use of org.elasticsearch.transport.ReceiveTimeoutTransportException in project nifi by apache.
the class FetchElasticsearch method onTrigger.
@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
FlowFile flowFile = session.get();
if (flowFile == null) {
return;
}
final String index = context.getProperty(INDEX).evaluateAttributeExpressions(flowFile).getValue();
final String docId = context.getProperty(DOC_ID).evaluateAttributeExpressions(flowFile).getValue();
final String docType = context.getProperty(TYPE).evaluateAttributeExpressions(flowFile).getValue();
final Charset charset = Charset.forName(context.getProperty(CHARSET).evaluateAttributeExpressions(flowFile).getValue());
final ComponentLog logger = getLogger();
try {
logger.debug("Fetching {}/{}/{} from Elasticsearch", new Object[] { index, docType, docId });
final long startNanos = System.nanoTime();
GetRequestBuilder getRequestBuilder = esClient.get().prepareGet(index, docType, docId);
if (authToken != null) {
getRequestBuilder.putHeader("Authorization", authToken);
}
final GetResponse getResponse = getRequestBuilder.execute().actionGet();
if (getResponse == null || !getResponse.isExists()) {
logger.debug("Failed to read {}/{}/{} from Elasticsearch: Document not found", new Object[] { index, docType, docId });
// We couldn't find the document, so penalize it and send it to "not found"
flowFile = session.penalize(flowFile);
session.transfer(flowFile, REL_NOT_FOUND);
} else {
flowFile = session.putAttribute(flowFile, "filename", docId);
flowFile = session.putAttribute(flowFile, "es.index", index);
flowFile = session.putAttribute(flowFile, "es.type", docType);
flowFile = session.write(flowFile, new OutputStreamCallback() {
@Override
public void process(OutputStream out) throws IOException {
out.write(getResponse.getSourceAsString().getBytes(charset));
}
});
logger.debug("Elasticsearch document " + docId + " fetched, routing to success");
final long millis = TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - startNanos);
final String uri = context.getProperty(HOSTS).evaluateAttributeExpressions().getValue() + "/" + index + "/" + docType + "/" + docId;
session.getProvenanceReporter().fetch(flowFile, uri, millis);
session.transfer(flowFile, REL_SUCCESS);
}
} catch (NoNodeAvailableException | ElasticsearchTimeoutException | ReceiveTimeoutTransportException | NodeClosedException exceptionToRetry) {
logger.error("Failed to read into Elasticsearch due to {}, this may indicate an error in configuration " + "(hosts, username/password, etc.). Routing to retry", new Object[] { exceptionToRetry.getLocalizedMessage() }, exceptionToRetry);
session.transfer(flowFile, REL_RETRY);
context.yield();
} catch (Exception e) {
logger.error("Failed to read {} from Elasticsearch due to {}", new Object[] { flowFile, e.getLocalizedMessage() }, e);
session.transfer(flowFile, REL_FAILURE);
context.yield();
}
}
use of org.elasticsearch.transport.ReceiveTimeoutTransportException in project nifi by apache.
the class PutElasticsearch method onTrigger.
@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
final ComponentLog logger = getLogger();
final String id_attribute = context.getProperty(ID_ATTRIBUTE).getValue();
final int batchSize = context.getProperty(BATCH_SIZE).evaluateAttributeExpressions().asInteger();
final List<FlowFile> flowFiles = session.get(batchSize);
if (flowFiles.isEmpty()) {
return;
}
// Keep track of the list of flow files that need to be transferred. As they are transferred, remove them from the list.
List<FlowFile> flowFilesToTransfer = new LinkedList<>(flowFiles);
try {
final BulkRequestBuilder bulk = esClient.get().prepareBulk();
if (authToken != null) {
bulk.putHeader("Authorization", authToken);
}
for (FlowFile file : flowFiles) {
final String index = context.getProperty(INDEX).evaluateAttributeExpressions(file).getValue();
final String docType = context.getProperty(TYPE).evaluateAttributeExpressions(file).getValue();
final String indexOp = context.getProperty(INDEX_OP).evaluateAttributeExpressions(file).getValue();
final Charset charset = Charset.forName(context.getProperty(CHARSET).evaluateAttributeExpressions(file).getValue());
final String id = file.getAttribute(id_attribute);
if (id == null) {
logger.error("No value in identifier attribute {} for {}, transferring to failure", new Object[] { id_attribute, file });
flowFilesToTransfer.remove(file);
session.transfer(file, REL_FAILURE);
} else {
session.read(file, new InputStreamCallback() {
@Override
public void process(final InputStream in) throws IOException {
String json = IOUtils.toString(in, charset).replace("\r\n", " ").replace('\n', ' ').replace('\r', ' ');
if (indexOp.equalsIgnoreCase("index")) {
bulk.add(esClient.get().prepareIndex(index, docType, id).setSource(json.getBytes(charset)));
} else if (indexOp.equalsIgnoreCase("upsert")) {
bulk.add(esClient.get().prepareUpdate(index, docType, id).setDoc(json.getBytes(charset)).setDocAsUpsert(true));
} else if (indexOp.equalsIgnoreCase("update")) {
bulk.add(esClient.get().prepareUpdate(index, docType, id).setDoc(json.getBytes(charset)));
} else {
throw new IOException("Index operation: " + indexOp + " not supported.");
}
}
});
}
}
final BulkResponse response = bulk.execute().actionGet();
if (response.hasFailures()) {
// Responses are guaranteed to be in order, remove them in reverse order
BulkItemResponse[] responses = response.getItems();
if (responses != null && responses.length > 0) {
for (int i = responses.length - 1; i >= 0; i--) {
final FlowFile flowFile = flowFilesToTransfer.get(i);
if (responses[i].isFailed()) {
logger.error("Failed to insert {} into Elasticsearch due to {}, transferring to failure", new Object[] { flowFile, responses[i].getFailure().getMessage() });
session.transfer(flowFile, REL_FAILURE);
} else {
session.getProvenanceReporter().send(flowFile, context.getProperty(HOSTS).evaluateAttributeExpressions().getValue() + "/" + responses[i].getIndex());
session.transfer(flowFile, REL_SUCCESS);
}
flowFilesToTransfer.remove(flowFile);
}
}
}
// Transfer any remaining flowfiles to success
flowFilesToTransfer.forEach(file -> {
session.transfer(file, REL_SUCCESS);
// Record provenance event
session.getProvenanceReporter().send(file, context.getProperty(HOSTS).evaluateAttributeExpressions().getValue() + "/" + context.getProperty(INDEX).evaluateAttributeExpressions(file).getValue());
});
} catch (NoNodeAvailableException | ElasticsearchTimeoutException | ReceiveTimeoutTransportException | NodeClosedException exceptionToRetry) {
// Authorization errors and other problems are often returned as NoNodeAvailableExceptions without a
// traceable cause. However the cause seems to be logged, just not available to this caught exception.
// Since the error message will show up as a bulletin, we make specific mention to check the logs for
// more details.
logger.error("Failed to insert into Elasticsearch due to {}. More detailed information may be available in " + "the NiFi logs.", new Object[] { exceptionToRetry.getLocalizedMessage() }, exceptionToRetry);
session.transfer(flowFilesToTransfer, REL_RETRY);
context.yield();
} catch (Exception exceptionToFail) {
logger.error("Failed to insert into Elasticsearch due to {}, transferring to failure", new Object[] { exceptionToFail.getLocalizedMessage() }, exceptionToFail);
session.transfer(flowFilesToTransfer, REL_FAILURE);
context.yield();
}
}
use of org.elasticsearch.transport.ReceiveTimeoutTransportException in project elasticsearch by elastic.
the class AsyncShardFetch method processAsyncFetch.
/**
* Called by the response handler of the async action to fetch data. Verifies that its still working
* on the same cache generation, otherwise the results are discarded. It then goes and fills the relevant data for
* the shard (response + failures), issuing a reroute at the end of it to make sure there will be another round
* of allocations taking this new data into account.
*/
protected synchronized void processAsyncFetch(ShardId shardId, List<T> responses, List<FailedNodeException> failures) {
if (closed) {
// we are closed, no need to process this async fetch at all
logger.trace("{} ignoring fetched [{}] results, already closed", shardId, type);
return;
}
logger.trace("{} processing fetched [{}] results", shardId, type);
if (responses != null) {
for (T response : responses) {
NodeEntry<T> nodeEntry = cache.get(response.getNode().getId());
// if the entry is there, and not marked as failed already, process it
if (nodeEntry == null) {
continue;
}
if (nodeEntry.isFailed()) {
logger.trace("{} node {} has failed for [{}] (failure [{}])", shardId, nodeEntry.getNodeId(), type, nodeEntry.getFailure());
} else {
logger.trace("{} marking {} as done for [{}], result is [{}]", shardId, nodeEntry.getNodeId(), type, response);
nodeEntry.doneFetching(response);
}
}
}
if (failures != null) {
for (FailedNodeException failure : failures) {
logger.trace("{} processing failure {} for [{}]", shardId, failure, type);
NodeEntry<T> nodeEntry = cache.get(failure.nodeId());
// if the entry is there, and not marked as failed already, process it
if (nodeEntry != null && nodeEntry.isFailed() == false) {
Throwable unwrappedCause = ExceptionsHelper.unwrapCause(failure.getCause());
// if the request got rejected or timed out, we need to try it again next time...
if (unwrappedCause instanceof EsRejectedExecutionException || unwrappedCause instanceof ReceiveTimeoutTransportException || unwrappedCause instanceof ElasticsearchTimeoutException) {
nodeEntry.restartFetching();
} else {
logger.warn((Supplier<?>) () -> new ParameterizedMessage("{}: failed to list shard for {} on node [{}]", shardId, type, failure.nodeId()), failure);
nodeEntry.doneFetching(failure.getCause());
}
}
}
}
reroute(shardId, "post_response");
}
use of org.elasticsearch.transport.ReceiveTimeoutTransportException in project nifi by apache.
the class DeleteElasticsearch5 method onTrigger.
@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
synchronized (esClient) {
if (esClient.get() == null) {
setup(context);
}
}
FlowFile flowFile = session.get();
if (flowFile == null) {
return;
}
final String index = context.getProperty(INDEX).evaluateAttributeExpressions(flowFile).getValue();
final String documentId = context.getProperty(DOCUMENT_ID).evaluateAttributeExpressions(flowFile).getValue();
final String documentType = context.getProperty(TYPE).evaluateAttributeExpressions(flowFile).getValue();
final ComponentLog logger = getLogger();
if (StringUtils.isBlank(index)) {
logger.debug("Index is required but was empty {}", new Object[] { index });
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, "Index is required but was empty");
session.transfer(flowFile, REL_FAILURE);
return;
}
if (StringUtils.isBlank(documentType)) {
logger.debug("Document type is required but was empty {}", new Object[] { documentType });
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, "Document type is required but was empty");
session.transfer(flowFile, REL_FAILURE);
return;
}
if (StringUtils.isBlank(documentId)) {
logger.debug("Document id is required but was empty {}", new Object[] { documentId });
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, "Document id is required but was empty");
session.transfer(flowFile, REL_FAILURE);
return;
}
flowFile = session.putAllAttributes(flowFile, new HashMap<String, String>() {
{
put(ES_FILENAME, documentId);
put(ES_INDEX, index);
put(ES_TYPE, documentType);
}
});
try {
logger.debug("Deleting document {}/{}/{} from Elasticsearch", new Object[] { index, documentType, documentId });
DeleteRequestBuilder requestBuilder = prepareDeleteRequest(index, documentId, documentType);
final DeleteResponse response = doDelete(requestBuilder);
if (response.status() != RestStatus.OK) {
logger.warn("Failed to delete document {}/{}/{} from Elasticsearch: Status {}", new Object[] { index, documentType, documentId, response.status() });
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, UNABLE_TO_DELETE_DOCUMENT_MESSAGE);
flowFile = session.putAttribute(flowFile, ES_REST_STATUS, response.status().toString());
context.yield();
if (response.status() == RestStatus.NOT_FOUND) {
session.transfer(flowFile, REL_NOT_FOUND);
} else {
session.transfer(flowFile, REL_FAILURE);
}
} else {
logger.debug("Elasticsearch document " + documentId + " deleted");
session.transfer(flowFile, REL_SUCCESS);
}
} catch (ElasticsearchTimeoutException | ReceiveTimeoutTransportException exception) {
logger.error("Failed to delete document {} from Elasticsearch due to {}", new Object[] { documentId, exception.getLocalizedMessage() }, exception);
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, exception.getLocalizedMessage());
session.transfer(flowFile, REL_RETRY);
context.yield();
} catch (Exception e) {
logger.error("Failed to delete document {} from Elasticsearch due to {}", new Object[] { documentId, e.getLocalizedMessage() }, e);
flowFile = session.putAttribute(flowFile, ES_ERROR_MESSAGE, e.getLocalizedMessage());
session.transfer(flowFile, REL_FAILURE);
context.yield();
}
}
use of org.elasticsearch.transport.ReceiveTimeoutTransportException in project nifi by apache.
the class TestPutElasticsearch5 method testPutElasticsearch5OnTriggerWithExceptions.
@Test
public void testPutElasticsearch5OnTriggerWithExceptions() throws IOException {
PutElasticsearch5TestProcessor processor = new PutElasticsearch5TestProcessor(false);
runner = TestRunners.newTestRunner(processor);
runner.setProperty(AbstractElasticsearch5TransportClientProcessor.CLUSTER_NAME, "elasticsearch");
runner.setProperty(AbstractElasticsearch5TransportClientProcessor.HOSTS, "127.0.0.1:9300");
runner.setProperty(AbstractElasticsearch5TransportClientProcessor.PING_TIMEOUT, "5s");
runner.setProperty(AbstractElasticsearch5TransportClientProcessor.SAMPLER_INTERVAL, "5s");
runner.setProperty(PutElasticsearch5.INDEX, "doc");
runner.setProperty(PutElasticsearch5.TYPE, "status");
runner.setValidateExpressionUsage(true);
runner.setProperty(PutElasticsearch5.ID_ATTRIBUTE, "doc_id");
// No Node Available exception
processor.setExceptionToThrow(new NoNodeAvailableException("test"));
runner.enqueue(docExample, new HashMap<String, String>() {
{
put("doc_id", "28039652140");
}
});
runner.run(1, true, true);
runner.assertAllFlowFilesTransferred(FetchElasticsearch5.REL_RETRY, 1);
runner.clearTransferState();
// Elasticsearch5 Timeout exception
processor.setExceptionToThrow(new ElasticsearchTimeoutException("test"));
runner.enqueue(docExample, new HashMap<String, String>() {
{
put("doc_id", "28039652141");
}
});
runner.run(1, true, true);
runner.assertAllFlowFilesTransferred(FetchElasticsearch5.REL_RETRY, 1);
runner.clearTransferState();
// Receive Timeout Transport exception
processor.setExceptionToThrow(new ReceiveTimeoutTransportException(mock(StreamInput.class)));
runner.enqueue(docExample, new HashMap<String, String>() {
{
put("doc_id", "28039652142");
}
});
runner.run(1, true, true);
runner.assertAllFlowFilesTransferred(FetchElasticsearch5.REL_RETRY, 1);
runner.clearTransferState();
// Node Closed exception
processor.setExceptionToThrow(new NodeClosedException(mock(StreamInput.class)));
runner.enqueue(docExample, new HashMap<String, String>() {
{
put("doc_id", "28039652143");
}
});
runner.run(1, true, true);
runner.assertAllFlowFilesTransferred(FetchElasticsearch5.REL_RETRY, 1);
runner.clearTransferState();
// Elasticsearch5 Parse exception
processor.setExceptionToThrow(new ElasticsearchParseException("test"));
runner.enqueue(docExample, new HashMap<String, String>() {
{
put("doc_id", "28039652144");
}
});
runner.run(1, true, true);
// This test generates an exception on execute(),routes to failure
runner.assertTransferCount(PutElasticsearch5.REL_FAILURE, 1);
}
Aggregations