Skip to content

Spark: Use UUIDUtil.convertToByteBuffer to avoid rewinding buffer #7525

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
nastra merged 1 commit into from
May 8, 2023
Merged

Spark: Use UUIDUtil.convertToByteBuffer to avoid rewinding buffer #7525

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
9 changes: 3 additions & 6 deletions core/src/main/java/org/apache/iceberg/avro/ValueWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.DecimalUtil;
import org.apache.iceberg.util.UUIDUtil;

public class ValueWriters {
private ValueWriters() {}
Expand Down Expand Up @@ -263,12 +264,8 @@ private UUIDWriter() {}
@Override
@SuppressWarnings("ByteBufferBackingArray")
public void write(UUID uuid, Encoder encoder) throws IOException {
// TODO: direct conversion from string to byte buffer
ByteBuffer buffer = BUFFER.get();
buffer.rewind();
buffer.putLong(uuid.getMostSignificantBits());
buffer.putLong(uuid.getLeastSignificantBits());
encoder.writeFixed(buffer.array());
// calling array() is safe because the buffer is always allocated by the thread-local
encoder.writeFixed(UUIDUtil.convertToByteBuffer(uuid, BUFFER.get()).array());
}
}

Expand Down
8 changes: 3 additions & 5 deletions spark/v3.1/spark/src/main/java/org/apache/iceberg/spark/data/SparkValueWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import org.apache.iceberg.avro.ValueWriter;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.DecimalUtil;
import org.apache.iceberg.util.UUIDUtil;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.util.ArrayData;
import org.apache.spark.sql.catalyst.util.MapData;
Expand Down Expand Up @@ -102,11 +103,8 @@ private UUIDWriter() {}
public void write(UTF8String s, Encoder encoder) throws IOException {
// TODO: direct conversion from string to byte buffer
UUID uuid = UUID.fromString(s.toString());
ByteBuffer buffer = BUFFER.get();
buffer.rewind();
buffer.putLong(uuid.getMostSignificantBits());
buffer.putLong(uuid.getLeastSignificantBits());
encoder.writeFixed(buffer.array());
// calling array() is safe because the buffer is always allocated by the thread-local
encoder.writeFixed(UUIDUtil.convertToByteBuffer(uuid, BUFFER.get()).array());
}
}

Expand Down
8 changes: 3 additions & 5 deletions spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/data/SparkValueWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import org.apache.iceberg.avro.ValueWriter;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.DecimalUtil;
import org.apache.iceberg.util.UUIDUtil;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.util.ArrayData;
import org.apache.spark.sql.catalyst.util.MapData;
Expand Down Expand Up @@ -102,11 +103,8 @@ private UUIDWriter() {}
public void write(UTF8String s, Encoder encoder) throws IOException {
// TODO: direct conversion from string to byte buffer
UUID uuid = UUID.fromString(s.toString());
ByteBuffer buffer = BUFFER.get();
buffer.rewind();
buffer.putLong(uuid.getMostSignificantBits());
buffer.putLong(uuid.getLeastSignificantBits());
encoder.writeFixed(buffer.array());
// calling array() is safe because the buffer is always allocated by the thread-local
encoder.writeFixed(UUIDUtil.convertToByteBuffer(uuid, BUFFER.get()).array());
}
}

Expand Down
8 changes: 3 additions & 5 deletions spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/data/SparkValueWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import org.apache.iceberg.avro.ValueWriter;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.DecimalUtil;
import org.apache.iceberg.util.UUIDUtil;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.util.ArrayData;
import org.apache.spark.sql.catalyst.util.MapData;
Expand Down Expand Up @@ -102,11 +103,8 @@ private UUIDWriter() {}
public void write(UTF8String s, Encoder encoder) throws IOException {
// TODO: direct conversion from string to byte buffer
UUID uuid = UUID.fromString(s.toString());
ByteBuffer buffer = BUFFER.get();
buffer.rewind();
buffer.putLong(uuid.getMostSignificantBits());
buffer.putLong(uuid.getLeastSignificantBits());
encoder.writeFixed(buffer.array());
// calling array() is safe because the buffer is always allocated by the thread-local
encoder.writeFixed(UUIDUtil.convertToByteBuffer(uuid, BUFFER.get()).array());
}
}

Expand Down
8 changes: 3 additions & 5 deletions spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/SparkValueWriters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import org.apache.iceberg.avro.ValueWriter;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.DecimalUtil;
import org.apache.iceberg.util.UUIDUtil;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.util.ArrayData;
import org.apache.spark.sql.catalyst.util.MapData;
Expand Down Expand Up @@ -102,11 +103,8 @@ private UUIDWriter() {}
public void write(UTF8String s, Encoder encoder) throws IOException {
// TODO: direct conversion from string to byte buffer
UUID uuid = UUID.fromString(s.toString());
ByteBuffer buffer = BUFFER.get();
buffer.rewind();
buffer.putLong(uuid.getMostSignificantBits());
buffer.putLong(uuid.getLeastSignificantBits());
encoder.writeFixed(buffer.array());
// calling array() is safe because the buffer is always allocated by the thread-local
encoder.writeFixed(UUIDUtil.convertToByteBuffer(uuid, BUFFER.get()).array());
}
}

Expand Down