veghlaci05 commented on code in PR #3746:
URL: https://github.com/apache/hive/pull/3746#discussion_r1026515897
##########
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/txn/compactor/TestCrudCompactorOnTez.java:
##########
@@ -89,6 +89,270 @@
@SuppressWarnings("deprecation")
public class TestCrudCompactorOnTez extends CompactorOnTezTest {
+ @Test
+ public void testRebalanceCompactionNotPartitionedWithoutBuckets() throws
Exception {
+ conf.setBoolVar(HiveConf.ConfVars.COMPACTOR_CRUD_QUERY_BASED, true);
+ conf.setBoolVar(HiveConf.ConfVars.HIVE_COMPACTOR_GATHER_STATS, false);
+ conf.setBoolVar(HiveConf.ConfVars.HIVESTATSAUTOGATHER, false);
+
+ //set grouping size to have 3 buckets, and re-create driver with the new
config
+ conf.set("tez.grouping.min-size", "1000");
+ conf.set("tez.grouping.max-size", "80000");
+ driver = new Driver(conf);
+
+ final String stageTableName = "stage_rebalance_test";
+ final String tableName = "rebalance_test";
+ AcidOutputFormat.Options options = new AcidOutputFormat.Options(conf);
+
+ TestDataProvider testDataProvider = new TestDataProvider();
+ testDataProvider.createFullAcidTable(stageTableName, true, false);
+ testDataProvider.insertTestDataPartitioned(stageTableName);
+
+ executeStatementOnDriver("drop table if exists " + tableName, driver);
+ executeStatementOnDriver("CREATE TABLE " + tableName + "(a string, b int)
" +
+ "STORED AS ORC TBLPROPERTIES('transactional'='true')", driver);
+ executeStatementOnDriver("INSERT OVERWRITE TABLE " + tableName + " select
a, b from " + stageTableName, driver);
+
+ //do some single inserts to have more data in the first bucket.
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('12',12)", driver);
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('13',13)", driver);
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('14',14)", driver);
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('15',15)", driver);
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('16',16)", driver);
+ executeStatementOnDriver("INSERT INTO TABLE " + tableName + " values
('17',17)", driver);
+
+ // Verify buckets and their content before rebalance
+ Table table = msClient.getTable("default", tableName);
+ FileSystem fs = FileSystem.get(conf);
+ Assert.assertEquals("Test setup does not match the expected: different
buckets",
+ Arrays.asList("bucket_00000_0", "bucket_00001_0", "bucket_00002_0"),
+ CompactorTestUtil.getBucketFileNames(fs, table, null, "base_0000001"));
+ String[][] expectedBuckets = new String[][] {
+ {
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":0}\t5\t4",
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":1}\t6\t2",
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":2}\t6\t3",
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":3}\t6\t4",
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":4}\t5\t2",
+ "{\"writeid\":1,\"bucketid\":536870912,\"rowid\":5}\t5\t3",
+ "{\"writeid\":2,\"bucketid\":536870912,\"rowid\":0}\t12\t12",
+ "{\"writeid\":3,\"bucketid\":536870912,\"rowid\":0}\t13\t13",
+ "{\"writeid\":4,\"bucketid\":536870912,\"rowid\":0}\t14\t14",
+ "{\"writeid\":5,\"bucketid\":536870912,\"rowid\":0}\t15\t15",
+ "{\"writeid\":6,\"bucketid\":536870912,\"rowid\":0}\t16\t16",
+ "{\"writeid\":7,\"bucketid\":536870912,\"rowid\":0}\t17\t17",
+ },
+ {
+ "{\"writeid\":1,\"bucketid\":536936448,\"rowid\":0}\t2\t4",
+ "{\"writeid\":1,\"bucketid\":536936448,\"rowid\":1}\t3\t3",
+ "{\"writeid\":1,\"bucketid\":536936448,\"rowid\":2}\t4\t4",
+ "{\"writeid\":1,\"bucketid\":536936448,\"rowid\":3}\t4\t3",
+ },
+ {
+ "{\"writeid\":1,\"bucketid\":537001984,\"rowid\":0}\t2\t3",
+ "{\"writeid\":1,\"bucketid\":537001984,\"rowid\":1}\t3\t4",
+ },
+ };
+ for(int i = 0; i < 3; i++) {
+ Assert.assertEquals("rebalanced bucket " + i,
Arrays.asList(expectedBuckets[i]),
Review Comment:
Yes, fixed
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
