[ https://issues.apache.org/jira/browse/MAPREDUCE-6245?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
lbkzman updated MAPREDUCE-6245: ------------------------------- Affects Version/s: 2.6.0 Release Note: index 72b47f2..8b89782 100644 --- src/java/org/apache/hadoop/mapreduce/lib/partition/InputSampler.java +++ src/java/org/apache/hadoop/mapreduce/lib/partition/InputSampler.java @@ -203,12 +203,8 @@ public class InputSampler<K,V> extends Configured implement s Tool { r.setSeed(seed); LOG.debug("seed: " + seed); // shuffle splits - for (int i = 0; i < splits.size(); ++i) { - InputSplit tmp = splits.get(i); - int j = r.nextInt(splits.size()); - splits.set(i, splits.get(j)); - splits.set(j, tmp); - } + Collections.shuffle(splits); + // our target rate is in terms of the maximum number of sample splits, // but we accept the possibility of sampling additional splits to hit // the target sample keyset Status: Patch Available (was: Open) > Fixed split shuffling. > ---------------------- > > Key: MAPREDUCE-6245 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-6245 > Project: Hadoop Map/Reduce > Issue Type: Bug > Affects Versions: 2.6.0 > Reporter: lbkzman > -- This message was sent by Atlassian JIRA (v6.3.4#6332)