wrench::BatchComputeService Class Reference

A batch-scheduled compute service that manages a set of compute hosts and controls access to their resource via a batch queue. More...

#include <BatchComputeService.h>

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

Public Member Functions

 BatchComputeService (const std::string &hostname, 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...
 
std::vector< std::tuple< std::string, std::string, int, int, int, double, double > > getQueue ()
 Gets the state of the batch queue. More...
 
std::map< std::string, double > getStartTimeEstimates (std::set< std::tuple< std::string, unsigned long, unsigned long, double >> resources)
 Retrieve start time estimates for a set of job configurations. 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< 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.
 
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 ()
 
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.
 

Static Public Member Functions

static unsigned long parseUnsignedLongServiceSpecificArgument (std::string key, const std::map< std::string, std::string > &args)
 Helper function for service-specific job arguments. 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.
 

Additional Inherited Members

- Public Types inherited from wrench::S4U_Daemon
enum  State { UP, DOWN, SUSPENDED }
 Daemon states. More...
 
- 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...
 
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< 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 batch-scheduled compute service that manages a set of compute hosts and controls access to their resource via a batch queue.

In the current implementation of this service, like for many of its real-world counterparts, memory_manager_service partitioning among jobs onq the same host is not handled. When multiple jobs share hosts, which can happen when jobs require only a few cores per host and can thus be co-located on the same hosts in a non-exclusive fashion, each job simply runs as if it had access to the full RAM of each compute host it is scheduled on. The simulation of these memory_manager_service contended scenarios is thus, for now, not realistic as there is no simulation of the effects of memory_manager_service sharing (e.g., swapping).

Constructor & Destructor Documentation

◆ BatchComputeService()

wrench::BatchComputeService::BatchComputeService ( const std::string &  hostname,
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 hostname on which to start the service
compute_hoststhe list of names of the available compute hosts
  • the hosts must be homogeneous (speed, number of cores, and RAM size)
  • all cores are usable by the batch service on each host
  • all RAM is usable by the batch service on each host
scratch_space_mount_pointthe mount point of the scratch storage space for the service ("" means "no scratch space")
property_lista property list that specifies BatchComputeServiceProperty values ({} means "use all defaults")
messagepayload_lista message payload list that specifies BatchComputeServiceMessagePayload values ({} means "use all defaults")

Member Function Documentation

◆ getQueue()

std::vector< std::tuple< std::string, std::string, int, int, int, double, double > > wrench::BatchComputeService::getQueue ( )

Gets the state of the batch queue.

Returns
A vector of tuples:
  • std::string: username
  • string: job name
  • int: num hosts
  • int: num cores per host
  • int: time in seconds
  • double: submit time
  • double: start time (-1.0 if not started yet)

◆ getStartTimeEstimates()

std::map< std::string, double > wrench::BatchComputeService::getStartTimeEstimates ( std::set< std::tuple< std::string, unsigned long, unsigned long, double >>  set_of_jobs)

Retrieve start time estimates for a set of job configurations.

Parameters
set_of_jobsthe set of job configurations, each of them with an id. Each configuration is a tuple as follows:
  • a configuration id (std::string)
  • a number of hosts (unsigned long)
  • a number of cores per host (unsigned long)
  • a duration in seconds (double)
Returns
start date predictions in seconds (as a map of ids). A prediction that's negative means that the job configuration can not run on the service (e.g., not enough hosts, not enough cores per host)

◆ parseUnsignedLongServiceSpecificArgument()

unsigned long wrench::BatchComputeService::parseUnsignedLongServiceSpecificArgument ( std::string  key,
const std::map< std::string, std::string > &  args 
)
static

Helper function for service-specific job arguments.

Parameters
keythe argument key ("-N", "-c", "-t")
argsthe argument map
Returns
the value of the argument
Exceptions
std::invalid_argument

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