forked from linkedin/dr-elephant
-
Notifications
You must be signed in to change notification settings - Fork 0
/
JobTypeConf.xml
95 lines (91 loc) · 3.22 KB
/
JobTypeConf.xml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
<?xml version="1.0" encoding="UTF-8"?>
<!--
Copyright 2016 LinkedIn Corp.
Licensed under the Apache License, Version 2.0 (the "License"); you may not
use this file except in compliance with the License. You may obtain a copy of
the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
License for the specific language governing permissions and limitations under
the License.
-->
<!--
This file defines MapReduce jobtype identified by Dr. Elephant
Dr. will match jobtype by looking at particular MR job conf property and value
defined for that job type. For example, if a MR job has 'pig.script' in its configuration,
it will be classified as Pig jobtype; if a MR job has configuration 'mapred.reducer.class'
and value 'HadoopStoreBuilderReducer', it will be a voldemort job.
For each jobtype defined in this file, it is required to have a type name <name>, a conf
name <conf>, and an optional conf value <value>. The optional <value> requires a regex
expression with '.*'(any char multiple times) by default.
<isDefault/> when present is indicating the current JobType is the default choice for an application type. One
application type should have one and only one default choice.
Type matching is top-down - If a job matches multiple types in this file, it will be First
Defined Comes First. If no jobtype in this file matches the job, it will have default jobtype,
which is HadoopJava.
-->
<jobTypes>
<jobType>
<name>Spark</name>
<applicationtype>spark</applicationtype>
<conf>spark.app.id</conf>
<isDefault/>
</jobType>
<jobType>
<name>Pig</name>
<applicationtype>mapreduce</applicationtype>
<conf>pig.script</conf>
</jobType>
<jobType>
<name>Hive-Tez</name>
<applicationtype>TEZ</applicationtype>
<conf>hive.execution.engine</conf>
<isDefault/>
</jobType>
<jobType>
<name>Pig-Tez</name>
<applicationtype>TEZ</applicationtype>
<conf>exectype</conf>
<value>TEZ</value>
</jobType>
<jobType>
<name>Hive</name>
<applicationtype>mapreduce</applicationtype>
<conf>hive.mapred.mode</conf>
</jobType>
<jobType>
<name>OozieLauncher</name>
<applicationtype>mapreduce</applicationtype>
<conf>oozie.launcher.action.main.class</conf>
</jobType>
<jobType>
<name>Cascading</name>
<applicationtype>mapreduce</applicationtype>
<conf>cascading.app.frameworks</conf>
</jobType>
<jobType>
<name>Voldemort</name>
<applicationtype>mapreduce</applicationtype>
<conf>mapred.reducer.class</conf>
<value>voldemort.store.readonly.mr.*</value>
</jobType>
<jobType>
<name>Kafka</name>
<applicationtype>mapreduce</applicationtype>
<conf>kafka.url</conf>
</jobType>
<jobType>
<name>HadoopJava</name>
<applicationtype>mapreduce</applicationtype>
<conf>mapred.child.java.opts</conf>
<isDefault/>
</jobType>
<jobType>
<name>TonY</name>
<applicationtype>TONY</applicationtype>
<conf>tony.application.name</conf>
<isDefault/>
</jobType>
</jobTypes>