lw309637554 commented on a change in pull request #3259:
URL: https://github.com/apache/hudi/pull/3259#discussion_r672888552
##########
File path:
hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
##########
@@ -121,17 +141,26 @@ public static void main(String[] args) {
public int cluster(int retry) {
this.fs = FSUtils.getFs(cfg.basePath, jsc.hadoopConfiguration());
int ret = UtilHelpers.retry(retry, () -> {
- if (cfg.runSchedule) {
- LOG.info("Do schedule");
- Option<String> instantTime = doSchedule(jsc);
- int result = instantTime.isPresent() ? 0 : -1;
- if (result == 0) {
- LOG.info("The schedule instant time is " + instantTime.get());
+ String runningMode = cfg.runningMode == null ? "" :
cfg.runningMode.toLowerCase();
Review comment:
make sense
##########
File path:
hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
##########
@@ -171,4 +200,38 @@ private int doCluster(JavaSparkContext jsc) throws
Exception {
return client.scheduleClustering(Option.empty());
}
}
+
+ @TestOnly
+ public int doScheduleAndCluster() throws Exception {
+ return this.doScheduleAndCluster(jsc);
+ }
+
+ public int doScheduleAndCluster(JavaSparkContext jsc) throws Exception {
+ LOG.info("Step 1: Do schedule");
+ String schemaStr = getSchemaFromLatestInstant();
+ try (SparkRDDWriteClient client = UtilHelpers.createHoodieClient(jsc,
cfg.basePath, schemaStr, cfg.parallelism, Option.empty(), props)) {
+
+ Option<String> instantTime;
+ if (cfg.clusteringInstantTime != null) {
+ client.scheduleClusteringAtInstant(cfg.clusteringInstantTime,
Option.empty());
+ instantTime = Option.of(cfg.clusteringInstantTime);
+ } else {
+ instantTime = client.scheduleClustering(Option.empty());
+ }
+
+ int result = instantTime.isPresent() ? 0 : -1;
Review comment:
can we reuse the sparkclient
modify doCluster(sc) to doCluster(sc, client)
--
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]
