Examples with BlockInStreamSource alluxio.client.block.stream.BlockInStream.BlockInStreamSource used on opensource projects

Example 1 with BlockInStreamSource

use of alluxio.client.block.stream.BlockInStream.BlockInStreamSource in project alluxio by Alluxio.

the class AlluxioBlockStore method getInStream.

/**
 * {@link #getInStream(long, InStreamOptions, Map)}.
 *
 * @param info the block info
 * @param options the options associated with the read request
 * @param failedWorkers the map of workers address to most recent failure time
 * @return a stream which reads from the beginning of the block
 */
public BlockInStream getInStream(BlockInfo info, InStreamOptions options, Map<WorkerNetAddress, Long> failedWorkers) throws IOException {
    Pair<WorkerNetAddress, BlockInStreamSource> dataSourceAndType = getDataSourceAndType(info, options.getStatus(), options.getUfsReadLocationPolicy(), failedWorkers);
    WorkerNetAddress dataSource = dataSourceAndType.getFirst();
    BlockInStreamSource dataSourceType = dataSourceAndType.getSecond();
    try {
        return BlockInStream.create(mContext, info, dataSource, dataSourceType, options);
    } catch (UnavailableException e) {
        // When BlockInStream created failed, it will update the passed-in failedWorkers
        // to attempt to avoid reading from this failed worker in next try.
        failedWorkers.put(dataSource, System.currentTimeMillis());
        throw e;
    }
}

Example 2 with BlockInStreamSource

use of alluxio.client.block.stream.BlockInStream.BlockInStreamSource in project alluxio by Alluxio.

the class AlluxioBlockStore method getDataSourceAndType.

/**
 * Gets the data source and type of data source of a block. This method is primarily responsible
 * for determining the data source and type of data source. It takes a map of failed workers and
 * their most recently failed time and tries to update it when BlockInStream created failed,
 * attempting to avoid reading from a recently failed worker.
 *
 * @param info the info of the block to read
 * @param status the URIStatus associated with the read request
 * @param policy the policy determining the Alluxio worker location
 * @param failedWorkers the map of workers address to most recent failure time
 * @return the data source and type of data source of the block
 */
public Pair<WorkerNetAddress, BlockInStreamSource> getDataSourceAndType(BlockInfo info, URIStatus status, BlockLocationPolicy policy, Map<WorkerNetAddress, Long> failedWorkers) throws IOException {
    List<BlockLocation> locations = info.getLocations();
    List<BlockWorkerInfo> blockWorkerInfo = Collections.EMPTY_LIST;
    // Initial target workers to read the block given the block locations.
    Set<WorkerNetAddress> workerPool;
    // Note that, it is possible that the blocks have been written as UFS blocks
    if (status.isPersisted() || status.getPersistenceState().equals("TO_BE_PERSISTED")) {
        blockWorkerInfo = mContext.getCachedWorkers();
        if (blockWorkerInfo.isEmpty()) {
            throw new UnavailableException(ExceptionMessage.NO_WORKER_AVAILABLE.getMessage());
        }
        workerPool = blockWorkerInfo.stream().map(BlockWorkerInfo::getNetAddress).collect(toSet());
    } else {
        if (locations.isEmpty()) {
            blockWorkerInfo = mContext.getCachedWorkers();
            if (blockWorkerInfo.isEmpty()) {
                throw new UnavailableException(ExceptionMessage.NO_WORKER_AVAILABLE.getMessage());
            }
            throw new UnavailableException(ExceptionMessage.BLOCK_UNAVAILABLE.getMessage(info.getBlockId()));
        }
        workerPool = locations.stream().map(BlockLocation::getWorkerAddress).collect(toSet());
    }
    // Workers to read the block, after considering failed workers.
    Set<WorkerNetAddress> workers = handleFailedWorkers(workerPool, failedWorkers);
    // TODO(calvin, jianjian): Consider containing these two variables in one object
    BlockInStreamSource dataSourceType = null;
    WorkerNetAddress dataSource = null;
    locations = locations.stream().filter(location -> workers.contains(location.getWorkerAddress())).collect(toList());
    // First try to read data from Alluxio
    if (!locations.isEmpty()) {
        // TODO(calvin): Get location via a policy
        List<WorkerNetAddress> tieredLocations = locations.stream().map(location -> location.getWorkerAddress()).collect(toList());
        Collections.shuffle(tieredLocations);
        Optional<Pair<WorkerNetAddress, Boolean>> nearest = BlockLocationUtils.nearest(mTieredIdentity, tieredLocations, mContext.getClusterConf());
        if (nearest.isPresent()) {
            dataSource = nearest.get().getFirst();
            dataSourceType = nearest.get().getSecond() ? mContext.hasProcessLocalWorker() ? BlockInStreamSource.PROCESS_LOCAL : BlockInStreamSource.NODE_LOCAL : BlockInStreamSource.REMOTE;
        }
    }
    // Can't get data from Alluxio, get it from the UFS instead
    if (dataSource == null) {
        dataSourceType = BlockInStreamSource.UFS;
        Preconditions.checkNotNull(policy, PreconditionMessage.UFS_READ_LOCATION_POLICY_UNSPECIFIED);
        blockWorkerInfo = blockWorkerInfo.stream().filter(workerInfo -> workers.contains(workerInfo.getNetAddress())).collect(toList());
        GetWorkerOptions getWorkerOptions = GetWorkerOptions.defaults().setBlockInfo(new BlockInfo().setBlockId(info.getBlockId()).setLength(info.getLength()).setLocations(locations)).setBlockWorkerInfos(blockWorkerInfo);
        dataSource = policy.getWorker(getWorkerOptions);
        if (dataSource != null) {
            if (mContext.hasProcessLocalWorker() && dataSource.equals(mContext.getNodeLocalWorker())) {
                dataSourceType = BlockInStreamSource.PROCESS_LOCAL;
                LOG.debug("Create BlockInStream to read data from UFS through process local worker {}", dataSource);
            } else {
                LOG.debug("Create BlockInStream to read data from UFS through worker {} " + "(client embedded in local worker process: {}," + "client co-located with worker in different processes: {}, " + "local worker address: {})", dataSource, mContext.hasProcessLocalWorker(), mContext.hasNodeLocalWorker(), mContext.hasNodeLocalWorker() ? mContext.getNodeLocalWorker() : "N/A");
            }
        }
    }
    if (dataSource == null) {
        throw new UnavailableException(ExceptionMessage.NO_WORKER_AVAILABLE.getMessage());
    }
    return new Pair<>(dataSource, dataSourceType);
}