View Javadoc

1   /**
2   *
3   * Licensed to the Apache Software Foundation (ASF) under one
4   * or more contributor license agreements.  See the NOTICE file
5   * distributed with this work for additional information
6   * regarding copyright ownership.  The ASF licenses this file
7   * to you under the Apache License, Version 2.0 (the
8   * "License"); you may not use this file except in compliance
9   * with the License.  You may obtain a copy of the License at
10  *
11  *     http://www.apache.org/licenses/LICENSE-2.0
12  *
13  * Unless required by applicable law or agreed to in writing, software
14  * distributed under the License is distributed on an "AS IS" BASIS,
15  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16  * See the License for the specific language governing permissions and
17  * limitations under the License.
18  */
19  package org.apache.hadoop.hbase.mapreduce;
20  
21  import java.io.IOException;
22  
23  import org.apache.commons.logging.Log;
24  import org.apache.commons.logging.LogFactory;
25  import org.apache.hadoop.classification.InterfaceAudience;
26  import org.apache.hadoop.classification.InterfaceStability;
27  import org.apache.hadoop.conf.Configuration;
28  import org.apache.hadoop.conf.Configured;
29  import org.apache.hadoop.fs.Path;
30  import org.apache.hadoop.hbase.HBaseConfiguration;
31  import org.apache.hadoop.hbase.client.Result;
32  import org.apache.hadoop.hbase.client.Scan;
33  import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
34  import org.apache.hadoop.hbase.filter.Filter;
35  import org.apache.hadoop.hbase.filter.IncompatibleFilterException;
36  import org.apache.hadoop.hbase.filter.PrefixFilter;
37  import org.apache.hadoop.hbase.filter.RegexStringComparator;
38  import org.apache.hadoop.hbase.filter.RowFilter;
39  import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
40  import org.apache.hadoop.hbase.util.Bytes;
41  import org.apache.hadoop.mapreduce.Job;
42  import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
43  import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
44  import org.apache.hadoop.util.GenericOptionsParser;
45  import org.apache.hadoop.util.Tool;
46  import org.apache.hadoop.util.ToolRunner;
47  
48  /**
49  * Export an HBase table.
50  * Writes content to sequence files up in HDFS.  Use {@link Import} to read it
51  * back in again.
52  */
53  @InterfaceAudience.Public
54  @InterfaceStability.Stable
55  public class Export extends Configured implements Tool {
56    private static final Log LOG = LogFactory.getLog(Export.class);
57    final static String NAME = "export";
58    final static String RAW_SCAN = "hbase.mapreduce.include.deleted.rows";
59    final static String EXPORT_BATCHING = "hbase.export.scanner.batch";
60  
61    /**
62     * Sets up the actual job.
63     *
64     * @param conf  The current configuration.
65     * @param args  The command line parameters.
66     * @return The newly created job.
67     * @throws IOException When setting up the job fails.
68     */
69    public static Job createSubmittableJob(Configuration conf, String[] args)
70    throws IOException {
71      String tableName = args[0];
72      Path outputDir = new Path(args[1]);
73      Job job = Job.getInstance(conf, NAME + "_" + tableName);
74      job.setJobName(NAME + "_" + tableName);
75      job.setJarByClass(Export.class);
76      // Set optional scan parameters
77      Scan s = getConfiguredScanForJob(conf, args);
78      IdentityTableMapper.initJob(tableName, s, IdentityTableMapper.class, job);
79      // No reducers.  Just write straight to output files.
80      job.setNumReduceTasks(0);
81      job.setOutputFormatClass(SequenceFileOutputFormat.class);
82      job.setOutputKeyClass(ImmutableBytesWritable.class);
83      job.setOutputValueClass(Result.class);
84      FileOutputFormat.setOutputPath(job, outputDir); // job conf doesn't contain the conf so doesn't have a default fs.
85      return job;
86    }
87  
88    private static Scan getConfiguredScanForJob(Configuration conf, String[] args) throws IOException {
89      Scan s = new Scan();
90      // Optional arguments.
91      // Set Scan Versions
92      int versions = args.length > 2? Integer.parseInt(args[2]): 1;
93      s.setMaxVersions(versions);
94      // Set Scan Range
95      long startTime = args.length > 3? Long.parseLong(args[3]): 0L;
96      long endTime = args.length > 4? Long.parseLong(args[4]): Long.MAX_VALUE;
97      s.setTimeRange(startTime, endTime);
98      // Set cache blocks
99      s.setCacheBlocks(false);
100     // set Start and Stop row
101     if (conf.get(TableInputFormat.SCAN_ROW_START) != null) {
102       s.setStartRow(Bytes.toBytes(conf.get(TableInputFormat.SCAN_ROW_START)));
103     }
104     if (conf.get(TableInputFormat.SCAN_ROW_STOP) != null) {
105       s.setStopRow(Bytes.toBytes(conf.get(TableInputFormat.SCAN_ROW_STOP)));
106     }
107     // Set Scan Column Family
108     boolean raw = Boolean.parseBoolean(conf.get(RAW_SCAN));
109     if (raw) {
110       s.setRaw(raw);
111     }
112     
113     if (conf.get(TableInputFormat.SCAN_COLUMN_FAMILY) != null) {
114       s.addFamily(Bytes.toBytes(conf.get(TableInputFormat.SCAN_COLUMN_FAMILY)));
115     }
116     // Set RowFilter or Prefix Filter if applicable.
117     Filter exportFilter = getExportFilter(args);
118     if (exportFilter!= null) {
119         LOG.info("Setting Scan Filter for Export.");
120       s.setFilter(exportFilter);
121     }
122 
123     int batching = conf.getInt(EXPORT_BATCHING, -1);
124     if (batching !=  -1){
125       try {
126         s.setBatch(batching);
127       } catch (IncompatibleFilterException e) {
128         LOG.error("Batching could not be set", e);
129       }
130     }
131     LOG.info("versions=" + versions + ", starttime=" + startTime +
132       ", endtime=" + endTime + ", keepDeletedCells=" + raw);
133     return s;
134   }
135 
136   private static Filter getExportFilter(String[] args) {
137     Filter exportFilter = null;
138     String filterCriteria = (args.length > 5) ? args[5]: null;
139     if (filterCriteria == null) return null;
140     if (filterCriteria.startsWith("^")) {
141       String regexPattern = filterCriteria.substring(1, filterCriteria.length());
142       exportFilter = new RowFilter(CompareOp.EQUAL, new RegexStringComparator(regexPattern));
143     } else {
144       exportFilter = new PrefixFilter(Bytes.toBytes(filterCriteria));
145     }
146     return exportFilter;
147   }
148 
149   /*
150    * @param errorMsg Error message.  Can be null.
151    */
152   private static void usage(final String errorMsg) {
153     if (errorMsg != null && errorMsg.length() > 0) {
154       System.err.println("ERROR: " + errorMsg);
155     }
156     System.err.println("Usage: Export [-D <property=value>]* <tablename> <outputdir> [<versions> " +
157       "[<starttime> [<endtime>]] [^[regex pattern] or [Prefix] to filter]]\n");
158     System.err.println("  Note: -D properties will be applied to the conf used. ");
159     System.err.println("  For example: ");
160     System.err.println("   -D mapreduce.output.fileoutputformat.compress=true");
161     System.err.println("   -D mapreduce.output.fileoutputformat.compress.codec=org.apache.hadoop.io.compress.GzipCodec");
162     System.err.println("   -D mapreduce.output.fileoutputformat.compress.type=BLOCK");
163     System.err.println("  Additionally, the following SCAN properties can be specified");
164     System.err.println("  to control/limit what is exported..");
165     System.err.println("   -D " + TableInputFormat.SCAN_COLUMN_FAMILY + "=<familyName>");
166     System.err.println("   -D " + RAW_SCAN + "=true");
167     System.err.println("   -D " + TableInputFormat.SCAN_ROW_START + "=<ROWSTART>");
168     System.err.println("   -D " + TableInputFormat.SCAN_ROW_STOP + "=<ROWSTOP>");
169     System.err.println("For performance consider the following properties:\n"
170         + "   -Dhbase.client.scanner.caching=100\n"
171         + "   -Dmapreduce.map.speculative=false\n"
172         + "   -Dmapreduce.reduce.speculative=false");
173     System.err.println("For tables with very wide rows consider setting the batch size as below:\n"
174         + "   -D" + EXPORT_BATCHING + "=10");
175   }
176 
177 
178   @Override
179   public int run(String[] args) throws Exception {
180     String[] otherArgs = new GenericOptionsParser(getConf(), args).getRemainingArgs();
181     if (otherArgs.length < 2) {
182       usage("Wrong number of arguments: " + otherArgs.length);
183       return -1;
184     }
185     Job job = createSubmittableJob(getConf(), otherArgs);
186     return (job.waitForCompletion(true) ? 0 : 1);
187   }
188 
189   /**
190    * Main entry point.
191    * @param args The command line parameters.
192    * @throws Exception When running the job fails.
193    */
194   public static void main(String[] args) throws Exception {
195     int errCode = ToolRunner.run(HBaseConfiguration.create(), new Export(), args);
196     System.exit(errCode);
197   }
198 }