Virtually Owned Computers-A New Paradigm for Distributed Operating System

Existing distributed operating systems lack two key features-predictability and choice. Predictability refers to the ability of the system to provide each user with a computing environment whose performance is independent of the behavior of other users. Choice refers to the ability of a user to select a computer system that meets that user''s specifications, needs or budget. In this paper, we introduce the virtually owned computers (VOC) paradigm that allows one to incorporate these concepts into the design of distributed operating systems. In a distributed system based on the VOC paradigm, each user is promised a given quality of service, and the system seeks to provide each user with at least that level of service. One can view the service promised to a user as a virtual computer owned by that user. Ultimately, a user should receive the promised service independent of the location where the actual execution takes place and where the user accesses the system. Different users may be promised different levels of service corresponding to different "types" of virtual computer. In order to support the VOC paradigm, many issues in the design of a distributed operating system must be reconsidered including resource management, naming, protection, and service provision. In this paper, we focus on scheduling issues. We demonstrate that existing scheduling algorithms for distributed and real time systems are not directly applicable to VOC systems and study the basic problems associated with scheduling under the VOC paradigm.

[1]  R. Chawla,et al.  The Stealth distributed scheduler , 1991, [1991] Proceedings. 11th International Conference on Distributed Computing Systems.

[2]  Ken Thompson,et al.  Plan 9 from Bell Labs , 1995 .

[3]  Banu Özden,et al.  Scalable and non-intrusive load sharing in owner-based distributed systems , 1993, Proceedings of 1993 5th IEEE Symposium on Parallel and Distributed Processing.

[4]  Fred Douglis,et al.  Transparent process migration: Design alternatives and the sprite implementation , 1991, Softw. Pract. Exp..

[5]  Michael Stumm,et al.  The design and implementation of a decentralized scheduling facility for a workstation cluster , 1988, [1988] Proceedings. 2nd IEEE Conference on Computer Workstations.

[6]  Amnon Barak,et al.  Mos: A multicomputer distributed operating system , 1985, Softw. Pract. Exp..

[7]  Krithi Ramamritham,et al.  Tutorial on hard real-time systems , 1989 .

[8]  Andrew S. Tanenbaum,et al.  Distributed operating systems , 2009, CSUR.