Changes between Version 67 and Version 68 of ProjectOptions


Ignore:
Timestamp:
Jun 1, 2008, 3:05:10 PM (16 years ago)
Author:
davea
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • ProjectOptions

    v67 v68  
    1212}}}
    1313
    14 == Scheduling: limiting work distribution ==
     14== Scheduling: general ==
    1515
    1616{{{
     
    6363}}}
    6464If set, [AppFiltering user application selection] applies to [BetaTest beta test applications] as well as others.
    65 
    66 == Scheduling: array-based scheduling ==
    6765{{{
    6866<nowork_skip> 0|1 </nowork_skip>
    6967}}}
    7068If the scheduling server has no work, it replies to RPCs without doing any database access (e.g., without looking up the user or host record). This reduces DB load, but it fails to update preferences when users click on Update. Use it if your server DB is overloaded.
     69
     70== Scheduling: job-cache scheduling ==
     71
     72This is the default.
     73The feeder (a daemon program) maintains a cache of jobs in shared memory.
     74Instances of the scheduler get jobs from this cache,
     75reducing their database access overhead.
     76
    7177{{{
    7278<shmem_work_items>N</shmem_work_items>
    7379}}}
    74 The size of the shared-memory array of jobs.  Default is 100.
     80The size of the job cache.  Default is 100 jobs.
    7581{{{
    7682<feeder_query_size>N</feeder_query_size>
     
    96102Results with priority at least 'reliable_on_priority' will be sent only to reliable hosts; increase priority of duplicate results by 'reliable_priority_on_over'; increase priority of duplicates caused by timeout (not error) by 'reliable_priority_on_over_except_error'.
    97103
     104== Scheduling: matchmaker scheduling ==
     105
     106This is a variant of job-cache scheduling.
     107The job selection policy is determined by a "score function";
     108this highest-scoring jobs are sent to the client.
     109
     110{{{
     111<matchmaker>0|1</matchmaker>
     112}}}
     113If set, enable matchmaker scheduling.
     114{{{
     115<mm_min_slots>N</mm_min_slots>
     116<mm_max_slots>N</mm_max_slots>
     117}}}
     118Specify the min and max number of jobs to scan for a given client request.
     119Defaults are 20 and 50.
     120{{{
     121<job_size_matching>0|1</job_size_matching>
     122}}}
     123If set, include a term in the score function that
     124favors sending large jobs to fast hosts.
     125To use this, you must run the census program as a periodic task
     126to maintain statistics on the distribution of host speeds.
    98127
    99128== Scheduling: locality scheduling ==