lokeshj1703 commented on code in PR #3272:
URL: https://github.com/apache/ozone/pull/3272#discussion_r845752131
##########
hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/balancer/ContainerBalancer.java:
##########
@@ -462,49 +462,80 @@ private void checkIterationResults(boolean
isMoveGenerated,
private void checkIterationMoveResults(Set<DatanodeDetails> selectedTargets)
{
this.countDatanodesInvolvedPerIteration = 0;
this.sizeMovedPerIteration = 0;
- for (Map.Entry<ContainerMoveSelection,
- CompletableFuture<ReplicationManager.MoveResult>>
- futureEntry : moveSelectionToFutureMap.entrySet()) {
- ContainerMoveSelection moveSelection = futureEntry.getKey();
- CompletableFuture<ReplicationManager.MoveResult> future =
- futureEntry.getValue();
+
+ CompletableFuture<Void> allFuturesResult = CompletableFuture.allOf(
+ moveSelectionToFutureMap.values()
+ .toArray(new CompletableFuture[moveSelectionToFutureMap.size()]));
+ try {
+ allFuturesResult.get(config.getMoveTimeout().toMillis(),
+ TimeUnit.MILLISECONDS);
+ } catch (InterruptedException e) {
+ Thread.currentThread().interrupt();
+ } catch (Exception e) {
+ // For exceptions other than InterruptedException, we ignore them.
+ e.printStackTrace();
Review Comment:
Better to log the exception here indicating that exception was encountered
while waiting for move to finish.
##########
hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/balancer/ContainerBalancer.java:
##########
@@ -462,49 +462,80 @@ private void checkIterationResults(boolean
isMoveGenerated,
private void checkIterationMoveResults(Set<DatanodeDetails> selectedTargets)
{
this.countDatanodesInvolvedPerIteration = 0;
this.sizeMovedPerIteration = 0;
- for (Map.Entry<ContainerMoveSelection,
- CompletableFuture<ReplicationManager.MoveResult>>
- futureEntry : moveSelectionToFutureMap.entrySet()) {
- ContainerMoveSelection moveSelection = futureEntry.getKey();
- CompletableFuture<ReplicationManager.MoveResult> future =
- futureEntry.getValue();
+
+ CompletableFuture<Void> allFuturesResult = CompletableFuture.allOf(
+ moveSelectionToFutureMap.values()
+ .toArray(new CompletableFuture[moveSelectionToFutureMap.size()]));
+ try {
+ allFuturesResult.get(config.getMoveTimeout().toMillis(),
+ TimeUnit.MILLISECONDS);
+ } catch (InterruptedException e) {
+ Thread.currentThread().interrupt();
+ } catch (Exception e) {
+ // For exceptions other than InterruptedException, we ignore them.
+ e.printStackTrace();
+ }
+
+ List<ContainerMoveSelection> completeKeyList =
+ moveSelectionToFutureMap.keySet().stream()
+ .filter(key -> moveSelectionToFutureMap.get(key).isDone())
+ .collect(Collectors.toList());
+
+ // Handle completed futures
+ for (ContainerMoveSelection moveSelection : completeKeyList) {
try {
- ReplicationManager.MoveResult result = future.get(
- config.getMoveTimeout().toMillis(), TimeUnit.MILLISECONDS);
- if (result == ReplicationManager.MoveResult.COMPLETED) {
+ CompletableFuture<ReplicationManager.MoveResult> future =
+ moveSelectionToFutureMap.get(moveSelection);
+ if (future.isCompletedExceptionally()) {
try {
- ContainerInfo container =
- containerManager.getContainer(moveSelection.getContainerID());
- this.sizeMovedPerIteration += container.getUsedBytes();
- metrics.incrementNumContainerMovesInLatestIteration(1);
- LOG.info("Container move completed for container {} to target {}",
- container.containerID(),
- moveSelection.getTargetNode().getUuidString());
- } catch (ContainerNotFoundException e) {
- LOG.warn("Could not find Container {} while " +
- "checking move results in ContainerBalancer",
- moveSelection.getContainerID(), e);
+ future.join();
+ } catch (CompletionException ex) {
+ LOG.info("Container move for container {} to target {} " +
+ "failed with exceptions",
+ moveSelection.getContainerID().toString(),
+ moveSelection.getTargetNode().getUuidString(),
+ ex.getCause());
}
} else {
- if (LOG.isDebugEnabled()) {
- LOG.debug("Container move for container {} to target {} failed:
{}",
- moveSelection.getContainerID(),
- moveSelection.getTargetNode().getUuidString(), result);
+ ReplicationManager.MoveResult result = future.join();
+ if (result == ReplicationManager.MoveResult.COMPLETED) {
+ try {
Review Comment:
I think we can simplify all the remaining logic by using whenComplete call
for CompletableFuture.
##########
hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/balancer/ContainerBalancer.java:
##########
@@ -462,49 +462,80 @@ private void checkIterationResults(boolean
isMoveGenerated,
private void checkIterationMoveResults(Set<DatanodeDetails> selectedTargets)
{
this.countDatanodesInvolvedPerIteration = 0;
this.sizeMovedPerIteration = 0;
- for (Map.Entry<ContainerMoveSelection,
- CompletableFuture<ReplicationManager.MoveResult>>
- futureEntry : moveSelectionToFutureMap.entrySet()) {
- ContainerMoveSelection moveSelection = futureEntry.getKey();
- CompletableFuture<ReplicationManager.MoveResult> future =
- futureEntry.getValue();
+
+ CompletableFuture<Void> allFuturesResult = CompletableFuture.allOf(
+ moveSelectionToFutureMap.values()
+ .toArray(new CompletableFuture[moveSelectionToFutureMap.size()]));
+ try {
+ allFuturesResult.get(config.getMoveTimeout().toMillis(),
+ TimeUnit.MILLISECONDS);
+ } catch (InterruptedException e) {
+ Thread.currentThread().interrupt();
+ } catch (Exception e) {
+ // For exceptions other than InterruptedException, we ignore them.
+ e.printStackTrace();
+ }
+
+ List<ContainerMoveSelection> completeKeyList =
+ moveSelectionToFutureMap.keySet().stream()
+ .filter(key -> moveSelectionToFutureMap.get(key).isDone())
+ .collect(Collectors.toList());
+
+ // Handle completed futures
+ for (ContainerMoveSelection moveSelection : completeKeyList) {
try {
- ReplicationManager.MoveResult result = future.get(
- config.getMoveTimeout().toMillis(), TimeUnit.MILLISECONDS);
- if (result == ReplicationManager.MoveResult.COMPLETED) {
+ CompletableFuture<ReplicationManager.MoveResult> future =
+ moveSelectionToFutureMap.get(moveSelection);
+ if (future.isCompletedExceptionally()) {
try {
- ContainerInfo container =
- containerManager.getContainer(moveSelection.getContainerID());
- this.sizeMovedPerIteration += container.getUsedBytes();
- metrics.incrementNumContainerMovesInLatestIteration(1);
- LOG.info("Container move completed for container {} to target {}",
- container.containerID(),
- moveSelection.getTargetNode().getUuidString());
- } catch (ContainerNotFoundException e) {
- LOG.warn("Could not find Container {} while " +
- "checking move results in ContainerBalancer",
- moveSelection.getContainerID(), e);
+ future.join();
+ } catch (CompletionException ex) {
+ LOG.info("Container move for container {} to target {} " +
+ "failed with exceptions",
+ moveSelection.getContainerID().toString(),
+ moveSelection.getTargetNode().getUuidString(),
+ ex.getCause());
}
} else {
- if (LOG.isDebugEnabled()) {
- LOG.debug("Container move for container {} to target {} failed:
{}",
- moveSelection.getContainerID(),
- moveSelection.getTargetNode().getUuidString(), result);
+ ReplicationManager.MoveResult result = future.join();
+ if (result == ReplicationManager.MoveResult.COMPLETED) {
+ try {
Review Comment:
Also it would be good to add metrics around total move timeouts in the
whenComplete call.
--
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]
