ArkoSharma commented on a change in pull request #2539:
URL: https://github.com/apache/hive/pull/2539#discussion_r759005160
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/exec/repl/ReplExternalTables.java
##########
@@ -189,57 +191,137 @@ private void dirLocationToCopy(String tableName,
FileList fileList, Path sourceP
targetPath = new Path(Utils.replaceHost(targetPath.toString(),
sourcePath.toUri().getHost()));
sourcePath = new Path(Utils.replaceHost(sourcePath.toString(),
remoteNS));
}
- fileList.add(new DirCopyWork(tableName, sourcePath, targetPath, copyMode,
snapshotPrefix).convertToString());
+ fileList.add(new DirCopyWork(tableName, sourcePath, targetPath, copyMode,
snapshotPrefix, isBootstrap).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 {
+ 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 {
if (!isSnapshotEnabled) {
LOG.info("Snapshot copy not enabled for path {} Will use normal distCp
for copying data.", sourcePath);
return FALLBACK_COPY;
}
DistributedFileSystem sourceDfs = SnapshotUtils.getDFS(sourcePath, conf);
try {
- if(isBootstrap) {
- // 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;
+ if(isBootstrap &&
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();
+ String prefix;
+ if (snapShotName.contains(OLD_SNAPSHOT)) {
+ prefix = snapShotName.substring(0,
snapShotName.lastIndexOf(OLD_SNAPSHOT));
+ if(!prefix.equals(snapshotPrefix)) {
+ sourceDfs.renameSnapshot(sourcePath, firstSnapshot(prefix),
firstSnapshot(snapshotPrefix));
+ }
+ }
+ if (snapShotName.contains(NEW_SNAPSHOT)) {
+ prefix = snapShotName.substring(0,
snapShotName.lastIndexOf(NEW_SNAPSHOT));
+ if(!prefix.equals(snapshotPrefix)) {
+ sourceDfs.renameSnapshot(sourcePath, secondSnapshot(prefix),
secondSnapshot(snapshotPrefix));
+ }
+ }
+ }
+ } catch (SnapshotException e) {
+ //dir not snapshottable, continue
+ }
}
+ boolean firstSnapAvailable =
+ SnapshotUtils.isSnapshotAvailable(sourceDfs, sourcePath,
snapshotPrefix, OLD_SNAPSHOT, conf);
+ boolean secondSnapAvailable =
+ SnapshotUtils.isSnapshotAvailable(sourceDfs, sourcePath,
snapshotPrefix, NEW_SNAPSHOT, conf);
+ //While resuming a failed replication
if (prevSnaps.contains(sourcePath.toString())) {
// We already created a snapshot for this, just refresh the latest
snapshot and leave.
- sourceDfs.deleteSnapshot(sourcePath, secondSnapshot(snapshotPrefix));
- replSnapshotCount.incrementNumDeleted();
+ // In case of reverse replication after fail-over, in some paths,
second snapshot may not be present.
+ if(SnapshotUtils.deleteSnapshotIfExists(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf)) {
+ replSnapshotCount.incrementNumDeleted();
+ }
SnapshotUtils.createSnapshot(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf);
replSnapshotCount.incrementNumCreated();
snapPathFileList.add(sourcePath.toString());
return SnapshotUtils
- .isSnapshotAvailable(sourceDfs, sourcePath, snapshotPrefix,
OLD_SNAPSHOT, conf) ? DIFF_COPY : INITIAL_COPY;
+ .isSnapshotAvailable(sourceDfs, sourcePath, snapshotPrefix,
OLD_SNAPSHOT, conf) ? DIFF_COPY : INITIAL_COPY;
}
- // check if second snapshot exists.
- boolean isSecondSnapAvlb = SnapshotUtils.isSnapshotAvailable(sourceDfs,
sourcePath, snapshotPrefix,
- OLD_SNAPSHOT, conf);
- if (isSecondSnapAvlb) {
- sourceDfs.deleteSnapshot(sourcePath, firstSnapshot(snapshotPrefix));
- replSnapshotCount.incrementNumDeleted();
- sourceDfs.renameSnapshot(sourcePath, secondSnapshot(snapshotPrefix),
firstSnapshot(snapshotPrefix));
- SnapshotUtils.createSnapshot(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf);
- replSnapshotCount.incrementNumCreated();
- snapPathFileList.add(sourcePath.toString());
- return DIFF_COPY;
- } else {
- // Check if first snapshot is available
- boolean isFirstSnapshotAvailable =
- SnapshotUtils.isSnapshotAvailable(sourceDfs, sourcePath,
snapshotPrefix, NEW_SNAPSHOT, conf);
- if (isFirstSnapshotAvailable) {
+
+ //for bootstrap and forward replication
+ if(isBootstrap && !(!secondSnapAvailable && firstSnapAvailable)) {
+ if (conf.getBoolVar(HiveConf.ConfVars.REPL_REUSE_SNAPSHOTS)) {
+ //this can be used in re-bootstrap cases after irrecoverable error
+ if(SnapshotUtils.deleteSnapshotIfExists(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf)) {
+ replSnapshotCount.incrementNumDeleted();
+ }
+ SnapshotUtils.createSnapshot(sourceDfs, sourcePath,
secondSnapshot(snapshotPrefix), conf);
+ snapPathFileList.add(sourcePath.toString());
+ replSnapshotCount.incrementNumCreated();
+ return SnapshotUtils
+ .isSnapshotAvailable(sourceDfs, sourcePath, snapshotPrefix,
OLD_SNAPSHOT, conf) ? DIFF_COPY : INITIAL_COPY;
+ } else {
Review comment:
This case is included in the following block (included in comment).
(!secondSnapAvailable && firstSnapAvailable) - this condition denotes
reverse replication taking place for the first time for a particular path. So
the execution is similar for both incremental and bootstrap - whereby we either
reuse the snaps or don't depending upon the conf. For this purpose, this case
is clubbed for both.
--
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]
