charlesconnell commented on code in PR #7129:
URL: https://github.com/apache/hbase/pull/7129#discussion_r2175588904
##########
hbase-mapreduce/src/main/java/org/apache/hadoop/hbase/snapshot/ExportSnapshot.java:
##########
@@ -800,29 +857,63 @@ public List<InputSplit> getSplits(JobContext context)
throws IOException, Interr
conf.setInt(MR_NUM_MAPS, mappers);
}
- List<List<Pair<SnapshotFileInfo, Long>>> groups =
getBalancedSplits(snapshotFiles, mappers);
- List<InputSplit> splits = new ArrayList(groups.size());
- for (List<Pair<SnapshotFileInfo, Long>> files : groups) {
- splits.add(new ExportSnapshotInputSplit(files));
+ Class<? extends CustomFileGrouper> inputFileGrouperClass = conf.getClass(
+ CONF_INPUT_FILE_GROUPER_CLASS, NoopCustomFileGrouper.class,
CustomFileGrouper.class);
+ CustomFileGrouper customFileGrouper =
+ ReflectionUtils.newInstance(inputFileGrouperClass, conf);
+ Collection<Collection<Pair<SnapshotFileInfo, Long>>> groups =
+ customFileGrouper.getGroupedInputFiles(snapshotFiles);
+
+ LOG.info("CustomFileGrouper {} split input files into {} groups",
inputFileGrouperClass,
+ groups.size());
+ int mappersPerGroup = groups.isEmpty() ? 1 : Math.max(mappers /
groups.size(), 1);
+ LOG.info(
+ "Splitting each group into {} InputSplits, "
+ + "to achieve closest possible amount of mappers to target of {}",
+ mappersPerGroup, mappers);
+
+ Collection<List<Pair<SnapshotFileInfo, Long>>> balancedGroups =
+ groups.stream().map(g -> getBalancedSplits(g,
mappersPerGroup)).flatMap(Collection::stream)
+ .collect(Collectors.toList());
+
Review Comment:
done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
