kbuci commented on code in PR #18302:
URL: https://github.com/apache/hudi/pull/18302#discussion_r3013224466
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieClusteringConfig.java:
##########
@@ -235,14 +237,45 @@ public class HoodieClusteringConfig extends HoodieConfig {
.sinceVersion("0.7.0")
.withDocumentation("Columns to sort the data by when clustering");
+ static final String SPARK_ALLOW_UPDATE_STRATEGY_CLASS_NAME =
+
"org.apache.hudi.client.clustering.update.strategy.SparkAllowUpdateStrategy";
+
+ static final String SPARK_REJECT_UPDATE_STRATEGY_CLASS_NAME =
+
"org.apache.hudi.client.clustering.update.strategy.SparkRejectUpdateStrategy";
+
public static final ConfigProperty<String> UPDATES_STRATEGY = ConfigProperty
.key("hoodie.clustering.updates.strategy")
-
.defaultValue("org.apache.hudi.client.clustering.update.strategy.SparkRejectUpdateStrategy")
+ .noDefaultValue()
+ .withInferFunction(cfg -> {
+ String strategy =
cfg.getStringOrDefault(HoodieLockConfig.WRITE_CONFLICT_RESOLUTION_STRATEGY_CLASS_NAME,
"");
+ if
(PreferWriterConflictResolutionStrategy.class.getName().equals(strategy)) {
+ return Option.of(SPARK_ALLOW_UPDATE_STRATEGY_CLASS_NAME);
+ }
+ return Option.of(SPARK_REJECT_UPDATE_STRATEGY_CLASS_NAME);
+ })
.markAdvanced()
.sinceVersion("0.7.0")
.withDocumentation("Determines how to handle updates, deletes to file
groups that are under clustering."
+ " Default strategy just rejects the update");
+ public static final ConfigProperty<Boolean> ENABLE_EXPIRATIONS =
ConfigProperty
+ .key("hoodie.clustering.enable.expirations")
+ .defaultValue(false)
+ .markAdvanced()
+ .withDocumentation("When enabled, rollback of failed writes (under LAZY
cleaning policy) will also attempt to rollback "
+ + "clustering replacecommit instants whose heartbeat has expired.
Clustering jobs will start a heartbeat before "
+ + "scheduling a plan, so that other writers can detect stale/failed
clustering attempts. Note that the same "
+ + "client must be used to schedule, execute, and commit the
clustering instant. And a clustering plan cannot be "
+ + "re-attempted");
+
+ public static final ConfigProperty<Long> EXPIRATION_TIME_MINS =
ConfigProperty
Review Comment:
Sure updates to mins
--
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]
