A cloud-based compute service that manages a set of physical hosts and controls access to their resources by (transparently) executing jobs in VM instances.
More...
|
| CloudComputeService (const std::string &hostname, std::vector< std::string > execution_hosts, std::string scratch_space_mount_point, WRENCH_PROPERTY_COLLECTION_TYPE property_list={}, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE messagepayload_list={}) |
| Constructor. More...
|
|
| ~CloudComputeService () |
| Destructor.
|
|
virtual std::string | createVM (unsigned long num_cores, double ram_memory, std::string desired_vm_name, WRENCH_PROPERTY_COLLECTION_TYPE property_list={}, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE messagepayload_list={}) |
| Create a BareMetalComputeService VM (balances load on execution hosts) More...
|
|
virtual std::string | createVM (unsigned long num_cores, double ram_memory, WRENCH_PROPERTY_COLLECTION_TYPE property_list={}, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE messagepayload_list={}) |
| Create a BareMetalComputeService VM (balances load on execution hosts) More...
|
|
virtual void | destroyVM (const std::string &vm_name) |
| Destroy a VM. More...
|
|
std::vector< std::string > | getExecutionHosts () |
| Get the list of execution hosts available to run VMs. More...
|
|
virtual std::shared_ptr< BareMetalComputeService > | getVMComputeService (const std::string &vm_name) |
| Get the compute service running on a VM, if any. More...
|
|
virtual std::string | getVMPhysicalHostname (const std::string &vm_name) |
| Get the name of the physical host on which a VM is running. More...
|
|
virtual bool | isVMDown (const std::string &vm_name) |
| Method to check whether a VM is currently down. More...
|
|
virtual bool | isVMRunning (const std::string &vm_name) |
| Method to check whether a VM is currently running. More...
|
|
virtual bool | isVMSuspended (const std::string &vm_name) |
| Method to check whether a VM is currently running. More...
|
|
virtual void | resumeVM (const std::string &vm_name) |
| Resume a suspended VM. More...
|
|
virtual void | shutdownVM (const std::string &vm_name) |
| Shutdown an active VM. More...
|
|
virtual void | shutdownVM (const std::string &vm_name, bool send_failure_notifications, ComputeService::TerminationCause termination_cause) |
| Shutdown an active VM. More...
|
|
virtual std::shared_ptr< BareMetalComputeService > | startVM (const std::string &vm_name) |
| Start a VM. More...
|
|
void | submitCompoundJob (std::shared_ptr< CompoundJob > job, const std::map< std::string, std::string > &service_specific_args) override |
| Method to submit a compound job to the 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...
|
|
virtual void | suspendVM (const std::string &vm_name) |
| Suspend a running VM. More...
|
|
void | terminateCompoundJob (std::shared_ptr< CompoundJob > job) override |
| Method to terminate a compound job. More...
|
|
void | validateProperties () |
| Validate the service's properties. More...
|
|
| 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...
|
|
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.
|
|
| 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.
|
|
|
int | main () override |
| Main method of the daemon. More...
|
|
virtual void | processBareMetalComputeServiceTermination (std::shared_ptr< BareMetalComputeService > cs, int exit_code) |
| Process a termination by a previously started BareMetalComputeService on a VM. More...
|
|
virtual void | processCreateVM (simgrid::s4u::Mailbox *answer_mailbox, unsigned long requested_num_cores, double requested_ram, std::string desired_vm_name, WRENCH_PROPERTY_COLLECTION_TYPE property_list, WRENCH_MESSAGE_PAYLOADCOLLECTION_TYPE messagepayload_list) |
| Create a BareMetalComputeService VM on a physical machine. More...
|
|
virtual void | processDestroyVM (simgrid::s4u::Mailbox *answer_mailbox, const std::string &vm_name) |
| : Process a VM destruction request More...
|
|
virtual void | processGetExecutionHosts (simgrid::s4u::Mailbox *answer_mailbox) |
| Process a execution host list request. More...
|
|
virtual void | processGetResourceInformation (simgrid::s4u::Mailbox *answer_mailbox, const std::string &key) |
| Process a "get resource information message". More...
|
|
virtual void | processIsThereAtLeastOneHostWithAvailableResources (simgrid::s4u::Mailbox *answer_mailbox, unsigned long num_cores, double ram) |
| Process a host available resource request. More...
|
|
virtual bool | processNextMessage () |
| Wait for and react to any incoming message. More...
|
|
virtual void | processResumeVM (simgrid::s4u::Mailbox *answer_mailbox, const std::string &vm_name) |
| : Process a VM resume request More...
|
|
virtual void | processShutdownVM (simgrid::s4u::Mailbox *answer_mailbox, const std::string &vm_name, bool send_failure_notifications, ComputeService::TerminationCause termination_cause) |
| : Process a VM shutdown request More...
|
|
virtual void | processStartVM (simgrid::s4u::Mailbox *answer_mailbox, const std::string &vm_name, const std::string &pm_name) |
| : Process a VM start request by startibnng a VM on a host (using best fit for RAM first, and then for cores) More...
|
|
virtual void | processSuspendVM (simgrid::s4u::Mailbox *answer_mailbox, const std::string &vm_name) |
| : Process a VM suspend request More...
|
|
std::shared_ptr< SimulationMessage > | sendRequest (simgrid::s4u::Mailbox *answer_mailbox, ComputeServiceMessage *message) |
| Send a message request. More...
|
|
void | stopAllVMs (bool send_failure_notifications, ComputeService::TerminationCause termination_cause) |
| Terminate all VMs. More...
|
|
| 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...
|
|
virtual void | validateJobsUseOfScratch (std::map< std::string, std::string > &service_specific_args) |
| Method to validate that a job's use of the scratch space if ok. Throws exception if not. More...
|
|
virtual void | validateServiceSpecificArguments (std::shared_ptr< CompoundJob > job, std::map< std::string, std::string > &service_specific_args) |
| Method the validates service-specific arguments (throws std::invalid_argument if invalid) More...
|
|
| 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...
|
|
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)
|
|
A cloud-based compute service that manages a set of physical hosts and controls access to their resources by (transparently) executing jobs in VM instances.