Module Mapred_job_config

module Mapred_job_config: sig .. end

type m_job_config 

val extract_job_config : Netplex_types.config_file ->
       (string * string) list ->
       string list -> Mapred_def.mapred_job_config * m_job_config

val mapred_job_config : m_job_config -> Mapred_def.mapred_job_config

val marshal : m_job_config -> string

val unmarshal : string -> m_job_config

val update_job_config : ?name:string ->
       ?input_dir:string ->
       ?input_dir_designation:Mapred_def.designation ->
       ?output_dir:string ->
       ?work_dir:string ->
       ?log_dir:string ->
       ?task_files:string list ->
       ?bigblock_size:int ->
       ?map_tasks:int ->
       ?merge_limit:int ->
       ?split_limit:int ->
       ?partitions:int ->
       ?enhanced_mapping:int ->
       ?phases:Mapred_def.phases ->
       ?custom:(string * string) list ->
       ?map_whole_files:bool ->
       m_job_config -> m_job_config

val test_job_config : unit -> m_job_config

       netplex {
         ...
         mapredjob {
           <name> = <value>;
           ...
         }
       }
    

The possible names are the method names of Mapred_def.mapred_job_config. The values should have the right type.

Example:

       netplex {
         mapredjob {
            name = "my_job";
            input_dir = "/input";
            input_dir_designation = "deep_dir";
            output_dir = "/output";
            work_dir = "/work";
            log_dir = "/log";
            bigblock_size = 65536;
            map_tasks = 100;
            merge_limit = 4;
            split_limit = 4;
            partitions = 20;
            phases = "map_sort_reduce";
         }
       }
    

All settings have default values:

• name is set to an automatically generated name
• bigblock_size is 16M
• map_tasks is 0 (meaning a good value is computed at runtime)
• merge_limit and split_limit are 4
• partitions is 1
• phases is `Map_sort_reduce
• map_whole_files is false
• The directories are initialized to names that are guaranteed not to exist