sumitagrawl commented on code in PR #3751:
URL: https://github.com/apache/ozone/pull/3751#discussion_r977563198
##########
hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/balancer/ContainerBalancer.java:
##########
@@ -529,22 +529,17 @@ private void checkIterationMoveResults() {
allFuturesResult.get(config.getMoveTimeout().toMillis(),
TimeUnit.MILLISECONDS);
} catch (InterruptedException e) {
+ long cancelCount = cancelAndCountPendingMoves();
+ metrics.incrementNumContainerMovesFailed(cancelCount);
+ LOG.warn("Container balancer is interrupted and moves are cancelled {}",
+ cancelCount);
Thread.currentThread().interrupt();
} catch (TimeoutException e) {
- long timeoutCounts = moveSelectionToFutureMap.entrySet().stream()
- .filter(entry -> !entry.getValue().isDone())
- .peek(entry -> {
- LOG.warn("Container move canceled for container {} from source {}"
+
- " to target {} due to timeout.",
- entry.getKey().getContainerID(),
- containerToSourceMap.get(entry.getKey().getContainerID())
- .getUuidString(),
- entry.getKey().getTargetNode().getUuidString());
- entry.getValue().cancel(true);
- }).count();
+ long timeoutCounts = cancelAndCountPendingMoves();
LOG.warn("{} Container moves are canceled.", timeoutCounts);
metrics.incrementNumContainerMovesTimeoutInLatestIteration(timeoutCounts);
} catch (ExecutionException e) {
+ cancelAndCountPendingMoves();
Review Comment:
Not doing any count of failed metrics in this exception case
--
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]
