649 
     
478.   ttl = 1 
     
479. } 
     
480. 
     
481. /* You can specify as many udp_recv_channels as you like as well. */ 
     
482. udp_recv_channel { 
     
483.   #mcast_join = 239.2.11.71 
     
484.   port = 8649 
     
485.   #bind = 239.2.11.71 
     
486. } 
     
487. 
     
488. /* You can specify as many tcp_accept_channels as you like to share 
     
489.    an xml description of the state of the cluster */ 
     
490. tcp_accept_channel { 
     
491.   port = 8649 
     
492. } 
     
493. 
     
494. /* Each metrics module that is referenced by gmond must be specified and 
     
495.    loaded. If the module has been statically linked with gmond, it does not 
     
496.    require a load path. However all dynamically loadable modules must include 
     
497.    a load path. */ 
     
498. modules { 
     
499.   module { 
     
500.     name = "core_metrics" 
     
501.   } 
     
502.   module { 
     
503.     name = "cpu_module" 
     
504.     path = "/usr/lib/ganglia/modcpu.so" 
     
505.   } 
     
506.   module { 
     
507.     name = "disk_module" 
     
508.     path = "/usr/lib/ganglia/moddisk.so" 
     
509.   } 
     
510.   module { 
     
511.     name = "load_module" 
     
512.     path = "/usr/lib/ganglia/modload.so" 
     
513.   } 
     
514.   module { 
     
515.     name = "mem_module" 
     
516.     path = "/usr/lib/ganglia/modmem.so" 
     
517.   } 
     
518.   module { 
     
519.     name = "net_module" 
     
520.     path = "/usr/lib/ganglia/modnet.so" 
     
521.   } 
     
522.   module { 
     
523.     name = "proc_module" 
     
524.     path = "/usr/lib/ganglia/modproc.so" 
     
525.   } 
     
526.   module { 
     
527.     name = "sys_module" 
     
528.     path = "/usr/lib/ganglia/modsys.so" 
     
529.   } 
     
530. } 
     
531. 
     
532. include ('/etc/ganglia/conf.d/*.conf') 
     
533. 
     
534. 
     
535. /* The old internal 2.5.x metric array has been replaced by the following 
     
536.    collection_group directives.  What follows is the default behavior for 
     
537.    collecting and sending metrics that is as close to 2.5.x behavior as 
     
538.    possible. */
     
539. 
     
540. /* This collection group will cause a heartbeat (or beacon) to be sent every 
     
541.    20 seconds.  In the heartbeat is the GMOND_STARTED data which expresses 
     
542.    the age of the running gmond. */ 
     
543. collection_group { 
     
544.   collect_once = yes 
     
545.   time_threshold = 20 
     
546.   metric { 
     
547.     name = "heartbeat" 
     
548.   } 
     
549. } 
     
550. 
     
551. /* This collection group will send general info about this host every 1200 secs. 
     
552.    This information doesn't change between reboots and is only collected once. */ 
     
553. collection_group { 
     
554.   collect_once = yes 
     
555.   time_threshold = 1200 
     
556.   metric { 
     
557.     name = "cpu_num" 
     
558.     title = "CPU Count" 
     
559.   } 
     
560.   metric { 
     
561.     name = "cpu_speed" 
     
562.     title = "CPU Speed" 
     
563.   } 
     
564.   metric { 
     
565.     name = "mem_total" 
     
566.     title = "Memory Total" 
     
567.   } 
     
568.   /* Should this be here? Swap can be added/removed between reboots. */ 
     
569.   metric { 
     
570.     name = "swap_total" 
     
571.     title = "Swap Space Total" 
     
572.   } 
     
573.   metric { 
     
574.     name = "boottime" 
     
575.     title = "Last Boot Time" 
     
576.   } 
     
577.   metric { 
     
578.     name = "machine_type" 
     
579.     title = "Machine Type" 
     
580.   } 
     
581.   metric { 
     
582.     name = "os_name" 
     
583.     title = "Operating System" 
     
584.   } 
     
585.   metric { 
     
586.     name = "os_release" 
     
587.     title = "Operating System Release" 
     
588.   } 
     
589.   metric { 
     
590.     name = "location" 
     
591.     title = "Location" 
     
592.   } 
     
593. } 
     
594. 
     
595. /* This collection group will send the status of gexecd for this host every 300 secs */
     
596. /* Unlike 2.5.x the default behavior is to report gexecd OFF.  */ 
     
597. collection_group { 
     
598.   collect_once = yes 
     
599.   time_threshold = 300 
     
600.   metric { 
     
601.     name = "gexec" 
     
602.     title = "Gexec Status" 
     
603.   } 
     
604. } 
     
605. 
     
606. /* This collection group will collect the CPU status info every 20 secs. 
     
607.    The time threshold is set to 90 seconds.  In honesty, this time_threshold could be 
     
608.    set significantly higher to reduce unneccessary network chatter. */ 
     
609. collection_group { 
     
610.   collect_every = 20 
     
611.   time_threshold = 90 
     
612.   /* CPU status */ 
     
613.   metric { 
     
614.     name = "cpu_user"  
     
615.     value_threshold = "1.0" 
     
616.     title = "CPU User" 
     
617.   } 
     
618.   metric { 
     
619.     name = "cpu_system"   
     
620.     value_threshold = "1.0" 
     
621.     title = "CPU System" 
     
622.   } 
     
623.   metric { 
     
624.     name = "cpu_idle"  
     
625.     value_threshold = "5.0" 
     
626.     title = "CPU Idle" 
     
627.   } 
     
628.   metric { 
     
629.     name = "cpu_nice"  
     
630.     value_threshold = "1.0" 
     
631.     title = "CPU Nice" 
     
632.   } 
     
633.   metric { 
     
634.     name = "cpu_aidle" 
     
635.     value_threshold = "5.0" 
     
636.     title = "CPU aidle" 
     
637.   } 
     
638.   metric { 
     
639.     name = "cpu_wio" 
     
640.     value_threshold = "1.0" 
     
641.     title = "CPU wio" 
     
642.   } 
     
643.   /* The next two metrics are optional if you want more detail... 
     
644.      ... since they are accounted for in cpu_system.  
     
645.   metric { 
     
646.     name = "cpu_intr" 
     
647.     value_threshold = "1.0" 
     
648.     title = "CPU intr" 
     
649.   } 
     
650.   metric { 
     
651.     name = "cpu_sintr" 
     
652.     value_threshold = "1.0" 
     
653.     title = "CPU sintr" 
     
654.   } 
     
655.   */ 
     
656. } 
     
657. 
     
658. collection_group { 
     
659.   collect_every = 20 
     
660.   time_threshold = 90 
     
661.   /* Load Averages */ 
     
662.   metric { 
     
663.     name = "load_one" 
     
664.     value_threshold = "1.0" 
     
665.     title = "One Minute Load Average" 
     
666.   } 
     
667.   metric { 
     
668.     name = "load_five" 
     
669.     value_threshold = "1.0" 
     
670.     title = "Five Minute Load Average" 
     
671.   } 
     
672.   metric { 
     
673.     name = "load_fifteen" 
     
674.     value_threshold = "1.0" 
     
675.     title = "Fifteen Minute Load Average" 
     
676.   }
     
677. } 
     
678. 
     
679. /* This group collects the number of running and total processes */ 
     
680. collection_group { 
     
681.   collect_every = 80 
     
682.   time_threshold = 950 
     
683.   metric { 
     
684.     name = "proc_run" 
     
685.     value_threshold = "1.0" 
     
686.     title = "Total Running Processes" 
     
687.   } 
     
688.   metric { 
     
689.     name = "proc_total" 
     
690.     value_threshold = "1.0" 
     
691.     title = "Total Processes" 
     
692.   } 
     
693. }
     
694. 
     
695. /* This collection group grabs the volatile memory metrics every 40 secs and 
     
696.    sends them at least every 180 secs.  This time_threshold can be increased 
     
697.    significantly to reduce unneeded network traffic. */ 
     
698. collection_group { 
     
699.   collect_every = 40 
     
700.   time_threshold = 180 
     
701.   metric { 
     
702.     name = "mem_free" 
     
703.     value_threshold = "1024.0" 
     
704.     title = "Free Memory" 
     
705.   } 
     
706.   metric { 
     
707.     name = "mem_shared" 
     
708.     value_threshold = "1024.0" 
     
709.     title = "Shared Memory" 
     
710.   } 
     
711.   metric { 
     
712.     name = "mem_buffers" 
     
713.     value_threshold = "1024.0" 
     
714.     title = "Memory Buffers" 
     
715.   } 
     
716.   metric { 
     
717.     name = "mem_cached" 
     
718.     value_threshold = "1024.0" 
     
719.     title = "Cached Memory" 
     
720.   } 
     
721.   metric { 
     
722.     name = "swap_free" 
     
723.     value_threshold = "1024.0" 
     
724.     title = "Free Swap Space" 
     
725.   } 
     
726. } 
     
727. 
     
728. collection_group { 
     
729.   collect_every = 40 
     
730.   time_threshold = 300 
     
731.   metric { 
     
732.     name = "bytes_out" 
     
733.     value_threshold = 4096 
     
734.     title = "Bytes Sent" 
     
735.   } 
     
736.   metric { 
     
737.     name = "bytes_in" 
     
738.     value_threshold = 4096 
     
739.     title = "Bytes Received" 
     
740.   } 
     
741.   metric { 
     
742.     name = "pkts_in" 
     
743.     value_threshold = 256 
     
744.     title = "Packets Received" 
     
745.   } 
     
746.   metric { 
     
747.     name = "pkts_out" 
     
748.     value_threshold = 256 
     
749.     title = "Packets Sent" 
     
750.   } 
     
751. }
     
752. 
     
753. /* Different than 2.5.x default since the old config made no sense */ 
     
754. collection_group { 
     
755.   collect_every = 1800 
     
756.   time_threshold = 3600 
     
757.   metric { 
     
758.     name = "disk_total" 
     
759.     value_threshold = 1.0 
     
760.     title = "Total Disk Space" 
     
761.   } 
     
762. }
     
763. 
     
764. collection_group { 
     
765.   collect_every = 40 
     
766.   time_threshold = 180 
     
767.   metric { 
     
768.     name = "disk_free" 
     
769.     value_threshold = 1.0 
     
770.     title = "Disk Space Available" 
     
771.   } 
     
772.   metric { 
     
773.     name = "part_max_used" 
     
774.     value_threshold = 1.0 
     
775.     title = "Maximum Disk Space Used" 
     
776.   } 
     
777. }
     
778. slave-hadoop-metrics2-hbase.properties.md Raw
     
779. slave节点hadoop-metrics2-hbase.properties配置
     
780. 
     
781. # syntax: [prefix].[source|sink].[instance].[options]
     
782. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
     
783. 
     
784. #*.sink.file*.class=org.apache.hadoop.metrics2.sink.FileSink
     
785. # default sampling period
     
786. #*.period=10
     
787. 
     
788. # Below are some examples of sinks that could be used
     
789. # to monitor different hbase daemons.
     
790. 
     
791. # hbase.sink.file-all.class=org.apache.hadoop.metrics2.sink.FileSink
     
792. # hbase.sink.file-all.filename=all.metrics
     
793. 
     
794. # hbase.sink.file0.class=org.apache.hadoop.metrics2.sink.FileSink
     
795. # hbase.sink.file0.context=hmaster
     
796. # hbase.sink.file0.filename=master.metrics
     
797. 
     
798. # hbase.sink.file1.class=org.apache.hadoop.metrics2.sink.FileSink
     
799. # hbase.sink.file1.context=thrift-one
     
800. # hbase.sink.file1.filename=thrift-one.metrics
     
801. 
     
802. # hbase.sink.file2.class=org.apache.hadoop.metrics2.sink.FileSink
     
803. # hbase.sink.file2.context=thrift-two
     
804. # hbase.sink.file2.filename=thrift-one.metrics
     
805. 
     
806. # hbase.sink.file3.class=org.apache.hadoop.metrics2.sink.FileSink
     
807. # hbase.sink.file3.context=rest
     
808. # hbase.sink.file3.filename=rest.metrics
     
809. 
     
810. 
     
811. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
     
812. *.sink.ganglia.period=10  
     
813. 
     
814. hbase.sink.ganglia.period=10  
     
815. hbase.sink.ganglia.servers=master:8649
     
816. slave-hadoop-metrics2.properties.md Raw
     
817. slave节点hadoop-metrics2.properties配置
     
818. 
     
819. #
     
820. #   Licensed to the Apache Software Foundation (ASF) under one or more
     
821. #   contributor license agreements.  See the NOTICE file distributed with
     
822. #   this work for additional information regarding copyright ownership.
     
823. #   The ASF licenses this file to You under the Apache License, Version 2.0
     
824. #   (the "License"); you may not use this file except in compliance with
     
825. #   the License.  You may obtain a copy of the License at
     
826. #
     
827. #       http://www.apache.org/licenses/LICENSE-2.0
     
828. #
     
829. #   Unless required by applicable law or agreed to in writing, software
     
830. #   distributed under the License is distributed on an "AS IS" BASIS,
     
831. #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     
832. #   See the License for the specific language governing permissions and
     
833. #   limitations under the License.
     
834. #
     
835. 
     
836. # syntax: [prefix].[source|sink].[instance].[options]
     
837. # See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
     
838. 
     
839. #*.sink.file.class=org.apache.hadoop.metrics2.sink.FileSink
     
840. # default sampling period, in seconds
     
841. #*.period=10
     
842. 
     
843. # The namenode-metrics.out will contain metrics from all context
     
844. #namenode.sink.file.filename=namenode-metrics.out
     
845. # Specifying a special sampling period for namenode:
     
846. #namenode.sink.*.period=8
     
847. 
     
848. #datanode.sink.file.filename=datanode-metrics.out
     
849. 
     
850. # the following example split metrics of different
     
851. # context to different sinks (in this case files)
     
852. #jobtracker.sink.file_jvm.context=jvm
     
853. #jobtracker.sink.file_jvm.filename=jobtracker-jvm-metrics.out
     
854. #jobtracker.sink.file_mapred.context=mapred
     
855. #jobtracker.sink.file_mapred.filename=jobtracker-mapred-metrics.out
     
856. 
     
857. #tasktracker.sink.file.filename=tasktracker-metrics.out
     
858. 
     
859. #maptask.sink.file.filename=maptask-metrics.out
     
860. 
     
861. #reducetask.sink.file.filename=reducetask-metrics.out
     
862. 
     
863. *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31  
     
864. *.sink.ganglia.period=10
     
865. 
     
866. *.sink.ganglia.slope=jvm.metrics.gcCount=zero,jvm.metrics.memHeapUsedM=both  
     
867. *.sink.ganglia.dmax=jvm.metrics.threadsBlocked=70,jvm.metrics.memHeapUsedM=40  
     
868. 
     
869. namenode.sink.ganglia.servers=master:8649  
     
870. resourcemanager.sink.ganglia.servers=master:8649  
     
871. 
     
872. datanode.sink.ganglia.servers=master:8649    
     
873. nodemanager.sink.ganglia.servers=master:8649    
     
874. 
     
875. 
     
876. maptask.sink.ganglia.servers=master:8649    
     
877. reducetask.sink.ganglia.servers=master:8649
     

复制代码