#include <MPIWorkPoolJobDistributor.hh>

Public Member Functions
virtual	~MPIWorkPoolJobDistributor ()
	dtor WARNING WARNING! SINGLETONS' DESTRUCTORS ARE NEVER CALLED IN MINI! DO NOT TRY TO PUT THINGS IN THIS FUNCTION! here's a nice link explaining why: http://www.research.ibm.com/designpatterns/pubs/ph-jun96.txt More...

virtual void	go (protocols::moves::MoverOP mover)
	dummy for master/slave version More...

virtual core::Size	get_new_job_id ()
	dummy for master/slave version More...

virtual void	mark_current_job_id_for_repetition ()
	dummy for master/slave version More...

virtual void	remove_bad_inputs_from_job_list ()
	dummy for master/slave version More...

virtual void	job_succeeded (core::pose::Pose &pose, core::Real run_time, std::string const &tag)
	dummy for master/slave version More...

virtual void	mpi_finalize (bool finalize)
	should the go() function call MPI_finalize()? It probably should, this is true by default. More...

Public Member Functions inherited from protocols::jd2::JobDistributor
virtual	~JobDistributor ()

void	go (protocols::moves::MoverOP mover, JobOutputterOP jo)
	invokes go, after setting JobOutputter More...

JobOP	current_job () const
	Movers may ask their controlling job distributor for information about the current job. They may also load information into this job for later output. More...

std::string	current_output_name () const
	Movers may ask their controlling job distributor for the output name as defined by the Job and JobOutputter. More...

JobOutputterOP	job_outputter () const
	Movers (or derived classes) may ask for the JobOutputter. More...

void	set_job_outputter (const JobOutputterOP &new_job_outputter)
	Movers (or derived classes) may ask for the JobOutputter. More...

JobInputterOP	job_inputter () const
	JobInputter access. More...

JobInputterInputSource::Enum	job_inputter_input_source () const
	The input source for the current JobInputter. More...

virtual void	restart ()

core::Size	total_nr_jobs () const

core::Size	current_job_id () const
	integer access - which job are we on? More...

std::string	get_current_batch () const
	what is the current batch ? — name refers to the flag-file used for this batch More...

virtual void	add_batch (std::string const &, core::Size id=0)
	add a new batch ( name will be interpreted as flag_file ) More...

core::Size	current_batch_id () const
	what is the current batch number ? — refers to position in batches_ More...

Protected Member Functions
	MPIWorkPoolJobDistributor ()
	ctor is protected; singleton pattern More...

virtual void	handle_interrupt ()
	This function got called when job is not yet finished and got termitated abnormaly (ctrl-c, kill etc). when implimenting it in subclasses make sure to delete all in-progress-data that your job spawn. More...

virtual void	master_go (protocols::moves::MoverOP mover)
	Handles the receiving of job requests and the sending of job ids to and from slaves. More...

virtual void	slave_go (protocols::moves::MoverOP mover)
	Proceeds to the parent class go_main() as usual. More...

virtual core::Size	master_get_new_job_id ()
	Always returns zero, simply increments next_job_to_assign_ to the next job that should be run based on what has been completeted and the overwrite flags. More...

virtual core::Size	slave_get_new_job_id ()
	requests, receives, and returns a new job id from the master node or returns the current job id if the repeat_job_ flag is set to true More...

virtual void	master_mark_current_job_id_for_repetition ()
	This should never be called as this is handled internally by the slave nodes, it utility_exits. More...

virtual void	slave_mark_current_job_id_for_repetition ()
	Sets the repeat_job_ flag to true. More...

virtual void	master_remove_bad_inputs_from_job_list ()
	Simply increments next_job_to_assign_ to the next job that should be run based on what has been completed and if the input job tag of the job marked as having bad input. More...

virtual void	slave_remove_bad_inputs_from_job_list ()
	Sends a message to the head node that contains the id of a job that had bad input. More...

virtual void	master_job_succeeded (core::pose::Pose &pose, std::string const &tag)
	This should never be called as this is handled internally by the slave nodes, it utility_exits. More...

virtual void	slave_job_succeeded (core::pose::Pose &pose, std::string const &tag)
	Sends a message to the head node upon successful job completion to avoid output interleaving. More...

Protected Member Functions inherited from protocols::jd2::JobDistributor
	JobDistributor ()
	Singleton instantiation pattern; Derived classes will call default ctor, but their ctors, too must be protected (and the JDFactory must be their friend.) More...

	JobDistributor (bool empty)
	MPIArchiveJobDistributor starts with an empty job-list... More...

void	go_main (protocols::moves::MoverOP mover)
	Non-virtual get-job, run it, & output loop. This function is pretty generic and your subclass may be able to use it. It is NOT virtual - this implementation can be shared by (at least) the simple FileSystemJobDistributor, the MPIWorkPoolJobDistributor, and the MPIWorkPartitionJobDistributor. Do not feel that you need to use it as-is in your class - but DO plan on implementing all its functionality! More...

Jobs const &	get_jobs () const
	Read access to private data for derived classes. More...

void	mark_job_as_completed (core::Size job_id, core::Real run_time)
	Jobs is the container of Job objects need non-const to mark Jobs as completed on Master in MPI-JobDistributor. More...

void	mark_job_as_bad (core::Size job_id)

ParserOP	parser () const
	Parser access. More...

void	begin_critical_section ()

void	end_critical_section ()

bool	obtain_new_job (bool re_consider_current_job=false)
	this function updates the current_job_id_ and current_job_ fields. The boolean return states whether or not a new job was obtained (if false, quit distributing!) More...

virtual void	job_succeeded_additional_output (core::pose::Pose &pose, std::string const &tag)
	This function is called upon a successful job completion if there are additional poses generated by the mover base implementation is just a call to the job outputter. More...

virtual void	job_failed (core::pose::Pose &, bool)
	This function is called when we give up on the job; it has been virtualized so BOINC and MPI can delay/protect output base implementation is just a call to the job outputter. More...

virtual void	current_job_finished ()
	Derived classes are allowed to clean up any temporary files or data relating to the current job after the current job has completed. Called inside go_main loop. Default implementation is a no-op. More...

virtual void	note_all_jobs_finished ()
	Derived classes are allowed to perform some kind of action when the job distributor runs out of jobs to execute. Called inside go_main. Default implementation is a no-op. More...

void	clear_current_job_output ()

void	set_batch_id (core::Size setting)
	set current_batch_id — eg for slave nodes in MPI framework More...

virtual bool	next_batch ()
	switch current_batch_id_ to next batch More...

virtual void	batch_underflow ()
	if end of batches_ reached via next_batch or set_batch_id ... More...

virtual void	load_new_batch ()
	called by next_batch() or set_batch_id() to switch-over and restart JobDistributor on new batch More...

core::Size	nr_batches () const
	how many batches are in our list ... this can change dynamically More...

std::string const &	batch (core::Size batch_id)
	give name of batch with given id More...

Protected Attributes
core::Size	npes_
	total number of processing elements More...

core::Size	rank_
	rank of the "local" instance More...

core::Size	current_job_id_
	where slave jobs store current job id More...

core::Size	next_job_to_assign_
	where master stores next job to assign (in a good state after get_new_job_id up until it's used) More...

core::Size	bad_job_id_
	where master temporarily stores id of jobs with bad input More...

bool	repeat_job_
	where slave stores whether it should repeat its current job id More...

bool	finalize_MPI_
	should the go() function call MPI_finalize? There are very few cases where this should be false More...

Friends
class	JobDistributorFactory

Additional Inherited Members
Static Public Member Functions inherited from protocols::jd2::JobDistributor
static JobDistributor *	get_instance ()
	static function to get the instance of ( pointer to) this singleton class More...

Static Protected Member Functions inherited from protocols::jd2::JobDistributor
static void	setup_system_signal_handler (void(*prev_fn)(int)=jd2_signal_handler)
	Setting up callback function that will be call when our process is about to terminate. More...

static void	remove_system_signal_handler ()
	Set signal handler back to default state. More...

static void	jd2_signal_handler (int Signal)
	Default callback function for signal handling. More...

Detailed Description

This job distributor is meant for running jobs where the machine you are using has a large number of processors, the number of jobs is much greater than the number of processors, or the runtimes of the individual jobs could vary greatly. It dedicates the head node (whichever processor gets processor rank #0) to handling job requests from the slave nodes (all nonzero ranks). Unlike the MPIWorkPartitionJobDistributor, this JD will not work at all without MPI and the implementations of all but the interface functions have been put inside of ifdef directives. Generally each function has a master and slave version, and the interface functions call one or the other depending on processor rank.

Constructor & Destructor Documentation

protocols::jd2::MPIWorkPoolJobDistributor::MPIWorkPoolJobDistributor ( )

protected

ctor is protected; singleton pattern

constructor. Notice it calls the parent class! It also builds some internal variables for determining which processor it is in MPI land.

References npes_, rank_, and utility_exit_with_message.

protocols::jd2::MPIWorkPoolJobDistributor::~MPIWorkPoolJobDistributor ( )

virtual

dtor WARNING WARNING! SINGLETONS' DESTRUCTORS ARE NEVER CALLED IN MINI! DO NOT TRY TO PUT THINGS IN THIS FUNCTION! here's a nice link explaining why: http://www.research.ibm.com/designpatterns/pubs/ph-jun96.txt

WARNING WARNING! SINGLETONS' DESTRUCTORS ARE NEVER CALLED IN MINI! DO NOT TRY TO PUT THINGS IN THIS FUNCTION! here's a nice link explaining why: http://www.research.ibm.com/designpatterns/pubs/ph-jun96.txt

Member Function Documentation

core::Size protocols::jd2::MPIWorkPoolJobDistributor::get_new_job_id ( )

virtual

dummy for master/slave version

Implements protocols::jd2::JobDistributor.

References master_get_new_job_id(), rank_, and slave_get_new_job_id().

void protocols::jd2::MPIWorkPoolJobDistributor::go ( protocols::moves::MoverOP mover )

virtual

dummy for master/slave version

Reimplemented from protocols::jd2::JobDistributor.

References finalize_MPI_, master_go(), rank_, and slave_go().

virtual void protocols::jd2::MPIWorkPoolJobDistributor::handle_interrupt ( )

inlineprotectedvirtual

This function got called when job is not yet finished and got termitated abnormaly (ctrl-c, kill etc). when implimenting it in subclasses make sure to delete all in-progress-data that your job spawn.

Implements protocols::jd2::JobDistributor.

void protocols::jd2::MPIWorkPoolJobDistributor::job_succeeded	(	core::pose::Pose &	pose,
		core::Real	run_time,
		std::string const &	tag
	)

virtual

dummy for master/slave version

Reimplemented from protocols::jd2::JobDistributor.

References master_job_succeeded(), rank_, and slave_job_succeeded().

void protocols::jd2::MPIWorkPoolJobDistributor::mark_current_job_id_for_repetition ( )

virtual

dummy for master/slave version

Implements protocols::jd2::JobDistributor.

References protocols::jd2::JobDistributor::clear_current_job_output(), master_mark_current_job_id_for_repetition(), rank_, and slave_mark_current_job_id_for_repetition().

core::Size protocols::jd2::MPIWorkPoolJobDistributor::master_get_new_job_id ( )

protectedvirtual

Always returns zero, simply increments next_job_to_assign_ to the next job that should be run based on what has been completeted and the overwrite flags.

References protocols::jd2::JobDistributor::get_jobs(), protocols::jd2::JobDistributor::job_outputter(), next_job_to_assign_, option, out::overwrite, and protocols::jd2::TR.

Referenced by get_new_job_id(), protocols::unfolded_state_energy_calculator::UnfoldedStateEnergyCalculatorMPIWorkPoolJobDistributor::master_go(), master_go(), and master_remove_bad_inputs_from_job_list().

void protocols::jd2::MPIWorkPoolJobDistributor::master_go ( protocols::moves::MoverOP mover )

protectedvirtual

Handles the receiving of job requests and the sending of job ids to and from slaves.

This is the heart of the MPIWorkPoolJobDistributor. It consists of two while loops: the job distribution loop (JDL) and the node spin down loop (NSDL). The JDL has three functions. The first is to receive and process messages from the slave nodes requesting new job ids. The second is to receive and process messages from the slave nodes indicating a bad input. The third is to receive and process job_success messages from the slave nodes and block while the slave node is writing its output. This is prevent interleaving of output in score files and silent files. The function of the NSDL is to keep the head node alive while there are still slave nodes processing. Without the NSDL if a slave node finished its allocated job after the head node had finished handing out all of the jobs and exiting (a very likely scenario), it would wait indefinitely for a response from the head node when requesting a new job id.

Reimplemented in protocols::unfolded_state_energy_calculator::UnfoldedStateEnergyCalculatorMPIWorkPoolJobDistributor.

References protocols::jd2::BAD_INPUT_TAG, bad_job_id_, protocols::jd2::JOB_SUCCESS_TAG, listener_tag_to_name(), master_get_new_job_id(), master_remove_bad_inputs_from_job_list(), MPI_ANY_SOURCE, protocols::jd2::NEW_JOB_ID_TAG, next_job_to_assign_, npes_, rank_, utility::receive_string_from_node(), protocols::jd2::REQUEST_MESSAGE_TAG, runtime_assert, utility::send_string_to_node(), protocols::jd2::TR, and utility_exit_with_message.

Referenced by go().

void protocols::jd2::MPIWorkPoolJobDistributor::master_job_succeeded	(	core::pose::Pose &	pose,
		std::string const &	tag
	)

protectedvirtual

This should never be called as this is handled internally by the slave nodes, it utility_exits.

References rank_, runtime_assert, protocols::jd2::TR, and utility_exit_with_message.

Referenced by job_succeeded().

void protocols::jd2::MPIWorkPoolJobDistributor::master_mark_current_job_id_for_repetition ( )

protectedvirtual

This should never be called as this is handled internally by the slave nodes, it utility_exits.

References rank_, runtime_assert, protocols::jd2::TR, and utility_exit_with_message.

Referenced by mark_current_job_id_for_repetition().

void protocols::jd2::MPIWorkPoolJobDistributor::master_remove_bad_inputs_from_job_list ( )

protectedvirtual

Simply increments next_job_to_assign_ to the next job that should be run based on what has been completed and if the input job tag of the job marked as having bad input.

References bad_job_id_, protocols::jd2::JobDistributor::get_jobs(), protocols::jd2::JobDistributor::job_outputter(), master_get_new_job_id(), next_job_to_assign_, rank_, runtime_assert, and protocols::jd2::TR.

Referenced by protocols::unfolded_state_energy_calculator::UnfoldedStateEnergyCalculatorMPIWorkPoolJobDistributor::master_go(), master_go(), and remove_bad_inputs_from_job_list().

void protocols::jd2::MPIWorkPoolJobDistributor::mpi_finalize ( bool finalize )

virtual

should the go() function call MPI_finalize()? It probably should, this is true by default.

Reimplemented from protocols::jd2::JobDistributor.

References finalize_MPI_.

void protocols::jd2::MPIWorkPoolJobDistributor::remove_bad_inputs_from_job_list ( )

virtual

dummy for master/slave version

Reimplemented from protocols::jd2::JobDistributor.

References master_remove_bad_inputs_from_job_list(), rank_, and slave_remove_bad_inputs_from_job_list().