User-Level Communication in a System with Gang Scheduling
نویسندگان
چکیده
One of the scarce resources that limits communication performance is buffer space on the network interface card. This becomes even worse when it is partitioned among several time-sliced processes. However, if gang scheduling is used, it is possible to swap buffer contents as part of the context switch, giving each job the full buffer space for the duration of its quantum. This does not suffer undue overhead, as the buffer space is mainly used to allow a larger flow-control window, and typically does not contain many packets that need to be stored.
منابع مشابه
Network Interface Sharing with an Experimental Gang Scheduler on Cenju-3/de
We have implemented an experimental gang sched-uler on Cenju-3/DEE1] in order to investigate ef-cient scheduling schemes for multiple user environment with high performance communication on parallel machines. The Cenju-3/DE system provides user-level inter-processor communication mechanisms for a single user. It realizes high performance communication, but cannot be shared among multiple users....
متن کاملOverhead Analysis of Preemptive Gang Scheduling
A preemptive gang scheduler is developed and evaluated. The gang scheduler, called SCoreD , is implemented on top of a UNIX operating system and runs on workstation and PC clusters connected by Myrinet, a giga-bit class, high-performance network. To have high-performance communication at the user-level and a multiuser environment simultaneously, we propose network preemption to save and restore...
متن کاملOverhead Analysis of Preemptive
A preemptive gang scheduler is developed and evaluated. The gang scheduler, called SCoreD , is implemented on top of a UNIX operating system and runs on workstation and PC clusters connected by Myrinet, a giga-bit class, high-performance network. To have high-performance communication at the user-level and a multiuser environment simultaneously, we propose network preemption to save and restore...
متن کاملGang Scheduling with Lightweight User-Level Communication
In this paper, we explore the performance of gang scheduling on a cluster using the Quadrics interconnection network. In such a cluster, the scheduler can take advantage of this network’s unique capabilities, including a network interface card-based processor and memory and efficient user-level communication libraries. We developed a micro-benchmark to test the scheduler’s performance under var...
متن کاملEvaluation of Design Choices for Gang Scheduling Using Distributed Hierarchical Control
several other experimental systems [13, 39, 4, 17, 6]. At first blush, it might appear that gang scheduling is a luxury that may not be worth the price. An optimal packing of gangs that gives minimal wasted processors is an NPcomplete problem. Migration of gangs might be required to compensate for a poor initial mapping. The code to simultaneously schedule all the threads of each gang might be ...
متن کامل