danny0405 commented on code in PR #10460:
URL: https://github.com/apache/hudi/pull/10460#discussion_r1527009211
##########
hudi-aws/src/main/java/org/apache/hudi/aws/sync/AWSGlueCatalogSyncClient.java:
##########
@@ -141,105 +156,196 @@ public AWSGlueCatalogSyncClient(HiveSyncConfig config) {
this.databaseName = config.getStringOrDefault(META_SYNC_DATABASE_NAME);
this.skipTableArchive =
config.getBooleanOrDefault(GlueCatalogSyncClientConfig.GLUE_SKIP_TABLE_ARCHIVE);
this.enableMetadataTable =
Boolean.toString(config.getBoolean(GLUE_METADATA_FILE_LISTING)).toUpperCase();
+ this.allPartitionsReadParallelism =
config.getIntOrDefault(ALL_PARTITIONS_READ_PARALLELISM);
+ this.changedPartitionsReadParallelism =
config.getIntOrDefault(CHANGED_PARTITIONS_READ_PARALLELISM);
+ this.changeParallelism =
config.getIntOrDefault(PARTITION_CHANGE_PARALLELISM);
+ }
+
+ private List<Partition> getPartitionsSegment(Segment segment, String
tableName) {
+ try {
+ List<Partition> partitions = new ArrayList<>();
+ String nextToken = null;
+ do {
+ GetPartitionsResponse result =
awsGlue.getPartitions(GetPartitionsRequest.builder()
+ .databaseName(databaseName)
+ .tableName(tableName)
+ .segment(segment)
Review Comment:
Please fire a JIRA issue to trace this improvement.
--
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]
