USENIX 2005 Annual Technical Conference, General Track Abstract
Pp. 399402 of the Proceedings
Hyper-Threading Aware Process Scheduling Heuristics
James R. Bulpin and Ian A. Pratt, University of Cambridge Computer Laboratory
Abstract
Intel Corporation's "Hyper-Threading Technology" is the first commercial implementation of simultaneous multithreading. Hyper-Threading allows a single physical processor to execute two heavyweight threads (processes) at the same time, dynamically sharing processor resources. This dynamic sharing of resources, particularly caches, causes a wide variety of inter-thread behaviour. Threads competing for the same resource can experience a low combined throughput.
Hyper-Threads are abstracted by the hardware as logical processors. Current generation operating systems are aware of the logical-physical processor hierarchy and are able to perform simple load-balancing. However, the particular resource requirements of the individual threads are not taken into account and sub-optimal schedules can arise and remain undetected.
We present a method to incorporate knowledge of per-thread Hyper-Threading performance into a commodity scheduler through the use of hardware performance counters and the modification of dynamic priority.
- View the full text of this paper in HTML and PDF.
Until April 2006, you will need your USENIX membership identification in order to access the full papers. The Proceedings are published as a collective work, © 2005 by the USENIX Association. All Rights Reserved. Rights to individual papers remain with the author or the author's employer. Permission is granted for the noncommercial reproduction of the complete work for educational or research purposes. USENIX acknowledges all trademarks within this paper.
- If you need the latest Adobe Acrobat Reader, you can download it from Adobe's site.
|