ajantha-bhat commented on a change in pull request #4020: URL: https://github.com/apache/carbondata/pull/4020#discussion_r531366602
########## File path: integration/spark/src/test/scala/org/apache/carbondata/spark/testsuite/datacompaction/MajorCompactionIgnoreInMinorTest.scala ########## @@ -186,6 +187,78 @@ class MajorCompactionIgnoreInMinorTest extends QueryTest with BeforeAndAfterAll } + def generateData(numOrders: Int = 100000): DataFrame = { + import sqlContext.implicits._ + sqlContext.sparkContext.parallelize(1 to numOrders, 4) + .map { x => ("country" + x, x, "07/23/2015", "name" + x, "phonetype" + x, + "serialname" + x, x + 10000) + }.toDF("country", "ID", "date", "name", "phonetype", "serialname", "salary") + } + + test("test skip segment whose data size exceed threshold in minor compaction") { Review comment: can simplify the test case (no need of huge rows) Just insert 1 row 4 times and do minor compaction, it should work. and set table property to 1 MB and insert 1 row 4 times and do minor compaction, it shouldn't compact. ---------------------------------------------------------------- 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