add roundtrip check

Author: arthurpassos

src/Storages/StorageMergeTree.cpp

@@ -630,9 +630,9 @@ void StorageMergeTree::exportPartitionToTable(const PartitionCommand & command,
     }
     else
     {
-        exportPartsImpl(exports_tagger, transaction_id, dest_storage);
-
-        commitExportPartitionTask(manifest, dest_storage, getContext());
+        /// always in the background for now. I need to sort out the locks
+        background_moves_assignee.scheduleMoveTask(
+            std::make_shared<ExecutableLambdaAdapter>(export_partition_function, moves_assignee_trigger, getStorageID()));
     }
 }
 

tests/queries/0_stateless/03572_export_mt_part_to_object_storage.reference

@@ -23,3 +23,11 @@ test/s3_table_NAME/year=2020/SNOWFLAKE_ID.parquet	3	2020
 test/s3_table_NAME/year=2021/SNOWFLAKE_ID.parquet	4	2021
 test/s3_table_NAME/year=2020/SNOWFLAKE_ID.parquet	5	2020
 test/s3_table_NAME/year=2020/SNOWFLAKE_ID.parquet	6	2020
+---- Round trip check: create a new MergeTree table as SELECT * from s3_table
+---- Data in roundtrip MergeTree table (should match s3_table)
+1	2020
+2	2020
+3	2020
+4	2021
+5	2020
+6	2020

tests/queries/0_stateless/03572_export_mt_part_to_object_storage.sh

@@ -6,12 +6,13 @@ CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
 
 mt_table="mt_table_${RANDOM}"
 s3_table="s3_table_${RANDOM}"
+mt_table_roundtrip="mt_table_roundtrip_${RANDOM}"
 
 query() {
     $CLICKHOUSE_CLIENT --query "$1"
 }
 
-query "DROP TABLE IF EXISTS $mt_table, $s3_table"
+query "DROP TABLE IF EXISTS $mt_table, $s3_table, $mt_table_roundtrip"
 
 query "CREATE TABLE $mt_table (id UInt64, year UInt16) ENGINE = MergeTree() PARTITION BY year ORDER BY tuple()"
 query "CREATE TABLE $s3_table (id UInt64, year UInt16) ENGINE = S3(s3_conn, filename='$s3_table', format=Parquet, partition_strategy='hive') PARTITION BY year"
@@ -41,5 +42,12 @@ query "ALTER TABLE $mt_table EXPORT PARTITION ID '2021' TO TABLE $s3_table SETTI
 echo "---- Assert both partitions are there"
 query "SELECT DISTINCT ON (id) replaceRegexpAll(replaceRegexpAll(_path, '$s3_table', 's3_table_NAME'), '[^/]+\\.parquet', 'SNOWFLAKE_ID.parquet'), * FROM $s3_table ORDER BY id"
 
+echo "---- Round trip check: create a new MergeTree table as SELECT * from s3_table"
+
+query "CREATE TABLE $mt_table_roundtrip ENGINE = MergeTree() PARTITION BY year ORDER BY tuple() AS SELECT * FROM $s3_table"
+
+echo "---- Data in roundtrip MergeTree table (should match s3_table)"
+query "SELECT DISTINCT ON (id) * FROM $mt_table_roundtrip ORDER BY id"
+
 query "SYSTEM START MERGES"
-query "DROP TABLE IF EXISTS $mt_table, $s3_table"
+query "DROP TABLE IF EXISTS $mt_table, $s3_table, $mt_table_roundtrip"