Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
start [2016/02/24 21:48]
neyron
start [2018/05/27 11:59]
neyron
Line 14: Line 14:
 {{ ::​oar-logo_100px.png?​nolink|}} {{ ::​oar-logo_100px.png?​nolink|}}
   * Batch and Interactive jobs   * Batch and Interactive jobs
 +  * Advance Reservation
   * Admission rules   * Admission rules
   * Walltime   * Walltime
Line 23: Line 24:
   * Check compute nodes before launching   * Check compute nodes before launching
   * Epilogue/​Prologue scripts   * Epilogue/​Prologue scripts
-  * Activity ​visualization tools (Monika)+  * Jobs and resources ​visualization tools (Monika, Drawgantt)
   * No Daemon on compute nodes   * No Daemon on compute nodes
-  * rsh and ssh as remote execution protocols (managed by Taktuk)+  * SSH based remote execution protocols (managed by [[http://​taktuk.gforge.inria.fr|TakTuk]])
   * Dynamic insertion/​deletion of compute node   * Dynamic insertion/​deletion of compute node
   * Logging   * Logging
   * Backfilling   * Backfilling
   * First-Fit Scheduler with matching resource   * First-Fit Scheduler with matching resource
-  * Advance Reservation +  * On demand OS deployment ​support ​with [[http://​kadeploy3.gforge.inria.fr|Kadeploy3]] coupling 
-  * Environnement of Demand ​support ​(Ka-tools integration) +  * Grid computing support ​with [[http://​cigri.imag.fr|Cigri]]
-  * Grid integration ​with [[http://​cigri.imag.fr|Cigri ​system]] +
-  * Simple Desktop Computing Mode+
  
 ===== Why using OAR ===== ===== Why using OAR =====
Line 90: Line 89:
   * 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). +  * Configurable for multicore, hyperthreading and GPUs 
-  * All administration tasks are performed with the taktuk command (a large scale remote execution deployment): ​http://​taktuk.gforge.inria.fr/​. +  * Remote procedure calls using the [[http://​taktuk.gforge.inria.fr/​|TakTuk]] software: a large scale remote execution deployment tool
-  * Hierarchical resource requests (handle ​heterogeneous clusters). +  * Hierarchical resource requests (multiple/heterogeneous clusters ​support). 
-  * Gantt scheduling (so you can visualize the internal scheduler decisions).+  * Gantt scheduling (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