You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hbase.apache.org by st...@apache.org on 2010/10/29 01:40:47 UTC
svn commit: r1028546 - in /hbase/trunk: CHANGES.txt
src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java
Author: stack
Date: Thu Oct 28 23:40:47 2010
New Revision: 1028546
URL: http://svn.apache.org/viewvc?rev=1028546&view=rev
Log:
HBASE-3167 HBase Export: Add ability to export specific Column Family; Turn Block Cache off during export; improve usage doc
Modified:
hbase/trunk/CHANGES.txt
hbase/trunk/src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java
Modified: hbase/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/hbase/trunk/CHANGES.txt?rev=1028546&r1=1028545&r2=1028546&view=diff
==============================================================================
--- hbase/trunk/CHANGES.txt (original)
+++ hbase/trunk/CHANGES.txt Thu Oct 28 23:40:47 2010
@@ -1049,6 +1049,9 @@ Release 0.21.0 - Unreleased
LZO when LZO isn't available
HBASE-3082 For ICV gets, first look in MemStore before reading StoreFiles
(prakash via jgray)
+ HBASE-3167 HBase Export: Add ability to export specific Column Family;
+ Turn Block Cache off during export; improve usage doc
+ (Kannan Muthukkaruppan via Stack)
NEW FEATURES
HBASE-1961 HBase EC2 scripts
Modified: hbase/trunk/src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java
URL: http://svn.apache.org/viewvc/hbase/trunk/src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java?rev=1028546&r1=1028545&r2=1028546&view=diff
==============================================================================
--- hbase/trunk/src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java (original)
+++ hbase/trunk/src/main/java/org/apache/hadoop/hbase/mapreduce/Export.java Thu Oct 28 23:40:47 2010
@@ -27,6 +27,7 @@ import org.apache.hadoop.hbase.HBaseConf
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
+import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
@@ -91,6 +92,10 @@ public class Export {
long startTime = args.length > 3? Long.parseLong(args[3]): 0L;
long endTime = args.length > 4? Long.parseLong(args[4]): Long.MAX_VALUE;
s.setTimeRange(startTime, endTime);
+ s.setCacheBlocks(false);
+ if (conf.get(TableInputFormat.SCAN_COLUMN_FAMILY) != null) {
+ s.addFamily(Bytes.toBytes(conf.get(TableInputFormat.SCAN_COLUMN_FAMILY)));
+ }
LOG.info("verisons=" + versions + ", starttime=" + startTime +
", endtime=" + endTime);
TableMapReduceUtil.initTableMapperJob(tableName, s, Exporter.class, null,
@@ -111,8 +116,16 @@ public class Export {
if (errorMsg != null && errorMsg.length() > 0) {
System.err.println("ERROR: " + errorMsg);
}
- System.err.println("Usage: Export <tablename> <outputdir> [<versions> " +
- "[<starttime> [<endtime>]]]");
+ System.err.println("Usage: Export [-D <property=value>]* <tablename> <outputdir> [<versions> " +
+ "[<starttime> [<endtime>]]]\n");
+ System.err.println(" Note: -D properties will be applied to the conf used. ");
+ System.err.println(" For example: ");
+ System.err.println(" -D mapred.output.compress=true");
+ System.err.println(" -D mapred.output.compression.codec=org.apache.hadoop.io.compress.GzipCodec");
+ System.err.println(" -D mapred.output.compression.type=BLOCK");
+ System.err.println(" Additionally, the following SCAN properties can be specified");
+ System.err.println(" to control/limit what is exported..");
+ System.err.println(" -D " + TableInputFormat.SCAN_COLUMN_FAMILY + "=<familyName>");
}
/**