Skip to content

HDFS-17892 RBF: permit not released during invokeConcurrent if getOrderedNamenodes throws an exception #8345

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dParikesit wants to merge 3 commits into
base: trunk
Choose a base branch
from
+43 −36
Open

HDFS-17892 RBF: permit not released during invokeConcurrent if getOrderedNamenodes throws an exception #8345

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
56279d6
add test
dParikesit Mar 14, 2026
8d5f919
fix invokeConcurrent
dParikesit Mar 14, 2026
912178b
move getRemoteResults outside the try-finally block
dParikesit Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 39 additions & 33 deletions ...fs-rbf/src/main/java/org/apache/hadoop/hdfs/server/federation/router/RouterRpcClient.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1599,48 +1599,54 @@ protected static <T extends RemoteLocationContext, R> Map<T, R> postProcessResul
// transfer originCall & callerContext to worker threads of executor.
final Call originCall = Server.getCurCall().get();
final CallerContext originContext = CallerContext.getCurrent();
for (final T location : locations) {
String nsId = location.getNameserviceId();
boolean isObserverRead = isObserverReadEligible(nsId, m);
final List<? extends FederationNamenodeContext> namenodes =
getOrderedNamenodes(nsId, isObserverRead);
final Class<?> proto = method.getProtocol();
final Object[] paramList = method.getParams(location);
if (standby) {
// Call the objectGetter to all NNs (including standby)
for (final FederationNamenodeContext nn : namenodes) {
String nnId = nn.getNamenodeId();
final List<FederationNamenodeContext> nnList =
Collections.singletonList(nn);
T nnLocation = location;
if (location instanceof RemoteLocation) {
nnLocation = (T)new RemoteLocation(nsId, nnId, location.getDest());
try{
for (final T location : locations) {
String nsId = location.getNameserviceId();
boolean isObserverRead = isObserverReadEligible(nsId, m);
final List<? extends FederationNamenodeContext> namenodes =
getOrderedNamenodes(nsId, isObserverRead);
final Class<?> proto = method.getProtocol();
final Object[] paramList = method.getParams(location);
if (standby) {
// Call the objectGetter to all NNs (including standby)
for (final FederationNamenodeContext nn : namenodes) {
String nnId = nn.getNamenodeId();
final List<FederationNamenodeContext> nnList =
Collections.singletonList(nn);
T nnLocation = location;
if (location instanceof RemoteLocation) {
nnLocation = (T)new RemoteLocation(nsId, nnId, location.getDest());
}
orderedLocations.add(nnLocation);
callables.add(
() -> {
transferThreadLocalContext(originCall, originContext);
return invokeMethod(
ugi, nnList, isObserverRead, proto, m, paramList);
});
}
orderedLocations.add(nnLocation);
} else {
// Call the objectGetter in order of nameservices in the NS list
orderedLocations.add(location);
callables.add(
() -> {
transferThreadLocalContext(originCall, originContext);
return invokeMethod(
ugi, nnList, isObserverRead, proto, m, paramList);
ugi, namenodes, isObserverRead, proto, m, paramList);
});
}
} else {
// Call the objectGetter in order of nameservices in the NS list
orderedLocations.add(location);
callables.add(
() -> {
transferThreadLocalContext(originCall, originContext);
return invokeMethod(
ugi, namenodes, isObserverRead, proto, m, paramList);
});
}
}

if (rpcMonitor != null) {
rpcMonitor.proxyOp();
}
if (this.router.getRouterClientMetrics() != null) {
this.router.getRouterClientMetrics().incInvokedConcurrent(m);
if (rpcMonitor != null) {
rpcMonitor.proxyOp();
}
if (this.router.getRouterClientMetrics() != null) {
this.router.getRouterClientMetrics().incInvokedConcurrent(m);
}

} catch (IOException e) {
releasePermit(CONCURRENT_NS, ugi, method, controller);
throw e;
}

return getRemoteResults(method, timeOutMs, controller, orderedLocations, callables);
Expand Down
7 changes: 4 additions & 3 deletions ...st/java/org/apache/hadoop/hdfs/server/federation/fairness/TestRouterHandlersFairness.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,19 +215,20 @@ public void testReleasedWhenExceptionOccurs(
// Use renewLease test invokeConcurrent.
Collection<RemoteLocation> locations = new ArrayList<>();
locations.add(new RemoteLocation("ns0", "/", "/"));
locations.add(new RemoteLocation("ns1", "/", "/"));
RemoteMethod renewLease = new RemoteMethod(
"renewLease",
new Class[]{java.lang.String.class, java.util.List.class},
new Object[]{null, null});
availablePermits =
rpcClient.getRouterRpcFairnessPolicyController().getAvailablePermits("ns0");
rpcClient.getRouterRpcFairnessPolicyController().getAvailablePermits(CONCURRENT_NS);
LambdaTestUtils.intercept(IOException.class, () -> {
LOG.info("Use renewLease test invokeConcurrent.");
rpcClient.invokeConcurrent(locations, renewLease);
});
// Ensure that the semaphore is not acquired.
// Ensure that the concurrent semaphore is released.
assertEquals(availablePermits,
rpcClient.getRouterRpcFairnessPolicyController().getAvailablePermits("ns0"));
rpcClient.getRouterRpcFairnessPolicyController().getAvailablePermits(CONCURRENT_NS));
}

/**
Expand Down
Loading