Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revisionBoth sides next revision
start [2016/02/24 21:48] neyronstart [2016/02/24 22:09] – [More technical details] neyron
Line 90: Line 90:
   * scalable exploiting tool Taktuk.   * scalable exploiting tool Taktuk.
  
-It is flexible enough to be suitable to manage production HPC clusters as well as other computer infrastructures such as research testbeds like [[http://www.grid5000.fr|Grid'5000]]. +It is flexible enough to be suitable to manage large HPC clusters as well as other computer infrastructures such as research testbeds like [[http://www.grid5000.fr|Grid'5000]]. 
  
-OAR advantages:+Features:
  
-  * No specific daemon on nodes. +  * Only need a SSH daemon on nodes. 
-  * No dependence on specific computing libraries like MPI. We support all sort of parallel user applications. +  * No tied to any specific libraries such as MPI. OAR supports any sort of parallel user applications. 
-  * Upgrades are made on the servers, nothing to do on computing nodes. +  * Cpuset/cgroup integration to restricts jobs to assigned resources (corememory bench
-  * CPUSET (2.6 linux kernel) integration which restricts the jobs on assigned resources (also useful to clean completely a jobeven parallel jobs). +  * Remote procedure calls using the [[http://taktuk.gforge.inria.fr/|TakTuk]] software: a large scale remote execution deployment tool
-  * All administration tasks are performed with the taktuk command (a large scale remote execution deployment): http://taktuk.gforge.inria.fr/+  * Hierarchical resource requests (multiple/heterogeneous clusters support). 
-  * Hierarchical resource requests (handle heterogeneous clusters). +  * Gantt scheduling (can visualize the internal scheduler decisions).
-  * Gantt scheduling (so you can visualize the internal scheduler decisions).+
   * Full or partial time-sharing.   * Full or partial time-sharing.
   * Checkpoint/resubmit.   * Checkpoint/resubmit.
-  * Licences servers management support+  * Support for software licenses servers (license tokens)
-  * Best effort jobs : if another job wants the same resources then it is deleted automatically (useful to execute programs like SETI@home)+  * Best effort jobs: such a job is stopped automatically as soon as another job requires the resources. 
-  * Environment deployment support (Kadeploy): http://kadeploy3.gforge.inria.fr/. +  * Special job types: 
- +    * deploy: support for in job OS deployment with software such as [[http://kadeploy3.gforge.inria.fr|Kadeploy]] 
-Other more common features+    * cosystem: support for a delegation to another job and resource management system 
- +    * noopreservation only jobs (no execution) 
-  * Batch and Interactive jobs. +    * placeholder, container: meta jobs   
-  * Admission rules. +  * Batch and Interactive jobs 
-  * Walltime.+  * Advance reservations 
 +  * Admission rules 
 +  * Job walltime
   * Multi-schedulers support.   * Multi-schedulers support.
-  * Multi-queues with priority+  * Multi-queues with priority 
-  * Backfilling. +  * First-Fit Scheduler with conservative backfilling 
-  * First-Fit Scheduler. +  * Moldable tasks.
-  * Reservation. +
-  * Support of moldable tasks+
-  * Check compute nodes.+
   * Epilogue/Prologue scripts.   * Epilogue/Prologue scripts.
-  * Support of dynamic nodes.+  * Dynamic resources definition
   * Logging/Accounting.   * Logging/Accounting.
   * Suspend/resume jobs.   * Suspend/resume jobs.
  
start.txt · Last modified: 2018/05/27 11:59 by neyron
Recent changes RSS feed GNU Free Documentation License 1.3 Donate Powered by PHP Valid XHTML 1.0 Valid CSS Driven by DokuWiki