maheshk114 commented on a change in pull request #578: HIVE-21471: Replicating conversion of managed to external table leaks HDFS files at target. URL: https://github.com/apache/hive/pull/578#discussion_r268128979
########## File path: ql/src/java/org/apache/hadoop/hive/ql/ddl/table/CreateTableOperation.java ########## @@ -54,17 +55,24 @@ public int execute() throws HiveException { Table tbl = desc.toTable(context.getConf()); LOG.debug("creating table {} on {}", tbl.getFullyQualifiedName(), tbl.getDataLocation()); - if (desc.getReplicationSpec().isInReplicationScope() && (!desc.getReplaceMode())){ - // if this is a replication spec, then replace-mode semantics might apply. - // if we're already asking for a table replacement, then we can skip this check. - // however, otherwise, if in replication scope, and we've not been explicitly asked - // to replace, we should check if the object we're looking at exists, and if so, + boolean dataLocationChanged = false; + if (desc.getReplicationSpec().isInReplicationScope()) { + // If in replication scope, we should check if the object we're looking at exists, and if so, // trigger replace-mode semantics. Table existingTable = context.getDb().getTable(tbl.getDbName(), tbl.getTableName(), false); - if (existingTable != null){ + if (existingTable != null) { if (desc.getReplicationSpec().allowEventReplacementInto(existingTable.getParameters())) { desc.setReplaceMode(true); // we replace existing table. ReplicationSpec.copyLastReplId(existingTable.getParameters(), tbl.getParameters()); + + // If location of an existing managed table is changed, then need to delete the old location if exists. + // This scenario occurs when a managed table is converted into external table at source. In this case, + // at target, the table data would be moved to different location under base directory for external tables. + if (existingTable.getTableType().equals(TableType.MANAGED_TABLE) + && tbl.getTableType().equals(TableType.EXTERNAL_TABLE) + && (!existingTable.getDataLocation().equals(tbl.getDataLocation()))) { Review comment: in what scenario the location will be same for conversion from managed to external in replication flow ? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services