NihalJain commented on code in PR #7975:
URL: https://github.com/apache/hbase/pull/7975#discussion_r2988900383
##########
hbase-mapreduce/src/main/java/org/apache/hadoop/hbase/mapreduce/TableSnapshotInputFormatImpl.java:
##########
@@ -424,74 +424,76 @@ public static List<InputSplit> getSplits(Scan scan,
SnapshotManifest manifest,
Connection connection = null;
RegionLocator regionLocator = null;
- if (localityEnabled && useRegionLoc) {
- Configuration newConf = new Configuration(conf);
- newConf.setInt("hbase.hconnection.threads.max", 1);
- try {
+ List<InputSplit> splits = new ArrayList<>();
+ try {
+ if (localityEnabled && useRegionLoc) {
+ Configuration newConf = new Configuration(conf);
+ newConf.setInt("hbase.hconnection.threads.max", 1);
+
connection = ConnectionFactory.createConnection(newConf);
regionLocator = connection.getRegionLocator(htd.getTableName());
/* Get all locations for the table and cache it */
regionLocator.getAllRegionLocations();
- } finally {
- if (connection != null) {
- connection.close();
- }
}
- }
- List<InputSplit> splits = new ArrayList<>();
- for (RegionInfo hri : regionManifests) {
- // load region descriptor
- List<String> hosts = null;
- if (localityEnabled) {
- if (regionLocator != null) {
- /* Get Location from the local cache */
- HRegionLocation location =
regionLocator.getRegionLocation(hri.getStartKey(), false);
-
- hosts = new ArrayList<>(1);
- hosts.add(location.getHostname());
- } else {
- hosts = calculateLocationsForInputSplit(conf, htd, hri, tableDir);
+ for (RegionInfo hri : regionManifests) {
+ // load region descriptor
+ List<String> hosts = null;
+ if (localityEnabled) {
+ if (regionLocator != null) {
+ /* Get Location from the local cache */
+ HRegionLocation location =
regionLocator.getRegionLocation(hri.getStartKey(), false);
+
+ hosts = new ArrayList<>(1);
+ hosts.add(location.getHostname());
+ } else {
+ hosts = calculateLocationsForInputSplit(conf, htd, hri, tableDir);
+ }
}
- }
- if (numSplits > 1) {
- byte[][] sp = sa.split(hri.getStartKey(), hri.getEndKey(), numSplits,
true);
- for (int i = 0; i < sp.length - 1; i++) {
+ if (numSplits > 1) {
+ byte[][] sp = sa.split(hri.getStartKey(), hri.getEndKey(),
numSplits, true);
+ for (int i = 0; i < sp.length - 1; i++) {
+ if (
+ PrivateCellUtil.overlappingKeys(scan.getStartRow(),
scan.getStopRow(), sp[i],
+ sp[i + 1])
+ ) {
+
+ Scan boundedScan = new Scan(scan);
+ if (scan.getStartRow().length == 0) {
+ boundedScan.withStartRow(sp[i]);
+ } else {
+ boundedScan.withStartRow(
+ Bytes.compareTo(scan.getStartRow(), sp[i]) > 0 ?
scan.getStartRow() : sp[i]);
+ }
+
+ if (scan.getStopRow().length == 0) {
+ boundedScan.withStopRow(sp[i + 1]);
+ } else {
+ boundedScan.withStopRow(Bytes.compareTo(scan.getStopRow(),
sp[i + 1]) < 0
+ ? scan.getStopRow()
+ : sp[i + 1]);
+ }
+
+ splits.add(new InputSplit(htd, hri, hosts, boundedScan,
restoreDir));
+ }
+ }
+ } else {
if (
- PrivateCellUtil.overlappingKeys(scan.getStartRow(),
scan.getStopRow(), sp[i], sp[i + 1])
+ PrivateCellUtil.overlappingKeys(scan.getStartRow(),
scan.getStopRow(),
+ hri.getStartKey(), hri.getEndKey())
) {
- Scan boundedScan = new Scan(scan);
- if (scan.getStartRow().length == 0) {
- boundedScan.withStartRow(sp[i]);
- } else {
- boundedScan.withStartRow(
- Bytes.compareTo(scan.getStartRow(), sp[i]) > 0 ?
scan.getStartRow() : sp[i]);
- }
-
- if (scan.getStopRow().length == 0) {
- boundedScan.withStopRow(sp[i + 1]);
- } else {
- boundedScan.withStopRow(
- Bytes.compareTo(scan.getStopRow(), sp[i + 1]) < 0 ?
scan.getStopRow() : sp[i + 1]);
- }
-
- splits.add(new InputSplit(htd, hri, hosts, boundedScan,
restoreDir));
+ splits.add(new InputSplit(htd, hri, hosts, scan, restoreDir));
}
}
- } else {
- if (
- PrivateCellUtil.overlappingKeys(scan.getStartRow(),
scan.getStopRow(), hri.getStartKey(),
- hri.getEndKey())
- ) {
-
- splits.add(new InputSplit(htd, hri, hosts, scan, restoreDir));
- }
+ }
+ } finally {
+ if (connection != null) {
Review Comment:
i believe all changes are just because we added an extra block {} and code
got shifted?
--
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]
