You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pulsar.apache.org by GitBox <gi...@apache.org> on 2022/12/16 07:37:29 UTC
[GitHub] [pulsar] eolivelli commented on a diff in pull request #18858: [improve][broker] Write the child ownership to `ServiceUnitStateChannel` instead of ZK when handling bundle split
eolivelli commented on code in PR #18858:
URL: https://github.com/apache/pulsar/pull/18858#discussion_r1050449602
##########
pulsar-broker/src/main/java/org/apache/pulsar/broker/loadbalance/extensions/channel/ServiceUnitStateChannelImpl.java:
##########
@@ -510,25 +526,109 @@ private CompletableFuture<Integer> closeServiceUnit(String serviceUnit) {
});
}
- private CompletableFuture<Void> splitServiceUnit(String serviceUnit) {
- // TODO: after the split we need to write the child ownerships to BSC instead of ZK.
+ private CompletableFuture<Void> splitServiceUnit(String serviceUnit, ServiceUnitStateData data) {
+ // Write the child ownerships to BSC.
long startTime = System.nanoTime();
- return pulsar.getNamespaceService()
- .splitAndOwnBundle(getNamespaceBundle(serviceUnit),
- false,
- NamespaceBundleSplitAlgorithm.of(pulsar.getConfig().getDefaultNamespaceBundleSplitAlgorithm()),
- null)
- .whenComplete((__, ex) -> {
- double splitBundleTime = TimeUnit.NANOSECONDS
- .toMillis((System.nanoTime() - startTime));
- if (ex == null) {
- log.info("Successfully split {} namespace-bundle in {} ms",
- serviceUnit, splitBundleTime);
- } else {
- log.error("Failed to split {} namespace-bundle in {} ms",
- serviceUnit, splitBundleTime, ex);
- }
- });
+ NamespaceService namespaceService = pulsar.getNamespaceService();
+ NamespaceBundleFactory bundleFactory = namespaceService.getNamespaceBundleFactory();
+ NamespaceBundle bundle = getNamespaceBundle(serviceUnit);
+ CompletableFuture<Void> completionFuture = new CompletableFuture<>();
+ final AtomicInteger counter = new AtomicInteger(0);
+ this.splitServiceUnitOnceAndRetry(namespaceService, bundleFactory, bundle, serviceUnit, data,
+ counter, startTime, completionFuture);
+ return completionFuture;
+ }
+
+ @VisibleForTesting
+ protected void splitServiceUnitOnceAndRetry(NamespaceService namespaceService,
+ NamespaceBundleFactory bundleFactory,
+ NamespaceBundle bundle,
+ String serviceUnit,
+ ServiceUnitStateData data,
+ AtomicInteger counter,
+ long startTime,
+ CompletableFuture<Void> completionFuture) {
+ CompletableFuture<List<NamespaceBundle>> updateFuture = new CompletableFuture<>();
+
+ pulsar.getNamespaceService().getSplitBoundary(bundle, null).thenAccept(splitBundlesPair -> {
+ // Split and updateNamespaceBundles. Update may fail because of concurrent write to Zookeeper.
+ if (splitBundlesPair == null) {
+ String msg = format("Bundle %s not found under namespace", serviceUnit);
+ updateFuture.completeExceptionally(new BrokerServiceException.ServiceUnitNotReadyException(msg));
+ return;
+ }
+ List<CompletableFuture<Void>> futures = new ArrayList<>();
+ ServiceUnitStateData next = new ServiceUnitStateData(Owned, data.broker());
+ NamespaceBundles targetNsBundle = splitBundlesPair.getLeft();
+ List<NamespaceBundle> splitBundles = splitBundlesPair.getRight();
+ List<NamespaceBundle> successPublishedBundles = new CopyOnWriteArrayList<>();
+ for (NamespaceBundle sBundle : splitBundles) {
+ futures.add(pubAsync(sBundle.toString(), next).thenAccept(__ -> {
+ successPublishedBundles.add(sBundle);
+ }));
+ }
+ NamespaceName nsname = bundle.getNamespaceObject();
+ FutureUtil.waitForAll(futures)
+ .thenCompose(__ -> namespaceService.updateNamespaceBundles(nsname, targetNsBundle))
+ .thenCompose(__ -> namespaceService.updateNamespaceBundlesForPolicies(nsname, targetNsBundle))
+ .thenRun(() -> {
+ bundleFactory.invalidateBundleCache(bundle.getNamespaceObject());
+ updateFuture.complete(splitBundles);
+ }).exceptionally(e -> {
+ // Clean the new bundle when has exception.
+ List<CompletableFuture<Void>> futureList = new ArrayList<>();
+ for (NamespaceBundle sBundle : successPublishedBundles) {
+ futureList.add(tombstoneAsync(sBundle.toString()).thenAccept(__ -> {}));
+ }
+ FutureUtil.waitForAll(futureList)
+ .whenComplete((__, ex) -> {
+ if (ex != null) {
+ log.warn("Clean new bundles failed,", ex);
+ }
+ updateFuture.completeExceptionally(e);
+ });
+ return null;
+ });
+ }).exceptionally(e -> {
+ updateFuture.completeExceptionally(e);
+ return null;
+ });
+
+ updateFuture.thenAccept(r -> {
+ // Free the old bundle
+ tombstoneAsync(serviceUnit).thenRun(() -> {
+ // Update bundled_topic cache for load-report-generation
+ pulsar.getBrokerService().refreshTopicToStatsMaps(bundle);
+ // TODO: Update the load data immediately if needed.
+ completionFuture.complete(null);
+ double splitBundleTime = TimeUnit.NANOSECONDS.toMillis((System.nanoTime() - startTime));
+ log.info("Successfully split {} parent namespace-bundle to {} in {} ms", serviceUnit, r,
+ splitBundleTime);
+ }).exceptionally(e -> {
+ double splitBundleTime = TimeUnit.NANOSECONDS.toMillis((System.nanoTime() - startTime));
+ String msg = format("Failed to free bundle %s in %s ms, under namespace [%s] with error %s",
+ bundle.getNamespaceObject().toString(), splitBundleTime, bundle, e.getMessage());
+ completionFuture.completeExceptionally(new BrokerServiceException.ServiceUnitNotReadyException(msg));
+ return null;
+ });
+ }).exceptionally(ex -> {
+ // Retry several times on BadVersion
+ if ((ex.getCause() instanceof MetadataStoreException.BadVersionException)
+ && (counter.incrementAndGet() < NamespaceService.BUNDLE_SPLIT_RETRY_LIMIT)) {
+ pulsar.getExecutor().schedule(() -> pulsar.getOrderedExecutor()
Review Comment:
Why do we chain two executors 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: commits-unsubscribe@pulsar.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org