Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
GiraphRunner |
|
| 2.8;2.8 |
1 | /* | |
2 | * Licensed to the Apache Software Foundation (ASF) under one | |
3 | * or more contributor license agreements. See the NOTICE file | |
4 | * distributed with this work for additional information | |
5 | * regarding copyright ownership. The ASF licenses this file | |
6 | * to you under the Apache License, Version 2.0 (the | |
7 | * "License"); you may not use this file except in compliance | |
8 | * with the License. You may obtain a copy of the License at | |
9 | * | |
10 | * http://www.apache.org/licenses/LICENSE-2.0 | |
11 | * | |
12 | * Unless required by applicable law or agreed to in writing, software | |
13 | * distributed under the License is distributed on an "AS IS" BASIS, | |
14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
15 | * See the License for the specific language governing permissions and | |
16 | * limitations under the License. | |
17 | */ | |
18 | package org.apache.giraph; | |
19 | ||
20 | import org.apache.commons.cli.CommandLine; | |
21 | import org.apache.giraph.io.formats.FileOutputFormatUtil; | |
22 | import org.apache.giraph.utils.ConfigurationUtils; | |
23 | import org.apache.giraph.conf.GiraphConfiguration; | |
24 | import org.apache.giraph.job.GiraphJob; | |
25 | /*if[PURE_YARN] | |
26 | import org.apache.giraph.yarn.GiraphYarnClient; | |
27 | end[PURE_YARN]*/ | |
28 | import org.apache.hadoop.conf.Configuration; | |
29 | import org.apache.hadoop.filecache.DistributedCache; | |
30 | import org.apache.hadoop.fs.Path; | |
31 | import org.apache.hadoop.util.Tool; | |
32 | import org.apache.hadoop.util.ToolRunner; | |
33 | import org.apache.log4j.Logger; | |
34 | import java.net.URI; | |
35 | ||
36 | /** | |
37 | * Helper class to run Giraph applications by specifying the actual class name | |
38 | * to use (i.e. vertex, vertex input/output format, combiner, etc.). | |
39 | * | |
40 | * This is the default entry point for Giraph jobs running on any Hadoop | |
41 | * cluster, MRv1 or v2, including Hadoop-specific configuration and setup. | |
42 | */ | |
43 | 0 | public class GiraphRunner implements Tool { |
44 | static { | |
45 | 0 | Configuration.addDefaultResource("giraph-site.xml"); |
46 | } | |
47 | ||
48 | /** Class logger */ | |
49 | 0 | private static final Logger LOG = Logger.getLogger(GiraphRunner.class); |
50 | /** Writable conf */ | |
51 | private Configuration conf; | |
52 | ||
53 | @Override | |
54 | public Configuration getConf() { | |
55 | 0 | return conf; |
56 | } | |
57 | ||
58 | @Override | |
59 | public void setConf(Configuration conf) { | |
60 | 0 | this.conf = conf; |
61 | 0 | } |
62 | ||
63 | @Override | |
64 | /** | |
65 | * Drives a job run configured for "Giraph on Hadoop MR cluster" | |
66 | * @param args the command line arguments | |
67 | * @return job run exit code | |
68 | */ | |
69 | public int run(String[] args) throws Exception { | |
70 | 0 | if (null == getConf()) { // for YARN profile |
71 | 0 | conf = new Configuration(); |
72 | } | |
73 | 0 | GiraphConfiguration giraphConf = new GiraphConfiguration(getConf()); |
74 | 0 | CommandLine cmd = ConfigurationUtils.parseArgs(giraphConf, args); |
75 | 0 | if (null == cmd) { |
76 | 0 | return 0; // user requested help/info printout, don't run a job. |
77 | } | |
78 | ||
79 | // set up job for various platforms | |
80 | 0 | final String vertexClassName = args[0]; |
81 | 0 | final String jobName = "Giraph: " + vertexClassName; |
82 | /*if[PURE_YARN] | |
83 | GiraphYarnClient job = new GiraphYarnClient(giraphConf, jobName); | |
84 | else[PURE_YARN]*/ | |
85 | 0 | GiraphJob job = new GiraphJob(giraphConf, jobName); |
86 | 0 | prepareHadoopMRJob(job, cmd); |
87 | /*end[PURE_YARN]*/ | |
88 | ||
89 | // run the job, collect results | |
90 | 0 | if (LOG.isDebugEnabled()) { |
91 | 0 | LOG.debug("Attempting to run Vertex: " + vertexClassName); |
92 | } | |
93 | 0 | boolean verbose = !cmd.hasOption('q'); |
94 | 0 | return job.run(verbose) ? 0 : -1; |
95 | } | |
96 | ||
97 | /** | |
98 | * Populate internal Hadoop Job (and Giraph IO Formats) with Hadoop-specific | |
99 | * configuration/setup metadata, propagating exceptions to calling code. | |
100 | * @param job the GiraphJob object to help populate Giraph IO Format data. | |
101 | * @param cmd the CommandLine for parsing Hadoop MR-specific args. | |
102 | */ | |
103 | private void prepareHadoopMRJob(final GiraphJob job, final CommandLine cmd) | |
104 | throws Exception { | |
105 | 0 | if (cmd.hasOption("vof") || cmd.hasOption("eof")) { |
106 | 0 | if (cmd.hasOption("op")) { |
107 | 0 | FileOutputFormatUtil.setOutputPath(job.getInternalJob(), |
108 | 0 | new Path(cmd.getOptionValue("op"))); |
109 | } | |
110 | } | |
111 | 0 | if (cmd.hasOption("cf")) { |
112 | 0 | DistributedCache.addCacheFile(new URI(cmd.getOptionValue("cf")), |
113 | 0 | job.getConfiguration()); |
114 | } | |
115 | 0 | } |
116 | ||
117 | /** | |
118 | * Execute GiraphRunner. | |
119 | * | |
120 | * @param args Typically command line arguments. | |
121 | * @throws Exception Any exceptions thrown. | |
122 | */ | |
123 | public static void main(String[] args) throws Exception { | |
124 | 0 | System.exit(ToolRunner.run(new GiraphRunner(), args)); |
125 | 0 | } |
126 | } |