jobtracker

type Allocator interface {
	New(jobSessionName string, jobTrackerInitParams interface{}) (JobTracker, error)
}

type Closer interface {
	Close() error
}

type ContactStringer interface {
	Contact() (string, error)
}

type JobTemplater interface {
	JobTemplate(jobid string) (drmaa2interface.JobTemplate, error)
}

type JobTracker interface {
	// ListJobs returns all visible job IDs or an error.
	ListJobs() ([]string, error)
	// ListArrayJobs returns all job IDs an job array ID (or array job ID)
	// represents or an error.
	ListArrayJobs(arrayjobID string) ([]string, error)
	// AddJob typically submits or starts a new job at the backend. The function
	// returns the unique job ID or an error if job submission (or starting of
	// the job in case there is no queueing system) has failed.
	AddJob(jt drmaa2interface.JobTemplate) (string, error)
	// AddArrayJob makes a mass submission of jobs defined by the same job template.
	// Many HPC workload manager support job arrays for submitting 10s of thousands
	// of similar jobs by one call. The additional parameters define how many jobs
	// are submitted by defining a TASK_ID range. Begin is the first task ID (like 1),
	// end is the last task ID (like 10), step is a positive integeger which defines
	// the increments from one task ID to the next task ID (like 1). maxParallel is
	// an arguments representating an optional functionality which instructs the
	// backend to limit maxParallel tasks of this job arary to run in parallel.
	// Note, that jobs use the TASK_ID environment variable to identifiy which
	// task they are and determine that way what to do (like which data set is
	// accessed).
	AddArrayJob(jt drmaa2interface.JobTemplate, begin int, end int, step int, maxParallel int) (string, error)
	// JobState returns the DRMAA2 state and substate (free form string) of the job.
	JobState(jobID string) (drmaa2interface.JobState, string, error)
	// JobInfo returns the job status of a job in form of a JobInfo struct or an error.
	JobInfo(jobID string) (drmaa2interface.JobInfo, error)
	// JobControl sends a request to the backend to either "terminate", "suspend",
	// "resume", "hold", or "release" a job. The strings are fixed and are defined
	// by the JobControl constants. This could change in the future to be limited
	// only to constants representing the actions. When the request is not accepted
	// by the system the function must return an error.
	JobControl(jobID, action string) error
	// Wait blocks until the job is either in one of the given states, the max.
	// waiting time (specified by timeout) is reached or an other internal
	// error occured (like job was not found). In case of a timeout also an
	// error must be returned.
	Wait(jobID string, timeout time.Duration, state ...drmaa2interface.JobState) error
	// DeleteJob removes a job from a potential internal database. It does not stop
	// a job. A job must be in an endstate (terminated, failed) in order to call
	// DeleteJob. In case of an error or the job is not in an end state error must be
	// returned. If the backend does not support cleaning up resources for a finished
	// job nil should be returned.
	DeleteJob(jobID string) error
	// ListJobCategories returns a list of job categories which can be used in the
	// JobCategory field of the job template. The list is informational. An example
	// is returning a list of supported container images. AddJob() and AddArrayJob()
	// processes a JobTemplate and hence also the JobCategory field.
	ListJobCategories() ([]string, error)
}

type Monitorer interface {
	OpenMonitoringSession(name string) error
	GetAllJobIDs(filter *drmaa2interface.JobInfo) ([]string, error)
	GetAllQueueNames(filter []string) ([]string, error)
	GetAllMachines(filter []string) ([]drmaa2interface.Machine, error)
	CloseMonitoringSession(name string) error
	// JobInfoFromMonitor might collect job state and job info in a
	// different way as a JobSession with persistent storage does
	JobInfoFromMonitor(id string) (drmaa2interface.JobInfo, error)
}