Transmitir dados usando a API StorageWrite

Neste documento, descrevemos como usar a API BigQuery Storage Write para fazer streaming de dados para o BigQuery.

Em cenários de streaming, os dados chegam continuamente e precisam estar disponíveis para leituras com latência mínima. Ao usar a API BigQuery Storage write para cargas de trabalho de streaming, pense em quais garantias são necessárias:

• Se o app só precisa da semântica do tipo "pelo menos uma vez", use o stream padrão.
• Se você precisar de semântica exatamente uma vez, crie um ou mais streams no modo confirmado e use deslocamentos de stream para garantir gravações exatamente uma vez.

No modo confirmado, os dados gravados no stream ficam disponíveis para consulta assim que o servidor reconhece a solicitação de gravação. O stream padrão também usa o modo confirmado, mas não oferece garantias exatas.

Usar o fluxo padrão para semânticas do tipo "pelo menos uma vez"

Se o aplicativo puder aceitar a possibilidade de registros duplicados aparecerem na tabela de destino, recomendamos o uso do stream padrão para cenários de streaming.

O código a seguir mostra como gravar dados no stream padrão:

Java

Para saber como instalar e usar a biblioteca de cliente do BigQuery, consulte Bibliotecas do cliente do BigQuery. Para mais informações, consulte a documentação de referência da API BigQuery Java.

Para autenticar no BigQuery, configure o Application Default Credentials. Para mais informações, acesse Configurar a autenticação para bibliotecas de cliente.

import com.google.api.core.ApiFuture;
import com.google.api.core.ApiFutureCallback;
import com.google.api.core.ApiFutures;
import com.google.api.gax.core.FixedExecutorProvider;
import com.google.api.gax.retrying.RetrySettings;
import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.TableResult;
import com.google.cloud.bigquery.storage.v1.AppendRowsRequest;
import com.google.cloud.bigquery.storage.v1.AppendRowsResponse;
import com.google.cloud.bigquery.storage.v1.BigQueryWriteClient;
import com.google.cloud.bigquery.storage.v1.BigQueryWriteSettings;
import com.google.cloud.bigquery.storage.v1.Exceptions;
import com.google.cloud.bigquery.storage.v1.Exceptions.AppendSerializationError;
import com.google.cloud.bigquery.storage.v1.Exceptions.MaximumRequestCallbackWaitTimeExceededException;
import com.google.cloud.bigquery.storage.v1.Exceptions.StorageException;
import com.google.cloud.bigquery.storage.v1.Exceptions.StreamWriterClosedException;
import com.google.cloud.bigquery.storage.v1.JsonStreamWriter;
import com.google.cloud.bigquery.storage.v1.TableName;
import com.google.common.util.concurrent.MoreExecutors;
import com.google.protobuf.ByteString;
import com.google.protobuf.Descriptors.DescriptorValidationException;
import java.io.IOException;
import java.util.Map;
import java.util.concurrent.Executors;
import java.util.concurrent.Phaser;
import java.util.concurrent.atomic.AtomicInteger;
import javax.annotation.concurrent.GuardedBy;
import org.json.JSONArray;
import org.json.JSONObject;
import org.threeten.bp.Duration;

public class WriteToDefaultStream {

  public static void runWriteToDefaultStream()
      throws DescriptorValidationException, InterruptedException, IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "MY_PROJECT_ID";
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    writeToDefaultStream(projectId, datasetName, tableName);
  }

  private static ByteString buildByteString() {
    byte[] bytes = new byte[] {1, 2, 3, 4, 5};
    return ByteString.copyFrom(bytes);
  }

  // Create a JSON object that is compatible with the table schema.
  private static JSONObject buildRecord(int i, int j) {
    JSONObject record = new JSONObject();
    StringBuilder sbSuffix = new StringBuilder();
    for (int k = 0; k < j; k++) {
      sbSuffix.append(k);
    }
    record.put("test_string", String.format("record %03d-%03d %s", i, j, sbSuffix.toString()));
    ByteString byteString = buildByteString();
    record.put("test_bytes", byteString);
    return record;
  }

  public static void writeToDefaultStream(String projectId, String datasetName, String tableName)
      throws DescriptorValidationException, InterruptedException, IOException {
    TableName parentTable = TableName.of(projectId, datasetName, tableName);

    DataWriter writer = new DataWriter();
    // One time initialization for the worker.
    writer.initialize(parentTable);

    // Write two batches of fake data to the stream, each with 10 JSON records.  Data may be
    // batched up to the maximum request size:
    // https://cloud.google.com/bigquery/quotas#write-api-limits
    for (int i = 0; i < 2; i++) {
      JSONArray jsonArr = new JSONArray();
      for (int j = 0; j < 10; j++) {
        JSONObject record = buildRecord(i, j);
        jsonArr.put(record);
      }

      writer.append(new AppendContext(jsonArr));
    }

    // Final cleanup for the stream during worker teardown.
    writer.cleanup();
    verifyExpectedRowCount(parentTable, 12);
    System.out.println("Appended records successfully.");
  }

  private static void verifyExpectedRowCount(TableName parentTable, int expectedRowCount)
      throws InterruptedException {
    String queryRowCount =
        "SELECT COUNT(*) FROM `"
            + parentTable.getProject()
            + "."
            + parentTable.getDataset()
            + "."
            + parentTable.getTable()
            + "`";
    QueryJobConfiguration queryConfig = QueryJobConfiguration.newBuilder(queryRowCount).build();
    BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
    TableResult results = bigquery.query(queryConfig);
    int countRowsActual =
        Integer.parseInt(results.getValues().iterator().next().get("f0_").getStringValue());
    if (countRowsActual != expectedRowCount) {
      throw new RuntimeException(
          "Unexpected row count. Expected: " + expectedRowCount + ". Actual: " + countRowsActual);
    }
  }

  private static class AppendContext {

    JSONArray data;

    AppendContext(JSONArray data) {
      this.data = data;
    }
  }

  private static class DataWriter {

    private static final int MAX_RECREATE_COUNT = 3;

    private BigQueryWriteClient client;

    // Track the number of in-flight requests to wait for all responses before shutting down.
    private final Phaser inflightRequestCount = new Phaser(1);
    private final Object lock = new Object();
    private JsonStreamWriter streamWriter;

    @GuardedBy("lock")
    private RuntimeException error = null;

    private AtomicInteger recreateCount = new AtomicInteger(0);

    private JsonStreamWriter createStreamWriter(String tableName)
        throws DescriptorValidationException, IOException, InterruptedException {
      // Configure in-stream automatic retry settings.
      // Error codes that are immediately retried:
      // * ABORTED, UNAVAILABLE, CANCELLED, INTERNAL, DEADLINE_EXCEEDED
      // Error codes that are retried with exponential backoff:
      // * RESOURCE_EXHAUSTED
      RetrySettings retrySettings =
          RetrySettings.newBuilder()
              .setInitialRetryDelay(Duration.ofMillis(500))
              .setRetryDelayMultiplier(1.1)
              .setMaxAttempts(5)
              .setMaxRetryDelay(Duration.ofMinutes(1))
              .build();

      // Use the JSON stream writer to send records in JSON format. Specify the table name to write
      // to the default stream.
      // For more information about JsonStreamWriter, see:
      // https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/JsonStreamWriter.html
      return JsonStreamWriter.newBuilder(tableName, client)
          .setExecutorProvider(FixedExecutorProvider.create(Executors.newScheduledThreadPool(100)))
          .setChannelProvider(
              BigQueryWriteSettings.defaultGrpcTransportProviderBuilder()
                  .setKeepAliveTime(org.threeten.bp.Duration.ofMinutes(1))
                  .setKeepAliveTimeout(org.threeten.bp.Duration.ofMinutes(1))
                  .setKeepAliveWithoutCalls(true)
                  .setChannelsPerCpu(2)
                  .build())
          .setEnableConnectionPool(true)
          // If value is missing in json and there is a default value configured on bigquery
          // column, apply the default value to the missing value field.
          .setDefaultMissingValueInterpretation(
              AppendRowsRequest.MissingValueInterpretation.DEFAULT_VALUE)
          .setRetrySettings(retrySettings)
          .build();
    }

    public void initialize(TableName parentTable)
        throws DescriptorValidationException, IOException, InterruptedException {
      // Initialize client without settings, internally within stream writer a new client will be
      // created with full settings.
      client = BigQueryWriteClient.create();

      streamWriter = createStreamWriter(parentTable.toString());
    }

    public void append(AppendContext appendContext)
        throws DescriptorValidationException, IOException, InterruptedException {
      synchronized (this.lock) {
        if (!streamWriter.isUserClosed()
            && streamWriter.isClosed()
            && recreateCount.getAndIncrement() < MAX_RECREATE_COUNT) {
          streamWriter = createStreamWriter(streamWriter.getStreamName());
          this.error = null;
        }
        // If earlier appends have failed, we need to reset before continuing.
        if (this.error != null) {
          throw this.error;
        }
      }
      // Append asynchronously for increased throughput.
      ApiFuture<AppendRowsResponse> future = streamWriter.append(appendContext.data);
      ApiFutures.addCallback(
          future, new AppendCompleteCallback(this, appendContext), MoreExecutors.directExecutor());

      // Increase the count of in-flight requests.
      inflightRequestCount.register();
    }

    public void cleanup() {
      // Wait for all in-flight requests to complete.
      inflightRequestCount.arriveAndAwaitAdvance();

      client.close();
      // Close the connection to the server.
      streamWriter.close();

      // Verify that no error occurred in the stream.
      synchronized (this.lock) {
        if (this.error != null) {
          throw this.error;
        }
      }
    }

    static class AppendCompleteCallback implements ApiFutureCallback<AppendRowsResponse> {

      private final DataWriter parent;
      private final AppendContext appendContext;

      public AppendCompleteCallback(DataWriter parent, AppendContext appendContext) {
        this.parent = parent;
        this.appendContext = appendContext;
      }

      public void onSuccess(AppendRowsResponse response) {
        System.out.format("Append success\n");
        this.parent.recreateCount.set(0);
        done();
      }

      public void onFailure(Throwable throwable) {
        if (throwable instanceof AppendSerializationError) {
          AppendSerializationError ase = (AppendSerializationError) throwable;
          Map<Integer, String> rowIndexToErrorMessage = ase.getRowIndexToErrorMessage();
          if (rowIndexToErrorMessage.size() > 0) {
            // Omit the faulty rows
            JSONArray dataNew = new JSONArray();
            for (int i = 0; i < appendContext.data.length(); i++) {
              if (!rowIndexToErrorMessage.containsKey(i)) {
                dataNew.put(appendContext.data.get(i));
              } else {
                // process faulty rows by placing them on a dead-letter-queue, for instance
              }
            }

            // Retry the remaining valid rows, but using a separate thread to
            // avoid potentially blocking while we are in a callback.
            if (dataNew.length() > 0) {
              try {
                this.parent.append(new AppendContext(dataNew));
              } catch (DescriptorValidationException e) {
                throw new RuntimeException(e);
              } catch (IOException e) {
                throw new RuntimeException(e);
              } catch (InterruptedException e) {
                throw new RuntimeException(e);
              }
            }
            // Mark the existing attempt as done since we got a response for it
            done();
            return;
          }
        }

        boolean resendRequest = false;
        if (throwable instanceof MaximumRequestCallbackWaitTimeExceededException) {
          resendRequest = true;
        } else if (throwable instanceof StreamWriterClosedException) {
          if (!parent.streamWriter.isUserClosed()) {
            resendRequest = true;
          }
        }
        if (resendRequest) {
          // Retry this request.
          try {
            this.parent.append(new AppendContext(appendContext.data));
          } catch (DescriptorValidationException e) {
            throw new RuntimeException(e);
          } catch (IOException e) {
            throw new RuntimeException(e);
          } catch (InterruptedException e) {
            throw new RuntimeException(e);
          }
          // Mark the existing attempt as done since we got a response for it
          done();
          return;
        }

        synchronized (this.parent.lock) {
          if (this.parent.error == null) {
            StorageException storageException = Exceptions.toStorageException(throwable);
            this.parent.error =
                (storageException != null) ? storageException : new RuntimeException(throwable);
          }
        }
        done();
      }

      private void done() {
        // Reduce the count of in-flight requests.
        this.parent.inflightRequestCount.arriveAndDeregister();
      }
    }
  }
}

Usar multiplexação

Você ativa a multiplexação no nível do gravador de stream apenas para o stream padrão. Para ativar a multiplexação no Java, chame o método setEnableConnectionPool ao criar um objeto StreamWriter ou JsonStreamWriter:

// One possible way for constructing StreamWriter
StreamWriter.newBuilder(streamName)
              .setWriterSchema(protoSchema)
              .setEnableConnectionPool(true)
              .build();
// One possible way for constructing JsonStreamWriter
JsonStreamWriter.newBuilder(tableName, bigqueryClient)
              .setEnableConnectionPool(true)
              .build();

Para ativar a multiplexação no Go, consulte Compartilhamento de conexão (multiplexação).

Usar o modo confirmado para a semântica exatamente uma vez

Se você precisar de semântica de gravação única, crie um stream de gravação no modo comprometido. No modo confirmado, os registros estão disponíveis para consulta assim que o cliente recebe a confirmação do back-end.

O modo confirmado fornece uma entrega única uma vez em um stream por meio de deslocamentos de registro. Ao usar deslocamentos de registro, o aplicativo especifica o próximo deslocamento de anexação em cada chamada para AppendRows. A operação de gravação só será executada se o valor de ajuste corresponder ao próximo deslocamento de anexação. Para mais informações, consulte Gerenciar deslocamentos de stream para conseguir semânticas exatamente uma vez.

Se você não fornecer um deslocamento, os registros serão anexados à extremidade atual do fluxo. Nesse caso, se um pedido de anexo retornar um erro, uma nova tentativa poderá fazer com que o registro apareça mais de uma vez no stream.

Para usar o tipo de compromisso, siga estas etapas:

1. Chame CreateWriteStream para criar um ou mais streams no modo confirmado.
2. Para cada stream, chame AppendRows em um loop para gravar lotes de registros.
3. Chame FinalizeWriteStream para cada stream para liberar o stream. Depois de chamar esse método, não será possível gravar mais linhas no stream. Essa etapa é opcional no modo confirmado, mas ajuda a evitar exceder o limite de fluxos ativos. Para mais informações, consulte Limitar a taxa de criação de stream.

Não é possível excluir um stream explicitamente. Os streams seguem o time to live (TTL) definido pelo sistema:

• Se não houver tráfego no stream, ele será transmitido por TTL em três dias.
• Por padrão, um stream em buffer tem um TTL de sete dias se não houver tráfego nele.

O código a seguir mostra como usar o modo confirmado.

Java

Para saber como instalar e usar a biblioteca de cliente do BigQuery, consulte Bibliotecas do cliente do BigQuery. Para mais informações, consulte a documentação de referência da API BigQuery Java.

Para autenticar no BigQuery, configure o Application Default Credentials. Para mais informações, acesse Configurar a autenticação para bibliotecas de cliente.

import com.google.api.core.ApiFuture;
import com.google.api.core.ApiFutureCallback;
import com.google.api.core.ApiFutures;
import com.google.api.gax.retrying.RetrySettings;
import com.google.cloud.bigquery.storage.v1.AppendRowsResponse;
import com.google.cloud.bigquery.storage.v1.BigQueryWriteClient;
import com.google.cloud.bigquery.storage.v1.CreateWriteStreamRequest;
import com.google.cloud.bigquery.storage.v1.Exceptions;
import com.google.cloud.bigquery.storage.v1.Exceptions.StorageException;
import com.google.cloud.bigquery.storage.v1.FinalizeWriteStreamResponse;
import com.google.cloud.bigquery.storage.v1.JsonStreamWriter;
import com.google.cloud.bigquery.storage.v1.TableName;
import com.google.cloud.bigquery.storage.v1.WriteStream;
import com.google.common.util.concurrent.MoreExecutors;
import com.google.protobuf.Descriptors.DescriptorValidationException;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Phaser;
import javax.annotation.concurrent.GuardedBy;
import org.json.JSONArray;
import org.json.JSONObject;
import org.threeten.bp.Duration;

public class WriteCommittedStream {

  public static void runWriteCommittedStream()
      throws DescriptorValidationException, InterruptedException, IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "MY_PROJECT_ID";
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";

    writeCommittedStream(projectId, datasetName, tableName);
  }

  public static void writeCommittedStream(String projectId, String datasetName, String tableName)
      throws DescriptorValidationException, InterruptedException, IOException {
    BigQueryWriteClient client = BigQueryWriteClient.create();
    TableName parentTable = TableName.of(projectId, datasetName, tableName);

    DataWriter writer = new DataWriter();
    // One time initialization.
    writer.initialize(parentTable, client);

    try {
      // Write two batches of fake data to the stream, each with 10 JSON records.  Data may be
      // batched up to the maximum request size:
      // https://cloud.google.com/bigquery/quotas#write-api-limits
      long offset = 0;
      for (int i = 0; i < 2; i++) {
        // Create a JSON object that is compatible with the table schema.
        JSONArray jsonArr = new JSONArray();
        for (int j = 0; j < 10; j++) {
          JSONObject record = new JSONObject();
          record.put("col1", String.format("batch-record %03d-%03d", i, j));
          jsonArr.put(record);
        }
        writer.append(jsonArr, offset);
        offset += jsonArr.length();
      }
    } catch (ExecutionException e) {
      // If the wrapped exception is a StatusRuntimeException, check the state of the operation.
      // If the state is INTERNAL, CANCELLED, or ABORTED, you can retry. For more information, see:
      // https://grpc.github.io/grpc-java/javadoc/io/grpc/StatusRuntimeException.html
      System.out.println("Failed to append records. \n" + e);
    }

    // Final cleanup for the stream.
    writer.cleanup(client);
    System.out.println("Appended records successfully.");
  }

  // A simple wrapper object showing how the stateful stream writer should be used.
  private static class DataWriter {

    private JsonStreamWriter streamWriter;
    // Track the number of in-flight requests to wait for all responses before shutting down.
    private final Phaser inflightRequestCount = new Phaser(1);

    private final Object lock = new Object();

    @GuardedBy("lock")
    private RuntimeException error = null;

    void initialize(TableName parentTable, BigQueryWriteClient client)
        throws IOException, DescriptorValidationException, InterruptedException {
      // Initialize a write stream for the specified table.
      // For more information on WriteStream.Type, see:
      // https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/WriteStream.Type.html
      WriteStream stream = WriteStream.newBuilder().setType(WriteStream.Type.COMMITTED).build();

      CreateWriteStreamRequest createWriteStreamRequest =
          CreateWriteStreamRequest.newBuilder()
              .setParent(parentTable.toString())
              .setWriteStream(stream)
              .build();
      WriteStream writeStream = client.createWriteStream(createWriteStreamRequest);

      // Configure in-stream automatic retry settings.
      // Error codes that are immediately retried:
      // * ABORTED, UNAVAILABLE, CANCELLED, INTERNAL, DEADLINE_EXCEEDED
      // Error codes that are retried with exponential backoff:
      // * RESOURCE_EXHAUSTED
      RetrySettings retrySettings =
          RetrySettings.newBuilder()
              .setInitialRetryDelay(Duration.ofMillis(500))
              .setRetryDelayMultiplier(1.1)
              .setMaxAttempts(5)
              .setMaxRetryDelay(Duration.ofMinutes(1))
              .build();

      // Use the JSON stream writer to send records in JSON format.
      // For more information about JsonStreamWriter, see:
      // https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/JsonStreamWriter.html
      streamWriter =
          JsonStreamWriter.newBuilder(writeStream.getName(), writeStream.getTableSchema(), client)
              .setRetrySettings(retrySettings)
              .build();
    }

    public void append(JSONArray data, long offset)
        throws DescriptorValidationException, IOException, ExecutionException {
      synchronized (this.lock) {
        // If earlier appends have failed, we need to reset before continuing.
        if (this.error != null) {
          throw this.error;
        }
      }
      // Append asynchronously for increased throughput.
      ApiFuture<AppendRowsResponse> future = streamWriter.append(data, offset);
      ApiFutures.addCallback(
          future, new DataWriter.AppendCompleteCallback(this), MoreExecutors.directExecutor());
      // Increase the count of in-flight requests.
      inflightRequestCount.register();
    }

    public void cleanup(BigQueryWriteClient client) {
      // Wait for all in-flight requests to complete.
      inflightRequestCount.arriveAndAwaitAdvance();

      // Close the connection to the server.
      streamWriter.close();

      // Verify that no error occurred in the stream.
      synchronized (this.lock) {
        if (this.error != null) {
          throw this.error;
        }
      }

      // Finalize the stream.
      FinalizeWriteStreamResponse finalizeResponse =
          client.finalizeWriteStream(streamWriter.getStreamName());
      System.out.println("Rows written: " + finalizeResponse.getRowCount());
    }

    public String getStreamName() {
      return streamWriter.getStreamName();
    }

    static class AppendCompleteCallback implements ApiFutureCallback<AppendRowsResponse> {

      private final DataWriter parent;

      public AppendCompleteCallback(DataWriter parent) {
        this.parent = parent;
      }

      public void onSuccess(AppendRowsResponse response) {
        System.out.format("Append %d success\n", response.getAppendResult().getOffset().getValue());
        done();
      }

      public void onFailure(Throwable throwable) {
        synchronized (this.parent.lock) {
          if (this.parent.error == null) {
            StorageException storageException = Exceptions.toStorageException(throwable);
            this.parent.error =
                (storageException != null) ? storageException : new RuntimeException(throwable);
          }
        }
        System.out.format("Error: %s\n", throwable.toString());
        done();
      }

      private void done() {
        // Reduce the count of in-flight requests.
        this.parent.inflightRequestCount.arriveAndDeregister();
      }
    }
  }
}