bbeaudreault commented on code in PR #5534:
URL: https://github.com/apache/hbase/pull/5534#discussion_r1407632654
##########
hbase-server/src/main/java/org/apache/hadoop/hbase/master/procedure/ReopenTableRegionsProcedure.java:
##########
@@ -139,33 +170,57 @@ protected Flow executeFromState(MasterProcedureEnv env,
ReopenTableRegionsState
case REOPEN_TABLE_REGIONS_CONFIRM_REOPENED:
regions =
regions.stream().map(env.getAssignmentManager().getRegionStates()::checkReopened)
.filter(l -> l != null).collect(Collectors.toList());
- if (regions.isEmpty()) {
- return Flow.NO_MORE_STATE;
+ // we need to create a set of region names because the HRegionLocation
hashcode is only
+ // based
+ // on the server name
+ Set<byte[]> currentRegionBatchNames = currentRegionBatch.stream()
+ .map(r -> r.getRegion().getRegionName()).collect(Collectors.toSet());
+ currentRegionBatch = regions.stream()
+ .filter(r ->
currentRegionBatchNames.contains(r.getRegion().getRegionName()))
+ .collect(Collectors.toList());
+ if (currentRegionBatch.isEmpty()) {
+ if (regions.isEmpty()) {
+ return Flow.NO_MORE_STATE;
+ } else {
+
setNextState(ReopenTableRegionsState.REOPEN_TABLE_REGIONS_REOPEN_REGIONS);
+ if (reopenBatchBackoffMillis > 0) {
+ backoff(reopenBatchBackoffMillis);
+ }
+ return Flow.HAS_MORE_STATE;
+ }
}
- if (regions.stream().anyMatch(loc -> canSchedule(env, loc))) {
+ if (currentRegionBatch.stream().anyMatch(loc -> canSchedule(env,
loc))) {
retryCounter = null;
setNextState(ReopenTableRegionsState.REOPEN_TABLE_REGIONS_REOPEN_REGIONS);
+ if (reopenBatchBackoffMillis > 0) {
+ backoff(reopenBatchBackoffMillis);
+ }
return Flow.HAS_MORE_STATE;
}
// We can not schedule TRSP for all the regions need to reopen, wait
for a while and retry
// again.
if (retryCounter == null) {
retryCounter =
ProcedureUtil.createRetryCounter(env.getMasterConfiguration());
}
- long backoff = retryCounter.getBackoffTimeAndIncrementAttempts();
+ long backoffMillis = retryCounter.getBackoffTimeAndIncrementAttempts();
LOG.info(
- "There are still {} region(s) which need to be reopened for table {}
are in "
+ "There are still {} region(s) which need to be reopened for table
{}. {} are in "
+ "OPENING state, suspend {}secs and try again later",
- regions.size(), tableName, backoff / 1000);
- setTimeout(Math.toIntExact(backoff));
- setState(ProcedureProtos.ProcedureState.WAITING_TIMEOUT);
- skipPersistence();
+ regions.size(), tableName, currentRegionBatch.size(), backoffMillis
/ 1000);
+ backoff(backoffMillis);
throw new ProcedureSuspendedException();
default:
throw new UnsupportedOperationException("unhandled state=" + state);
}
}
+ private void backoff(long millis) throws ProcedureSuspendedException {
+ setTimeout(Math.toIntExact(millis));
+ setState(ProcedureProtos.ProcedureState.WAITING_TIMEOUT);
+ skipPersistence();
Review Comment:
Ya so the current region list is serialized into the proto. I think we need
to not skip persistence and update the serialization to either remove the
current batch or add some sort of offset to the proto. Otherwise let's say this
crashed right before finishing -- restarting up, it's have to reopen all of the
regions again (in our case often many thousands). If we persist an offset we
can pick up right where we left off.
--
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]
