Don't fail on inline table service in deltastreamer unless new config…

… is set

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/BaseHoodieWriteClient.java

@@ -243,9 +243,22 @@ public boolean commitStats(String instantTime, List<HoodieWriteStat> stats, Opti
     } finally {
       this.txnManager.endTransaction(Option.of(inflightInstant));
     }
-    // do this outside of lock since compaction, clustering can be time taking and we don't need a lock for the entire execution period
-    runTableServicesInline(table, metadata, extraMetadata);
+
+    // We don't want to fail the commit if hoodie.fail.writes.on.inline.table.service.errors is false. We catch warn if false
+    try {
+      // do this outside of lock since compaction, clustering can be time taking and we don't need a lock for the entire execution period
+      runTableServicesInline(table, metadata, extraMetadata);
+    } catch (Exception e) {
+      LOG.warn("VEXLER: caught the exception");
+      if (config.isFailOnTableServiceExceptionEnabled()) {
+        LOG.warn("VEXLER: here");
+        throw e;
+      }
+      LOG.warn("Inline compaction or clustering failed with exception: " + e.getMessage() + ". Attempting to finish commit. ");
+    }
+
     emitCommitMetrics(instantTime, metadata, commitActionType);
+
     // callback if needed.
     if (config.writeCommitCallbackOn()) {
       if (null == commitCallback) {

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieWriteConfig.java

@@ -386,6 +386,12 @@ public class HoodieWriteConfig extends HoodieConfig {
       .withDocumentation("Timeline archiving removes older instants from the timeline, after each write operation, to minimize metadata overhead. "
           + "Controls whether or not, the write should be failed as well, if such archiving fails.");
 
+  public static final ConfigProperty<String> FAIL_ON_TABLE_SERVICE_EXCEPTION_ENABLE = ConfigProperty
+      .key("hoodie.deltastreamer.fail.writes.on.inline.table.service.errors")
+      .defaultValue("false")
+      .withDocumentation("Table services such as compaction and clustering can fail and prevent syncing to "
+          + "the metaclient in Deltastreamer. Set this to true to fail writes when table services fail");
+
   public static final ConfigProperty<Long> INITIAL_CONSISTENCY_CHECK_INTERVAL_MS = ConfigProperty
       .key("hoodie.consistency.check.initial_interval_ms")
       .defaultValue(2000L)
@@ -1151,6 +1157,10 @@ public boolean isFailOnTimelineArchivingEnabled() {
     return getBoolean(FAIL_ON_TIMELINE_ARCHIVING_ENABLE);
   }
 
+  public boolean isFailOnTableServiceExceptionEnabled() {
+    return getBoolean(FAIL_ON_TABLE_SERVICE_EXCEPTION_ENABLE);
+  }
+
   public int getMaxConsistencyChecks() {
     return getInt(MAX_CONSISTENCY_CHECKS);
   }