Skip to content

Skip empty bucket creation by default #1375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
findepi merged 1 commit into from
Jun 20, 2020
Merged

Skip empty bucket creation by default #1375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion presto-hive/src/main/java/io/prestosql/plugin/hive/HiveConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ public class HiveConfig
private HiveCompressionCodec hiveCompressionCodec = HiveCompressionCodec.GZIP;
private boolean respectTableFormat = true;
private boolean immutablePartitions;
private boolean createEmptyBucketFiles = true;
private boolean createEmptyBucketFiles;
private int maxPartitionsPerWriter = 100;
private int maxOpenSortFiles = 50;
private int writeValidationThreads = 16;
Expand Down
6 changes: 3 additions & 3 deletions presto-hive/src/test/java/io/prestosql/plugin/hive/TestHiveConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ public void testDefaults()
.setHiveCompressionCodec(HiveCompressionCodec.GZIP)
.setRespectTableFormat(true)
.setImmutablePartitions(false)
.setCreateEmptyBucketFiles(true)
.setCreateEmptyBucketFiles(false)
.setSortedWritingEnabled(true)
.setMaxPartitionsPerWriter(100)
.setMaxOpenSortFiles(50)
Expand Down Expand Up @@ -123,7 +123,7 @@ public void testExplicitPropertyMappings()
.put("hive.compression-codec", "NONE")
.put("hive.respect-table-format", "false")
.put("hive.immutable-partitions", "true")
.put("hive.create-empty-bucket-files", "false")
.put("hive.create-empty-bucket-files", "true")
.put("hive.max-partitions-per-writers", "222")
.put("hive.max-open-sort-files", "333")
.put("hive.write-validation-threads", "11")
Expand Down Expand Up @@ -190,7 +190,7 @@ public void testExplicitPropertyMappings()
.setHiveCompressionCodec(HiveCompressionCodec.NONE)
.setRespectTableFormat(false)
.setImmutablePartitions(true)
.setCreateEmptyBucketFiles(false)
.setCreateEmptyBucketFiles(true)
.setMaxPartitionsPerWriter(222)
.setMaxOpenSortFiles(333)
.setWriteValidationThreads(11)
Expand Down
12 changes: 6 additions & 6 deletions presto-product-tests/src/main/java/io/prestosql/tests/hive/TestHiveBasicTableStatistics.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,19 +307,19 @@ public void testInsertBucketed()
BasicStatistics statisticsAfterCreate = getBasicStatisticsForTable(onHive(), tableName);
assertThatStatisticsAreNonZero(statisticsAfterCreate);
assertThat(statisticsAfterCreate.getNumRows().getAsLong()).isEqualTo(25);
assertThat(statisticsAfterCreate.getNumFiles().getAsLong()).isEqualTo(50);
assertThat(statisticsAfterCreate.getNumFiles().getAsLong()).isEqualTo(25); // no files for empty buckets

insertNationData(onPresto(), tableName);

BasicStatistics statisticsAfterInsert = getBasicStatisticsForTable(onHive(), tableName);
assertThat(statisticsAfterInsert.getNumRows().getAsLong()).isEqualTo(50);
assertThat(statisticsAfterInsert.getNumFiles().getAsLong()).isEqualTo(100);
assertThat(statisticsAfterInsert.getNumFiles().getAsLong()).isEqualTo(50); // no files for empty buckets

insertNationData(onPresto(), tableName);

BasicStatistics statisticsAfterInsert2 = getBasicStatisticsForTable(onHive(), tableName);
assertThat(statisticsAfterInsert2.getNumRows().getAsLong()).isEqualTo(75);
assertThat(statisticsAfterInsert2.getNumFiles().getAsLong()).isEqualTo(150);
assertThat(statisticsAfterInsert2.getNumFiles().getAsLong()).isEqualTo(75); // no files for empty buckets
}
finally {
onPresto().executeQuery(format("DROP TABLE IF EXISTS %s", tableName));
Expand Down Expand Up @@ -353,7 +353,7 @@ public void testInsertBucketedPartitioned()
BasicStatistics firstPartitionStatistics = getBasicStatisticsForPartition(onHive(), tableName, "n_regionkey=1");
assertThatStatisticsAreNonZero(firstPartitionStatistics);
assertThat(firstPartitionStatistics.getNumRows().getAsLong()).isEqualTo(5);
assertThat(firstPartitionStatistics.getNumFiles().getAsLong()).isEqualTo(10);
assertThat(firstPartitionStatistics.getNumFiles().getAsLong()).isEqualTo(5); // no files for empty buckets

String insert = format("INSERT INTO %s (n_nationkey, n_regionkey, n_name, n_comment) " +
"SELECT n_nationkey, n_regionkey, n_name, n_comment " +
Expand All @@ -364,13 +364,13 @@ public void testInsertBucketedPartitioned()

BasicStatistics secondPartitionStatistics = getBasicStatisticsForPartition(onHive(), tableName, "n_regionkey=2");
assertThat(secondPartitionStatistics.getNumRows().getAsLong()).isEqualTo(5);
assertThat(secondPartitionStatistics.getNumFiles().getAsLong()).isEqualTo(10);
assertThat(secondPartitionStatistics.getNumFiles().getAsLong()).isEqualTo(4); // no files for empty buckets

onPresto().executeQuery(insert);

BasicStatistics secondPartitionUpdatedStatistics = getBasicStatisticsForPartition(onHive(), tableName, "n_regionkey=2");
assertThat(secondPartitionUpdatedStatistics.getNumRows().getAsLong()).isEqualTo(10);
assertThat(secondPartitionUpdatedStatistics.getNumFiles().getAsLong()).isEqualTo(20);
assertThat(secondPartitionUpdatedStatistics.getNumFiles().getAsLong()).isEqualTo(8); // no files for empty buckets
}
finally {
onPresto().executeQuery(format("DROP TABLE IF EXISTS %s", tableName));
Expand Down