Examples with ExtendedFileSystem com.facebook.presto.hive.filesystem.ExtendedFileSystem used on opensource projects

Example 1 with ExtendedFileSystem

use of com.facebook.presto.hive.filesystem.ExtendedFileSystem in project presto by prestodb.

the class ManifestPartitionLoader method createInternalHiveSplitFactory.

private InternalHiveSplitFactory createInternalHiveSplitFactory(Table table, HivePartitionMetadata partition, ConnectorSession session, Optional<Domain> pathDomain, HdfsEnvironment hdfsEnvironment, HdfsContext hdfsContext, boolean schedulerUsesHostAddresses) throws IOException {
    String partitionName = partition.getHivePartition().getPartitionId();
    Storage storage = partition.getPartition().map(Partition::getStorage).orElse(table.getStorage());
    String inputFormatName = storage.getStorageFormat().getInputFormat();
    int partitionDataColumnCount = partition.getPartition().map(p -> p.getColumns().size()).orElse(table.getDataColumns().size());
    List<HivePartitionKey> partitionKeys = getPartitionKeys(table, partition.getPartition(), partitionName);
    Path path = new Path(getPartitionLocation(table, partition.getPartition()));
    Configuration configuration = hdfsEnvironment.getConfiguration(hdfsContext, path);
    InputFormat<?, ?> inputFormat = getInputFormat(configuration, inputFormatName, false);
    ExtendedFileSystem fileSystem = hdfsEnvironment.getFileSystem(hdfsContext, path);
    return new InternalHiveSplitFactory(fileSystem, inputFormat, pathDomain, getNodeSelectionStrategy(session), getMaxInitialSplitSize(session), false, new HiveSplitPartitionInfo(storage, path.toUri(), partitionKeys, partitionName, partitionDataColumnCount, partition.getTableToPartitionMapping(), Optional.empty(), partition.getRedundantColumnDomains()), schedulerUsesHostAddresses, partition.getEncryptionInformation());
}

Example 2 with ExtendedFileSystem

use of com.facebook.presto.hive.filesystem.ExtendedFileSystem in project presto by prestodb.

the class StoragePartitionLoader method getBucketedSplits.

private List<InternalHiveSplit> getBucketedSplits(Path path, ExtendedFileSystem fileSystem, InternalHiveSplitFactory splitFactory, BucketSplitInfo bucketSplitInfo, Optional<HiveSplit.BucketConversion> bucketConversion, String partitionName, boolean splittable, PathFilter pathFilter) {
    int readBucketCount = bucketSplitInfo.getReadBucketCount();
    int tableBucketCount = bucketSplitInfo.getTableBucketCount();
    int partitionBucketCount = bucketConversion.map(HiveSplit.BucketConversion::getPartitionBucketCount).orElse(tableBucketCount);
    int bucketCount = max(readBucketCount, partitionBucketCount);
    checkState(readBucketCount <= tableBucketCount, "readBucketCount(%s) should be less than or equal to tableBucketCount(%s)", readBucketCount, tableBucketCount);
    // list all files in the partition
    List<HiveFileInfo> fileInfos = new ArrayList<>(partitionBucketCount);
    try {
        Iterators.addAll(fileInfos, directoryLister.list(fileSystem, table, path, namenodeStats, pathFilter, new HiveDirectoryContext(FAIL, isUseListDirectoryCache(session))));
    } catch (HiveFileIterator.NestedDirectoryNotAllowedException e) {
        // Fail here to be on the safe side. This seems to be the same as what Hive does
        throw new PrestoException(HIVE_INVALID_BUCKET_FILES, format("Hive table '%s' is corrupt. Found sub-directory in bucket directory for partition: %s", table.getSchemaTableName(), partitionName));
    }
    ListMultimap<Integer, HiveFileInfo> bucketToFileInfo = ArrayListMultimap.create();
    if (!shouldCreateFilesForMissingBuckets(table, session)) {
        fileInfos.stream().forEach(fileInfo -> {
            String fileName = fileInfo.getPath().getName();
            OptionalInt bucket = getBucketNumber(fileName);
            if (bucket.isPresent()) {
                bucketToFileInfo.put(bucket.getAsInt(), fileInfo);
            } else {
                throw new PrestoException(HIVE_INVALID_BUCKET_FILES, format("invalid hive bucket file name: %s", fileName));
            }
        });
    } else {
        // build mapping of file name to bucket
        for (HiveFileInfo file : fileInfos) {
            String fileName = file.getPath().getName();
            OptionalInt bucket = getBucketNumber(fileName);
            if (bucket.isPresent()) {
                bucketToFileInfo.put(bucket.getAsInt(), file);
                continue;
            }
            // legacy mode requires exactly one file per bucket
            if (fileInfos.size() != partitionBucketCount) {
                throw new PrestoException(HIVE_INVALID_BUCKET_FILES, format("Hive table '%s' is corrupt. File '%s' does not match the standard naming pattern, and the number " + "of files in the directory (%s) does not match the declared bucket count (%s) for partition: %s", table.getSchemaTableName(), fileName, fileInfos.size(), partitionBucketCount, partitionName));
            }
            if (fileInfos.get(0).getPath().getName().matches("\\d+")) {
                try {
                    // File names are integer if they are created when file_renaming_enabled is set to true
                    fileInfos.sort(Comparator.comparingInt(fileInfo -> Integer.parseInt(fileInfo.getPath().getName())));
                } catch (NumberFormatException e) {
                    throw new PrestoException(HIVE_INVALID_FILE_NAMES, format("Hive table '%s' is corrupt. Some of the filenames in the partition: %s are not integers", new SchemaTableName(table.getDatabaseName(), table.getTableName()), partitionName));
                }
            } else {
                // Sort FileStatus objects (instead of, e.g., fileStatus.getPath().toString). This matches org.apache.hadoop.hive.ql.metadata.Table.getSortedPaths
                fileInfos.sort(null);
            }
            // Use position in sorted list as the bucket number
            bucketToFileInfo.clear();
            for (int i = 0; i < fileInfos.size(); i++) {
                bucketToFileInfo.put(i, fileInfos.get(i));
            }
            break;
        }
    }
    // convert files internal splits
    List<InternalHiveSplit> splitList = new ArrayList<>();
    for (int bucketNumber = 0; bucketNumber < bucketCount; bucketNumber++) {
        // Physical bucket #. This determine file name. It also determines the order of splits in the result.
        int partitionBucketNumber = bucketNumber % partitionBucketCount;
        if (!bucketToFileInfo.containsKey(partitionBucketNumber)) {
            continue;
        }
        // Logical bucket #. Each logical bucket corresponds to a "bucket" from engine's perspective.
        int readBucketNumber = bucketNumber % readBucketCount;
        boolean containsIneligibleTableBucket = false;
        List<Integer> eligibleTableBucketNumbers = new ArrayList<>();
        for (int tableBucketNumber = bucketNumber % tableBucketCount; tableBucketNumber < tableBucketCount; tableBucketNumber += bucketCount) {
            // table bucket number: this is used for evaluating "$bucket" filters.
            if (bucketSplitInfo.isTableBucketEnabled(tableBucketNumber)) {
                eligibleTableBucketNumbers.add(tableBucketNumber);
            } else {
                containsIneligibleTableBucket = true;
            }
        }
        if (!eligibleTableBucketNumbers.isEmpty() && containsIneligibleTableBucket) {
            throw new PrestoException(NOT_SUPPORTED, "The bucket filter cannot be satisfied. There are restrictions on the bucket filter when all the following is true: " + "1. a table has a different buckets count as at least one of its partitions that is read in this query; " + "2. the table has a different but compatible bucket number with another table in the query; " + "3. some buckets of the table is filtered out from the query, most likely using a filter on \"$bucket\". " + "(table name: " + table.getTableName() + ", table bucket count: " + tableBucketCount + ", " + "partition bucket count: " + partitionBucketCount + ", effective reading bucket count: " + readBucketCount + ")");
        }
        if (!eligibleTableBucketNumbers.isEmpty()) {
            for (HiveFileInfo fileInfo : bucketToFileInfo.get(partitionBucketNumber)) {
                eligibleTableBucketNumbers.stream().map(tableBucketNumber -> splitFactory.createInternalHiveSplit(fileInfo, readBucketNumber, tableBucketNumber, splittable)).forEach(optionalSplit -> optionalSplit.ifPresent(splitList::add));
            }
        }
    }
    return splitList;
}

Example 3 with ExtendedFileSystem

use of com.facebook.presto.hive.filesystem.ExtendedFileSystem in project presto by prestodb.

the class RaptorCachingHdfsConfiguration method getConfiguration.

@Override
public Configuration getConfiguration(HdfsContext context, URI uri) {
    @SuppressWarnings("resource") Configuration config = new CachingJobConf((factoryConfig, factoryUri) -> {
        try {
            FileSystem fileSystem = (new Path(factoryUri)).getFileSystem(hiveHdfsConfiguration.getConfiguration(context, factoryUri));
            checkState(fileSystem instanceof ExtendedFileSystem);
            return new FileMergeCachingFileSystem(factoryUri, factoryConfig, cacheManager, (ExtendedFileSystem) fileSystem, cacheValidationEnabled);
        } catch (IOException e) {
            throw new PrestoException(GENERIC_INTERNAL_ERROR, "cannot create caching FS", e);
        }
    });
    Configuration defaultConfig = hiveHdfsConfiguration.getConfiguration(context, uri);
    copy(defaultConfig, config);
    return config;
}

Example 4 with ExtendedFileSystem

use of com.facebook.presto.hive.filesystem.ExtendedFileSystem in project presto by prestodb.

the class HdfsEnvironment method getFileSystem.

public ExtendedFileSystem getFileSystem(String user, Path path, Configuration configuration) throws IOException {
    return hdfsAuthentication.doAs(user, () -> {
        FileSystem fileSystem = path.getFileSystem(configuration);
        fileSystem.setVerifyChecksum(verifyChecksum);
        checkState(fileSystem instanceof ExtendedFileSystem);
        return (ExtendedFileSystem) fileSystem;
    });
}

Example 5 with ExtendedFileSystem

use of com.facebook.presto.hive.filesystem.ExtendedFileSystem in project presto by prestodb.

the class CacheFactory method createCachingFileSystem.

public ExtendedFileSystem createCachingFileSystem(Configuration factoryConfig, URI factoryUri, ExtendedFileSystem fileSystem, CacheManager cacheManager, boolean cachingEnabled, CacheType cacheType, boolean validationEnabled) throws IOException {
    if (!cachingEnabled) {
        return fileSystem;
    }
    checkState(cacheType != null);
    switch(cacheType) {
        case FILE_MERGE:
            return new FileMergeCachingFileSystem(factoryUri, factoryConfig, cacheManager, fileSystem, validationEnabled);
        case ALLUXIO:
            ExtendedFileSystem cachingFileSystem = new AlluxioCachingFileSystem(fileSystem, factoryUri, validationEnabled);
            cachingFileSystem.initialize(factoryUri, factoryConfig);
            return cachingFileSystem;
        default:
            throw new IllegalArgumentException("Invalid CacheType: " + cacheType.name());
    }
}