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

Example 21 with CheckpointId

use of org.apache.samza.checkpoint.CheckpointId 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 22 with CheckpointId

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

the class TestCheckpointId method testSerializationDeserialization.

@Test
public void testSerializationDeserialization() {
    CheckpointId checkpointId = CheckpointId.create();
    CheckpointId deserializedCheckpointId = CheckpointId.deserialize(checkpointId.serialize());
    assertEquals(checkpointId.getMillis(), deserializedCheckpointId.getMillis());
    assertEquals(checkpointId.getNanoId(), deserializedCheckpointId.getNanoId());
    assertEquals(checkpointId, deserializedCheckpointId);
}

Example 23 with CheckpointId

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

the class TestCheckpointId method testSerializationFormatForBackwardsCompatibility.

@Test
public void testSerializationFormatForBackwardsCompatibility() {
    CheckpointId checkpointId = CheckpointId.create();
    String serializedCheckpointId = checkpointId.serialize();
    // WARNING: This format is written to persisted remotes stores and local files, making a change in the format
    // would be backwards incompatible
    String legacySerializedFormat = serializeLegacy(checkpointId);
    assertEquals(checkpointId, CheckpointId.deserialize(legacySerializedFormat));
}

Example 24 with CheckpointId

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

the class KafkaChangelogSSPOffset method fromString.

public static KafkaChangelogSSPOffset fromString(String message) {
    if (StringUtils.isBlank(message)) {
        throw new IllegalArgumentException("Invalid checkpointed changelog message: " + message);
    }
    String[] checkpointIdAndOffset = message.split(SEPARATOR);
    if (checkpointIdAndOffset.length != 2) {
        throw new IllegalArgumentException("Invalid checkpointed changelog offset: " + message);
    }
    CheckpointId checkpointId = CheckpointId.deserialize(checkpointIdAndOffset[0]);
    String offset = null;
    if (!"null".equals(checkpointIdAndOffset[1])) {
        offset = checkpointIdAndOffset[1];
    }
    return new KafkaChangelogSSPOffset(checkpointId, offset);
}

Example 25 with CheckpointId

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

the class TestBlobStoreUtil method testPutDir.

@Test
public // TODO HIGH shesharm test with empty (0 byte) files
void testPutDir() throws IOException, InterruptedException, ExecutionException {
    BlobStoreManager blobStoreManager = mock(BlobStoreManager.class);
    // File, dir and recursive dir added, retained and removed in local
    String local = "[a, c, z/1, y/1, p/m/1, q/n/1]";
    String remote = "[a, b, z/1, x/1, p/m/1, p/m/2, r/o/1]";
    String expectedAdded = "[c, y/1, q/n/1]";
    String expectedRetained = "[a, z/1, p/m/1]";
    String expectedRemoved = "[b, x/1, r/o/1, p/m/2]";
    SortedSet<String> expectedAddedFiles = BlobStoreTestUtil.getExpected(expectedAdded);
    SortedSet<String> expectedRetainedFiles = BlobStoreTestUtil.getExpected(expectedRetained);
    SortedSet<String> expectedPresentFiles = new TreeSet<>(expectedAddedFiles);
    expectedPresentFiles.addAll(expectedRetainedFiles);
    SortedSet<String> expectedRemovedFiles = BlobStoreTestUtil.getExpected(expectedRemoved);
    // Set up environment
    Path localSnapshotDir = BlobStoreTestUtil.createLocalDir(local);
    String basePath = localSnapshotDir.toAbsolutePath().toString();
    DirIndex remoteSnapshotDir = BlobStoreTestUtil.createDirIndex(remote);
    SnapshotMetadata snapshotMetadata = new SnapshotMetadata(checkpointId, jobName, jobId, taskName, storeName);
    DirDiff dirDiff = DirDiffUtil.getDirDiff(localSnapshotDir.toFile(), remoteSnapshotDir, (localFile, remoteFile) -> localFile.getName().equals(remoteFile.getFileName()));
    SortedSet<String> allUploaded = new TreeSet<>();
    // Set up mocks
    when(blobStoreManager.put(any(InputStream.class), any(Metadata.class))).thenAnswer((Answer<CompletableFuture<String>>) invocation -> {
        Metadata metadata = invocation.getArgumentAt(1, Metadata.class);
        String path = metadata.getPayloadPath();
        allUploaded.add(path.substring(localSnapshotDir.toAbsolutePath().toString().length() + 1));
        return CompletableFuture.completedFuture(path);
    });
    // Execute
    BlobStoreUtil blobStoreUtil = new BlobStoreUtil(blobStoreManager, EXECUTOR, null, null);
    CompletionStage<DirIndex> dirIndexFuture = blobStoreUtil.putDir(dirDiff, snapshotMetadata);
    DirIndex dirIndex = null;
    try {
        // should be already complete. if not, future composition in putDir is broken.
        dirIndex = dirIndexFuture.toCompletableFuture().get(0, TimeUnit.MILLISECONDS);
    } catch (TimeoutException e) {
        fail("Future returned from putDir should be already complete.");
    }
    SortedSet<String> allPresent = new TreeSet<>();
    SortedSet<String> allRemoved = new TreeSet<>();
    BlobStoreTestUtil.getAllPresentInIndex("", dirIndex, allPresent);
    BlobStoreTestUtil.getAllRemovedInIndex("", dirIndex, allRemoved);
    // Assert
    assertEquals(expectedAddedFiles, allUploaded);
    assertEquals(expectedPresentFiles, allPresent);
    assertEquals(expectedRemovedFiles, allRemoved);
}