[GitHub] drill pull request #611: Drill-4800: Improve parquet reader performance

[paul-rogers <gi...@git.apache.org>]

Github user paul-rogers commented on a diff in the pull request:

    https://github.com/apache/drill/pull/611#discussion_r86393092
  
    --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/columnreaders/PageReader.java ---
    @@ -48,22 +48,26 @@
     import org.apache.parquet.hadoop.metadata.CompressionCodecName;
     import org.apache.parquet.schema.PrimitiveType;
     
    -import com.google.common.base.Preconditions;
    -import com.google.common.base.Stopwatch;
    +import java.io.IOException;
    +import java.nio.ByteBuffer;
    +import java.util.ArrayList;
    +import java.util.List;
    +import java.util.concurrent.TimeUnit;
     
    -import io.netty.buffer.ByteBuf;
    -import io.netty.buffer.DrillBuf;
    +import static org.apache.parquet.column.Encoding.valueOf;
    +import static org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics;
     
     // class to keep track of the read position of variable length columns
     final class PageReader {
    -  static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(PageReader.class);
    +  static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(
    +      org.apache.drill.exec.store.parquet.columnreaders.PageReader.class);
     
       public static final ParquetMetadataConverter METADATA_CONVERTER = ParquetFormatPlugin.parquetMetadataConverter;
     
    -  private final ColumnReader<?> parentColumnReader;
    -  private final ColumnDataReader dataReader;
    -
    -  // buffer to store bytes of current page
    +  private final org.apache.drill.exec.store.parquet.columnreaders.ColumnReader<?> parentColumnReader;
    +  //private final ColumnDataReader dataReader;
    +  private final DirectBufInputStream dataReader;
    +  //der; buffer to store bytes of current page
    --- End diff --
    
    der; ?


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---