AvalancheSchedulerSvc Class Reference

Introduction

More...

#include <src/AvalancheSchedulerSvc.h>

Inheritance diagram for AvalancheSchedulerSvc:

Collaboration diagram for AvalancheSchedulerSvc:

Classes
struct	enqueueSchedulerActionTask
class	SchedulerState

Public Member Functions
	~AvalancheSchedulerSvc () override=default
	Destructor. More...
StatusCode	initialize () override
	Initialise. More...
StatusCode	finalize () override
	Finalise. More...
StatusCode	pushNewEvent (EventContext *eventContext) override
	Make an event available to the scheduler. More...
StatusCode	pushNewEvents (std::vector< EventContext * > &eventContexts) override
StatusCode	popFinishedEvent (EventContext *&eventContext) override
	Blocks until an event is availble. More...
StatusCode	tryPopFinishedEvent (EventContext *&eventContext) override
	Try to fetch an event from the scheduler. More...
unsigned int	freeSlots () override
	Get free slots number. More...
void	addAlg (Algorithm *, EventContext *, pthread_t)
bool	delAlg (Algorithm *)
void	dumpState () override
Public Member Functions inherited from extends< Service, IScheduler >
void *	i_cast (const InterfaceID &tid) const override
	Implementation of IInterface::i_cast. More...
StatusCode	queryInterface (const InterfaceID &ti, void **pp) override
	Implementation of IInterface::queryInterface. More...
std::vector< std::string >	getInterfaceNames () const override
	Implementation of IInterface::getInterfaceNames. More...
	~extends () override=default
	Virtual destructor. More...
Public Member Functions inherited from Service
const std::string &	name () const override
	Retrieve name of the service. More...
StatusCode	configure () override
StatusCode	initialize () override
StatusCode	start () override
StatusCode	stop () override
StatusCode	finalize () override
StatusCode	terminate () override
Gaudi::StateMachine::State	FSMState () const override
Gaudi::StateMachine::State	targetFSMState () const override
StatusCode	reinitialize () override
StatusCode	restart () override
StatusCode	sysInitialize () override
	Initialize Service. More...
StatusCode	sysStart () override
	Initialize Service. More...
StatusCode	sysStop () override
	Initialize Service. More...
StatusCode	sysFinalize () override
	Finalize Service. More...
StatusCode	sysReinitialize () override
	Re-initialize the Service. More...
StatusCode	sysRestart () override
	Re-initialize the Service. More...
	Service (std::string name, ISvcLocator *svcloc)
	Standard Constructor. More...
SmartIF< ISvcLocator > &	serviceLocator () const override
	Retrieve pointer to service locator. More...
StatusCode	setProperties ()
	Method for setting declared properties to the values specified for the job. More...
template<class T >
StatusCode	service (const std::string &name, const T *&psvc, bool createIf=true) const
	Access a service by name, creating it if it doesn't already exist. More...
template<class T >
StatusCode	service (const std::string &name, T *&psvc, bool createIf=true) const
template<typename IFace = IService>
SmartIF< IFace >	service (const std::string &name, bool createIf=true) const
template<class T >
StatusCode	service (const std::string &svcType, const std::string &svcName, T *&psvc) const
	Access a service by name and type, creating it if it doesn't already exist. More...
template<class T >
StatusCode	declareTool (ToolHandle< T > &handle, std::string toolTypeAndName, bool createIf=true)
	Declare used tool. More...
SmartIF< IAuditorSvc > &	auditorSvc () const
	The standard auditor service.May not be invoked before sysInitialize() has been invoked. More...
Public Member Functions inherited from PropertyHolder< CommonMessaging< implements< IService, IProperty, IStateful > > >
	PropertyHolder ()=default
	~PropertyHolder () override=default
Gaudi::Details::PropertyBase &	declareProperty (Gaudi::Details::PropertyBase &prop)
	Declare a property. More...
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, TYPE &value, const std::string &doc="none")
	Helper to wrap a regular data member and use it as a regular property. More...
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, TYPE &value, const std::string &doc="none") const
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, Gaudi::Property< TYPE, VERIFIER, HANDLERS > &prop, const std::string &doc="none")
	Declare a PropertyBase instance setting name and documentation. More...
Gaudi::Details::PropertyBase *	declareRemoteProperty (const std::string &name, IProperty *rsvc, const std::string &rname="")
	Declare a remote property. More...
StatusCode	setProperty (const Gaudi::Details::PropertyBase &p) override
	set the property form another property More...
StatusCode	setProperty (const std::string &s) override
	set the property from the formatted string More...
StatusCode	setProperty (const std::string &n, const std::string &v) override
	set the property from name and the value More...
StatusCode	setProperty (const std::string &name, const TYPE &value)
	set the property form the value More...
StatusCode	getProperty (Gaudi::Details::PropertyBase *p) const override
	get the property More...
const Gaudi::Details::PropertyBase &	getProperty (const std::string &name) const override
	get the property by name More...
StatusCode	getProperty (const std::string &n, std::string &v) const override
	convert the property to the string More...
const std::vector< Gaudi::Details::PropertyBase * > &	getProperties () const override
	get all properties More...
bool	hasProperty (const std::string &name) const override
	Return true if we have a property with the given name. More...
	PropertyHolder (const PropertyHolder &)=delete
PropertyHolder &	operator= (const PropertyHolder &)=delete
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, GaudiHandleBase &ref, const std::string &doc="none")
	Specializations for various GaudiHandles. More...
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, GaudiHandleArrayBase &ref, const std::string &doc="none")
Gaudi::Details::PropertyBase *	declareProperty (const std::string &name, DataObjectHandleBase &ref, const std::string &doc="none")
Public Member Functions inherited from CommonMessagingBase
virtual	~CommonMessagingBase ()=default
	Virtual destructor. More...
SmartIF< IMessageSvc > &	msgSvc () const
	The standard message service. More...
MsgStream &	msgStream () const
	Return an uninitialized MsgStream. More...
MsgStream &	msgStream (const MSG::Level level) const
	Predefined configurable message stream for the efficient printouts. More...
MsgStream &	always () const
	shortcut for the method msgStream(MSG::ALWAYS) More...
MsgStream &	fatal () const
	shortcut for the method msgStream(MSG::FATAL) More...
MsgStream &	err () const
	shortcut for the method msgStream(MSG::ERROR) More...
MsgStream &	error () const
	shortcut for the method msgStream(MSG::ERROR) More...
MsgStream &	warning () const
	shortcut for the method msgStream(MSG::WARNING) More...
MsgStream &	info () const
	shortcut for the method msgStream(MSG::INFO) More...
MsgStream &	debug () const
	shortcut for the method msgStream(MSG::DEBUG) More...
MsgStream &	verbose () const
	shortcut for the method msgStream(MSG::VERBOSE) More...
MsgStream &	msg () const
	shortcut for the method msgStream(MSG::INFO) More...
MSG::Level	msgLevel () const
	get the output level from the embedded MsgStream More...
MSG::Level	outputLevel () const __attribute__((deprecated))
	Backward compatibility function for getting the output level. More...
bool	msgLevel (MSG::Level lvl) const
	get the output level from the embedded MsgStream More...
Public Member Functions inherited from extend_interfaces< Interfaces... >
	~extend_interfaces () override=default
	Virtual destructor. More...

Private Types
enum	ActivationState { INACTIVE = 0, ACTIVE = 1, FAILURE = 2 }

Private Member Functions
void	activate ()
	Activate scheduler. More...
StatusCode	deactivate ()
	Deactivate scheduler. More...
unsigned int	algname2index (const std::string &algoname)
	Convert a name to an integer. More...
const std::string &	index2algname (unsigned int index)
	Convert an integer to a name. More...
StatusCode	eventFailed (EventContext *eventContext)
	Method to check if an event failed and take appropriate actions. More...
StatusCode	updateStates (int si=-1, const std::string &algo_name=std::string())
	Loop on algorithm in the slots and promote them to successive states (-1 means all slots, while empty string means skipping an update of the Control Flow state) More...
StatusCode	promoteToScheduled (unsigned int iAlgo, int si)
	Algorithm promotion. More...
StatusCode	promoteToAsyncScheduled (unsigned int iAlgo, int si)
StatusCode	promoteToExecuted (unsigned int iAlgo, int si, IAlgorithm *algo, EventContext *)
	The call to this method is triggered only from within the AlgoExecutionTask. More...
StatusCode	promoteToAsyncExecuted (unsigned int iAlgo, int si, IAlgorithm *algo, EventContext *)
	The call to this method is triggered only from within the IOBoundAlgTask. More...
StatusCode	promoteToFinished (unsigned int iAlgo, int si)
StatusCode	isStalled (int si)
	Check if the scheduling is in a stall. More...
void	dumpSchedulerState (int iSlot)
	Dump the state of the scheduler. More...
StatusCode	m_drain ()
	Drain the actions present in the queue. More...
void	dumpState (std::ostringstream &)

Private Attributes
Gaudi::Property< int >	m_threadPoolSize
Gaudi::Property< std::string >	m_whiteboardSvcName {this, "WhiteboardSvc", "EventDataSvc", "The whiteboard name"}
Gaudi::Property< std::string >	m_IOBoundAlgSchedulerSvcName {this, "IOBoundAlgSchedulerSvc", "IOBoundAlgSchedulerSvc"}
Gaudi::Property< unsigned int >	m_maxIOBoundAlgosInFlight
Gaudi::Property< bool >	m_simulateExecution
Gaudi::Property< std::string >	m_optimizationMode
Gaudi::Property< bool >	m_dumpIntraEventDynamics
Gaudi::Property< bool >	m_useIOBoundAlgScheduler
Gaudi::Property< bool >	m_checkDeps {this, "CheckDependencies", false, "Runtime check of Algorithm Data Dependencies"}
Gaudi::Property< std::string >	m_useDataLoader
Gaudi::Property< bool >	m_enableCondSvc {this, "EnableConditions", false, "Enable ConditionsSvc"}
Gaudi::Property< bool >	m_showDataDeps
Gaudi::Property< bool >	m_showDataFlow
Gaudi::Property< bool >	m_showControlFlow
std::atomic< ActivationState >	m_isActive {INACTIVE}
	Flag to track if the scheduler is active or not. More...
std::thread	m_thread
	The thread in which the activate function runs. More...
std::unordered_map< std::string, unsigned int >	m_algname_index_map
	Map to bookkeep the information necessary to the name2index conversion. More...
std::vector< std::string >	m_algname_vect
	Vector to bookkeep the information necessary to the index2name conversion. More...
SmartIF< IPrecedenceSvc >	m_precSvc
	A shortcut to the Precedence Service. More...
SmartIF< IHiveWhiteBoard >	m_whiteboard
	A shortcut to the whiteboard. More...
SmartIF< IAccelerator >	m_IOBoundAlgScheduler
	A shortcut to IO-bound algorithm scheduler. More...
std::vector< EventSlot >	m_eventSlots
	Vector of events slots. More...
std::atomic_int	m_freeSlots
	Atomic to account for asyncronous updates by the scheduler wrt the rest. More...
tbb::concurrent_bounded_queue< EventContext * >	m_finishedEvents
	Queue of finished events. More...
SmartIF< IAlgExecStateSvc >	m_algExecStateSvc
	Algorithm execution state manager. More...
SmartIF< ICondSvc >	m_condSvc
	A shortcut to service for Conditions handling. More...
unsigned int	m_algosInFlight = 0
	Number of algoritms presently in flight. More...
unsigned int	m_IOBoundAlgosInFlight = 0
	Number of algoritms presently in flight. More...
bool	m_updateNeeded = true
	Keep track of update actions scheduled. More...
SmartIF< IAlgResourcePool >	m_algResourcePool
	Cache for the algorithm resource pool. More...
tbb::concurrent_bounded_queue< action >	m_actionsQueue
	Queue where closures are stored and picked for execution. More...
SmartIF< IThreadPoolSvc >	m_threadPoolSvc
size_t	m_maxEventsInFlight {0}
size_t	m_maxAlgosInFlight {1}
bool	m_first = true

Static Private Attributes
static std::list< SchedulerState >	m_sState
static std::mutex	m_ssMut

Additional Inherited Members
Public Types inherited from extends< Service, IScheduler >
using	base_class = extends
	Typedef to this class. More...
using	extend_interfaces_base = extend_interfaces< Interfaces... >
	Typedef to the base of this class. More...
Public Types inherited from Service
typedef Gaudi::PluginService::Factory< IService *, const std::string &, ISvcLocator * >	Factory
Public Types inherited from PropertyHolder< CommonMessaging< implements< IService, IProperty, IStateful > > >
using	PropertyHolderImpl = PropertyHolder< CommonMessaging< implements< IService, IProperty, IStateful > > >
	Typedef used to refer to this class from derived classes, as in. More...
Public Types inherited from CommonMessaging< implements< IService, IProperty, IStateful > >
using	base_class = CommonMessaging
Public Types inherited from extend_interfaces< Interfaces... >
using	ext_iids = typename Gaudi::interface_list_cat< typename Interfaces::ext_iids... >::type
	take union of the ext_iids of all Interfaces... More...
Protected Member Functions inherited from Service
	~Service () override
	Standard Destructor. More...
int	outputLevel () const
	get the Service's output level More...
Protected Member Functions inherited from PropertyHolder< CommonMessaging< implements< IService, IProperty, IStateful > > >
Gaudi::Details::PropertyBase *	property (const std::string &name) const
Protected Member Functions inherited from CommonMessaging< implements< IService, IProperty, IStateful > >
void	updateMsgStreamOutputLevel (int level)
	Update the output level of the cached MsgStream. More...
Protected Attributes inherited from Service
Gaudi::StateMachine::State	m_state = Gaudi::StateMachine::OFFLINE
	Service state. More...
Gaudi::StateMachine::State	m_targetState = Gaudi::StateMachine::OFFLINE
	Service state. More...
Gaudi::Property< int >	m_outputLevel {this, "OutputLevel", MSG::NIL, "output level"}
Gaudi::Property< bool >	m_auditInit {this, "AuditServices", false, "[[deprecated]] unused"}
Gaudi::Property< bool >	m_auditorInitialize {this, "AuditInitialize", false, "trigger auditor on initialize()"}
Gaudi::Property< bool >	m_auditorStart {this, "AuditStart", false, "trigger auditor on start()"}
Gaudi::Property< bool >	m_auditorStop {this, "AuditStop", false, "trigger auditor on stop()"}
Gaudi::Property< bool >	m_auditorFinalize {this, "AuditFinalize", false, "trigger auditor on finalize()"}
Gaudi::Property< bool >	m_auditorReinitialize {this, "AuditReinitialize", false, "trigger auditor on reinitialize()"}
Gaudi::Property< bool >	m_auditorRestart {this, "AuditRestart", false, "trigger auditor on restart()"}
SmartIF< IAuditorSvc >	m_pAuditorSvc
	Auditor Service. More...

Detailed Description

Introduction

The scheduler is named after its ability to generically maximize the average intra-event task occupancy by inducing avalanche-like concurrency disclosure waves in conditions of arbitrary intra-event task precedence constraints (see section 3.2 of http://cern.ch/go/7Jn7).

Task precedence management

The scheduler is driven by graph-based task precedence management. When compared to approach used in the ForwardSchedulerSvc, the following advantages can be emphasized:

(1) Faster decision making (thus lower concurrency disclosure downtime); (2) Capacity for proactive task scheduling decision making.

Point (2) allowed to implement a number of generic, non-intrusive intra-event throughput maximization scheduling strategies.

Scheduling principles

o Task scheduling prerequisites

A task is scheduled ASA all following conditions are met:

• if a control flow (CF) graph traversal reaches the task;
• when all data flow (DF) dependencies of the task are satisfied;
• when the DF-ready task pool parsing mechanism (*) considers it, and:
  • a free (or re-entrant) algorithm instance to run within the task is available;
  • there is a free computational resource to run the task.

o (*) Avalanche induction strategies

The scheduler is able to maximize the intra-event throughput by applying several search strategies within the pool, prioritizing tasks according to the following types of precedence rules graph asymmetries:

(A) Local task-to-data asymmetry; (B) Local task-to-task asymmetry; (C) Global task-to-task asymmetry.

o Other mechanisms of throughput maximization

The scheduler is able to maximize the overall throughput of data processing by scheduling the CPU-blocking tasks efficiently. The mechanism can be applied to the following types of tasks:

• I/O-bound tasks;
• tasks with computation offloading (accelerators, GPGPUs, clouds, quantum computing devices..joke);
• synchronization-bound tasks.

Credits

Historically, the AvalancheSchedulerSvc branched off the ForwardSchedulerSvc and in many ways built its success on ideas and code of the latter.

Author

Illya Shapoval

Version

1.0

Definition at line 102 of file AvalancheSchedulerSvc.h.

Member Enumeration Documentation

enum AvalancheSchedulerSvc::ActivationState

private

Enumerator
INACTIVE
ACTIVE
FAILURE

Definition at line 133 of file AvalancheSchedulerSvc.h.

{ INACTIVE = 0, ACTIVE = 1, FAILURE = 2 };

Constructor & Destructor Documentation

AvalancheSchedulerSvc::~AvalancheSchedulerSvc ( )

overridedefault

Destructor.

Member Function Documentation

void AvalancheSchedulerSvc::activate ( )

private

Activate scheduler.

Activate the scheduler.

From this moment on the queue of actions is checked. The checking will stop when the m_isActive flag is false and the queue is not empty. This will guarantee that all actions are executed and a stall is not created. The TBB pool must be initialised in the thread from where the tasks are launched (http://threadingbuildingblocks.org/docs/doxygen/a00342.html) The scheduler is initialised here since this method runs in a separate thread and spawns the tasks (through the execution of the lambdas)

Definition at line 363 of file AvalancheSchedulerSvc.cpp.

{

  if ( msgLevel( MSG::DEBUG ) ) debug() << "AvalancheSchedulerSvc::activate()" << endmsg;

  if ( m_threadPoolSvc->initPool( m_threadPoolSize ).isFailure() ) {
    error() << "problems initializing ThreadPoolSvc" << endmsg;
    m_isActive = FAILURE;
    return;
  }

  // Wait for actions pushed into the queue by finishing tasks.
  action thisAction;
  StatusCode sc( StatusCode::SUCCESS );

  m_isActive = ACTIVE;

  // Continue to wait if the scheduler is running or there is something to do
  info() << "Start checking the actionsQueue" << endmsg;
  while ( m_isActive == ACTIVE or m_actionsQueue.size() != 0 ) {
    m_actionsQueue.pop( thisAction );
    sc = thisAction();
    if ( sc != StatusCode::SUCCESS )
      verbose() << "Action did not succeed (which is not bad per se)." << endmsg;
    else
      verbose() << "Action succeeded." << endmsg;
  }

  info() << "Terminating thread-pool resources" << endmsg;
  if ( m_threadPoolSvc->terminatePool().isFailure() ) {
    error() << "Problems terminating thread pool" << endmsg;
    m_isActive = FAILURE;
  }
}

void AvalancheSchedulerSvc::addAlg	(	Algorithm *	a,
		EventContext *	e,
		pthread_t	t
	)

Definition at line 1100 of file AvalancheSchedulerSvc.cpp.

{

  std::lock_guard<std::mutex> lock( m_ssMut );
  m_sState.push_back( SchedulerState( a, e, t ) );
}

unsigned int AvalancheSchedulerSvc::algname2index ( const std::string &  algoname )

inlineprivate

Convert a name to an integer.

Definition at line 431 of file AvalancheSchedulerSvc.cpp.

{
  unsigned int index = m_algname_index_map[algoname];
  return index;
}

StatusCode AvalancheSchedulerSvc::deactivate ( )

private

Deactivate scheduler.

Deactivates the scheduler.

Two actions are pushed into the queue: 1) Drain the scheduler until all events are finished. 2) Flip the status flag m_isActive to false This second action is the last one to be executed by the scheduler.

Definition at line 406 of file AvalancheSchedulerSvc.cpp.

{

  if ( m_isActive == ACTIVE ) {
    // Drain the scheduler
    m_actionsQueue.push( std::bind( &AvalancheSchedulerSvc::m_drain, this ) );
    // This would be the last action
    m_actionsQueue.push( [this]() -> StatusCode {
      m_isActive = INACTIVE;
      return StatusCode::SUCCESS;
    } );
  }

  return StatusCode::SUCCESS;
}

bool AvalancheSchedulerSvc::delAlg

(

Algorithm *

a

)

Definition at line 1108 of file AvalancheSchedulerSvc.cpp.

{

  std::lock_guard<std::mutex> lock( m_ssMut );

  for ( std::list<SchedulerState>::iterator itr = m_sState.begin(); itr != m_sState.end(); ++itr ) {
    if ( *itr == a ) {
      m_sState.erase( itr );
      return true;
    }
  }

  error() << "could not find Alg " << a->name() << " in Scheduler!" << endmsg;
  return false;
}

void AvalancheSchedulerSvc::dumpSchedulerState ( int  iSlot )

private

Dump the state of the scheduler.

Used for debugging purposes, the state of the scheduler is dumped on screen in order to be inspected.

The dependencies of each algo are printed and the missing ones specified.

Definition at line 809 of file AvalancheSchedulerSvc.cpp.

{

  // To have just one big message
  std::ostringstream outputMessageStream;

  outputMessageStream << "============================== Execution Task State ============================="
                      << std::endl;
  dumpState( outputMessageStream );

  outputMessageStream << std::endl
                      << "============================== Scheduler State  ================================="
                      << std::endl;

  int slotCount = -1;
  for ( auto& thisSlot : m_eventSlots ) {
    slotCount++;
    if ( thisSlot.complete ) continue;

    // dump temporal and topological precedence analysis (if enabled in the PrecedenceSvc)
    if ( msgLevel( MSG::DEBUG ) ) m_precSvc->dumpPrecedenceRules( thisSlot );

    outputMessageStream << "-----------  slot: " << thisSlot.eventContext->slot()
                        << "  event: " << thisSlot.eventContext->evt() << " -----------" << std::endl;

    if ( 0 > iSlot or iSlot == slotCount ) {
      outputMessageStream << "Algorithms states:" << std::endl;

      const DataObjIDColl& wbSlotContent( thisSlot.dataFlowMgr.content() );
      for ( unsigned int algoIdx = 0; algoIdx < thisSlot.algsStates.size(); ++algoIdx ) {
        outputMessageStream << " o " << index2algname( algoIdx ) << " ["
                            << AlgsExecutionStates::stateNames[thisSlot.algsStates[algoIdx]] << "]  Data deps: ";
        DataObjIDColl deps( thisSlot.dataFlowMgr.dataDependencies( algoIdx ) );
        const int depsSize = deps.size();
        if ( depsSize == 0 ) outputMessageStream << " none";

        DataObjIDColl missing;
        for ( auto d : deps ) {
          outputMessageStream << d << " ";
          if ( wbSlotContent.find( d ) == wbSlotContent.end() ) {
            //      outputMessageStream << "[missing] ";
            missing.insert( d );
          }
        }

        if ( !missing.empty() ) {
          outputMessageStream << ". The following are missing: ";
          for ( auto d : missing ) {
            outputMessageStream << d << " ";
          }
        }

        outputMessageStream << std::endl;
      }

      // Snapshot of the WhiteBoard
      outputMessageStream << "\nWhiteboard contents: " << std::endl;
      for ( auto& product : wbSlotContent ) outputMessageStream << " o " << product << std::endl;

      // Snapshot of the ControlFlow
      outputMessageStream << "\nControl Flow:" << std::endl;
      outputMessageStream << m_precSvc->printState( thisSlot ) << std::endl;
    }
  }

  outputMessageStream << "=================================== END ======================================" << std::endl;

  info() << "Dumping Scheduler State " << std::endl << outputMessageStream.str() << endmsg;
}

void AvalancheSchedulerSvc::dumpState ( )

override

Definition at line 1136 of file AvalancheSchedulerSvc.cpp.

{

  std::lock_guard<std::mutex> lock( m_ssMut );

  std::ostringstream ost;
  ost << "dumping Executing Threads: [" << m_sState.size() << "]" << std::endl;
  dumpState( ost );

  info() << ost.str() << endmsg;
}

void AvalancheSchedulerSvc::dumpState ( std::ostringstream &  ost )

private

Definition at line 1125 of file AvalancheSchedulerSvc.cpp.

{

  std::lock_guard<std::mutex> lock( m_ssMut );

  for ( auto it : m_sState ) {
    ost << "  " << it << std::endl;
  }
}

StatusCode AvalancheSchedulerSvc::eventFailed ( EventContext *  eventContext )

private

Method to check if an event failed and take appropriate actions.

It can be possible that an event fails.

In this case this method is called. It dumps the state of the scheduler, drains the actions (without executing them) and events in the queues and returns a failure.

Definition at line 569 of file AvalancheSchedulerSvc.cpp.

{

  // Set the number of slots available to an error code
  m_freeSlots.store( 0 );

  fatal() << "*** Event " << eventContext->evt() << " on slot " << eventContext->slot() << " failed! ***" << endmsg;

  std::ostringstream ost;
  m_algExecStateSvc->dump( ost, *eventContext );

  info() << "Dumping Alg Exec State for slot " << eventContext->slot() << ":\n" << ost.str() << endmsg;

  dumpSchedulerState( -1 );

  // Empty queue and deactivate the service
  action thisAction;
  while ( m_actionsQueue.try_pop( thisAction ) ) {
  };
  deactivate();

  // Push into the finished events queue the failed context
  EventContext* thisEvtContext;
  while ( m_finishedEvents.try_pop( thisEvtContext ) ) {
    m_finishedEvents.push( thisEvtContext );
  };
  m_finishedEvents.push( eventContext );

  return StatusCode::FAILURE;
}

StatusCode AvalancheSchedulerSvc::finalize ( )

override

Finalise.

Here the scheduler is deactivated and the thread joined.

Definition at line 332 of file AvalancheSchedulerSvc.cpp.

{

  StatusCode sc( Service::finalize() );
  if ( !sc.isSuccess() ) warning() << "Base class could not be finalized" << endmsg;

  sc = deactivate();
  if ( !sc.isSuccess() ) warning() << "Scheduler could not be deactivated" << endmsg;

  info() << "Joining Scheduler thread" << endmsg;
  m_thread.join();

  // Final error check after thread pool termination
  if ( m_isActive == FAILURE ) {
    error() << "problems in scheduler thread" << endmsg;
    return StatusCode::FAILURE;
  }

  return sc;
}

unsigned int AvalancheSchedulerSvc::freeSlots ( )

override

Get free slots number.

Definition at line 506 of file AvalancheSchedulerSvc.cpp.

{ return std::max( m_freeSlots.load(), 0 ); }

const std::string & AvalancheSchedulerSvc::index2algname ( unsigned int  index )

inlineprivate

Convert an integer to a name.

Definition at line 427 of file AvalancheSchedulerSvc.cpp.

{ return m_algname_vect[index]; }

StatusCode AvalancheSchedulerSvc::initialize ( )

override

Initialise.

Here, among some "bureaucracy" operations, the scheduler is activated, executing the activate() function in a new thread.

In addition the algorithms list is acquired from the algResourcePool.

Definition at line 61 of file AvalancheSchedulerSvc.cpp.

{

  // Initialise mother class (read properties, ...)
  StatusCode sc( Service::initialize() );
  if ( !sc.isSuccess() ) warning() << "Base class could not be initialized" << endmsg;

  // Get hold of the TBBSvc. This should initialize the thread pool
  m_threadPoolSvc = serviceLocator()->service( "ThreadPoolSvc" );
  if ( !m_threadPoolSvc.isValid() ) {
    fatal() << "Error retrieving ThreadPoolSvc" << endmsg;
    return StatusCode::FAILURE;
  }

  // Activate the scheduler in another thread.
  info() << "Activating scheduler in a separate thread" << endmsg;
  m_thread = std::thread( std::bind( &AvalancheSchedulerSvc::activate, this ) );

  while ( m_isActive != ACTIVE ) {
    if ( m_isActive == FAILURE ) {
      fatal() << "Terminating initialization" << endmsg;
      return StatusCode::FAILURE;
    } else {
      info() << "Waiting for AvalancheSchedulerSvc to activate" << endmsg;
      sleep( 1 );
    }
  }

  if ( m_enableCondSvc ) {
    // Get hold of the CondSvc
    m_condSvc = serviceLocator()->service( "CondSvc" );
    if ( !m_condSvc.isValid() ) {
      warning() << "No CondSvc found, or not enabled. "
                << "Will not manage CondAlgorithms" << endmsg;
      m_enableCondSvc = false;
    }
  }

  // Get the algo resource pool
  m_algResourcePool = serviceLocator()->service( "AlgResourcePool" );
  if ( !m_algResourcePool.isValid() ) {
    fatal() << "Error retrieving AlgoResourcePool" << endmsg;
    return StatusCode::FAILURE;
  }

  // Get the precedence service
  m_precSvc = serviceLocator()->service( "PrecedenceSvc" );
  if ( !m_precSvc.isValid() ) {
    fatal() << "Error retrieving PrecedenceSvc" << endmsg;
    return StatusCode::FAILURE;
  }
  const PrecedenceSvc* precSvc = dynamic_cast<const PrecedenceSvc*>( m_precSvc.get() );
  if ( !precSvc ) {
    fatal() << "Unable to dcast PrecedenceSvc" << endmsg;
    return StatusCode::FAILURE;
  }

  m_algExecStateSvc = serviceLocator()->service( "AlgExecStateSvc" );
  if ( !m_algExecStateSvc.isValid() ) {
    fatal() << "Error retrieving AlgExecStateSvc" << endmsg;
    return StatusCode::FAILURE;
  }

  // Get Whiteboard
  m_whiteboard = serviceLocator()->service( m_whiteboardSvcName );
  if ( !m_whiteboard.isValid() ) {
    fatal() << "Error retrieving EventDataSvc interface IHiveWhiteBoard." << endmsg;
    return StatusCode::FAILURE;
  }

  // Get dedicated scheduler for I/O-bound algorithms
  if ( m_useIOBoundAlgScheduler ) {
    m_IOBoundAlgScheduler = serviceLocator()->service( m_IOBoundAlgSchedulerSvcName );
    if ( !m_IOBoundAlgScheduler.isValid() )
      fatal() << "Error retrieving IOBoundSchedulerAlgSvc interface IAccelerator." << endmsg;
  }

  // Set the MaxEventsInFlight parameters from the number of WB stores
  m_maxEventsInFlight = m_whiteboard->getNumberOfStores();

  // Set the number of free slots
  m_freeSlots = m_maxEventsInFlight;

  // set global concurrency flags
  Gaudi::Concurrency::ConcurrencyFlags::setNumConcEvents( m_maxEventsInFlight );

  // Get the list of algorithms
  const std::list<IAlgorithm*>& algos = m_algResourcePool->getFlatAlgList();
  const unsigned int algsNumber       = algos.size();
  info() << "Found " << algsNumber << " algorithms" << endmsg;

  /* Dependencies
   1) Look for handles in algo, if none
   2) Assume none are required
  */

  DataObjIDColl globalInp, globalOutp;

  // figure out all outputs
  for ( IAlgorithm* ialgoPtr : algos ) {
    Algorithm* algoPtr = dynamic_cast<Algorithm*>( ialgoPtr );
    if ( !algoPtr ) {
      fatal() << "Could not convert IAlgorithm into Algorithm: this will result in a crash." << endmsg;
    }
    for ( auto id : algoPtr->outputDataObjs() ) {
      auto r = globalOutp.insert( id );
      if ( !r.second ) {
        warning() << "multiple algorithms declare " << id << " as output! could be a single instance in multiple paths "
                                                             "though, or control flow may guarantee only one runs...!"
                  << endmsg;
      }
    }
  }

  std::ostringstream ostdd;
  ostdd << "Data Dependencies for Algorithms:";

  std::vector<DataObjIDColl> m_algosDependencies;
  for ( IAlgorithm* ialgoPtr : algos ) {
    Algorithm* algoPtr = dynamic_cast<Algorithm*>( ialgoPtr );
    if ( nullptr == algoPtr ) {
      fatal() << "Could not convert IAlgorithm into Algorithm for " << ialgoPtr->name()
              << ": this will result in a crash." << endmsg;
      return StatusCode::FAILURE;
    }

    ostdd << "\n  " << algoPtr->name();

    DataObjIDColl algoDependencies;
    if ( !algoPtr->inputDataObjs().empty() || !algoPtr->outputDataObjs().empty() ) {
      for ( const DataObjID* idp : sortedDataObjIDColl( algoPtr->inputDataObjs() ) ) {
        DataObjID id = *idp;
        ostdd << "\n    o INPUT  " << id;
        if ( id.key().find( ":" ) != std::string::npos ) {
          ostdd << " contains alternatives which require resolution...\n";
          auto tokens = boost::tokenizer<boost::char_separator<char>>{id.key(), boost::char_separator<char>{":"}};
          auto itok   = std::find_if( tokens.begin(), tokens.end(), [&]( const std::string& t ) {
            return globalOutp.find( DataObjID{t} ) != globalOutp.end();
          } );
          if ( itok != tokens.end() ) {
            ostdd << "found matching output for " << *itok << " -- updating scheduler info\n";
            id.updateKey( *itok );
          } else {
            error() << "failed to find alternate in global output list"
                    << " for id: " << id << " in Alg " << algoPtr->name() << endmsg;
            m_showDataDeps = true;
          }
        }
        algoDependencies.insert( id );
        globalInp.insert( id );
      }
      for ( const DataObjID* id : sortedDataObjIDColl( algoPtr->outputDataObjs() ) ) {
        ostdd << "\n    o OUTPUT " << *id;
        if ( id->key().find( ":" ) != std::string::npos ) {
          error() << " in Alg " << algoPtr->name() << " alternatives are NOT allowed for outputs! id: " << *id
                  << endmsg;
          m_showDataDeps = true;
        }
      }
    } else {
      ostdd << "\n      none";
    }
    m_algosDependencies.emplace_back( algoDependencies );
  }

  if ( m_showDataDeps ) {
    info() << ostdd.str() << endmsg;
  }

  // Fill the containers to convert algo names to index
  m_algname_vect.resize( algsNumber );
  IAlgorithm* dataLoaderAlg( nullptr );
  for ( IAlgorithm* algo : algos ) {
    const std::string& name    = algo->name();
    auto index                 = precSvc->getRules()->getAlgorithmNode( name )->getAlgoIndex();
    m_algname_index_map[name]  = index;
    m_algname_vect.at( index ) = name;
    if ( algo->name() == m_useDataLoader ) {
      dataLoaderAlg = algo;
    }
  }

  // Check if we have unmet global input dependencies
  if ( m_checkDeps ) {
    DataObjIDColl unmetDep;
    for ( auto o : globalInp ) {
      if ( globalOutp.find( o ) == globalOutp.end() ) {
        unmetDep.insert( o );
      }
    }

    if ( unmetDep.size() > 0 ) {

      std::ostringstream ost;
      for ( const DataObjID* o : sortedDataObjIDColl( unmetDep ) ) {
        ost << "\n   o " << *o << "    required by Algorithm: ";
        for ( size_t i = 0; i < m_algosDependencies.size(); ++i ) {
          if ( m_algosDependencies[i].find( *o ) != m_algosDependencies[i].end() ) {
            ost << "\n       * " << m_algname_vect[i];
          }
        }
      }

      if ( m_useDataLoader != "" ) {
        // Find the DataLoader Alg
        if ( dataLoaderAlg == nullptr ) {
          fatal() << "No DataLoader Algorithm \"" << m_useDataLoader.value()
                  << "\" found, and unmet INPUT dependencies "
                  << "detected:\n"
                  << ost.str() << endmsg;
          return StatusCode::FAILURE;
        }

        info() << "Will attribute the following unmet INPUT dependencies to \"" << dataLoaderAlg->type() << "/"
               << dataLoaderAlg->name() << "\" Algorithm" << ost.str() << endmsg;

        // Set the property Load of DataLoader Alg
        Algorithm* dataAlg = dynamic_cast<Algorithm*>( dataLoaderAlg );
        if ( !dataAlg ) {
          fatal() << "Unable to dcast DataLoader \"" << m_useDataLoader.value() << "\" IAlg to Algorithm" << endmsg;
          return StatusCode::FAILURE;
        }

        for ( auto& id : unmetDep ) {
          debug() << "adding OUTPUT dep \"" << id << "\" to " << dataLoaderAlg->type() << "/" << dataLoaderAlg->name()
                  << endmsg;
          dataAlg->addDependency( id, Gaudi::DataHandle::Writer );
        }

      } else {
        fatal() << "Auto DataLoading not requested, "
                << "and the following unmet INPUT dependencies were found:" << ost.str() << endmsg;
        return StatusCode::FAILURE;
      }

    } else {
      info() << "No unmet INPUT data dependencies were found" << endmsg;
    }
  }

  // Shortcut for the message service
  SmartIF<IMessageSvc> messageSvc( serviceLocator() );
  if ( !messageSvc.isValid() ) error() << "Error retrieving MessageSvc interface IMessageSvc." << endmsg;

  m_eventSlots.assign( m_maxEventsInFlight, EventSlot( m_algosDependencies, algsNumber,
                                                       precSvc->getRules()->getControlFlowNodeCounter(), messageSvc ) );
  std::for_each( m_eventSlots.begin(), m_eventSlots.end(), []( EventSlot& slot ) { slot.complete = true; } );

  if ( m_threadPoolSize > 1 ) {
    m_maxAlgosInFlight = (size_t)m_threadPoolSize;
  }

  // Clearly inform about the level of concurrency
  info() << "Concurrency level information:" << endmsg;
  info() << " o Number of events in flight: " << m_maxEventsInFlight << endmsg;
  info() << " o TBB thread pool size: " << m_threadPoolSize << endmsg;

  if ( m_showControlFlow ) m_precSvc->dumpControlFlow();

  if ( m_showDataFlow ) m_precSvc->dumpDataFlow();

  // Simulate execution flow
  if ( m_simulateExecution ) m_precSvc->simulate( m_eventSlots[0] );

  return sc;
}

StatusCode AvalancheSchedulerSvc::isStalled ( int  iSlot )

private

Check if the scheduling is in a stall.

Check if we are in present of a stall condition for a particular slot.

This is the case when no actions are present in the actionsQueue, no algorithm is in flight and no algorithm has all of its dependencies satisfied.

Definition at line 784 of file AvalancheSchedulerSvc.cpp.

{
  // Get the slot
  EventSlot& thisSlot = m_eventSlots[iSlot];

  if ( m_actionsQueue.empty() && m_algosInFlight == 0 && m_IOBoundAlgosInFlight == 0 &&
       ( !thisSlot.algsStates.algsPresent( AlgsExecutionStates::DATAREADY ) ) ) {

    info() << "About to declare a stall" << endmsg;
    fatal() << "*** Stall detected! ***\n" << endmsg;
    dumpSchedulerState( iSlot );
    // throw GaudiException ("Stall detected",name(),StatusCode::FAILURE);

    return StatusCode::FAILURE;
  }
  return StatusCode::SUCCESS;
}

StatusCode AvalancheSchedulerSvc::m_drain ( )

private

Drain the actions present in the queue.

Update the states for all slots until nothing is left to do.

Definition at line 512 of file AvalancheSchedulerSvc.cpp.

{

  unsigned int slotNum = 0;
  for ( auto& thisSlot : m_eventSlots ) {
    if ( not thisSlot.algsStates.allAlgsExecuted() and not thisSlot.complete ) {
      updateStates( slotNum );
    }
    slotNum++;
  }
  return StatusCode::SUCCESS;
}

StatusCode AvalancheSchedulerSvc::popFinishedEvent ( EventContext *&  eventContext )

override

Blocks until an event is availble.

Get a finished event or block until one becomes available.

Definition at line 529 of file AvalancheSchedulerSvc.cpp.

{
  // debug() << "popFinishedEvent: queue size: " << m_finishedEvents.size() << endmsg;
  if ( m_freeSlots.load() == (int)m_maxEventsInFlight or m_isActive == INACTIVE ) {
    // debug() << "freeslots: " << m_freeSlots << "/" << m_maxEventsInFlight
    //      << " active: " << m_isActive << endmsg;
    return StatusCode::FAILURE;
  } else {
    // debug() << "freeslots: " << m_freeSlots << "/" << m_maxEventsInFlight
    //      << " active: " << m_isActive << endmsg;
    m_finishedEvents.pop( eventContext );
    m_freeSlots++;
    if ( msgLevel( MSG::DEBUG ) )
      debug() << "Popped slot " << eventContext->slot() << "(event " << eventContext->evt() << ")" << endmsg;
    return StatusCode::SUCCESS;
  }
}

StatusCode AvalancheSchedulerSvc::promoteToAsyncExecuted ( unsigned int  iAlgo, int  si, IAlgorithm *  algo, EventContext *  eventContext  )

private

The call to this method is triggered only from within the IOBoundAlgTask.

Definition at line 1047 of file AvalancheSchedulerSvc.cpp.

{
  // Put back the instance
  Algorithm* castedAlgo = dynamic_cast<Algorithm*>( algo ); // DP: expose context getter in IAlgo?
  if ( !castedAlgo ) fatal() << "[Asynchronous] The casting did not succeed!" << endmsg;
  // EventContext* eventContext = castedAlgo->getContext();

  // Check if the execution failed
  if ( m_algExecStateSvc->eventStatus( *eventContext ) != EventStatus::Success ) eventFailed( eventContext ).ignore();

  StatusCode sc = m_algResourcePool->releaseAlgorithm( algo->name(), algo );

  if ( !sc.isSuccess() ) {
    error() << "[Asynchronous]  [Event " << eventContext->evt() << ", Slot " << eventContext->slot() << "] "
            << "Instance of algorithm " << algo->name() << " could not be properly put back." << endmsg;
    return StatusCode::FAILURE;
  }

  m_IOBoundAlgosInFlight--;

  EventSlot& thisSlot = m_eventSlots[si];

  if ( msgLevel( MSG::DEBUG ) )
    debug() << "[Asynchronous] Algorithm " << algo->name() << " executed in slot " << si
            << ". Algorithms scheduled are " << m_IOBoundAlgosInFlight << endmsg;

  // Schedule an update of the status of the algorithms
  auto updateAction = std::bind( &AvalancheSchedulerSvc::updateStates, this, -1, algo->name() );
  m_actionsQueue.push( updateAction );
  m_updateNeeded = false;

  if ( msgLevel( MSG::DEBUG ) )
    debug() << "[Asynchronous] Trying to handle execution result of " << index2algname( iAlgo ) << " on slot " << si
            << endmsg;
  State state;
  if ( algo->filterPassed() ) {
    state = State::EVTACCEPTED;
  } else {
    state = State::EVTREJECTED;
  }

  sc = thisSlot.algsStates.updateState( iAlgo, state );

  if ( sc.isSuccess() )
    if ( msgLevel( MSG::VERBOSE ) )
      verbose() << "[Asynchronous] Promoting " << index2algname( iAlgo ) << " on slot " << si << " to "
                << AlgsExecutionStates::stateNames[state] << endmsg;

  return sc;
}

StatusCode AvalancheSchedulerSvc::promoteToAsyncScheduled ( unsigned int  iAlgo, int  si  )

private

Definition at line 943 of file AvalancheSchedulerSvc.cpp.

{

  if ( m_IOBoundAlgosInFlight == m_maxIOBoundAlgosInFlight ) return StatusCode::FAILURE;

  // bool IOBound = m_precSvc->isBlocking(algName);

  const std::string& algName( index2algname( iAlgo ) );
  IAlgorithm* ialgoPtr = nullptr;
  StatusCode sc( m_algResourcePool->acquireAlgorithm( algName, ialgoPtr ) );

  if ( sc.isSuccess() ) { // if we managed to get an algorithm instance try to schedule it
    EventContext* eventContext( m_eventSlots[si].eventContext );
    if ( !eventContext ) {
      fatal() << "[Asynchronous] Event context for algorithm " << algName << " is a nullptr (slot " << si << ")"
              << endmsg;
      return StatusCode::FAILURE;
    }

    ++m_IOBoundAlgosInFlight;
    // Can we use tbb-based overloaded new-operator for a "custom" task (an algorithm wrapper, not derived from
    // tbb::task)? it seems it works..
    IOBoundAlgTask* theTask = new ( tbb::task::allocate_root() )
        IOBoundAlgTask( ialgoPtr, eventContext, serviceLocator(), m_algExecStateSvc );
    m_IOBoundAlgScheduler->push( *theTask );

    if ( msgLevel( MSG::DEBUG ) )
      debug() << "[Asynchronous] Algorithm " << algName << " was submitted on event " << eventContext->evt()
              << " in slot " << si << ". algorithms scheduled are " << m_IOBoundAlgosInFlight << endmsg;

    StatusCode updateSc( m_eventSlots[si].algsStates.updateState( iAlgo, AlgsExecutionStates::SCHEDULED ) );

    if ( updateSc.isSuccess() )
      if ( msgLevel( MSG::VERBOSE ) )
        verbose() << "[Asynchronous] Promoting " << index2algname( iAlgo ) << " to SCHEDULED on slot " << si << endmsg;
    return updateSc;
  } else {
    if ( msgLevel( MSG::DEBUG ) )
      debug() << "[Asynchronous] Could not acquire instance for algorithm " << index2algname( iAlgo ) << " on slot "
              << si << endmsg;
    return sc;
  }
}

StatusCode AvalancheSchedulerSvc::promoteToExecuted ( unsigned int  iAlgo, int  si, IAlgorithm *  algo, EventContext *  eventContext  )

private

The call to this method is triggered only from within the AlgoExecutionTask.

Definition at line 991 of file AvalancheSchedulerSvc.cpp.

{
  // Put back the instance
  Algorithm* castedAlgo = dynamic_cast<Algorithm*>( algo ); // DP: expose context getter in IAlgo?
  if ( !castedAlgo ) fatal() << "The casting did not succeed!" << endmsg;
  //  EventContext* eventContext = castedAlgo->getContext();

  // Check if the execution failed
  if ( m_algExecStateSvc->eventStatus( *eventContext ) != EventStatus::Success ) eventFailed( eventContext ).ignore();

  Gaudi::Hive::setCurrentContext( eventContext );
  StatusCode sc = m_algResourcePool->releaseAlgorithm( algo->name(), algo );

  if ( !sc.isSuccess() ) {
    error() << "[Event " << eventContext->evt() << ", Slot " << eventContext->slot() << "] "
            << "Instance of algorithm " << algo->name() << " could not be properly put back." << endmsg;
    return StatusCode::FAILURE;
  }

  m_algosInFlight--;

  EventSlot& thisSlot = m_eventSlots[si];

  if ( msgLevel( MSG::DEBUG ) )
    debug() << "Algorithm " << algo->name() << " executed in slot " << si << ". Algorithms scheduled are "
            << m_algosInFlight << endmsg;

  // Schedule an update of the status of the algorithms
  auto updateAction = std::bind( &AvalancheSchedulerSvc::updateStates, this, -1, algo->name() );
  m_actionsQueue.push( updateAction );
  m_updateNeeded = false;

  if ( msgLevel( MSG::DEBUG ) )
    debug() << "Trying to handle execution result of " << index2algname( iAlgo ) << " on slot " << si << endmsg;
  State state;
  if ( algo->filterPassed() ) {
    state = State::EVTACCEPTED;
  } else {
    state = State::EVTREJECTED;
  }

  sc = thisSlot.algsStates.updateState( iAlgo, state );

  if ( sc.isSuccess() )
    if ( msgLevel( MSG::VERBOSE ) )
      verbose() << "Promoting " << index2algname( iAlgo ) << " on slot " << si << " to "
                << AlgsExecutionStates::stateNames[state] << endmsg;

  return sc;
}

StatusCode AvalancheSchedulerSvc::promoteToFinished ( unsigned int  iAlgo, int  si  )

private

StatusCode AvalancheSchedulerSvc::promoteToScheduled ( unsigned int  iAlgo, int  si  )

private

Algorithm promotion.

Definition at line 881 of file AvalancheSchedulerSvc.cpp.

{

  if ( m_algosInFlight == m_maxAlgosInFlight ) return StatusCode::FAILURE;

  const std::string& algName( index2algname( iAlgo ) );
  IAlgorithm* ialgoPtr = nullptr;
  StatusCode sc( m_algResourcePool->acquireAlgorithm( algName, ialgoPtr ) );

  if ( sc.isSuccess() ) { // if we managed to get an algorithm instance try to schedule it
    EventContext* eventContext( m_eventSlots[si].eventContext );
    if ( !eventContext ) {
      fatal() << "Event context for algorithm " << algName << " is a nullptr (slot " << si << ")" << endmsg;
      return StatusCode::FAILURE;
    }

    ++m_algosInFlight;
    auto promote2ExecutedClosure = std::bind( &AvalancheSchedulerSvc::promoteToExecuted, this, iAlgo,
                                              eventContext->slot(), ialgoPtr, eventContext );
    // Avoid to use tbb if the pool size is 1 and run in this thread
    if ( -100 != m_threadPoolSize ) {

      // this parent task is needed to promote an Algorithm as EXECUTED,
      // it will be started as soon as the child task (see below) is completed
      tbb::task* triggerAlgoStateUpdate =
          new ( tbb::task::allocate_root() ) enqueueSchedulerActionTask( this, promote2ExecutedClosure );
      // setting parent's refcount to 1 is made here only for consistency
      // (in this case since it is not scheduled explicitly and there it has only one child task)
      triggerAlgoStateUpdate->set_ref_count( 1 );
      // the child task that executes an Algorithm
      tbb::task* algoTask = new ( triggerAlgoStateUpdate->allocate_child() )
          AlgoExecutionTask( ialgoPtr, eventContext, serviceLocator(), m_algExecStateSvc );
      // schedule the algoTask
      tbb::task::enqueue( *algoTask );

    } else {
      AlgoExecutionTask theTask( ialgoPtr, eventContext, serviceLocator(), m_algExecStateSvc );
      theTask.execute();
      promote2ExecutedClosure();
    }

    if ( msgLevel( MSG::DEBUG ) )
      debug() << "Algorithm " << algName << " was submitted on event " << eventContext->evt() << " in slot " << si
              << ". Algorithms scheduled are " << m_algosInFlight << endmsg;

    StatusCode updateSc( m_eventSlots[si].algsStates.updateState( iAlgo, AlgsExecutionStates::SCHEDULED ) );

    if ( msgLevel( MSG::VERBOSE ) ) dumpSchedulerState( -1 );

    if ( updateSc.isSuccess() )
      if ( msgLevel( MSG::VERBOSE ) )
        verbose() << "Promoting " << index2algname( iAlgo ) << " to SCHEDULED on slot " << si << endmsg;
    return updateSc;
  } else {
    if ( msgLevel( MSG::DEBUG ) )
      debug() << "Could not acquire instance for algorithm " << index2algname( iAlgo ) << " on slot " << si << endmsg;
    return sc;
  }
}

StatusCode AvalancheSchedulerSvc::pushNewEvent ( EventContext *  eventContext )

override

Make an event available to the scheduler.

Add event to the scheduler.

There are two cases possible: 1) No slot is free. A StatusCode::FAILURE is returned. 2) At least one slot is free. An action which resets the slot and kicks off its update is queued.

Definition at line 445 of file AvalancheSchedulerSvc.cpp.

{

  if ( m_first ) {
    m_first = false;
  }

  if ( !eventContext ) {
    fatal() << "Event context is nullptr" << endmsg;
    return StatusCode::FAILURE;
  }

  if ( m_freeSlots.load() == 0 ) {
    if ( msgLevel( MSG::DEBUG ) ) debug() << "A free processing slot could not be found." << endmsg;
    return StatusCode::FAILURE;
  }

  // no problem as push new event is only called from one thread (event loop manager)
  m_freeSlots--;

  auto action = [this, eventContext]() -> StatusCode {
    // Event processing slot forced to be the same as the wb slot
    const unsigned int thisSlotNum = eventContext->slot();
    EventSlot& thisSlot            = m_eventSlots[thisSlotNum];
    if ( !thisSlot.complete ) {
      fatal() << "The slot " << thisSlotNum << " is supposed to be a finished event but it's not" << endmsg;
      return StatusCode::FAILURE;
    }

    debug() << "Executing event " << eventContext->evt() << " on slot " << thisSlotNum << endmsg;
    thisSlot.reset( eventContext );

    // promote to CR and DR the initial set of algorithms
    Cause cs = {Cause::source::Root, "RootDecisionHub"};
    m_precSvc->iterate( thisSlot, cs );

    return this->updateStates( thisSlotNum );
  }; // end of lambda

  // Kick off the scheduling!
  if ( msgLevel( MSG::VERBOSE ) ) {
    verbose() << "Pushing the action to update the scheduler for slot " << eventContext->slot() << endmsg;
    verbose() << "Free slots available " << m_freeSlots.load() << endmsg;
  }
  m_actionsQueue.push( action );

  return StatusCode::SUCCESS;
}

StatusCode AvalancheSchedulerSvc::pushNewEvents ( std::vector< EventContext * > &  eventContexts )

override

Definition at line 495 of file AvalancheSchedulerSvc.cpp.

{
  StatusCode sc;
  for ( auto context : eventContexts ) {
    sc = pushNewEvent( context );
    if ( sc != StatusCode::SUCCESS ) return sc;
  }
  return sc;
}

StatusCode AvalancheSchedulerSvc::tryPopFinishedEvent ( EventContext *&  eventContext )

override

Try to fetch an event from the scheduler.

Try to get a finished event, if not available just return a failure.

Definition at line 551 of file AvalancheSchedulerSvc.cpp.

{
  if ( m_finishedEvents.try_pop( eventContext ) ) {
    if ( msgLevel( MSG::DEBUG ) )
      debug() << "Try Pop successful slot " << eventContext->slot() << "(event " << eventContext->evt() << ")"
              << endmsg;
    m_freeSlots++;
    return StatusCode::SUCCESS;
  }
  return StatusCode::FAILURE;
}

StatusCode AvalancheSchedulerSvc::updateStates ( int  si = -1, const std::string &  algo_name = std::string()  )

private

Loop on algorithm in the slots and promote them to successive states (-1 means all slots, while empty string means skipping an update of the Control Flow state)

Update the state of the algorithms.

The oldest events are checked before the newest, in order to reduce the event backlog. To check if the event is finished the algorithm checks if:

• No algorithms have been signed off by the control flow
• No algorithms have been signed off by the data flow
• No algorithms have been scheduled

Definition at line 614 of file AvalancheSchedulerSvc.cpp.

{

  m_updateNeeded = true;

  StatusCode global_sc( StatusCode::FAILURE, true );

  // Sort from the oldest to the newest event
  // Prepare a vector of pointers to the slots to avoid copies
  std::vector<EventSlot*> eventSlotsPtrs;

  // Consider all slots if si <0 or just one otherwise
  if ( si < 0 ) {
    const int eventsSlotsSize( m_eventSlots.size() );
    eventSlotsPtrs.reserve( eventsSlotsSize );
    for ( auto slotIt = m_eventSlots.begin(); slotIt != m_eventSlots.end(); slotIt++ ) {
      if ( !slotIt->complete ) eventSlotsPtrs.push_back( &( *slotIt ) );
    }
    std::sort( eventSlotsPtrs.begin(), eventSlotsPtrs.end(),
               []( EventSlot* a, EventSlot* b ) { return a->eventContext->evt() < b->eventContext->evt(); } );
  } else {
    eventSlotsPtrs.push_back( &m_eventSlots[si] );
  }

  for ( EventSlot* thisSlotPtr : eventSlotsPtrs ) {
    int iSlot = thisSlotPtr->eventContext->slot();

    // Cache the states of the algos to improve readability and performance
    auto& thisSlot                      = m_eventSlots[iSlot];
    AlgsExecutionStates& thisAlgsStates = thisSlot.algsStates;

    // Perform the I->CR->DR transitions
    if ( !algo_name.empty() ) {
      Cause cs = {Cause::source::Task, algo_name};
      m_precSvc->iterate( thisSlot, cs );
    }

    StatusCode partial_sc( StatusCode::FAILURE, true );

    // Perform DR->SCHEDULED
    if ( !m_optimizationMode.empty() ) {
      auto comp_nodes = [this]( const uint& i, const uint& j ) {
        return ( m_precSvc->getPriority( index2algname( i ) ) < m_precSvc->getPriority( index2algname( j ) ) );
      };
      std::priority_queue<uint, std::vector<uint>, std::function<bool( const uint&, const uint& )>> buffer(
          comp_nodes, std::vector<uint>() );
      for ( auto it = thisAlgsStates.begin( AlgsExecutionStates::State::DATAREADY );
            it != thisAlgsStates.end( AlgsExecutionStates::State::DATAREADY ); ++it )
        buffer.push( *it );
      /*std::stringstream s;
      auto buffer2 = buffer;
      while (!buffer2.empty()) {
        s << m_precSvc->getPriority(index2algname(buffer2.top())) << ", ";
        buffer2.pop();
      }
      info() << "DRBuffer is: [ " << s.str() << " ]  <--" << algo_name << " executed" << endmsg;*/

      /*while (!buffer.empty()) {
        partial_sc = promoteToScheduled(buffer.top(), iSlot);
        if (partial_sc.isFailure()) {
          if (msgLevel(MSG::VERBOSE))
            verbose() << "Could not apply transition from "
                      << AlgsExecutionStates::stateNames[AlgsExecutionStates::State::DATAREADY]
                      << " for algorithm " << index2algname(buffer.top()) << " on processing slot " << iSlot << endmsg;
          if (m_useIOBoundAlgScheduler) {
            partial_sc = promoteToAsyncScheduled(buffer.top(), iSlot);
            if (msgLevel(MSG::VERBOSE))
              if (partial_sc.isFailure())
                verbose() << "[Asynchronous] Could not apply transition from "
                          << AlgsExecutionStates::stateNames[AlgsExecutionStates::State::DATAREADY]
                          << " for algorithm " << index2algname(buffer.top()) << " on processing slot " << iSlot <<
      endmsg;
          }
        }
        buffer.pop();
      }*/
      while ( !buffer.empty() ) {
        bool IOBound                            = false;
        if ( m_useIOBoundAlgScheduler ) IOBound = m_precSvc->isBlocking( index2algname( buffer.top() ) );

        if ( !IOBound )
          partial_sc = promoteToScheduled( buffer.top(), iSlot );
        else
          partial_sc = promoteToAsyncScheduled( buffer.top(), iSlot );

        if ( msgLevel( MSG::VERBOSE ) )
          if ( partial_sc.isFailure() )
            verbose() << "Could not apply transition from "
                      << AlgsExecutionStates::stateNames[AlgsExecutionStates::State::DATAREADY] << " for algorithm "
                      << index2algname( buffer.top() ) << " on processing slot " << iSlot << endmsg;

        buffer.pop();
      }

    } else {
      for ( auto it = thisAlgsStates.begin( AlgsExecutionStates::State::DATAREADY );
            it != thisAlgsStates.end( AlgsExecutionStates::State::DATAREADY ); ++it ) {
        uint algIndex = *it;

        bool IOBound                            = false;
        if ( m_useIOBoundAlgScheduler ) IOBound = m_precSvc->isBlocking( index2algname( algIndex ) );

        if ( !IOBound )
          partial_sc = promoteToScheduled( algIndex, iSlot );
        else
          partial_sc = promoteToAsyncScheduled( algIndex, iSlot );

        if ( msgLevel( MSG::VERBOSE ) )
          if ( partial_sc.isFailure() )
            verbose() << "Could not apply transition from "
                      << AlgsExecutionStates::stateNames[AlgsExecutionStates::State::DATAREADY] << " for algorithm "
                      << index2algname( algIndex ) << " on processing slot " << iSlot << endmsg;
      }
    }

    if ( m_dumpIntraEventDynamics ) {
      std::stringstream s;
      s << algo_name << ", " << thisAlgsStates.sizeOfSubset( State::CONTROLREADY ) << ", "
        << thisAlgsStates.sizeOfSubset( State::DATAREADY ) << ", " << thisAlgsStates.sizeOfSubset( State::SCHEDULED )
        << ", " << std::chrono::high_resolution_clock::now().time_since_epoch().count() << "\n";
      auto threads = ( m_threadPoolSize != -1 ) ? std::to_string( m_threadPoolSize )
                                                : std::to_string( tbb::task_scheduler_init::default_num_threads() );
      std::ofstream myfile;
      myfile.open( "IntraEventConcurrencyDynamics_" + threads + "T.csv", std::ios::app );
      myfile << s.str();
      myfile.close();
    }

    // Not complete because this would mean that the slot is already free!
    if ( !thisSlot.complete && m_precSvc->CFRulesResolved( thisSlot ) &&
         !thisSlot.algsStates.algsPresent( AlgsExecutionStates::CONTROLREADY ) &&
         !thisSlot.algsStates.algsPresent( AlgsExecutionStates::DATAREADY ) &&
         !thisSlot.algsStates.algsPresent( AlgsExecutionStates::SCHEDULED ) ) {

      thisSlot.complete = true;
      // if the event did not fail, add it to the finished events
      // otherwise it is taken care of in the error handling already
      if ( m_algExecStateSvc->eventStatus( *thisSlot.eventContext ) == EventStatus::Success ) {
        m_finishedEvents.push( thisSlot.eventContext );
        if ( msgLevel( MSG::DEBUG ) )
          debug() << "Event " << thisSlot.eventContext->evt() << " finished (slot " << thisSlot.eventContext->slot()
                  << ")." << endmsg;
      }

      // now let's return the fully evaluated result of the control flow
      if ( msgLevel( MSG::DEBUG ) ) debug() << m_precSvc->printState( thisSlot ) << endmsg;

      thisSlot.eventContext = nullptr;
    } else {
      StatusCode eventStalledSC = isStalled( iSlot );
      if ( !eventStalledSC.isSuccess() ) {
        m_algExecStateSvc->setEventStatus( EventStatus::AlgStall, *thisSlot.eventContext );
        eventFailed( thisSlot.eventContext ).ignore();
      }
    }
  } // end loop on slots

  verbose() << "States Updated." << endmsg;

  return global_sc;
}

Member Data Documentation

tbb::concurrent_bounded_queue<action> AvalancheSchedulerSvc::m_actionsQueue

private

Queue where closures are stored and picked for execution.

Definition at line 260 of file AvalancheSchedulerSvc.h.

SmartIF<IAlgExecStateSvc> AvalancheSchedulerSvc::m_algExecStateSvc

private

Algorithm execution state manager.

Definition at line 216 of file AvalancheSchedulerSvc.h.

std::unordered_map<std::string, unsigned int> AvalancheSchedulerSvc::m_algname_index_map

private

Map to bookkeep the information necessary to the name2index conversion.

Definition at line 186 of file AvalancheSchedulerSvc.h.

std::vector<std::string> AvalancheSchedulerSvc::m_algname_vect

private

Vector to bookkeep the information necessary to the index2name conversion.

Definition at line 192 of file AvalancheSchedulerSvc.h.

unsigned int AvalancheSchedulerSvc::m_algosInFlight = 0

private

Number of algoritms presently in flight.

Definition at line 224 of file AvalancheSchedulerSvc.h.

SmartIF<IAlgResourcePool> AvalancheSchedulerSvc::m_algResourcePool

private

Cache for the algorithm resource pool.

Definition at line 252 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_checkDeps {this, "CheckDependencies", false, "Runtime check of Algorithm Data Dependencies"}

private

Definition at line 152 of file AvalancheSchedulerSvc.h.

SmartIF<ICondSvc> AvalancheSchedulerSvc::m_condSvc

private

A shortcut to service for Conditions handling.

Definition at line 219 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_dumpIntraEventDynamics

private

Initial value:

{this, "DumpIntraEventDynamics", false,
                                                 "Dump intra-event concurrency dynamics to csv file"}

Definition at line 147 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_enableCondSvc {this, "EnableConditions", false, "Enable ConditionsSvc"}

private

Definition at line 157 of file AvalancheSchedulerSvc.h.

std::vector<EventSlot> AvalancheSchedulerSvc::m_eventSlots

private

Vector of events slots.

Definition at line 204 of file AvalancheSchedulerSvc.h.

tbb::concurrent_bounded_queue<EventContext*> AvalancheSchedulerSvc::m_finishedEvents

private

Queue of finished events.

Definition at line 210 of file AvalancheSchedulerSvc.h.

bool AvalancheSchedulerSvc::m_first = true

private

Definition at line 286 of file AvalancheSchedulerSvc.h.

std::atomic_int AvalancheSchedulerSvc::m_freeSlots

private

Atomic to account for asyncronous updates by the scheduler wrt the rest.

Definition at line 207 of file AvalancheSchedulerSvc.h.

unsigned int AvalancheSchedulerSvc::m_IOBoundAlgosInFlight = 0

private

Number of algoritms presently in flight.

Definition at line 227 of file AvalancheSchedulerSvc.h.

SmartIF<IAccelerator> AvalancheSchedulerSvc::m_IOBoundAlgScheduler

private

A shortcut to IO-bound algorithm scheduler.

Definition at line 201 of file AvalancheSchedulerSvc.h.

Gaudi::Property<std::string> AvalancheSchedulerSvc::m_IOBoundAlgSchedulerSvcName {this, "IOBoundAlgSchedulerSvc", "IOBoundAlgSchedulerSvc"}

private

Definition at line 139 of file AvalancheSchedulerSvc.h.

std::atomic<ActivationState> AvalancheSchedulerSvc::m_isActive {INACTIVE}

private

Flag to track if the scheduler is active or not.

Definition at line 177 of file AvalancheSchedulerSvc.h.

size_t AvalancheSchedulerSvc::m_maxAlgosInFlight {1}

private

Definition at line 285 of file AvalancheSchedulerSvc.h.

size_t AvalancheSchedulerSvc::m_maxEventsInFlight {0}

private

Definition at line 284 of file AvalancheSchedulerSvc.h.

Gaudi::Property<unsigned int> AvalancheSchedulerSvc::m_maxIOBoundAlgosInFlight

private

Initial value:

{this, "MaxIOBoundAlgosInFlight", 0,
                                                          "Maximum number of simultaneous I/O-bound algorithms"}

Definition at line 140 of file AvalancheSchedulerSvc.h.

Gaudi::Property<std::string> AvalancheSchedulerSvc::m_optimizationMode

private

Initial value:

{this, "Optimizer", "",
                                                  "The following modes are currently available: PCE, COD, DRE,  E"}

Definition at line 145 of file AvalancheSchedulerSvc.h.

SmartIF<IPrecedenceSvc> AvalancheSchedulerSvc::m_precSvc

private

A shortcut to the Precedence Service.

Definition at line 195 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_showControlFlow

private

Initial value:

{this, "ShowControlFlow", false,
                                          "Show the configuration of all Algorithms and Sequences"}

Definition at line 165 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_showDataDeps

private

Initial value:

{this, "ShowDataDependencies", true,
                                       "Show the INPUT and OUTPUT data dependencies of Algorithms"}

Definition at line 159 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_showDataFlow

private

Initial value:

{this, "ShowDataFlow", false,
                                       "Show the configuration of DataFlow between Algorithms"}

Definition at line 162 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_simulateExecution

private

Initial value:

{
      this, "SimulateExecution", false,
      "Flag to perform single-pass simulation of execution flow before the actual execution"}

Definition at line 142 of file AvalancheSchedulerSvc.h.

std::mutex AvalancheSchedulerSvc::m_ssMut

staticprivate

Definition at line 318 of file AvalancheSchedulerSvc.h.

std::list< AvalancheSchedulerSvc::SchedulerState > AvalancheSchedulerSvc::m_sState

staticprivate

Definition at line 317 of file AvalancheSchedulerSvc.h.

std::thread AvalancheSchedulerSvc::m_thread

private

The thread in which the activate function runs.

Definition at line 180 of file AvalancheSchedulerSvc.h.

Gaudi::Property<int> AvalancheSchedulerSvc::m_threadPoolSize

private

Initial value:

{
      this, "ThreadPoolSize", -1,
      "Size of the threadpool initialised by TBB; a value of -1 gives TBB the freedom to choose"}

Definition at line 135 of file AvalancheSchedulerSvc.h.

SmartIF<IThreadPoolSvc> AvalancheSchedulerSvc::m_threadPoolSvc

private

Definition at line 283 of file AvalancheSchedulerSvc.h.

bool AvalancheSchedulerSvc::m_updateNeeded = true

private

Keep track of update actions scheduled.

Definition at line 248 of file AvalancheSchedulerSvc.h.

Gaudi::Property<std::string> AvalancheSchedulerSvc::m_useDataLoader

private

Initial value:

{this, "DataLoaderAlg", "",
                                               "Attribute unmet input dependencies to this DataLoader Algorithm"}

Definition at line 154 of file AvalancheSchedulerSvc.h.

Gaudi::Property<bool> AvalancheSchedulerSvc::m_useIOBoundAlgScheduler

private

Initial value:

{this, "PreemptiveIOBoundTasks", false,
                                                 "Turn on preemptive way of scheduling of I/O-bound algorithms"}

Definition at line 149 of file AvalancheSchedulerSvc.h.

SmartIF<IHiveWhiteBoard> AvalancheSchedulerSvc::m_whiteboard

private

A shortcut to the whiteboard.

Definition at line 198 of file AvalancheSchedulerSvc.h.

Gaudi::Property<std::string> AvalancheSchedulerSvc::m_whiteboardSvcName {this, "WhiteboardSvc", "EventDataSvc", "The whiteboard name"}

private

Definition at line 138 of file AvalancheSchedulerSvc.h.

---

The documentation for this class was generated from the following files:

• GaudiHive/src/AvalancheSchedulerSvc.h
• GaudiHive/src/AvalancheSchedulerSvc.cpp