difin commented on code in PR #5540:
URL: https://github.com/apache/hive/pull/5540#discussion_r1934752803
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/compaction/IcebergQueryCompactor.java:
##########
@@ -62,20 +63,32 @@ public boolean run(CompactorContext context) throws
IOException, HiveException,
Table icebergTable = IcebergTableUtil.getTable(conf, table.getTTable());
String compactionQuery;
String orderBy = ci.orderByClause == null ? "" : ci.orderByClause;
+ String fileSizeCond = null;
+
+ if (ci.type == CompactionType.MINOR) {
+ long fileSizeInBytesThreshold =
IcebergCompactionUtil.getFileSizeThreshold(ci, conf);
+ fileSizeCond = String.format("%1$s in (select file_path from %2$s.files
where file_size_in_bytes < %3$d)",
+ VirtualColumn.FILE_PATH.getName(), compactTableName,
fileSizeInBytesThreshold);
+ conf.setLong(CompactorContext.COMPACTION_FILE_SIZE_THRESHOLD,
fileSizeInBytesThreshold);
+ // IOW query containing a join with Iceberg .files metadata table fails
with exception that Iceberg AVRO format
+ // doesn't support vectorization, hence disabling it in this case.
+ conf.setBoolVar(ConfVars.HIVE_VECTORIZATION_ENABLED, false);
+ }
if (partSpec == null) {
if (!icebergTable.spec().isPartitioned()) {
HiveConf.setVar(conf, ConfVars.REWRITE_POLICY,
RewritePolicy.FULL_TABLE.name());
- compactionQuery = String.format("insert overwrite table %s select *
from %<s %2$s", compactTableName, orderBy);
+ compactionQuery = String.format("insert overwrite table %s select *
from %<s %2$s %3$s", compactTableName,
Review Comment:
Created [HIVE-28731](https://issues.apache.org/jira/browse/HIVE-28731)
--
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: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For additional commands, e-mail: gitbox-h...@hive.apache.org
