A HTCondor central manager service implementation. More...

#include <HTCondorCentralManagerService.h>

Inheritance diagram for wrench::HTCondorCentralManagerService:

Public Member Functions
	HTCondorCentralManagerService (const std::string &hostname, double negotiator_startup_overhead, std::set< std::shared_ptr< ComputeService >> compute_services, std::map< std::string, std::string > property_list={}, std::map< std::string, double > messagepayload_list={})
	Constructor. More...

	~HTCondorCentralManagerService () override
	Destructor.

void	addComputeService (std::shared_ptr< ComputeService > compute_service)
	Add a new 'child' compute service. More...

bool	jobCanRunSomewhere (std::shared_ptr< WorkflowJob > job, std::map< std::string, std::string > service_specific_arguments)
	Helper function to check whether a job can run on at least one child compute service. More...

bool	jobKindIsSupported (const std::shared_ptr< WorkflowJob > &job, std::map< std::string, std::string > service_specific_arguments)
	Helper function to check whether a job kind is supported. More...

void	submitPilotJob (std::shared_ptr< PilotJob > job, const std::map< std::string, std::string > &service_specific_arguments) override
	Asynchronously submit a pilot job to the cloud service. More...

void	submitStandardJob (std::shared_ptr< StandardJob > job, const std::map< std::string, std::string > &service_specific_arguments) override
	Submit a standard job to the HTCondor service. More...

void	terminatePilotJob (std::shared_ptr< PilotJob > job) override
	Terminate a pilot job to the compute service. More...

void	terminateStandardJob (std::shared_ptr< StandardJob > job) override
	Terminate a standard job to the compute service (virtual) More...

Public Member Functions inherited from wrench::ComputeService
	ComputeService (const std::string &hostname, std::string service_name, std::string mailbox_name_prefix, std::string scratch_space_mount_point)
	Constructor. More...

std::map< std::string, double >	getCoreFlopRate ()
	Get the per-core flop rate of the compute service's hosts. More...

double	getFreeScratchSpaceSize ()
	Get the free space on the compute service's scratch storage space. More...

std::vector< std::string >	getHosts ()
	Get the list of the compute service's compute host. More...

std::map< std::string, double >	getMemoryCapacity ()
	Get the RAM capacities for each of the compute service's hosts. More...

unsigned long	getNumHosts ()
	Get the number of hosts that the compute service manages. More...

std::map< std::string, double >	getPerHostAvailableMemoryCapacity ()
	Get ram availability for each of the compute service's host. More...

std::map< std::string, unsigned long >	getPerHostNumCores ()
	Get core counts for each of the compute service's host. More...

std::map< std::string, unsigned long >	getPerHostNumIdleCores ()
	Get idle core counts for each of the compute service's host. More...

std::shared_ptr< StorageService >	getScratch ()
	Method that returns the computer service's scratch space's storage service. More...

unsigned long	getTotalNumCores ()
	Get the total core counts for all hosts of the compute service. More...

virtual unsigned long	getTotalNumIdleCores ()
	Get the total idle core count for all hosts of the compute service. More...

double	getTotalScratchSpaceSize ()
	Get the total capacity of the compute service's scratch storage space. More...

double	getTTL ()
	Get the time-to-live of the compute service. More...

bool	hasScratch ()
	Checks if the compute service has a scratch space. More...

virtual bool	isThereAtLeastOneHostWithIdleResources (unsigned long num_cores, double ram)
	Method to find out if, right now, the compute service has at least one host with some idle number of cores and some available RAM. More...

void	stop () override
	Stop the compute service - must be called by the stop() method of derived classes.

bool	supportsPilotJobs ()
	Get whether the compute service supports pilot jobs or not. More...

bool	supportsStandardJobs ()
	Get whether the compute service supports standard jobs or not. More...

void	terminateJob (std::shared_ptr< WorkflowJob > job)
	Terminate a previously-submitted job (which may or may not be running yet) More...

Public Member Functions inherited from wrench::Service
void	assertServiceIsUp ()
	Throws an exception if the service is not up. More...

std::string	getHostname ()
	Get the name of the host on which the service is / will be running. More...

double	getMessagePayloadValue (std::string)
	Get a message payload of the Service as a double. More...

double	getNetworkTimeoutValue ()
	Returns the service's network timeout value. More...

bool	getPropertyValueAsBoolean (std::string)
	Get a property of the Service as a boolean. More...

double	getPropertyValueAsDouble (std::string)
	Get a property of the Service as a double. More...

std::string	getPropertyValueAsString (std::string)
	Get a property of the Service as a string. More...

unsigned long	getPropertyValueAsUnsignedLong (std::string)
	Get a property of the Service as an unsigned long. More...

bool	isUp ()
	Returns true if the service is UP, false otherwise. More...

void	resume ()
	Resume the service. More...

void	setNetworkTimeoutValue (double value)
	Sets the service's network timeout value. More...

void	setStateToDown ()
	Set the state of the service to DOWN.

void	start (std::shared_ptr< Service > this_service, bool daemonize, bool auto_restart)
	Start the service. More...

void	suspend ()
	Suspend the service.

Public Member Functions inherited from wrench::S4U_Daemon
	S4U_Daemon (std::string hostname, std::string process_name_prefix, std::string mailbox_prefix)
	Constructor (daemon with a mailbox) More...

virtual	~S4U_Daemon ()

virtual void	cleanup (bool has_returned_from_main, int return_value)
	Cleanup function called when the daemon terminates (for whatever reason). The default behavior is to throw an exception if the host is off. This method should be overriden in a daemons implements some fault-tolerant behavior, or is naturally tolerant. More...

void	createLifeSaver (std::shared_ptr< S4U_Daemon > reference)
	Create a life saver for the daemon. More...

std::string	getName ()
	Retrieve the process name. More...

int	getReturnValue ()
	Returns the value returned by main() (if the daemon has returned from main) More...

S4U_Daemon::State	getState ()
	Get the daemon's state. More...

bool	hasReturnedFromMain ()
	Returns true if the daemon has returned from main() (i.e., not brutally killed) More...

bool	isDaemonized ()
	Return the daemonized status of the daemon. More...

bool	isSetToAutoRestart ()
	Return the auto-restart status of the daemon. More...

std::pair< bool, int >	join ()
	Join (i.e., wait for) the daemon. More...

void	resumeActor ()
	Resume the daemon/actor.

void	setupOnExitFunction ()
	Sets up the on_exit functionf for the actor.

void	startDaemon (bool _daemonized, bool _auto_restart)
	Start the daemon. More...

void	suspendActor ()
	Suspend the daemon/actor.

Additional Inherited Members
Public Types inherited from wrench::S4U_Daemon
enum	State { UP, DOWN, SUSPENDED }
	Daemon states. More...

Static Public Member Functions inherited from wrench::Service
static void	cleanupTrackedServices ()
	Go through the tracked services and remove all entries with a refcount of 1!

static void	clearTrackedServices ()
	Forget all tracked services.

static void	increaseNumCompletedServicesCount ()
	Increase the completed service count.

Public Attributes inherited from wrench::S4U_Daemon
std::string	hostname
	The name of the host on which the daemon is running.

std::string	initial_mailbox_name
	The initial name of the daemon's mailbox.

LifeSaver *	life_saver = nullptr
	The daemon's life saver.

std::string	mailbox_name
	The current name of the daemon's mailbox.

std::string	process_name
	The name of the daemon.

Simulation *	simulation
	a pointer to the simulation object

Static Public Attributes inherited from wrench::ComputeService
static constexpr unsigned long	ALL_CORES = ULONG_MAX
	A convenient constant to mean "use all cores of a physical host" whenever a number of cores is needed when instantiating compute services.

static constexpr double	ALL_RAM = DBL_MAX
	A convenient constant to mean "use all ram of a physical host" whenever a ram capacity is needed when instantiating compute services.

Protected Member Functions inherited from wrench::ComputeService
	ComputeService (const std::string &hostname, std::string service_name, std::string mailbox_name_prefix, std::shared_ptr< StorageService > scratch_space)
	Constructor. More...

std::shared_ptr< StorageService >	getScratchSharedPtr ()
	Get a shared pointer to the compute service's scratch storage space. More...

void	submitJob (std::shared_ptr< WorkflowJob > job, const std::map< std::string, std::string > &={})
	Submit a job to the compute service. More...

Protected Member Functions inherited from wrench::Service
	Service (std::string hostname, std::string process_name_prefix, std::string mailbox_name_prefix)
	Constructor. More...

	~Service ()
	Destructor.

template<class T >
std::shared_ptr< T >	getSharedPtr ()
	Method to retrieve the shared_ptr to a service. More...

void	serviceSanityCheck ()
	Check whether the service is properly configured and running. More...

void	setMessagePayload (std::string, double)
	Set a message payload of the Service. More...

void	setMessagePayloads (std::map< std::string, double > default_messagepayload_values, std::map< std::string, double > overriden_messagepayload_values)
	Set default and user-defined message payloads. More...

void	setProperties (std::map< std::string, std::string > default_property_values, std::map< std::string, std::string > overriden_property_values)
	Set default and user-defined properties. More...

void	setProperty (std::string, std::string)
	Set a property of the Service. More...

Protected Member Functions inherited from wrench::S4U_Daemon
void	acquireDaemonLock ()
	Lock the daemon's lock.

void	killActor ()
	Kill the daemon/actor (does nothing if already dead) More...

void	releaseDaemonLock ()
	Unlock the daemon's lock.

void	runMainMethod ()
	Method that run's the user-defined main method (that's called by the S4U actor class)

Static Protected Member Functions inherited from wrench::Service
static void	assertServiceIsUp (std::shared_ptr< Service > s)
	Assert for the service being up. More...

template<class T >
static std::shared_ptr< T >	getServiceByName (std::string name)
	Method to retrieve the shared_ptr to a service based on the service's name (not efficient) More...

Protected Attributes inherited from wrench::ComputeService
std::shared_ptr< StorageService >	scratch_space_storage_service
	A scratch storage service associated to the compute service.

Protected Attributes inherited from wrench::Service
std::map< std::string, double >	messagepayload_list
	The service's messagepayload list.

std::string	name
	The service's name.

double	network_timeout = 30.0
	The time (in seconds) after which a service that doesn't send back a reply (control) message causes a NetworkTimeOut exception. (default: 30 second; if <0 never timeout)

std::map< std::string, std::string >	property_list
	The service's property list.

Protected Attributes inherited from wrench::S4U_Daemon
unsigned int	num_starts = 0
	The number of time that this daemon has started (i.e., 1 + number of restarts)

State	state
	The service's state.

Detailed Description

A HTCondor central manager service implementation.

Constructor & Destructor Documentation

◆ HTCondorCentralManagerService()

wrench::HTCondorCentralManagerService::HTCondorCentralManagerService	(	const std::string &	hostname,
		double	negotiator_startup_overhead,
		std::set< std::shared_ptr< ComputeService >>	compute_services,
		std::map< std::string, std::string >	property_list = `{}`,
		std::map< std::string, double >	messagepayload_list = `{}`
	)

Constructor.

Parameters

hostname	the hostname on which to start the service
negotiator_startup_overhead	negotiator startup overhead
compute_services	a set of 'child' compute resources available to and via the HTCondor pool
property_list	a property list ({} means "use all defaults")
messagepayload_list	a message payload list ({} means "use all defaults")

Exceptions

std::runtime_error

Member Function Documentation

◆ addComputeService()

void wrench::HTCondorCentralManagerService::addComputeService ( std::shared_ptr< ComputeService > compute_service )

Add a new 'child' compute service.

Parameters

compute_service the compute service to add

◆ jobCanRunSomewhere()

bool wrench::HTCondorCentralManagerService::jobCanRunSomewhere	(	std::shared_ptr< WorkflowJob >	job,
		std::map< std::string, std::string >	service_specific_arguments
	)

Helper function to check whether a job can run on at least one child compute service.

Parameters

job	the job
service_specific_arguments	the service-specific argument

Returns: true or false

◆ jobKindIsSupported()

bool wrench::HTCondorCentralManagerService::jobKindIsSupported	(	const std::shared_ptr< WorkflowJob > &	job,
		std::map< std::string, std::string >	service_specific_arguments
	)

Helper function to check whether a job kind is supported.

Parameters

job	the job
service_specific_arguments	the service-specific argument

Returns: true or false

◆ submitPilotJob()

void wrench::HTCondorCentralManagerService::submitPilotJob	(	std::shared_ptr< PilotJob >	job,
		const std::map< std::string, std::string > &	service_specific_args
	)

overridevirtual

Asynchronously submit a pilot job to the cloud service.

Parameters

job	a pilot job
service_specific_args	service specific arguments

Exceptions

WorkflowExecutionException
std::runtime_error

Implements wrench::ComputeService.

◆ submitStandardJob()

void wrench::HTCondorCentralManagerService::submitStandardJob	(	std::shared_ptr< StandardJob >	job,
		const std::map< std::string, std::string > &	service_specific_args
	)

overridevirtual

Submit a standard job to the HTCondor service.

Parameters

job	a standard job
service_specific_args	service specific arguments

Exceptions

WorkflowExecutionException
std::runtime_error

Implements wrench::ComputeService.

◆ terminatePilotJob()

void wrench::HTCondorCentralManagerService::terminatePilotJob ( std::shared_ptr< PilotJob > job )

overridevirtual

Terminate a pilot job to the compute service.

Parameters

job the job

Exceptions

std::runtime_error

Implements wrench::ComputeService.

◆ terminateStandardJob()

void wrench::HTCondorCentralManagerService::terminateStandardJob ( std::shared_ptr< StandardJob > job )

overridevirtual

Terminate a standard job to the compute service (virtual)

Parameters

job the job

Exceptions

std::runtime_error

Implements wrench::ComputeService.

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

HTCondorCentralManagerService.h
HTCondorCentralManagerService.cpp

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ HTCondorCentralManagerService()

Member Function Documentation

◆ addComputeService()

◆ jobCanRunSomewhere()

◆ jobKindIsSupported()

◆ submitPilotJob()

◆ submitStandardJob()

◆ terminatePilotJob()

◆ terminateStandardJob()