ArkoSharma commented on a change in pull request #2539:
URL: https://github.com/apache/hive/pull/2539#discussion_r722352700
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/exec/repl/ReplExternalTables.java
##########
@@ -192,64 +196,135 @@ private void dirLocationToCopy(String tableName,
FileList fileList, Path sourceP
fileList.add(new DirCopyWork(tableName, sourcePath, targetPath, copyMode,
snapshotPrefix).convertToString());
}
- private SnapshotUtils.SnapshotCopyMode createSnapshotsAtSource(Path
sourcePath, String snapshotPrefix,
- boolean isSnapshotEnabled, HiveConf conf,
SnapshotUtils.ReplSnapshotCount replSnapshotCount, FileList snapPathFileList,
- ArrayList<String> prevSnaps, boolean isBootstrap) throws IOException {
+ private Map<String, SnapshotUtils.SnapshotCopyMode>
createSnapshotsAtSource(Path sourcePath, Path targetPath, String snapshotPrefix,
+
boolean isSnapshotEnabled, HiveConf conf, SnapshotUtils.ReplSnapshotCount
replSnapshotCount, FileList snapPathFileList,
+
ArrayList<String> prevSnaps, boolean isBootstrap) throws IOException {
+ Map<String, SnapshotUtils.SnapshotCopyMode> ret = new HashMap<>();
+ ret.put(snapshotPrefix, FALLBACK_COPY);
if (!isSnapshotEnabled) {
LOG.info("Snapshot copy not enabled for path {} Will use normal distCp
for copying data.", sourcePath);
- return FALLBACK_COPY;
+ return ret;
}
+ String prefix = snapshotPrefix;
+ SnapshotUtils.SnapshotCopyMode copyMode = FALLBACK_COPY;
DistributedFileSystem sourceDfs = SnapshotUtils.getDFS(sourcePath, conf);
try {
- if(isBootstrap) {
+ if(conf.getBoolVar(HiveConf.ConfVars.REPL_REUSE_SNAPSHOTS)) {
+ try {
+ FileStatus[] listing = sourceDfs.listStatus(new Path(sourcePath,
".snapshot"));
+ for (FileStatus elem : listing) {
+ String snapShotName = elem.getPath().getName();
+ if (snapShotName.contains(OLD_SNAPSHOT)) {
+ prefix = snapShotName.substring(0,
snapShotName.lastIndexOf(OLD_SNAPSHOT));
+ break;
+ }
+ if (snapShotName.contains(NEW_SNAPSHOT)) {
+ prefix = snapShotName.substring(0,
snapShotName.lastIndexOf(NEW_SNAPSHOT));
+ break;
+ }
+ }
+ ret.clear();
+ ret.put(prefix, copyMode);
+ snapshotPrefix = prefix;
+ } catch (SnapshotException e) {
+ //dir not snapshottable, continue
+ }
+ }
+ boolean isFirstSnapshotAvl =
+ SnapshotUtils.isSnapshotAvailable(sourceDfs, sourcePath,
snapshotPrefix, OLD_SNAPSHOT, conf);
+ boolean isSecondSnapAvl =
+ SnapshotUtils.isSnapshotAvailable(sourceDfs, sourcePath,
snapshotPrefix, NEW_SNAPSHOT, conf);
+ //for bootstrap and non - failback case, use initial_copy
+ if(isBootstrap && !(!isSecondSnapAvl && isFirstSnapshotAvl)) {
// Delete any pre existing snapshots.
SnapshotUtils.deleteSnapshotIfExists(sourceDfs, sourcePath,
firstSnapshot(snapshotPrefix), conf);
SnapshotUtils.deleteSnapshotIfExists(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf);
allowAndCreateInitialSnapshot(sourcePath, snapshotPrefix, conf,
replSnapshotCount, snapPathFileList, sourceDfs);
- return INITIAL_COPY;
+ ret.put(prefix, INITIAL_COPY);
+ return ret;
}
+ //While resuming a failed replication
if (prevSnaps.contains(sourcePath.toString())) {
Review comment:
Added.
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/exec/repl/DirCopyTask.java
##########
@@ -243,18 +244,25 @@ boolean copyUsingDistCpSnapshots(Path sourcePath, Path
targetPath, UserGroupInfo
DistributedFileSystem targetFs = SnapshotUtils.getDFS(targetPath,
clonedConf);
boolean result = false;
+ boolean isSecondSnapshotAvl =
Review comment:
Renamed.
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/exec/repl/DirCopyTask.java
##########
@@ -243,18 +244,25 @@ boolean copyUsingDistCpSnapshots(Path sourcePath, Path
targetPath, UserGroupInfo
DistributedFileSystem targetFs = SnapshotUtils.getDFS(targetPath,
clonedConf);
boolean result = false;
+ boolean isSecondSnapshotAvl =
+ SnapshotUtils.isSnapshotAvailable(targetFs, targetPath,
work.getSnapshotPrefix(), NEW_SNAPSHOT, clonedConf);
if
(getWork().getCopyMode().equals(SnapshotUtils.SnapshotCopyMode.DIFF_COPY)) {
+ if(isSecondSnapshotAvl) {
Review comment:
Added.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
