[hudi] branch master updated: [HUDI-6359] Spark offline compaction/clustering will never rollback when both requested and inflight states exist (#8944)

[yihua]

This is an automated email from the ASF dual-hosted git repository.

yihua pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git


The following commit(s) were added to refs/heads/master by this push:
     new 51930298ce4 [HUDI-6359] Spark offline compaction/clustering will never 
rollback when both requested and inflight states exist (#8944)
51930298ce4 is described below

commit 51930298ce48a0b413612e985f24d14a97aa703e
Author: ksmou <135721692+ks...@users.noreply.github.com>
AuthorDate: Wed Aug 16 13:37:21 2023 +0800

    [HUDI-6359] Spark offline compaction/clustering will never rollback when 
both requested and inflight states exist (#8944)
    
    Co-authored-by: Y Ethan Guo <ethan.guoyi...@gmail.com>
---
 .../src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java  | 3 +--
 .../src/main/java/org/apache/hudi/utilities/HoodieCompactor.java      | 4 +---
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git 
a/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
 
b/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
index 9abeafb88fd..a859d791b7b 100644
--- 
a/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
+++ 
b/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieClusteringJob.java
@@ -212,8 +212,7 @@ public class HoodieClusteringJob {
         // Instant time is not specified
         // Find the earliest scheduled clustering instant for execution
         Option<HoodieInstant> firstClusteringInstant =
-            metaClient.getActiveTimeline().firstInstant(
-                HoodieTimeline.REPLACE_COMMIT_ACTION, 
HoodieInstant.State.REQUESTED);
+            
metaClient.getActiveTimeline().filterPendingReplaceTimeline().firstInstant();
         if (firstClusteringInstant.isPresent()) {
           cfg.clusteringInstantTime = 
firstClusteringInstant.get().getTimestamp();
           LOG.info("Found the earliest scheduled clustering instant which will 
be executed: "
diff --git 
a/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieCompactor.java 
b/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieCompactor.java
index e7213f93a55..0b0d6307067 100644
--- 
a/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieCompactor.java
+++ 
b/hudi-utilities/src/main/java/org/apache/hudi/utilities/HoodieCompactor.java
@@ -26,7 +26,6 @@ import org.apache.hudi.common.model.HoodieRecordPayload;
 import org.apache.hudi.common.table.HoodieTableMetaClient;
 import org.apache.hudi.common.table.TableSchemaResolver;
 import org.apache.hudi.common.table.timeline.HoodieInstant;
-import org.apache.hudi.common.table.timeline.HoodieTimeline;
 import org.apache.hudi.common.util.Option;
 import org.apache.hudi.common.util.StringUtils;
 import org.apache.hudi.config.HoodieCleanConfig;
@@ -263,8 +262,7 @@ public class HoodieCompactor {
       if (StringUtils.isNullOrEmpty(cfg.compactionInstantTime)) {
         HoodieTableMetaClient metaClient = UtilHelpers.createMetaClient(jsc, 
cfg.basePath, true);
         Option<HoodieInstant> firstCompactionInstant =
-            metaClient.getActiveTimeline().firstInstant(
-                HoodieTimeline.COMPACTION_ACTION, 
HoodieInstant.State.REQUESTED);
+            
metaClient.getActiveTimeline().filterPendingCompactionTimeline().firstInstant();
         if (firstCompactionInstant.isPresent()) {
           cfg.compactionInstantTime = 
firstCompactionInstant.get().getTimestamp();
           LOG.info("Found the earliest scheduled compaction instant which will 
be executed: "