Created
July 20, 2009 09:12
-
-
Save jmhodges/150217 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* Calculates the splits that will serve as input for the map tasks. | |
* <ul> | |
* Splits are created in number equal to the smallest between numSplits and | |
* the number of {@link HRegion}s in the table. If the number of splits is | |
* smaller than the number of {@link HRegion}s then splits are spanned across | |
* multiple {@link HRegion}s and are grouped the most evenly possible. In the | |
* case splits are uneven the bigger splits are placed first in the | |
* {@link InputSplit} array. | |
* | |
* @param job the map task {@link JobConf} | |
* @param numSplits a hint to calculate the number of splits (mapred.map.tasks). | |
* | |
* @return the input splits | |
* | |
* @see org.apache.hadoop.mapred.InputFormat#getSplits(org.apache.hadoop.mapred.JobConf, int) | |
*/ | |
public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException { | |
byte [][] startKeys = this.table.getStartKeys(); | |
if (startKeys == null || startKeys.length == 0) { | |
throw new IOException("Expecting at least one region"); | |
} | |
if (this.table == null) { | |
throw new IOException("No table was provided"); | |
} | |
if (this.inputColumns == null || this.inputColumns.length == 0) { | |
throw new IOException("Expecting at least one column"); | |
} | |
int realNumSplits = numSplits > startKeys.length? startKeys.length: | |
numSplits; | |
InputSplit[] splits = new InputSplit[realNumSplits]; | |
int middle = startKeys.length / realNumSplits; | |
int startPos = 0; | |
for (int i = 0; i < realNumSplits; i++) { | |
int lastPos = startPos + middle; | |
lastPos = startKeys.length % realNumSplits > i ? lastPos + 1 : lastPos; | |
String regionLocation = table.getRegionLocation(startKeys[startPos]). | |
getServerAddress().getHostname(); | |
splits[i] = new TableSplit(this.table.getTableName(), | |
startKeys[startPos], ((i + 1) < realNumSplits) ? startKeys[lastPos]: | |
HConstants.EMPTY_START_ROW, regionLocation); | |
LOG.info("split: " + i + "->" + splits[i]); | |
startPos = lastPos; | |
} | |
return splits; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment