wbtiger
/
foundationdb
mirror of https://github.com/apple/foundationdb.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: do not attempt to become the cluster controller before recovering files from disk

This commit is contained in:
Evan Tschannen 2018-05-01 12:05:43 -07:00
parent e27531d39e
commit c3f2e2bb38
3 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
fdbserver/ClusterController.actor.cpp
View File

@ -2022,7 +2022,8 @@ ACTOR Future<Void> clusterController( ServerCoordinators coordinators, Reference
} }
} }
ACTOR Future<Void> clusterController( Reference<ClusterConnectionFile> connFile, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> currentCC, Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo ) { ACTOR Future<Void> clusterController( Reference<ClusterConnectionFile> connFile, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> currentCC, Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo, Future<Void> recoveredDiskFiles ) {
Void _ = wait(recoveredDiskFiles);
state bool hasConnected = false; state bool hasConnected = false;
loop { loop {
try { try {

4
fdbserver/WorkerInterface.h
View File

@ -280,8 +280,8 @@ class Database openDBOnServer( Reference<AsyncVar<ServerDBInfo>> const& db, int
Future<Void> extractClusterInterface( Reference<AsyncVar<Optional<struct ClusterControllerFullInterface>>> const& a, Reference<AsyncVar<Optional<struct ClusterInterface>>> const& b ); Future<Void> extractClusterInterface( Reference<AsyncVar<Optional<struct ClusterControllerFullInterface>>> const& a, Reference<AsyncVar<Optional<struct ClusterInterface>>> const& b );
Future<Void> fdbd( Reference<ClusterConnectionFile> const&, LocalityData const& localities, ProcessClass const& processClass, std::string const& dataFolder, std::string const& coordFolder, int64_t const& memoryLimit, std::string const& metricsConnFile, std::string const& metricsPrefix ); Future<Void> fdbd( Reference<ClusterConnectionFile> const&, LocalityData const& localities, ProcessClass const& processClass, std::string const& dataFolder, std::string const& coordFolder, int64_t const& memoryLimit, std::string const& metricsConnFile, std::string const& metricsPrefix );
Future<Void> workerServer( Reference<ClusterConnectionFile> const&, Reference<AsyncVar<Optional<struct ClusterControllerFullInterface>>> const& ccInterface, LocalityData const& localities, Reference<AsyncVar<ClusterControllerPriorityInfo>> const& asyncPriorityInfo, ProcessClass const& initialClass, std::string const& filename, int64_t const& memoryLimit, Future<Void> const& forceFailure, std::string const& metricsConnFile, std::string const& metricsPrefix ); Future<Void> workerServer( Reference<ClusterConnectionFile> const&, Reference<AsyncVar<Optional<struct ClusterControllerFullInterface>>> const& ccInterface, LocalityData const& localities, Reference<AsyncVar<ClusterControllerPriorityInfo>> const& asyncPriorityInfo, ProcessClass const& initialClass, std::string const& filename, int64_t const& memoryLimit, Future<Void> const& forceFailure, std::string const& metricsConnFile, std::string const& metricsPrefix, Promise<Void> const& recoveredDiskFiles );
Future<Void> clusterController( Reference<ClusterConnectionFile> const&, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> const& currentCC, Reference<AsyncVar<ClusterControllerPriorityInfo>> const& asyncPriorityInfo ); Future<Void> clusterController( Reference<ClusterConnectionFile> const&, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> const& currentCC, Reference<AsyncVar<ClusterControllerPriorityInfo>> const& asyncPriorityInfo, Future<Void> const& recoveredDiskFiles );
// These servers are started by workerServer // These servers are started by workerServer
Future<Void> storageServer( Future<Void> storageServer(

9
fdbserver/worker.actor.cpp
View File

@ -479,7 +479,7 @@ ACTOR Future<Void> monitorServerDBInfo( Reference<AsyncVar<Optional<ClusterContr
} }
ACTOR Future<Void> workerServer( Reference<ClusterConnectionFile> connFile, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> ccInterface, LocalityData localities, ACTOR Future<Void> workerServer( Reference<ClusterConnectionFile> connFile, Reference<AsyncVar<Optional<ClusterControllerFullInterface>>> ccInterface, LocalityData localities,
Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo, ProcessClass initialClass, std::string folder, int64_t memoryLimit, std::string metricsConnFile, std::string metricsPrefix ) { Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo, ProcessClass initialClass, std::string folder, int64_t memoryLimit, std::string metricsConnFile, std::string metricsPrefix, Promise<Void> recoveredDiskFiles ) {
state PromiseStream< ErrorInfo > errors; state PromiseStream< ErrorInfo > errors;
state Future<Void> handleErrors = workerHandleErrors( errors.getFuture() ); // Needs to be stopped last state Future<Void> handleErrors = workerHandleErrors( errors.getFuture() ); // Needs to be stopped last
state ActorCollection errorForwarders(false); state ActorCollection errorForwarders(false);
@ -643,6 +643,8 @@ ACTOR Future<Void> workerServer( Reference<ClusterConnectionFile> connFile, Refe
startRole( interf.id(), interf.id(), "Worker", details ); startRole( interf.id(), interf.id(), "Worker", details );
Void _ = wait(waitForAll(recoveries)); Void _ = wait(waitForAll(recoveries));
recoveredDiskFiles.send(Void());
errorForwarders.add( registrationClient( ccInterface, interf, asyncPriorityInfo, initialClass ) ); errorForwarders.add( registrationClient( ccInterface, interf, asyncPriorityInfo, initialClass ) );
TraceEvent("RecoveriesComplete", interf.id()); TraceEvent("RecoveriesComplete", interf.id());
@ -979,12 +981,13 @@ ACTOR Future<Void> fdbd(
Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo(new AsyncVar<ClusterControllerPriorityInfo>( Reference<AsyncVar<ClusterControllerPriorityInfo>> asyncPriorityInfo(new AsyncVar<ClusterControllerPriorityInfo>(
ClusterControllerPriorityInfo(ProcessClass(processClass.classType(), ProcessClass::CommandLineSource).machineClassFitness(ProcessClass::ClusterController), false, ClusterControllerPriorityInfo::FitnessUnknown))); ClusterControllerPriorityInfo(ProcessClass(processClass.classType(), ProcessClass::CommandLineSource).machineClassFitness(ProcessClass::ClusterController), false, ClusterControllerPriorityInfo::FitnessUnknown)));
vector<Future<Void>> v; vector<Future<Void>> v;
state Promise<Void> recoveredDiskFiles;
if ( coordFolder.size() ) if ( coordFolder.size() )
v.push_back( fileNotFoundToNever( coordinationServer( coordFolder ) ) ); //SOMEDAY: remove the fileNotFound wrapper and make DiskQueue construction safe from errors setting up their files v.push_back( fileNotFoundToNever( coordinationServer( coordFolder ) ) ); //SOMEDAY: remove the fileNotFound wrapper and make DiskQueue construction safe from errors setting up their files
v.push_back( reportErrors( processClass == ProcessClass::TesterClass ? monitorLeader( connFile, cc ) : clusterController( connFile, cc , asyncPriorityInfo ), "clusterController") ); v.push_back( reportErrors( processClass == ProcessClass::TesterClass ? monitorLeader( connFile, cc ) : clusterController( connFile, cc , asyncPriorityInfo, recoveredDiskFiles.getFuture()), "clusterController") );
v.push_back( reportErrors(extractClusterInterface( cc, ci ), "extractClusterInterface") ); v.push_back( reportErrors(extractClusterInterface( cc, ci ), "extractClusterInterface") );
v.push_back( reportErrors(failureMonitorClient( ci, true ), "failureMonitorClient") ); v.push_back( reportErrors(failureMonitorClient( ci, true ), "failureMonitorClient") );
v.push_back( reportErrorsExcept(workerServer(connFile, cc, localities, asyncPriorityInfo, processClass, dataFolder, memoryLimit, metricsConnFile, metricsPrefix), "workerServer", UID(), &normalWorkerErrors()) ); v.push_back( reportErrorsExcept(workerServer(connFile, cc, localities, asyncPriorityInfo, processClass, dataFolder, memoryLimit, metricsConnFile, metricsPrefix, recoveredDiskFiles), "workerServer", UID(), &normalWorkerErrors()) );
state Future<Void> firstConnect = reportErrors( printOnFirstConnected(ci), "ClusterFirstConnectedError" ); state Future<Void> firstConnect = reportErrors( printOnFirstConnected(ci), "ClusterFirstConnectedError" );
Void _ = wait( quorum(v,1) ); Void _ = wait( quorum(v,1) );