aasha commented on a change in pull request #951: HIVE-22997 : Copy external
table to target during Repl Dump operation
URL: https://github.com/apache/hive/pull/951#discussion_r394293829
##########
File path: ql/src/java/org/apache/hadoop/hive/ql/exec/repl/ReplDumpTask.java
##########
@@ -122,33 +129,38 @@ public String getName() {
@Override
public int execute() {
try {
- Hive hiveDb = getHive();
- Path dumpRoot = new Path(conf.getVar(HiveConf.ConfVars.REPLDIR),
-
Base64.getEncoder().encodeToString(work.dbNameOrPattern.toLowerCase()
- .getBytes(StandardCharsets.UTF_8.name())));
- Path previousDumpMetaPath = getPreviousDumpMetadataPath(dumpRoot);
- Path previousHiveDumpPath =
- previousDumpMetaPath != null ? new Path(previousDumpMetaPath,
ReplUtils.REPL_HIVE_BASE_DIR) : null;
- //If no previous dump is present or previous dump was loaded, proceed
- if (shouldDump(previousHiveDumpPath)) {
- Path currentDumpPath = new Path(dumpRoot, getNextDumpDir());
- Path hiveDumpRoot = new Path(currentDumpPath,
ReplUtils.REPL_HIVE_BASE_DIR);
- DumpMetaData dmd = new DumpMetaData(hiveDumpRoot, conf);
- // Initialize ReplChangeManager instance since we will require it to
encode file URI.
- ReplChangeManager.getInstance(conf);
- Path cmRoot = new Path(conf.getVar(HiveConf.ConfVars.REPLCMDIR));
- Long lastReplId;
- if (previousHiveDumpPath == null) {
- lastReplId = bootStrapDump(hiveDumpRoot, dmd, cmRoot, hiveDb);
+ if (work.dirCopyIteratorInitialized() ||
work.replPathIteratorInitialized()) {
+ intitiateDataCopyTasks();
+ } else {
+ Hive hiveDb = getHive();
+ Path dumpRoot = new Path(conf.getVar(HiveConf.ConfVars.REPLDIR),
+
Base64.getEncoder().encodeToString(work.dbNameOrPattern.toLowerCase()
+ .getBytes(StandardCharsets.UTF_8.name())));
+ Path previousDumpMetaPath = getPreviousDumpMetadataPath(dumpRoot);
+ Path previousHiveDumpPath =
+ previousDumpMetaPath != null ? new Path(previousDumpMetaPath,
ReplUtils.REPL_HIVE_BASE_DIR) : null;
+ //If no previous dump is present or previous dump was loaded, proceed
+ if (shouldDump(previousHiveDumpPath)) {
+ Path currentDumpPath = new Path(dumpRoot, getNextDumpDir());
+ Path hiveDumpRoot = new Path(currentDumpPath,
ReplUtils.REPL_HIVE_BASE_DIR);
+ DumpMetaData dmd = new DumpMetaData(hiveDumpRoot, conf);
+ // Initialize ReplChangeManager instance since we will require it to
encode file URI.
+ ReplChangeManager.getInstance(conf);
+ Path cmRoot = new Path(conf.getVar(HiveConf.ConfVars.REPLCMDIR));
+ Long lastReplId;
+ if (previousHiveDumpPath == null) {
+ lastReplId = bootStrapDump(hiveDumpRoot, dmd, cmRoot, hiveDb);
+ } else {
+
work.setEventFrom(getEventFromPreviousDumpMetadata(previousHiveDumpPath));
+ lastReplId = incrementalDump(hiveDumpRoot, dmd, cmRoot, hiveDb);
+ }
+
prepareReturnValues(Arrays.asList(currentDumpPath.toUri().toString(),
String.valueOf(lastReplId)));
+ deleteAllPreviousDumpMeta(dumpRoot, currentDumpPath);
Review comment:
This should be done at the end
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
