A workload management framework compute service. More...

#include <HTCondorComputeService.h>

Inheritance diagram for wrench::HTCondorComputeService:

Public Member Functions
	HTCondorComputeService (const std::string &hostname, std::set< std::shared_ptr< ComputeService >> compute_services, WRENCH_PROPERTY_COLLECTION_TYPE property_list={}, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE messagepayload_list={})
	Constructor. More...

	~HTCondorComputeService () override
	Destructor.

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

std::shared_ptr< StorageService >	getLocalStorageService () const
	Get the service's local storage service. More...

void	setLocalStorageService (std::shared_ptr< StorageService > local_storage_service)
	Set the service's local storage service. More...

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

virtual bool	supportsCompoundJobs () override
	Returns true if the service supports compound jobs. More...

virtual bool	supportsPilotJobs () override
	Returns true if the service supports pilot jobs. More...

virtual bool	supportsStandardJobs () override
	Returns true if the service supports standard jobs. More...

void	terminateCompoundJob (std::shared_ptr< CompoundJob > job) override
	Method to terminate a compound job. More...

void	validateJobsUseOfScratch (std::map< std::string, std::string > &service_specific_args) override
	Determine whether compute service has scratch. More...

void	validateServiceSpecificArguments (std::shared_ptr< CompoundJob > compound_job, std::map< std::string, std::string > &service_specific_args) override
	Method the validates service-specific arguments (throws std::invalid_argument if invalid) More...

Public Member Functions inherited from wrench::ComputeService
	ComputeService (const std::string &hostname, std::string service_name, 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 ()
	Get the compute service's scratch storage space. 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. Note that this doesn't mean that asking for these cores right will mean immediate execution (since jobs may be pending and "ahead" in the queue, e.g., because they depend on current actions that are not using all available resources). 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...

virtual bool	hasScratch () const
	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. Note that this doesn't mean that asking for these resources right will mean immediate execution (since jobs may be pending and "ahead" in the queue, e.g., because they depend on current actions that are not using all available resources). More...

void	stop () override
	Stop the compute service.

virtual void	stop (bool send_failure_notifications, ComputeService::TerminationCause termination_cause)
	Stop the compute service. More...

void	terminateJob (std::shared_ptr< CompoundJob > 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...

const WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE &	getMessagePayloadList () const
	Get all message payloads and their values of the Service. More...

double	getMessagePayloadValue (WRENCH_MESSAGEPAYLOAD_TYPE)
	Get a message payload of the Service as a double. More...

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

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

bool	getPropertyValueAsBoolean (WRENCH_PROPERTY_TYPE)
	Get a property of the Service as a boolean. More...

double	getPropertyValueAsDouble (WRENCH_PROPERTY_TYPE)
	Get a property of the Service as a double. More...

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

unsigned long	getPropertyValueAsUnsignedLong (WRENCH_PROPERTY_TYPE)
	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)
	Constructor (daemon with a mailbox) More...

void	acquireDaemonLock ()
	Method to acquire the daemon's lock. More...

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...

Simulation *	getSimulation ()
	Get the service's simulation. 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	releaseDaemonLock ()
	Method to release the daemon's lock. More...

void	resumeActor ()
	Resume the daemon/actor.

void	setSimulation (Simulation *simulation)
	Set the service's simulation. More...

void	setupOnExitFunction ()
	Sets up the on_exit function 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::ComputeService
enum	TerminationCause { TERMINATION_NONE, TERMINATION_COMPUTE_SERVICE_TERMINATED, TERMINATION_JOB_KILLED, TERMINATION_JOB_TIMEOUT }
	Job termination cause enum.

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

Static Public Member Functions inherited from wrench::S4U_Daemon
static simgrid::s4u::Mailbox *	getRunningActorRecvMailbox ()
	Return the running actor's recv mailbox. More...

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

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

simgrid::s4u::Mailbox *	mailbox
	The daemon's mailbox.

std::string	process_name
	The name of the daemon.

simgrid::s4u::Mailbox *	recv_mailbox
	The daemon's receive mailbox (to send to another daemon so that that daemon can reply)

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.

Static Public Attributes inherited from wrench::S4U_Daemon
static std::unordered_map< aid_t, simgrid::s4u::Mailbox * >	map_actor_to_recv_mailbox

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

	~Service () override
	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 (WRENCH_MESSAGEPAYLOAD_TYPE, double)
	Set a message payload of the Service. More...

void	setMessagePayloads (WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE default_messagepayload_values, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE overriden_messagepayload_values)
	Set default and user-defined message payloads. More...

void	setProperties (WRENCH_PROPERTY_COLLECTION_TYPE default_property_values, WRENCH_PROPERTY_COLLECTION_TYPE overriden_property_values)
	Set default and user-defined properties. More...

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

Protected Member Functions inherited from wrench::S4U_Daemon
bool	killActor ()
	Kill the daemon/actor (does nothing if already dead) More...

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...

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
WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE	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)

WRENCH_PROPERTY_COLLECTION_TYPE	property_list
	The service's property list.

bool	shutting_down = false
	A boolean that indicates if the service is in the middle of shutting down.

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)

Simulation *	simulation
	a pointer to the simulation object

State	state
	The service's state.

Detailed Description

A workload management framework compute service.

Constructor & Destructor Documentation

◆ HTCondorComputeService()

wrench::HTCondorComputeService::HTCondorComputeService	(	const std::string &	hostname,
		std::set< std::shared_ptr< ComputeService >>	compute_services,
		WRENCH_PROPERTY_COLLECTION_TYPE	property_list = `{}`,
		WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE	messagepayload_list = `{}`
	)

Constructor.

Parameters

hostname	the name of the host on which to start the service
compute_services	a set of 'child' compute services that have been added to the simulation and that are available to and usable through the HTCondor pool. BatchComputeService instances will be used for Condor jobs in the "grid" universe BareMetalComputeService instances will be used for Condor jobs not in the "grid" universe other types of compute services are disallowed
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::HTCondorComputeService::addComputeService ( std::shared_ptr< ComputeService > compute_service )

Add a new 'child' compute service.

Parameters

compute_service the compute service to add

◆ getLocalStorageService()

std::shared_ptr< StorageService > wrench::HTCondorComputeService::getLocalStorageService ( ) const

Get the service's local storage service.

Returns: the local storage service object

◆ setLocalStorageService()

void wrench::HTCondorComputeService::setLocalStorageService ( std::shared_ptr< StorageService > local_storage_service )

Set the service's local storage service.

Parameters

local_storage_service a storage service

◆ submitCompoundJob()

void wrench::HTCondorComputeService::submitCompoundJob	(	std::shared_ptr< CompoundJob >	job,
		const std::map< std::string, std::string > &	service_specific_args
	)

overridevirtual

Submit a compound job to the HTCondor service.

Parameters

job	a compound job
service_specific_args	service specific arguments

Exceptions

ExecutionException
std::runtime_error

Implements wrench::ComputeService.

◆ supportsCompoundJobs()

bool wrench::HTCondorComputeService::supportsCompoundJobs ( )

overridevirtual

Returns true if the service supports compound jobs.

Returns: true or false

Implements wrench::ComputeService.

◆ supportsPilotJobs()

bool wrench::HTCondorComputeService::supportsPilotJobs ( )

overridevirtual

Returns true if the service supports pilot jobs.

Returns: true or false

Implements wrench::ComputeService.

◆ supportsStandardJobs()

bool wrench::HTCondorComputeService::supportsStandardJobs ( )

overridevirtual

Returns true if the service supports standard jobs.

Returns: true or false

Implements wrench::ComputeService.

◆ terminateCompoundJob()

void wrench::HTCondorComputeService::terminateCompoundJob ( std::shared_ptr< CompoundJob > job )

inlineoverridevirtual

Method to terminate a compound job.

Parameters

job	the standard job

Implements wrench::ComputeService.

◆ validateJobsUseOfScratch()

void wrench::HTCondorComputeService::validateJobsUseOfScratch ( std::map< std::string, std::string > & service_specific_args )

overridevirtual

Determine whether compute service has scratch.

Parameters

service_specific_args the service-specific arguments (useful for some services)

Reimplemented from wrench::ComputeService.

◆ validateServiceSpecificArguments()

void wrench::HTCondorComputeService::validateServiceSpecificArguments	(	std::shared_ptr< CompoundJob >	job,
		std::map< std::string, std::string > &	service_specific_args
	)

overridevirtual

Method the validates service-specific arguments (throws std::invalid_argument if invalid)

Parameters

job	the job that's being submitted
service_specific_args	the service-specific arguments

Reimplemented from wrench::ComputeService.

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

HTCondorComputeService.h
HTCondorComputeService.cpp

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ HTCondorComputeService()

Member Function Documentation

◆ addComputeService()

◆ getLocalStorageService()

◆ setLocalStorageService()

◆ submitCompoundJob()

◆ supportsCompoundJobs()

◆ supportsPilotJobs()

◆ supportsStandardJobs()

◆ terminateCompoundJob()

◆ validateJobsUseOfScratch()

◆ validateServiceSpecificArguments()