OpenLava Features and Roadmap

An overview of OpenLava features are listed below.

Features Benefits
Comprised of 100% open source components
  • Avoid restrictive license agreements and fees
  • Run on premises or in the cloud
  • Preserve flexibility
IBM® Platform LSFTM compatible
  • Leverage hundreds of existing integrations
  • Tap a large community of LSF expertise
  • Preserve investments in existing scripts and expertise
Fair-share scheduling
  • Allocate resources fairly according to configurable policies
  • Ensure that resource requirements are met for critical projects
Job pre-emption
  • Ensure critical jobs, users or groups get resources when they need them
  • Ensure service levels are met
  • Respect asset ownership
OpenMPI support
  • Integration through job start improves the reliability of MPI jobs
  • Prevents runaway MPI jobs/tasks
  • Provides up to date information on MPI job/task status
  • Maintains compability with future MPI versions
General purpose GPU support
  • Ensures that GPU jobs get the resources that they need
  • Leverages OpenLava ELIM facility for flexibility and future compatibility
Docker support
  • Provides resource guarantees and application isolation
  • Fast management operations
  • Application encapsulation and cloud mobility
Cloud & VM friendly auto-scaling
  • Easily add or remove nodes on the fly
  • Minimize administrator effort when changing cluster configurations
  • Quickly tap idle resources
RPM and Debian packages
  • Pre-built binaries to accelerate and simplify the deployment of OpenLava
Commercial support available from Teraproc
  • World-class cluster management expertise
  • Support from the source - leaders in the development of open source workload management
  • Clusters deployed in accordance with best practices

In addition to the features above, OpenLava provides a wealth of technical capabilities including:
  • Job arrays - for DOEs or parametric sweeps
  • Queue dispatch and run windows
  • Application license scheduling with pre-emption support
  • Exclusive scheduling
  • Interactive job support
  • Job limits per user, per queue and per host
  • Job dependencies for creating multi-step workflows
  • Mix serial and parallel jobs with workload tiling options
  • Scheduling based on dynamic machine load
  • Dynamic master selection, n-way failover
  • Plug-in authentication to enterprise data sources
  • Flexible resource requirement syntax
  • Pre-execution, post-execution and job wrapper scripts
  • Customizable job submission criteria
  • Support for popular x86 64 bit Linux distributions including RHEL, CentOS, SUSE, Debian and Ubuntu
Users can download the free installation packages from Teraproc and take advantage of:
  • Simplified installation and upgrades features
  • Pre-compiled binaries
  • Automated creation and installation of user accounts, start-up scripts and user-shell initialization scripts
  • Customization of cluster-name on installation
  • Shared file system support

OpenLava Roadmap

Please note: the roadmap below reflects our best understanding of development plans and commitments. This roadmap is subject to change.

Area Feature Status Beta availability
Scheduling Resource requirement enhancement to support multiple application license resources; e.g., availability of license A OR license B Committed to 3.1 Yes
Scheduling “Packing” and “striping” policies for scheduling of jobs among hosts to meet specific SLAs Committed to 3.1 Yes
Scheduling Intra-queue preemption Under evaluation - not in 3.1 No
Scheduling Heterogeneous resource requirement definitions; e.g., a parallel job requires 2 hosts with SSD and 10G of memory, and 3 hosts without SSD and 5G of memory under consideration No
Scheduling Ability to specify the maximum number of jobs for a newly added host in the cloud without the need to do a reconfiguration Committed to 3.1 No
Scheduling Setting of lsb_projectname environment variable for use by pre-exec Committed to 3.1 No
Scheduling Built-in metric to show the number of free slots without the need for elim Committed to 3.1 No
Installation Shared directory installation Committed to 3.1 No
License Scheduling Interact with FlexLM (commands and log files) to allocate software features based on configurable sharing policies and pre-empt licenses when required by higher priority users or groups under consideration No
Job control & management Linux cgroup integration to enforce memory usage and provide job isolation (cgroup support for memory only - not CPU) Committed to 3.1 No
Job control & management Job group support to allow management of multiple jobs as one unit under consideration No
Hardware & OS support Automatic host model detection Committed to 3.1 Yes
Hardware & OS support Built-in GPU support under consideration N/A
Hardware & OS support Xeon Phi support under consideration N/A
Hardware & OS support PowerLinux support under consideration N/A
Hardware & OS support Windows support under consideration N/A
Interfaces Support for streaming of job, user, host, resource data ( data) to enable direct input into database or a 3rd party data collector for analysis Committed to 3.1 Yes
Interfaces Web GUI job and monitoring enhancements under consideration n/a
Interfaces REST API under consideration n/a