use of org.apache.hadoop.hbase.exceptions.ScannerResetException in project hbase by apache.
the class TestFromClientSide method testScannerFailsAfterRetriesWhenCoprocessorThrowsIOE.
/**
* Tests the case where a coprocessor throws a regular IOException in the scan. The expectation
* is that the we will keep on retrying, but fail after the retries are exhausted instead of
* retrying indefinitely.
*/
@Test(timeout = 180000)
public void testScannerFailsAfterRetriesWhenCoprocessorThrowsIOE() throws IOException, InterruptedException {
TEST_UTIL.getConfiguration().setBoolean("hbase.client.log.scanner.activity", true);
final TableName tableName = TableName.valueOf(name.getMethodName());
TEST_UTIL.getConfiguration().setInt(HConstants.HBASE_CLIENT_RETRIES_NUMBER, 3);
HTableDescriptor htd = TEST_UTIL.createTableDescriptor(tableName, FAMILY);
htd.addCoprocessor(ExceptionInReseekRegionObserver.class.getName());
TEST_UTIL.getAdmin().createTable(htd);
ExceptionInReseekRegionObserver.reset();
// throw exceptions in every retry
ExceptionInReseekRegionObserver.throwOnce.set(false);
try (Table t = TEST_UTIL.getConnection().getTable(tableName)) {
TEST_UTIL.loadTable(t, FAMILY, false);
TEST_UTIL.getAdmin().flush(tableName);
TEST_UTIL.countRows(t, new Scan().addColumn(FAMILY, FAMILY));
fail("Should have thrown an exception");
} catch (DoNotRetryIOException expected) {
assertTrue(expected instanceof ScannerResetException);
// expected
}
assertTrue(ExceptionInReseekRegionObserver.reqCount.get() >= 3);
}
use of org.apache.hadoop.hbase.exceptions.ScannerResetException in project hbase by apache.
the class RSRpcServices method scan.
/**
* Scan data in a table.
*
* @param controller the RPC controller
* @param request the scan request
* @throws ServiceException
*/
@Override
public ScanResponse scan(final RpcController controller, final ScanRequest request) throws ServiceException {
if (controller != null && !(controller instanceof HBaseRpcController)) {
throw new UnsupportedOperationException("We only do " + "HBaseRpcControllers! FIX IF A PROBLEM: " + controller);
}
if (!request.hasScannerId() && !request.hasScan()) {
throw new ServiceException(new DoNotRetryIOException("Missing required input: scannerId or scan"));
}
try {
checkOpen();
} catch (IOException e) {
if (request.hasScannerId()) {
String scannerName = toScannerName(request.getScannerId());
if (LOG.isDebugEnabled()) {
LOG.debug("Server shutting down and client tried to access missing scanner " + scannerName);
}
final LeaseManager leaseManager = server.getLeaseManager();
if (leaseManager != null) {
try {
leaseManager.cancelLease(scannerName);
} catch (LeaseException le) {
// No problem, ignore
if (LOG.isTraceEnabled()) {
LOG.trace("Un-able to cancel lease of scanner. It could already be closed.");
}
}
}
}
throw new ServiceException(e);
}
requestCount.increment();
rpcScanRequestCount.increment();
RegionScannerHolder rsh;
ScanResponse.Builder builder = ScanResponse.newBuilder();
String scannerName;
try {
if (request.hasScannerId()) {
// The downstream projects such as AsyncHBase in OpenTSDB need this value. See HBASE-18000
// for more details.
long scannerId = request.getScannerId();
builder.setScannerId(scannerId);
scannerName = toScannerName(scannerId);
rsh = getRegionScanner(request);
} else {
Pair<String, RegionScannerHolder> scannerNameAndRSH = newRegionScanner(request, builder);
scannerName = scannerNameAndRSH.getFirst();
rsh = scannerNameAndRSH.getSecond();
}
} catch (IOException e) {
if (e == SCANNER_ALREADY_CLOSED) {
// the old client will still send a close request to us. Just ignore it and return.
return builder.build();
}
throw new ServiceException(e);
}
if (rsh.fullRegionScan) {
rpcFullScanRequestCount.increment();
}
HRegion region = rsh.r;
LeaseManager.Lease lease;
try {
// Remove lease while its being processed in server; protects against case
// where processing of request takes > lease expiration time. or null if none found.
lease = server.getLeaseManager().removeLease(scannerName);
} catch (LeaseException e) {
throw new ServiceException(e);
}
if (request.hasRenew() && request.getRenew()) {
// add back and return
addScannerLeaseBack(lease);
try {
checkScanNextCallSeq(request, rsh);
} catch (OutOfOrderScannerNextException e) {
throw new ServiceException(e);
}
return builder.build();
}
OperationQuota quota;
try {
quota = getRpcQuotaManager().checkQuota(region, OperationQuota.OperationType.SCAN);
} catch (IOException e) {
addScannerLeaseBack(lease);
throw new ServiceException(e);
}
try {
checkScanNextCallSeq(request, rsh);
} catch (OutOfOrderScannerNextException e) {
addScannerLeaseBack(lease);
throw new ServiceException(e);
}
// Now we have increased the next call sequence. If we give client an error, the retry will
// never success. So we'd better close the scanner and return a DoNotRetryIOException to client
// and then client will try to open a new scanner.
boolean closeScanner = request.hasCloseScanner() ? request.getCloseScanner() : false;
// this is scan.getCaching
int rows;
if (request.hasNumberOfRows()) {
rows = request.getNumberOfRows();
} else {
rows = closeScanner ? 0 : 1;
}
RpcCallContext context = RpcServer.getCurrentCall().orElse(null);
// now let's do the real scan.
long maxQuotaResultSize = Math.min(maxScannerResultSize, quota.getReadAvailable());
RegionScanner scanner = rsh.s;
// this is the limit of rows for this scan, if we the number of rows reach this value, we will
// close the scanner.
int limitOfRows;
if (request.hasLimitOfRows()) {
limitOfRows = request.getLimitOfRows();
} else {
limitOfRows = -1;
}
MutableObject<Object> lastBlock = new MutableObject<>();
boolean scannerClosed = false;
try {
List<Result> results = new ArrayList<>(Math.min(rows, 512));
if (rows > 0) {
boolean done = false;
// Call coprocessor. Get region info from scanner.
if (region.getCoprocessorHost() != null) {
Boolean bypass = region.getCoprocessorHost().preScannerNext(scanner, results, rows);
if (!results.isEmpty()) {
for (Result r : results) {
lastBlock.setValue(addSize(context, r, lastBlock.getValue()));
}
}
if (bypass != null && bypass.booleanValue()) {
done = true;
}
}
if (!done) {
scan((HBaseRpcController) controller, request, rsh, maxQuotaResultSize, rows, limitOfRows, results, builder, lastBlock, context);
} else {
builder.setMoreResultsInRegion(!results.isEmpty());
}
} else {
// This is a open scanner call with numberOfRow = 0, so set more results in region to true.
builder.setMoreResultsInRegion(true);
}
quota.addScanResult(results);
addResults(builder, results, (HBaseRpcController) controller, RegionReplicaUtil.isDefaultReplica(region.getRegionInfo()), isClientCellBlockSupport(context));
if (scanner.isFilterDone() && results.isEmpty()) {
// If the scanner's filter - if any - is done with the scan
// only set moreResults to false if the results is empty. This is used to keep compatible
// with the old scan implementation where we just ignore the returned results if moreResults
// is false. Can remove the isEmpty check after we get rid of the old implementation.
builder.setMoreResults(false);
}
// have already set this flag.
assert builder.hasMoreResultsInRegion();
// yet.
if (!builder.hasMoreResults()) {
builder.setMoreResults(true);
}
if (builder.getMoreResults() && builder.getMoreResultsInRegion() && !results.isEmpty()) {
// Record the last cell of the last result if it is a partial result
// We need this to calculate the complete rows we have returned to client as the
// mayHaveMoreCellsInRow is true does not mean that there will be extra cells for the
// current row. We may filter out all the remaining cells for the current row and just
// return the cells of the nextRow when calling RegionScanner.nextRaw. So here we need to
// check for row change.
Result lastResult = results.get(results.size() - 1);
if (lastResult.mayHaveMoreCellsInRow()) {
rsh.rowOfLastPartialResult = lastResult.getRow();
} else {
rsh.rowOfLastPartialResult = null;
}
}
if (!builder.getMoreResults() || !builder.getMoreResultsInRegion() || closeScanner) {
scannerClosed = true;
closeScanner(region, scanner, scannerName, context);
}
return builder.build();
} catch (IOException e) {
try {
// scanner is closed here
scannerClosed = true;
// The scanner state might be left in a dirty state, so we will tell the Client to
// fail this RPC and close the scanner while opening up another one from the start of
// row that the client has last seen.
closeScanner(region, scanner, scannerName, context);
// the client. See ClientScanner code to see how it deals with these special exceptions.
if (e instanceof DoNotRetryIOException) {
throw e;
}
// DoNotRetryIOException. This can avoid the retry in ClientScanner.
if (e instanceof FileNotFoundException) {
throw new DoNotRetryIOException(e);
}
// a special exception to save an RPC.
if (VersionInfoUtil.hasMinimumVersion(context.getClientVersionInfo(), 1, 4)) {
// 1.4.0+ clients know how to handle
throw new ScannerResetException("Scanner is closed on the server-side", e);
} else {
// older clients do not know about SRE. Just throw USE, which they will handle
throw new UnknownScannerException("Throwing UnknownScannerException to reset the client" + " scanner state for clients older than 1.3.", e);
}
} catch (IOException ioe) {
throw new ServiceException(ioe);
}
} finally {
if (!scannerClosed) {
// the closeCallBack will be set in closeScanner so here we only care about shippedCallback
if (context != null) {
context.setCallBack(rsh.shippedCallback);
} else {
// When context != null, adding back the lease will be done in callback set above.
addScannerLeaseBack(lease);
}
}
quota.close();
}
}
use of org.apache.hadoop.hbase.exceptions.ScannerResetException in project hbase by apache.
the class AsyncRpcRetryingCaller method onError.
protected final void onError(Throwable t, Supplier<String> errMsg, Consumer<Throwable> updateCachedLocation) {
if (future.isDone()) {
// Give up if the future is already done, this is possible if user has already canceled the
// future. And for timeline consistent read, we will also cancel some requests if we have
// already get one of the responses.
LOG.debug("The future is already done, canceled={}, give up retrying", future.isCancelled());
return;
}
Throwable error = preProcessError(translateException(t));
// exactly trying to open a new scanner, so we should retry on ScannerResetException.
if (error instanceof DoNotRetryIOException && !(error instanceof ScannerResetException)) {
future.completeExceptionally(error);
return;
}
if (tries > startLogErrorsCnt) {
LOG.warn(errMsg.get() + ", tries = " + tries + ", maxAttempts = " + maxAttempts + ", timeout = " + TimeUnit.NANOSECONDS.toMillis(operationTimeoutNs) + " ms, time elapsed = " + elapsedMs() + " ms", error);
}
updateCachedLocation.accept(error);
RetriesExhaustedException.ThrowableWithExtraContext qt = new RetriesExhaustedException.ThrowableWithExtraContext(error, EnvironmentEdgeManager.currentTime(), "");
exceptions.add(qt);
if (tries >= maxAttempts) {
completeExceptionally();
return;
}
// meta, so here we only check for disabled for some specific exception types.
if (error instanceof NotServingRegionException || error instanceof RegionOfflineException) {
Optional<TableName> tableName = getTableName();
if (tableName.isPresent()) {
FutureUtils.addListener(conn.getAdmin().isTableDisabled(tableName.get()), (disabled, e) -> {
if (e != null) {
if (e instanceof TableNotFoundException) {
future.completeExceptionally(e);
} else {
// failed to test whether the table is disabled, not a big deal, continue retrying
tryScheduleRetry(error);
}
return;
}
if (disabled) {
future.completeExceptionally(new TableNotEnabledException(tableName.get()));
} else {
tryScheduleRetry(error);
}
});
} else {
tryScheduleRetry(error);
}
} else {
tryScheduleRetry(error);
}
}
use of org.apache.hadoop.hbase.exceptions.ScannerResetException in project hbase by apache.
the class TestFromClientSideScanExcpetion method testScannerFailsAfterRetriesWhenCoprocessorThrowsIOE.
/**
* Tests the case where a coprocessor throws a regular IOException in the scan. The expectation is
* that the we will keep on retrying, but fail after the retries are exhausted instead of retrying
* indefinitely.
*/
@Test
public void testScannerFailsAfterRetriesWhenCoprocessorThrowsIOE() throws IOException, InterruptedException {
TableName tableName = TableName.valueOf(name.getMethodName());
reset();
// throw exceptions in every retry
THROW_ONCE.set(false);
try (Table t = TEST_UTIL.createTable(tableName, FAMILY)) {
TEST_UTIL.loadTable(t, FAMILY, false);
TEST_UTIL.getAdmin().flush(tableName);
inject();
TEST_UTIL.countRows(t, new Scan().addColumn(FAMILY, FAMILY));
fail("Should have thrown an exception");
} catch (ScannerResetException expected) {
// expected
} catch (RetriesExhaustedException e) {
// expected
assertThat(e.getCause(), instanceOf(ScannerResetException.class));
}
assertTrue(REQ_COUNT.get() >= 3);
}
use of org.apache.hadoop.hbase.exceptions.ScannerResetException in project hbase by apache.
the class ScannerCallable method next.
private ScanResponse next() throws IOException {
// Reset the heartbeat flag prior to each RPC in case an exception is thrown by the server
setHeartbeatMessage(false);
incRPCcallsMetrics();
ScanRequest request = RequestConverter.buildScanRequest(scannerId, caching, false, nextCallSeq, this.scanMetrics != null, renew, scan.getLimit());
try {
ScanResponse response = getStub().scan(getRpcController(), request);
nextCallSeq++;
return response;
} catch (Exception e) {
IOException ioe = ProtobufUtil.handleRemoteException(e);
if (logScannerActivity) {
LOG.info("Got exception making request " + ProtobufUtil.toText(request) + " to " + getLocation(), e);
}
if (logScannerActivity) {
if (ioe instanceof UnknownScannerException) {
try {
HRegionLocation location = getConnection().relocateRegion(getTableName(), scan.getStartRow());
LOG.info("Scanner=" + scannerId + " expired, current region location is " + location.toString());
} catch (Throwable t) {
LOG.info("Failed to relocate region", t);
}
} else if (ioe instanceof ScannerResetException) {
LOG.info("Scanner=" + scannerId + " has received an exception, and the server " + "asked us to reset the scanner state.", ioe);
}
}
// yeah and hard to follow and in need of a refactor).
if (ioe instanceof NotServingRegionException) {
// Attach NSRE to signal client that it needs to re-setup scanner.
if (this.scanMetrics != null) {
this.scanMetrics.countOfNSRE.incrementAndGet();
}
throw new DoNotRetryIOException("Resetting the scanner -- see exception cause", ioe);
} else if (ioe instanceof RegionServerStoppedException) {
// open scanner against new location.
throw new DoNotRetryIOException("Resetting the scanner -- see exception cause", ioe);
} else {
// The outer layers will retry
throw ioe;
}
}
}
Aggregations