wrench::BareMetalComputeService Class Reference

A compute service that manages a set of multi-core compute hosts and provides access to their resources. More...

#include <BareMetalComputeService.h>

Inheritance diagram for wrench::BareMetalComputeService:
wrench::ComputeService wrench::Service wrench::S4U_Daemon

Public Member Functions

 BareMetalComputeService (const std::string &hostname, const std::map< std::string, std::tuple< unsigned long, double >> compute_resources, std::string scratch_space_mount_point, std::map< std::string, std::string > property_list={}, std::map< std::string, double > messagepayload_list={})
 Constructor. More...
 
 BareMetalComputeService (const std::string &hostname, const std::vector< std::string > compute_hosts, std::string scratch_space_mount_point, std::map< std::string, std::string > property_list={}, std::map< std::string, double > messagepayload_list={})
 Constructor. More...
 
 ~BareMetalComputeService ()
 Destructor.
 
void submitPilotJob (PilotJob *job, std::map< std::string, std::string > &service_specific_args) override
 Asynchronously submit a pilot job to the compute service. This will raise a WorkflowExecutionException as this service does not support pilot jobs. More...
 
void submitStandardJob (StandardJob *job, std::map< std::string, std::string > &service_specific_args) override
 Submit a standard job to the compute service. More...
 
void terminatePilotJob (PilotJob *job) override
 Not implement implemented. Will throw. More...
 
void terminateStandardJob (StandardJob *job) override
 Synchronously terminate a standard job previously submitted to the compute service. 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::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< StorageServicegetScratch ()
 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...
 
void stop () override
 Stop the compute service - must be called by the stop() method of derived classes.
 
void submitJob (WorkflowJob *job, std::map< std::string, std::string >={})
 Submit a job to the compute service. More...
 
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 (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 ()
 
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.
 
Simulationsimulation
 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< StorageServicegetScratchSharedPtr ()
 Get a shared pointer to the compute service's scratch storage space. 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< StorageServicescratch_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 compute service that manages a set of multi-core compute hosts and provides access to their resources.

One can think of this as a simple service that allows the user to run tasks and to specify for each task on which host it should run and with how many cores. If no host is specified, the service will pick the least loaded host. If no number of cores is specified, the service will use as many cores as possible. The service will make sure that the RAM capacity of a host is not exceeded by possibly delaying task executions until enough RAM is available.

Constructor & Destructor Documentation

◆ BareMetalComputeService() [1/2]

wrench::BareMetalComputeService::BareMetalComputeService ( const std::string &  hostname,
const std::map< std::string, std::tuple< unsigned long, double >>  compute_resources,
std::string  scratch_space_mount_point,
std::map< std::string, std::string >  property_list = {},
std::map< std::string, double >  messagepayload_list = {} 
)

Constructor.

Parameters
hostnamethe name of the host on which the service should be started
compute_resourcesa map of <num_cores, memory> tuples, indexed by hostname, which represents the compute resources available to this service.
scratch_space_mount_pointthe compute service's scratch space's mount point ("" means none)
property_lista property list ({} means "use all defaults")
messagepayload_lista message payload list ({} means "use all defaults")

◆ BareMetalComputeService() [2/2]

wrench::BareMetalComputeService::BareMetalComputeService ( const std::string &  hostname,
const std::vector< std::string >  compute_hosts,
std::string  scratch_space_mount_point,
std::map< std::string, std::string >  property_list = {},
std::map< std::string, double >  messagepayload_list = {} 
)

Constructor.

Parameters
hostnamethe name of the host on which the service should be started
compute_hosts,:the names of the hosts available as compute resources (the service will use all the cores and all the RAM of each host)
scratch_space_mount_pointthe compute service's scratch space's mount point ("" means none)
property_lista property list ({} means "use all defaults")
messagepayload_lista message payload list ({} means "use all defaults")

Member Function Documentation

◆ submitPilotJob()

void wrench::BareMetalComputeService::submitPilotJob ( PilotJob job,
std::map< std::string, std::string > &  service_specific_args 
)
overridevirtual

Asynchronously submit a pilot job to the compute service. This will raise a WorkflowExecutionException as this service does not support pilot jobs.

Parameters
joba pilot job
service_specific_argsservice specific arguments (only {} is supported)
Exceptions
WorkflowExecutionException
std::runtime_error

Implements wrench::ComputeService.

◆ submitStandardJob()

void wrench::BareMetalComputeService::submitStandardJob ( StandardJob job,
std::map< std::string, std::string > &  service_specific_args 
)
overridevirtual

Submit a standard job to the compute service.

Parameters
joba standard job
service_specific_argsoptional service specific arguments

These arguments are provided as a map of strings, indexed by task IDs. These strings are formatted as "[hostname:][num_cores]" (e.g., "somehost:12", "somehost","6", "").

  • If a value is not provided for a task, then the service will choose a host and use as many cores as possible on that host.
  • If a "" value is provided for a task, then the service will choose a host and use as many cores as possible on that host.
  • If a "hostname" value is provided for a task, then the service will run the task on that host, using as many of its cores as possible
  • If a "num_cores" value is provided for a task, then the service will run that task with this many cores, but will choose the host on which to run it.
  • If a "hostname:num_cores" value is provided for a task, then the service will run that task with this many cores on that host.
Exceptions
WorkflowExecutionException
std::invalid_argument
std::runtime_error

Implements wrench::ComputeService.

◆ terminatePilotJob()

void wrench::BareMetalComputeService::terminatePilotJob ( PilotJob job)
overridevirtual

Not implement implemented. Will throw.

Parameters
joba pilot job to (supposedly) terminate
Exceptions
std::runtime_error

Implements wrench::ComputeService.

◆ terminateStandardJob()

void wrench::BareMetalComputeService::terminateStandardJob ( StandardJob job)
overridevirtual

Synchronously terminate a standard job previously submitted to the compute service.

Parameters
joba standard job
Exceptions
WorkflowExecutionException
std::runtime_error

Implements wrench::ComputeService.


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