smtwilio commented on code in PR #19811:
URL: https://github.com/apache/hudi/pull/19811#discussion_r3951501942
##########
hudi-utilities/src/main/java/org/apache/hudi/utilities/streamer/HoodieMultiTableStreamer.java:
##########
@@ -479,10 +518,137 @@ public void sync() {
}
}
}
+ }
- log.info("Ingestion was successful for topics: {}", successTables);
- if (!failedTables.isEmpty()) {
- log.info("Ingestion failed for topics: {}", failedTables);
+ /**
+ * Syncs all tables concurrently, one thread per table. Used for continuous
mode where each table's sync blocks
+ * indefinitely.
+ *
+ * <p>When {@code --fail-fast-on-continuous} is enabled, the first table
failure fails the whole job. The sibling
+ * streamers are shut down and a {@link HoodieException} is thrown so the
caller can exit with a non-zero status.
+ * Otherwise, every table is synced independently and a single failure does
not affect the others.
+ */
+ private void syncContinuously() {
+ if (tableExecutionContexts.isEmpty()) {
+ return;
+ }
+ // Streamer instances are registered from worker threads, so a thread-safe
list is required.
+ final List<HoodieStreamer> streamerInstances = new
CopyOnWriteArrayList<>();
+ // Set once fail fast trips, so tasks that register their streamer
afterwards stop before starting the sync.
+ final AtomicBoolean shutdownRequested = new AtomicBoolean(false);
+ final ExecutorService executor =
Executors.newFixedThreadPool(tableExecutionContexts.size(),
+ new CustomizedThreadFactory("multi-table-streamer", true));
+ boolean terminated = false;
+ try {
+ final List<CompletableFuture<Void>> tableFutures =
tableExecutionContexts.stream()
+ .map(context -> CompletableFuture.runAsync(() -> {
+ HoodieStreamer streamer = null;
+ try {
+ streamer = new HoodieStreamer(context.getConfig(), jssc,
Option.ofNullable(context.getProperties()));
+ streamerInstances.add(streamer);
+ // Register before checking the flag so a concurrent
shutdownStreamers() always sees this streamer.
+ if (shutdownRequested.get()) {
+ return;
+ }
+ streamer.sync();
+ // A streamer registered just before fail fast tripped can reach
here without ever ingesting.
+ // shutdown() call will be a no-op because its ingestion service
hadn't started yet.
+ // Don't count that as a success.
+ if (!shutdownRequested.get()) {
+ successTables.add(Helpers.getTableWithDatabase(context));
+ }
+ } catch (Exception e) {
+ log.error("error while running MultiTableDeltaStreamer for
table: {}", context.getTableName(), e);
+ failedTables.add(Helpers.getTableWithDatabase(context));
+ if (failFastOnContinuousMode) {
+ throw new CompletionException(e);
+ }
+ } finally {
+ if (streamer != null) {
+ streamer.shutdownGracefully();
+ }
+ }
+ }, executor)).collect(Collectors.toList());
+
+ if (failFastOnContinuousMode) {
+ log.info("Fail fast enabled in continuous mode. The whole job fails on
any single table failure");
+ awaitFailFast(tableFutures, streamerInstances, shutdownRequested);
+ } else {
+ CompletableFuture.allOf(tableFutures.toArray(new
CompletableFuture[0])).join();
+ }
+ log.info("Successful tables: {}, Failed tables: {}", successTables,
failedTables);
Review Comment:
Dropped it from `syncContinuously` and moved the `sync()` summary into
finally.
--
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]
