Title :
Resource policing to support fine-grain cycle stealing in networks of workstations
Author :
Ryu, Kyung Dong ; Hollingsworth, Jeffrey K.
Author_Institution :
Dept. of Comput. Sci. & Eng., Arizona State Univ., Tempe, AZ, USA
Abstract :
We present the design, implementation, and performance evaluation of a suite of resource policing mechanisms that allow guest processes to efficiently and unobtrusively exploit otherwise idle workstation resources. Unlike traditional policies that harvest cycles only from unused machines, we employ fine-grained cycle stealing to exploit resources even from machines that have active users. We developed a suite of kernel extensions that enable these policies to operate without significantly impacting host processes: 1) a new starvation-level CPU priority for guest jobs, 2) a new page replacement policy that imposes hard bounds on physical memory usage by guest processes, and 3) a new I/O scheduling mechanism called rate windows that throttle guest processes´ usage of I/O and network bandwidth. We evaluate both the individual impacts of each mechanism, and their utility for our fine-grain cycle stealing.
Keywords :
grid computing; performance evaluation; processor scheduling; resource allocation; workstation clusters; I/O scheduling; cluster computing; cycle stealing; grid computing; network bandwidth; page replacement policy; parallel computing; resource scheduling; starvation-level CPU priority; workstation clusters; workstation resources; Application software; Bandwidth; Computer Society; Computer networks; Concurrent computing; Grid computing; Intelligent networks; Kernel; Processor scheduling; Workstations; 65; Grid computing; cluster computing; cycle stealing.; networks of workstations; parallel computing; resource scheduling;
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
DOI :
10.1109/TPDS.2004.58