Skip to content

GH-3156: Enable vectored IO by default. #3155

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
wgtmac merged 1 commit into from
Mar 3, 2025
Merged

GH-3156: Enable vectored IO by default. #3155

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
6 changes: 3 additions & 3 deletions parquet-hadoop/src/main/java/org/apache/parquet/ParquetReadOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
import static org.apache.parquet.hadoop.ParquetInputFormat.BLOOM_FILTERING_ENABLED;
import static org.apache.parquet.hadoop.ParquetInputFormat.COLUMN_INDEX_FILTERING_ENABLED;
import static org.apache.parquet.hadoop.ParquetInputFormat.DICTIONARY_FILTERING_ENABLED;
import static org.apache.parquet.hadoop.ParquetInputFormat.HADOOP_VECTORED_IO_DEFAULT;
import static org.apache.parquet.hadoop.ParquetInputFormat.HADOOP_VECTORED_IO_ENABLED;
import static org.apache.parquet.hadoop.ParquetInputFormat.OFF_HEAP_DECRYPT_BUFFER_ENABLED;
import static org.apache.parquet.hadoop.ParquetInputFormat.PAGE_VERIFY_CHECKSUM_ENABLED;
Expand Down Expand Up @@ -56,7 +57,6 @@ public class ParquetReadOptions {
private static final boolean STATS_FILTERING_ENABLED_DEFAULT = true;
private static final boolean DICTIONARY_FILTERING_ENABLED_DEFAULT = true;
private static final boolean COLUMN_INDEX_FILTERING_ENABLED_DEFAULT = true;
private static final boolean HADOOP_VECTORED_IO_ENABLED_DEFAULT = false;
private static final int ALLOCATION_SIZE_DEFAULT = 8388608; // 8MB
private static final boolean PAGE_VERIFY_CHECKSUM_ENABLED_DEFAULT = false;
private static final boolean BLOOM_FILTER_ENABLED_DEFAULT = true;
Expand Down Expand Up @@ -253,7 +253,7 @@ public static class Builder {
protected boolean useStatsFilter = STATS_FILTERING_ENABLED_DEFAULT;
protected boolean useDictionaryFilter = DICTIONARY_FILTERING_ENABLED_DEFAULT;
protected boolean useRecordFilter = RECORD_FILTERING_ENABLED_DEFAULT;
protected boolean useHadoopVectoredIo = HADOOP_VECTORED_IO_ENABLED_DEFAULT;
protected boolean useHadoopVectoredIo = HADOOP_VECTORED_IO_DEFAULT;
protected boolean useColumnIndexFilter = COLUMN_INDEX_FILTERING_ENABLED_DEFAULT;
protected boolean usePageChecksumVerification = PAGE_VERIFY_CHECKSUM_ENABLED_DEFAULT;
protected boolean useBloomFilter = BLOOM_FILTER_ENABLED_DEFAULT;
Expand Down Expand Up @@ -286,7 +286,7 @@ public Builder(ParquetConfiguration conf) {
withCodecFactory(HadoopCodecs.newFactory(conf, 0));
withRecordFilter(getFilter(conf));
withMaxAllocationInBytes(conf.getInt(ALLOCATION_SIZE, 8388608));
withUseHadoopVectoredIo(conf.getBoolean(HADOOP_VECTORED_IO_ENABLED, HADOOP_VECTORED_IO_ENABLED_DEFAULT));
withUseHadoopVectoredIo(conf.getBoolean(HADOOP_VECTORED_IO_ENABLED, HADOOP_VECTORED_IO_DEFAULT));
String badRecordThresh = conf.get(BAD_RECORD_THRESHOLD_CONF_KEY);
if (badRecordThresh != null) {
set(BAD_RECORD_THRESHOLD_CONF_KEY, badRecordThresh);
Expand Down