Welcome to OAR’s documentation!¶
OAR is a versatile resource and task manager (also called a batch scheduler) for HPC clusters, and other computing infrastructures (like distributed computing experimental testbeds where versatility is a key).
OAR is suitable for production use.
OAR is also a support for scientific researches in the field of distributed computing.
See the OAR web site (http://oar.imag.fr/) for further information.
This documentation is organized into a few different sections below:
User Documentation¶
- Using OAR - Basic steps
- OAR Use Cases
- Interactive jobs
- Batch mode job
- Reservations
- Examples of resource requests
- X11 forwarding
- Using a parallel launcher: taktuk
- Using MPI with OARSH
- Tests of the CPUSET mechanism
- Using best effort mode jobs
- Testing the checkpointing trigger mechanism
- Testing the mechanism of dependency on an anterior job termination
- User commands
- Mechanisms
- How does an interactive oarsub work?
- Job launch
- CPUSET
- SSH connection key definition
- Suspend/resume
- Job deletion
- Checkpoint
- Scheduling
- Job dependencies
- User notification
- Accounting aggregator
- Dynamic nodes coupling features
- Timesharing
- Container jobs
- Besteffort jobs
- Cosystem jobs
- Deploy jobs
- Quotas
- Desktop computing
- Desktop computing
- User REST API
- FAQ - USER
Admin Documentation¶
- Installation
- Configuration file
- Admin commands
- Admin REST - API
- Security aspects
- Modules descriptions
- Internal mechanisms
- Database scheme
- accounting
- schema
- admission_rules
- event_logs
- event_log_hostnames
- files
- frag_jobs
- gantt_jobs_resources
- gantt_jobs_resources_visu
- gantt_jobs_predictions
- gantt_jobs_predictions_visu
- jobs
- job_dependencies
- moldable_job_descriptions
- job_resource_groups
- job_resource_descriptions
- job_state_logs
- job_types
- resources
- resource_logs
- assigned_resources
- queues
- challenges
- Admin FAQ
- Release policy
- What means the error “Bad configuration option: PermitLocalCommand” when I am using oarsh?
- How to manage start/stop of the nodes?
- How can I manage scheduling queues?
- How can I handle licence tokens?
- How can I handle multiple clusters with one OAR?
- How to configure a more ecological cluster (or how to make some power consumption economies)?
- How to enable jobs to connect to the frontales from the nodes using oarsh?
- A job remains in the “Finishing” state, what can I do?
- How to activate the memory management on nodes ?
Other Documentations¶
See the contribs section of OAR website: http://oar.imag.fr/wiki:contribs (and feel free to contribute !).