module Mapred_sched:Schedulersig..end
type plan_config
val configure_plan : ?keep_temp_files:bool ->
Mapred_def.mapred_job_config ->
Mapred_config.mapred_config -> plan_config configure_plan jc conf
Parameters:
keep_temp_files: if true, temporary files created during the
map/reduce execution are not immediately deletedtype plan
val create_plan : Plasma_client.plasma_cluster -> plan_config -> plan val bigblock_size : plan -> intconfigure_plan (via jc) rounded up to the next multiple of blocks.val add_inputs : plan -> unitval add_map_output : plan ->
int ->
(Mapred_tasks.file_tag * Mapred_tasks.file) list -> Unix.inet_addr -> unit
The IP addr points to the machine that executed the map or emap task
(which is also the likely storage for the files)
val plan_complete : plan -> boolval complete_inputs : plan -> unitval executable_tasks : plan -> Mapred_tasks.task listval hosts : plan -> (string * Unix.inet_addr) listval mark_as_finished : plan -> Mapred_tasks.task -> unitval mark_as_started : plan ->
Mapred_tasks.task -> Unix.inet_addr -> int -> bool -> unitval remove_marks : plan -> Mapred_tasks.task -> unitmark_as_started or mark_as_finishedval task_depends_on_list : plan -> Mapred_tasks.task -> Mapred_tasks.task listval plan_finished : plan -> boolval n_running : plan -> intval n_finished : plan -> intval n_total : plan -> intval avg_running : plan -> floatval cluster : plan -> Plasma_client.plasma_cluster val print_plan : plan -> unitval generate_svg : plan -> stringval task_stats : plan -> Mapred_tasks.task -> int * intNot_found if the task has never been started