Examples with CheckpointV1 org.apache.samza.checkpoint.CheckpointV1 used on opensource projects

Example 11 with CheckpointV1

use of org.apache.samza.checkpoint.CheckpointV1 in project samza by apache.

the class TransactionalStateTaskRestoreManager method getCheckpointId.

private CheckpointId getCheckpointId(Checkpoint checkpoint) {
    if (checkpoint == null)
        return null;
    if (checkpoint instanceof CheckpointV1) {
        for (Map.Entry<String, SystemStream> storeNameSystemStream : storeChangelogs.entrySet()) {
            SystemStreamPartition storeChangelogSSP = new SystemStreamPartition(storeNameSystemStream.getValue(), taskModel.getChangelogPartition());
            String checkpointMessage = checkpoint.getOffsets().get(storeChangelogSSP);
            if (StringUtils.isNotBlank(checkpointMessage)) {
                KafkaChangelogSSPOffset kafkaStateChanglogOffset = KafkaChangelogSSPOffset.fromString(checkpointMessage);
                return kafkaStateChanglogOffset.getCheckpointId();
            }
        }
    } else if (checkpoint instanceof CheckpointV2) {
        return ((CheckpointV2) checkpoint).getCheckpointId();
    } else {
        throw new SamzaException("Unsupported checkpoint version: " + checkpoint.getVersion());
    }
    return null;
}

Example 12 with CheckpointV1

use of org.apache.samza.checkpoint.CheckpointV1 in project samza by apache.

the class TransactionalStateTaskRestoreManager method getCheckpointedChangelogOffsets.

private Map<String, KafkaStateCheckpointMarker> getCheckpointedChangelogOffsets(Checkpoint checkpoint) {
    Map<String, KafkaStateCheckpointMarker> checkpointedChangelogOffsets = new HashMap<>();
    if (checkpoint == null)
        return checkpointedChangelogOffsets;
    if (checkpoint instanceof CheckpointV2) {
        Map<String, Map<String, String>> factoryStoreSCMs = ((CheckpointV2) checkpoint).getStateCheckpointMarkers();
        if (factoryStoreSCMs.containsKey(KafkaStateCheckpointMarker.KAFKA_STATE_BACKEND_FACTORY_NAME)) {
            factoryStoreSCMs.get(KafkaStateCheckpointMarker.KAFKA_STATE_BACKEND_FACTORY_NAME).forEach((storeName, scmString) -> {
                KafkaStateCheckpointMarker kafkaSCM = KafkaStateCheckpointMarker.deserialize(scmString);
                checkpointedChangelogOffsets.put(storeName, kafkaSCM);
            });
        }
    // skip the non-KafkaStateCheckpointMarkers
    } else if (checkpoint instanceof CheckpointV1) {
        // If the checkpoint v1 is used, we need to fetch the changelog SSPs in the inputOffsets in order to get the
        // store offset.
        Map<SystemStreamPartition, String> checkpointedOffsets = checkpoint.getOffsets();
        storeChangelogs.forEach((storeName, systemStream) -> {
            Partition changelogPartition = taskModel.getChangelogPartition();
            SystemStreamPartition storeChangelogSSP = new SystemStreamPartition(systemStream, changelogPartition);
            String checkpointedOffset = checkpointedOffsets.get(storeChangelogSSP);
            if (StringUtils.isNotBlank(checkpointedOffset)) {
                KafkaChangelogSSPOffset kafkaChangelogSSPOffset = KafkaChangelogSSPOffset.fromString(checkpointedOffset);
                KafkaStateCheckpointMarker marker = new KafkaStateCheckpointMarker(storeChangelogSSP, kafkaChangelogSSPOffset.getChangelogOffset());
                checkpointedChangelogOffsets.put(storeName, marker);
            }
        });
    } else {
        throw new SamzaException("Unsupported checkpoint version: " + checkpoint.getVersion());
    }
    return checkpointedChangelogOffsets;
}

Example 13 with CheckpointV1

use of org.apache.samza.checkpoint.CheckpointV1 in project samza by apache.

the class TaskStorageCommitManager method writeCheckpointToStoreDirectories.

/**
 * Writes the {@link Checkpoint} information returned by {@link #upload(CheckpointId, Map)}
 * in each store directory and store checkpoint directory. Written content depends on the type of {@code checkpoint}.
 * For {@link CheckpointV2}, writes the entire task {@link CheckpointV2}.
 * For {@link CheckpointV1}, only writes the changelog ssp offsets in the OFFSET* files.
 *
 * Note: The assumption is that this method will be invoked once for each {@link Checkpoint} version that the
 * task needs to write as determined by {@link org.apache.samza.config.TaskConfig#getCheckpointWriteVersions()}.
 * This is required for upgrade and rollback compatibility.
 *
 * @param checkpoint the latest checkpoint to be persisted to local file system
 */
public void writeCheckpointToStoreDirectories(Checkpoint checkpoint) {
    if (checkpoint instanceof CheckpointV1) {
        LOG.debug("Writing CheckpointV1 to store and checkpoint directories for taskName: {} with checkpoint: {}", taskName, checkpoint);
        // Write CheckpointV1 changelog offsets to store and checkpoint directories
        writeChangelogOffsetFiles(checkpoint.getOffsets());
    } else if (checkpoint instanceof CheckpointV2) {
        LOG.debug("Writing CheckpointV2 to store and checkpoint directories for taskName: {} with checkpoint: {}", taskName, checkpoint);
        storageEngines.forEach((storeName, storageEngine) -> {
            // Only write the checkpoint file if the store is durable and persisted to disk
            if (storageEngine.getStoreProperties().isDurableStore() && storageEngine.getStoreProperties().isPersistedToDisk()) {
                CheckpointV2 checkpointV2 = (CheckpointV2) checkpoint;
                try {
                    File storeDir = storageManagerUtil.getTaskStoreDir(durableStoreBaseDir, storeName, taskName, TaskMode.Active);
                    storageManagerUtil.writeCheckpointV2File(storeDir, checkpointV2);
                    CheckpointId checkpointId = checkpointV2.getCheckpointId();
                    File checkpointDir = Paths.get(storageManagerUtil.getStoreCheckpointDir(storeDir, checkpointId)).toFile();
                    storageManagerUtil.writeCheckpointV2File(checkpointDir, checkpointV2);
                } catch (Exception e) {
                    throw new SamzaException(String.format("Write checkpoint file failed for task: %s, storeName: %s, checkpointId: %s", taskName, storeName, ((CheckpointV2) checkpoint).getCheckpointId()), e);
                }
            }
        });
    } else {
        throw new SamzaException("Unsupported checkpoint version: " + checkpoint.getVersion());
    }
}

Example 14 with CheckpointV1

use of org.apache.samza.checkpoint.CheckpointV1 in project samza by apache.

the class TestContainerStorageManager method testNoConfiguredDurableStores.

@Test
public void testNoConfiguredDurableStores() throws InterruptedException {
    taskRestoreMetricGauges = new HashMap<>();
    this.tasks = new HashMap<>();
    this.taskInstanceMetrics = new HashMap<>();
    // Add two mocked tasks
    addMockedTask("task 0", 0);
    addMockedTask("task 1", 1);
    // Mock container metrics
    samzaContainerMetrics = mock(SamzaContainerMetrics.class);
    when(samzaContainerMetrics.taskStoreRestorationMetrics()).thenReturn(taskRestoreMetricGauges);
    // Create mocked configs for specifying serdes
    Map<String, String> configMap = new HashMap<>();
    configMap.put("serializers.registry.stringserde.class", StringSerdeFactory.class.getName());
    configMap.put(TaskConfig.TRANSACTIONAL_STATE_RETAIN_EXISTING_STATE, "true");
    Config config = new MapConfig(configMap);
    Map<String, Serde<Object>> serdes = new HashMap<>();
    serdes.put("stringserde", mock(Serde.class));
    CheckpointManager checkpointManager = mock(CheckpointManager.class);
    when(checkpointManager.readLastCheckpoint(any(TaskName.class))).thenReturn(new CheckpointV1(new HashMap<>()));
    ContainerContext mockContainerContext = mock(ContainerContext.class);
    ContainerModel mockContainerModel = new ContainerModel("samza-container-test", tasks);
    when(mockContainerContext.getContainerModel()).thenReturn(mockContainerModel);
    // Reset the expected number of sysConsumer create, start and stop calls, and store.restore() calls
    this.systemConsumerCreationCount = 0;
    this.systemConsumerStartCount = 0;
    this.systemConsumerStopCount = 0;
    this.storeRestoreCallCount = 0;
    StateBackendFactory backendFactory = mock(StateBackendFactory.class);
    TaskRestoreManager restoreManager = mock(TaskRestoreManager.class);
    when(backendFactory.getRestoreManager(any(), any(), any(), any(), any(), any(), any(), any(), any(), any(), any())).thenReturn(restoreManager);
    doAnswer(invocation -> {
        storeRestoreCallCount++;
        return CompletableFuture.completedFuture(null);
    }).when(restoreManager).restore();
    // Create the container storage manager
    ContainerStorageManager containerStorageManager = new ContainerStorageManager(checkpointManager, mockContainerModel, mock(StreamMetadataCache.class), mock(SystemAdmins.class), new HashMap<>(), new HashMap<>(), new HashMap<>(), new HashMap<>(), serdes, config, taskInstanceMetrics, samzaContainerMetrics, mock(JobContext.class), mockContainerContext, new HashMap<>(), mock(Map.class), DEFAULT_LOGGED_STORE_BASE_DIR, DEFAULT_STORE_BASE_DIR, null, new SystemClock());
    containerStorageManager.start();
    containerStorageManager.shutdown();
    for (Gauge gauge : taskRestoreMetricGauges.values()) {
        Assert.assertTrue("Restoration time gauge value should never be invoked", mockingDetails(gauge).getInvocations().size() == 0);
    }
    Assert.assertEquals("Store restore count should be 2 because there are 0 stores", 0, this.storeRestoreCallCount);
    Assert.assertEquals(0, this.systemConsumerCreationCount);
    Assert.assertEquals(0, this.systemConsumerStopCount);
    Assert.assertEquals(0, this.systemConsumerStartCount);
}

Example 15 with CheckpointV1

use of org.apache.samza.checkpoint.CheckpointV1 in project samza by apache.

the class TestContainerStorageManager method setUp.

/**
 * Method to create a containerStorageManager with mocked dependencies
 */
@Before
public void setUp() throws InterruptedException {
    taskRestoreMetricGauges = new HashMap<>();
    this.tasks = new HashMap<>();
    this.taskInstanceMetrics = new HashMap<>();
    // Add two mocked tasks
    addMockedTask("task 0", 0);
    addMockedTask("task 1", 1);
    // Mock container metrics
    samzaContainerMetrics = mock(SamzaContainerMetrics.class);
    when(samzaContainerMetrics.taskStoreRestorationMetrics()).thenReturn(taskRestoreMetricGauges);
    // Create a map of test changeLogSSPs
    Map<String, SystemStream> changelogSystemStreams = new HashMap<>();
    changelogSystemStreams.put(STORE_NAME, new SystemStream(SYSTEM_NAME, STREAM_NAME));
    // Create mocked storage engine factories
    Map<String, StorageEngineFactory<Object, Object>> storageEngineFactories = new HashMap<>();
    StorageEngineFactory mockStorageEngineFactory = (StorageEngineFactory<Object, Object>) mock(StorageEngineFactory.class);
    StorageEngine mockStorageEngine = mock(StorageEngine.class);
    when(mockStorageEngine.getStoreProperties()).thenReturn(new StoreProperties.StorePropertiesBuilder().setLoggedStore(true).setPersistedToDisk(true).build());
    doAnswer(invocation -> {
        return mockStorageEngine;
    }).when(mockStorageEngineFactory).getStorageEngine(anyString(), any(), any(), any(), any(), any(), any(), any(), any(), any());
    storageEngineFactories.put(STORE_NAME, mockStorageEngineFactory);
    // Add instrumentation to mocked storage engine, to record the number of store.restore() calls
    doAnswer(invocation -> {
        storeRestoreCallCount++;
        return CompletableFuture.completedFuture(null);
    }).when(mockStorageEngine).restore(any());
    // Set the mocked stores' properties to be persistent
    doAnswer(invocation -> {
        return new StoreProperties.StorePropertiesBuilder().setLoggedStore(true).build();
    }).when(mockStorageEngine).getStoreProperties();
    // Mock and setup sysconsumers
    SystemConsumer mockSystemConsumer = mock(SystemConsumer.class);
    doAnswer(invocation -> {
        systemConsumerStartCount++;
        return null;
    }).when(mockSystemConsumer).start();
    doAnswer(invocation -> {
        systemConsumerStopCount++;
        return null;
    }).when(mockSystemConsumer).stop();
    // Create mocked system factories
    Map<String, SystemFactory> systemFactories = new HashMap<>();
    // Count the number of sysConsumers created
    SystemFactory mockSystemFactory = mock(SystemFactory.class);
    doAnswer(invocation -> {
        this.systemConsumerCreationCount++;
        return mockSystemConsumer;
    }).when(mockSystemFactory).getConsumer(anyString(), any(), any());
    systemFactories.put(SYSTEM_NAME, mockSystemFactory);
    // Create mocked configs for specifying serdes
    Map<String, String> configMap = new HashMap<>();
    configMap.put("stores." + STORE_NAME + ".key.serde", "stringserde");
    configMap.put("stores." + STORE_NAME + ".msg.serde", "stringserde");
    configMap.put("stores." + STORE_NAME + ".factory", mockStorageEngineFactory.getClass().getName());
    configMap.put("stores." + STORE_NAME + ".changelog", SYSTEM_NAME + "." + STREAM_NAME);
    configMap.put("serializers.registry.stringserde.class", StringSerdeFactory.class.getName());
    configMap.put(TaskConfig.TRANSACTIONAL_STATE_RETAIN_EXISTING_STATE, "true");
    Config config = new MapConfig(configMap);
    Map<String, Serde<Object>> serdes = new HashMap<>();
    serdes.put("stringserde", mock(Serde.class));
    // Create mocked system admins
    SystemAdmin mockSystemAdmin = mock(SystemAdmin.class);
    doAnswer(new Answer<Void>() {

        public Void answer(InvocationOnMock invocation) {
            Object[] args = invocation.getArguments();
            System.out.println("called with arguments: " + Arrays.toString(args));
            return null;
        }
    }).when(mockSystemAdmin).validateStream(any());
    SystemAdmins mockSystemAdmins = mock(SystemAdmins.class);
    when(mockSystemAdmins.getSystemAdmin("kafka")).thenReturn(mockSystemAdmin);
    // Create a mocked mockStreamMetadataCache
    SystemStreamMetadata.SystemStreamPartitionMetadata sspMetadata = new SystemStreamMetadata.SystemStreamPartitionMetadata("0", "50", "51");
    Map<Partition, SystemStreamMetadata.SystemStreamPartitionMetadata> partitionMetadata = new HashMap<>();
    partitionMetadata.put(new Partition(0), sspMetadata);
    partitionMetadata.put(new Partition(1), sspMetadata);
    SystemStreamMetadata systemStreamMetadata = new SystemStreamMetadata(STREAM_NAME, partitionMetadata);
    StreamMetadataCache mockStreamMetadataCache = mock(StreamMetadataCache.class);
    when(mockStreamMetadataCache.getStreamMetadata(JavaConverters.asScalaSetConverter(new HashSet<SystemStream>(changelogSystemStreams.values())).asScala().toSet(), false)).thenReturn(new scala.collection.immutable.Map.Map1(new SystemStream(SYSTEM_NAME, STREAM_NAME), systemStreamMetadata));
    CheckpointManager checkpointManager = mock(CheckpointManager.class);
    when(checkpointManager.readLastCheckpoint(any(TaskName.class))).thenReturn(new CheckpointV1(new HashMap<>()));
    SSPMetadataCache mockSSPMetadataCache = mock(SSPMetadataCache.class);
    when(mockSSPMetadataCache.getMetadata(any(SystemStreamPartition.class))).thenReturn(new SystemStreamMetadata.SystemStreamPartitionMetadata("0", "10", "11"));
    ContainerContext mockContainerContext = mock(ContainerContext.class);
    ContainerModel mockContainerModel = new ContainerModel("samza-container-test", tasks);
    when(mockContainerContext.getContainerModel()).thenReturn(mockContainerModel);
    // Reset the expected number of sysConsumer create, start and stop calls, and store.restore() calls
    this.systemConsumerCreationCount = 0;
    this.systemConsumerStartCount = 0;
    this.systemConsumerStopCount = 0;
    this.storeRestoreCallCount = 0;
    StateBackendFactory backendFactory = mock(StateBackendFactory.class);
    TaskRestoreManager restoreManager = mock(TaskRestoreManager.class);
    ArgumentCaptor<ExecutorService> restoreExecutorCaptor = ArgumentCaptor.forClass(ExecutorService.class);
    when(backendFactory.getRestoreManager(any(), any(), any(), restoreExecutorCaptor.capture(), any(), any(), any(), any(), any(), any(), any())).thenReturn(restoreManager);
    doAnswer(invocation -> {
        storeRestoreCallCount++;
        return CompletableFuture.completedFuture(null);
    }).when(restoreManager).restore();
    // Create the container storage manager
    this.containerStorageManager = new ContainerStorageManager(checkpointManager, mockContainerModel, mockStreamMetadataCache, mockSystemAdmins, changelogSystemStreams, new HashMap<>(), storageEngineFactories, systemFactories, serdes, config, taskInstanceMetrics, samzaContainerMetrics, mock(JobContext.class), mockContainerContext, ImmutableMap.of(StorageConfig.KAFKA_STATE_BACKEND_FACTORY, backendFactory), mock(Map.class), DEFAULT_LOGGED_STORE_BASE_DIR, DEFAULT_STORE_BASE_DIR, null, new SystemClock());
}