Examples with CheckpointV2 org.apache.samza.checkpoint.CheckpointV2 used on opensource projects

Example 11 with CheckpointV2

use of org.apache.samza.checkpoint.CheckpointV2 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 12 with CheckpointV2

use of org.apache.samza.checkpoint.CheckpointV2 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 13 with CheckpointV2

use of org.apache.samza.checkpoint.CheckpointV2 in project samza by apache.

the class BlobStoreUtil method getStoreSnapshotIndexes.

/**
 * Get the blob id of {@link SnapshotIndex} and {@link SnapshotIndex}es for the provided {@code task}
 * in the provided {@code checkpoint}.
 * @param jobName job name is used to build request metadata
 * @param jobId job id is used to build request metadata
 * @param taskName task name to get the store state checkpoint markers and snapshot indexes for
 * @param checkpoint {@link Checkpoint} instance to get the store state checkpoint markers from. Only
 *                   {@link CheckpointV2} and newer are supported for blob stores.
 * @param storesToBackupOrRestore set of store names to be backed up or restored
 * @return Map of store name to its blob id of snapshot indices and their corresponding snapshot indices for the task.
 */
public Map<String, Pair<String, SnapshotIndex>> getStoreSnapshotIndexes(String jobName, String jobId, String taskName, Checkpoint checkpoint, Set<String> storesToBackupOrRestore) {
    // TODO MED shesharma document error handling (checkpoint ver, blob not found, getBlob)
    if (checkpoint == null) {
        LOG.debug("No previous checkpoint found for taskName: {}", taskName);
        return ImmutableMap.of();
    }
    if (checkpoint.getVersion() == 1) {
        LOG.warn("Checkpoint version 1 is not supported for blob store backup and restore.");
        return ImmutableMap.of();
    }
    Map<String, CompletableFuture<Pair<String, SnapshotIndex>>> storeSnapshotIndexFutures = new HashMap<>();
    CheckpointV2 checkpointV2 = (CheckpointV2) checkpoint;
    Map<String, Map<String, String>> factoryToStoreSCMs = checkpointV2.getStateCheckpointMarkers();
    Map<String, String> storeSnapshotIndexBlobIds = factoryToStoreSCMs.get(BlobStoreStateBackendFactory.class.getName());
    if (storeSnapshotIndexBlobIds != null) {
        storeSnapshotIndexBlobIds.forEach((storeName, snapshotIndexBlobId) -> {
            if (storesToBackupOrRestore.contains(storeName)) {
                try {
                    LOG.debug("Getting snapshot index for taskName: {} store: {} blobId: {}", taskName, storeName, snapshotIndexBlobId);
                    Metadata requestMetadata = new Metadata(Metadata.SNAPSHOT_INDEX_PAYLOAD_PATH, Optional.empty(), jobName, jobId, taskName, storeName);
                    CompletableFuture<SnapshotIndex> snapshotIndexFuture = getSnapshotIndex(snapshotIndexBlobId, requestMetadata).toCompletableFuture();
                    Pair<CompletableFuture<String>, CompletableFuture<SnapshotIndex>> pairOfFutures = Pair.of(CompletableFuture.completedFuture(snapshotIndexBlobId), snapshotIndexFuture);
                    // save the future and block once in the end instead of blocking for each request.
                    storeSnapshotIndexFutures.put(storeName, FutureUtil.toFutureOfPair(pairOfFutures));
                } catch (Exception e) {
                    throw new SamzaException(String.format("Error getting SnapshotIndex for blobId: %s for taskName: %s store: %s", snapshotIndexBlobId, taskName, storeName), e);
                }
            } else {
                LOG.debug("SnapshotIndex blob id {} for store {} is not present in the set of stores to be backed up/restores: {}", snapshotIndexBlobId, storeName, storesToBackupOrRestore);
            }
        });
    } else {
        LOG.debug("No store SCMs found for blob store state backend in for taskName: {} in checkpoint {}", taskName, checkpointV2.getCheckpointId());
    }
    try {
        return FutureUtil.toFutureOfMap(t -> {
            Throwable unwrappedException = FutureUtil.unwrapExceptions(CompletionException.class, t);
            if (unwrappedException instanceof DeletedException) {
                LOG.warn("Ignoring already deleted snapshot index for taskName: {}", taskName, t);
                return true;
            } else {
                return false;
            }
        }, storeSnapshotIndexFutures).join();
    } catch (Exception e) {
        throw new SamzaException(String.format("Error while waiting to get store snapshot indexes for task %s", taskName), e);
    }
}

Example 14 with CheckpointV2

use of org.apache.samza.checkpoint.CheckpointV2 in project samza by apache.

the class TestBlobStoreUtil method testGetSSIReturnsCorrectSCMSnapshotIndexPair.

@Test
public void testGetSSIReturnsCorrectSCMSnapshotIndexPair() {
    String storeName = "storeName";
    String otherStoreName = "otherStoreName";
    Set<String> storesToBackupOrRestore = ImmutableSet.of(storeName, otherStoreName);
    String storeSnapshotIndexBlobId = "snapshotIndexBlobId";
    String otherStoreSnapshotIndexBlobId = "otherSnapshotIndexBlobId";
    SnapshotIndex mockStoreSnapshotIndex = mock(SnapshotIndex.class);
    SnapshotIndex mockOtherStooreSnapshotIndex = mock(SnapshotIndex.class);
    CheckpointV2 checkpoint = createCheckpointV2(BlobStoreStateBackendFactory.class.getName(), ImmutableMap.of(storeName, storeSnapshotIndexBlobId, otherStoreName, otherStoreSnapshotIndexBlobId));
    BlobStoreUtil mockBlobStoreUtil = mock(BlobStoreUtil.class);
    when(mockBlobStoreUtil.getSnapshotIndex(eq(storeSnapshotIndexBlobId), any(Metadata.class))).thenReturn(CompletableFuture.completedFuture(mockStoreSnapshotIndex));
    when(mockBlobStoreUtil.getSnapshotIndex(eq(otherStoreSnapshotIndexBlobId), any(Metadata.class))).thenReturn(CompletableFuture.completedFuture(mockOtherStooreSnapshotIndex));
    when(mockBlobStoreUtil.getStoreSnapshotIndexes(anyString(), anyString(), anyString(), any(Checkpoint.class), anySetOf(String.class))).thenCallRealMethod();
    Map<String, Pair<String, SnapshotIndex>> snapshotIndexes = mockBlobStoreUtil.getStoreSnapshotIndexes("testJobName", "testJobId", "taskName", checkpoint, storesToBackupOrRestore);
    assertEquals(storeSnapshotIndexBlobId, snapshotIndexes.get(storeName).getKey());
    assertEquals(mockStoreSnapshotIndex, snapshotIndexes.get(storeName).getValue());
    assertEquals(otherStoreSnapshotIndexBlobId, snapshotIndexes.get(otherStoreName).getKey());
    assertEquals(mockOtherStooreSnapshotIndex, snapshotIndexes.get(otherStoreName).getValue());
    verify(mockBlobStoreUtil, times(2)).getSnapshotIndex(anyString(), any(Metadata.class));
}

Example 15 with CheckpointV2

use of org.apache.samza.checkpoint.CheckpointV2 in project samza by apache.

the class TestBlobStoreUtil method testGetSSIReturnsEmptyMapIfNoEntryForBlobStoreBackendFactory.

@Test
public void testGetSSIReturnsEmptyMapIfNoEntryForBlobStoreBackendFactory() {
    CheckpointV2 mockCheckpoint = mock(CheckpointV2.class);
    when(mockCheckpoint.getVersion()).thenReturn((short) 2);
    when(mockCheckpoint.getStateCheckpointMarkers()).thenReturn(ImmutableMap.of("com.OtherStateBackendFactory", ImmutableMap.of("storeName", "otherSCM")));
    BlobStoreUtil blobStoreUtil = new BlobStoreUtil(mock(BlobStoreManager.class), MoreExecutors.newDirectExecutorService(), null, null);
    Map<String, Pair<String, SnapshotIndex>> snapshotIndexes = blobStoreUtil.getStoreSnapshotIndexes("testJobName", "testJobId", "taskName", mockCheckpoint, new HashSet<>());
    assertTrue(snapshotIndexes.isEmpty());
}