Univa Grid Engine
8.6.7 / 5 August 2019
|Type||Grid computing Supercomputing|
|License||Proprietary commercial software|
Univa Grid Engine is a batch-queuing system, forked from Sun Grid Engine (SGE). The software schedules resources in a data center and applies policy management tools. The product can be deployed to run on-premises, using cloud computing or in a hybrid cloud environment.
The roots of Grid Engine as a commercial product date back to 1993 (under the names CODINE and later, in a variation of the product, GRD). A more comprehensive genealogy of the product is described in Sun Grid Engine. Grid Engine was first distributed by Genias Software and from 1999, after a company merger, by Gridware, Inc. In 2000, Sun Microsystems acquired Gridware. Sun renamed CODINE/GRD as Sun Grid Engine later that year, and released it as open-source in 2001.
In 2010, Oracle Corporation acquired Sun and thus renamed SGE to Oracle Grid Engine. The Oracle Grid Engine 6.2u6 source code was not included with the binaries, and changes were not put back to the project's source repository. In response to this, the Grid Engine community started the Open Grid Scheduler and the Son of Grid Engine projects to continue to develop and maintain a free implementation of Grid Engine.
On January 18, 2011, Univa announced that it had hired the principal engineers from the Sun Grid Engine team. Univa Grid Engine development is led by CTO Fritz Ferstl, who founded the Grid Engine project and ran the business within Sun/Oracle for the past 10 years.
Univa Grid Engine 8.0 was the first version, released on April 12, 2011. It was forked from SGE 6.2u5, the last open source release. It adds improved third party application integration, license and policy management, enhanced support for software and hardware platforms, and cloud management tools.
Univa Grid Engine 8.0.1 was released on October 4, 2011. It adds improved support for multi-core hardware, integration with NVIDIA GPUs, new job submission verifier extensions, and additional bug fixes.
Univa Grid Engine 8.1.0 has been announced on May 2 and has updated it to the latest release level 8.1.3 in Nov 15 2012. The 8.1.x releases deliver important new functionality such as Job Classes, PostGres Spooling, Resource Maps, Fair Urgency, deterministic Wildcard PE Selection, improved Diagnostics, pre-configured MPI integations and improved Apache Hadoop Integration  as well as many bug fixes and performance improvements.
Univa Grid Engine 8.1.6 has been announced on Oct 14, 2013. The update include improvements to the Grid Engine scheduler for larger clusters and Qmaster stability improvements for spooling and qalter commands.
Univa Grid Engine 8.2.0 was released on Sept 02, 2014. The new Univa Grid Engine version 8.2 includes native Windows support .
Univa Grid Engine 8.3.0 was released on June 22, 2015. The new Preemption feature in Univa Grid Engine 8.3.0 allows users to set priorities on different work so that, if a higher priority application must use resources currently allocated to a lower priority application, the lower priority application will effectively be “paused”—not lost—and work will automatically resume once the higher priority application is completed. Among a handful of other new features added to Grid Engine 8.3.0 to improve the overall reliability and efficiency of the cluster, is the new Run Time Modification of Resources feature. The Run Time Modification of Resources feature means much more efficient use of cluster resources.
Univa Grid Engine 8.3.1 was released on August 28, 2015. This release contained all of the new features in Univa Grid Engine 8.3.0 and additional fixes and enhancements identified since the release of 8.3.0.
Univa Grid Engine 8.5.0 was released on March 7, 2017. This release of Univa Grid Engine is 2x faster than open source Grid Engine 6.2u5. Grid Engine 8.5.0 also includes significant improvement to Docker support including mobility of GPU apps within the cluster.
8.6.0 was released on July 17, 2018. Univa Grid Engine now supports NVIDIA Docker 2.0. The new Univa Grid Engine Docker integration allows for more flexibility when running Docker containers in a Univa Grid Engine environment.
Univa Grid Engine 8.6.1 was released on August 8, 2018, providing improved control over GPU devices, and new affinity features, allowing jobs to gravitate towards, or away from, certain compute nodes.
8.6.2 was released on August 16, 2018. Univa Grid Engine performance and scalability has been improved in several key areas: network communications, job submission, memory allocation, and scheduler optimizations. This update also improved Univa Grid Engine job dispatch information.
8.6.3 was released on September 27, 2018. The new update provided bulk configuration changes for Univa Grid Engine hosts. The new bulk configuration commands perform operations on many hosts simultaneously, which makes it easier to manage a large Univa Grid Engine cluster.
8.6.4 was released on November 23, 2018, providing new core binding strategies to make it easier to distribute nodes and cores for jobs while also providing more flexibility. A new affinity-based job placement policy was included in this update. Jobs submitted using an affinity will either be packed close together with a “positive affinity” or “negative affinity” across the cluster, based on the resources requested. A new Univa Grid Engine Resource Maps can now control access to host devices such as NVIDIA GPUs. This allows jobs to request GPUs and that GPU is exclusively assigned to the job. Univa Grid Engine now also directly communicates with NVIDIA Data Center GPU Manager to collect GPU metrics for scheduling and accounting.
Univa Grid Engine 8.6.5 was released on May 6, 2019. The new key features are:
- Support for IBM Power 9 on Linux
- Many improvements to Docker support on Univa Grid Engine including supporting the latest Docker versions
- Very large cluster hostname management where IP for host is contained in the hostname
- Integration with Linux Out of Memory (OOM) Notification API ensuring that Univa Grid Engine is automatically notified of jobs that are terminated by the Linux kernel
- Improved responsiveness in heavily loaded cluster for Grid Engine administrator commands
- Performance improvements to Univa Grid Engine automatic job rescheduling
- Thread deadlock detection for Univa Grid Engine qmaster
- Updated support for NVIDIA DCGM versions up to 1.6.3
- GPU/CPU affinity can be specified as a hard or soft request
8.6.7 was released on August 5, 2019. Among the numerous enhancements, Univa Grid Engine 8.6.7 offers Red Hat Linux 8 support and NVIDIA GPU DCGM job usage.
- Job Scheduler and Batch Queuing for Clusters
- Beowulf cluster
- Maui Cluster Scheduler
- Open Source Cluster Application Resources (OSCAR)
- Slurm Workload Manager
- Univa Support and Term Software license
- Gentzsch, Wolfgang (2011-01-18). "Grid Engine Finds Safe Harbor at Univa". HPC in the Cloud. Retrieved April 17, 2011.
- Morgan, Timothy Prickett (2011-01-18). "Univa forks Oracle's Sun Grid Engine". The Register. Retrieved April 17, 2011.
- Feldman, Michael (January 18, 2011). "Univa Rescues Grid Engine From Oracle". HPCwire. Archived from the original on January 24, 2011. Retrieved April 17, 2011. Cite uses deprecated parameter
- "Gridware's resource management software increases efficiency and productivity in compute-intensive technical computing environments". Sun Microsystems. 2000-07-24.
- "Sun Microsystems makes SUN GRID ENGINE software available to open source community". Sun Microsystems. 2001-07-23.
- Open Grid Scheduler
- Son of Grid Engine
- Eadline, Ph.D., Douglas (September 1, 2010). "The State of Oracle/Sun Grid Engine". Linux Magazine. Retrieved 2011-01-18.
- Templeton, Daniel (2010-12-23). "Changes for a Bright Future at Oracle". Retrieved 2011-01-19.
- "Univa Acquires Grid Engine Expertise" (Press release). Univa. 2011-01-18. Retrieved April 17, 2011.
- "Biography of Fritz Ferstl". Univa. Retrieved April 17, 2011.
- "Univa completes acquisition of Grid Engine assets" (Press release). Univa. 2013-10-22. Retrieved October 22, 2013.
- "Univa Demonstrates Extreme Scale Automation by Deploying More Than One Million Cores in a Single Univa Grid Engine Cluster using AWS". Univa. 2018-06-24. Retrieved June 24, 2018.
- "Univa Grid Engine 8.0 Now Available" (Press release). Univa. 2011-04-12. Retrieved April 17, 2011.
- Ferstl, Fritz (2011-04-12). "Rebirth, Continuity and Expansion - Univa Grid Engine v8.0". Univa. Retrieved April 17, 2011.
- "Univa Widens Grid Engine Gap" (Press release). Univa. 2011-10-04. Retrieved January 20, 2012.
- "Univa Grid Engine Integration for Hadoop". Univa.
- univa. "New Version of Univa Grid Engine". www.univa.com. Retrieved 2016-06-13.
- "Introducing Univa Grid Engine 8.6.1: Next-Level Enterprise Grade Workload Management". blogs.univa.com. Retrieved 2018-10-23.