drill-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ppadma <...@git.apache.org>
Subject [GitHub] drill pull request #611: Drill-4800: Improve parquet reader performance
Date Wed, 26 Oct 2016 16:01:25 GMT
Github user ppadma commented on a diff in the pull request:

    https://github.com/apache/drill/pull/611#discussion_r84970854
  
    --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/columnreaders/AsyncPageReader.java
---
    @@ -0,0 +1,409 @@
    +/**
    + * Licensed to the Apache Software Foundation (ASF) under one
    + * or more contributor license agreements.  See the NOTICE file
    + * distributed with this work for additional information
    + * regarding copyright ownership.  The ASF licenses this file
    + * to you under the Apache License, Version 2.0 (the
    + * "License"); you may not use this file except in compliance
    + * with the License.  You may obtain a copy of the License at
    + *
    + * http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +package org.apache.drill.exec.store.parquet.columnreaders;
    +
    +import com.google.common.base.Stopwatch;
    +import io.netty.buffer.DrillBuf;
    +import io.netty.buffer.ByteBufUtil;
    +import org.apache.drill.common.exceptions.ExecutionSetupException;
    +import org.apache.drill.common.exceptions.UserException;
    +import org.apache.hadoop.io.compress.Decompressor;
    +import org.apache.hadoop.io.compress.DirectDecompressor;
    +import org.apache.hadoop.io.compress.GzipCodec;
    +import org.apache.parquet.hadoop.CodecFactory;
    +import org.apache.parquet.hadoop.codec.SnappyCodec;
    +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
    +import org.apache.drill.exec.util.filereader.DirectBufInputStream;
    +import org.apache.hadoop.fs.FileSystem;
    +import org.apache.hadoop.fs.Path;
    +import org.apache.parquet.column.page.DictionaryPage;
    +import org.apache.parquet.format.PageHeader;
    +import org.apache.parquet.format.PageType;
    +import org.apache.parquet.format.Util;
    +import org.apache.parquet.hadoop.metadata.CompressionCodecName;
    +import org.xerial.snappy.Snappy;
    +
    +import java.io.IOException;
    +import java.nio.ByteBuffer;
    +import java.util.concurrent.Callable;
    +import java.util.concurrent.ExecutorService;
    +import java.util.concurrent.Future;
    +import java.util.concurrent.TimeUnit;
    +
    +import static org.apache.parquet.column.Encoding.valueOf;
    +
    +class AsyncPageReader extends PageReader {
    +  static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(AsyncPageReader.class);
    +
    +
    +  private ExecutorService threadPool;
    +  private Future<ReadStatus> asyncPageRead;
    +
    +  AsyncPageReader(ColumnReader<?> parentStatus, FileSystem fs, Path path,
    +      ColumnChunkMetaData columnChunkMetaData) throws ExecutionSetupException {
    +    super(parentStatus, fs, path, columnChunkMetaData);
    +    if (threadPool == null) {
    +      threadPool = parentColumnReader.parentReader.getOperatorContext().getScanExecutor();
    +    }
    +    asyncPageRead = threadPool.submit(new AsyncPageReaderTask());
    +  }
    +
    +  @Override protected void loadDictionaryIfExists(final ColumnReader<?> parentStatus,
    +      final ColumnChunkMetaData columnChunkMetaData, final DirectBufInputStream f) throws
UserException {
    +    if (columnChunkMetaData.getDictionaryPageOffset() > 0) {
    +      try {
    +        dataReader.skip(columnChunkMetaData.getDictionaryPageOffset() - dataReader.getPos());
    +      } catch (IOException e) {
    +        handleAndThrowException(e, "Error Reading dictionary page.");
    +      }
    +      // parent constructor may call this method before the thread pool is set.
    +      if (threadPool == null) {
    +        threadPool = parentColumnReader.parentReader.getOperatorContext().getScanExecutor();
    +      }
    +      asyncPageRead = threadPool.submit(new AsyncPageReaderTask());
    +      readDictionaryPage(asyncPageRead, parentStatus);
    +      asyncPageRead = null; // reset after consuming
    +    }
    +  }
    +
    +  private DrillBuf getDecompressedPageData(ReadStatus readStatus) {
    +    DrillBuf data;
    +    boolean isDictionary = false;
    +    synchronized (this) {
    +      data = readStatus.getPageData();
    +      readStatus.setPageData(null);
    +      isDictionary = readStatus.isDictionaryPage;
    +    }
    +    if (parentColumnReader.columnChunkMetaData.getCodec() != CompressionCodecName.UNCOMPRESSED)
{
    +      DrillBuf uncompressedData = data;
    --- End diff --
    
    should this be compressedData ?


---
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.
---

Mime
View raw message