drill-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jinfengni <...@git.apache.org>
Subject [GitHub] drill pull request #569: DRILL-4846: Fix a few performance issues for metada...
Date Wed, 17 Aug 2016 05:30:57 GMT
Github user jinfengni commented on a diff in the pull request:

    https://github.com/apache/drill/pull/569#discussion_r75064413
  
    --- Diff: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/Metadata.java
---
    @@ -470,41 +483,38 @@ private ParquetTableMetadataBase readBlockMeta(String path) throws
IOException {
         mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
         FSDataInputStream is = fs.open(p);
     
    -    ParquetTableMetadataBase parquetTableMetadata = mapper.readValue(is, ParquetTableMetadataBase.class);
    -    logger.info("Took {} ms to read metadata from cache file", timer.elapsed(TimeUnit.MILLISECONDS));
    -    timer.stop();
    -    if (tableModified(parquetTableMetadata, p)) {
    -      parquetTableMetadata =
    -          (createMetaFilesRecursively(Path.getPathWithoutSchemeAndAuthority(p.getParent()).toString())).getLeft();
    -    }
    -    return parquetTableMetadata;
    -  }
    -
    -  private ParquetTableMetadataDirs readMetadataDirs(String path) throws IOException {
    -    Stopwatch timer = Stopwatch.createStarted();
    -    Path p = new Path(path);
    -    ObjectMapper mapper = new ObjectMapper();
    -
    -    final SimpleModule serialModule = new SimpleModule();
    -    serialModule.addDeserializer(SchemaPath.class, new SchemaPath.De());
    -
    -    AfterburnerModule module = new AfterburnerModule();
    -    module.setUseOptimizedBeanDeserializer(true);
    +    boolean alreadyCheckedModification = false;
    +    boolean newMetadata = false;
     
    -    mapper.registerModule(serialModule);
    -    mapper.registerModule(module);
    -    mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
    -    FSDataInputStream is = fs.open(p);
    +    if (metaContext != null) {
    +      alreadyCheckedModification = metaContext.getStatus(parentDir.toString());
    +    }
     
    -    ParquetTableMetadataDirs parquetTableMetadataDirs = mapper.readValue(is, ParquetTableMetadataDirs.class);
    -    logger.info("Took {} ms to read directories from directory cache file", timer.elapsed(TimeUnit.MILLISECONDS));
    -    timer.stop();
    +    if (dirsOnly) {
    +      parquetTableMetadataDirs = mapper.readValue(is, ParquetTableMetadataDirs.class);
    +      logger.info("Took {} ms to read directories from directory cache file", timer.elapsed(TimeUnit.MILLISECONDS));
    +      timer.stop();
    +      if (!alreadyCheckedModification && tableModified(parquetTableMetadataDirs.getDirectories(),
p, parentDir, metaContext)) {
    --- End diff --
    
    Make sense. 


---
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