An Evolutionary Meta Hierarchical Scheduler for the Linux Operating System

The need for supporting CSCW applications with heterogeneous and varying user requirements calls for adaptive and reconfigurable schedulers accommodating a mixture of real-time, proportional share, fixed priority and other policies, thus overcoming frustrating processor bottlenecks. In this paper we try to overcome this anomaly by proposing an evolutionary strategy for a Meta Hierarchical Scheduler (MHS) in which a user is actively involved in the design cycle of a scheduler. Our framework analyzes user requirements by formulating an Abstract Scheduler Model (ASM) for an optimum scheduler with the help of an evolutionary algorithm that satisfies the needs. Finally a C source code for this MHS is generated for the Linux kernel. Our experimental results demonstrate that our MHS enhances through the evolutionary approach, the user satisfaction level by a factor of two as compared to the satisfaction level achieved by the standard Linux scheduler. 1 The Evolutionary Algorithm in SAADI The emergence of the Internet market toward the end of the last century has revolutionized the traditional use of PC. Nowadays a user in a CSCW environment attends a multimedia business meeting, take notes for minutes of the meetings and reads/sends important documents at the same time. In CSCW applications the processor usage pattern becomes frequently unpredictable because of changing user needs. Conflicting but coexisting scheduling requirements make it an uphill and difficult task to create a generic scheduler that could easily, efficiently if not optimally, adapt to the user needs in collaborating communities. In SAADI framework we incorporate the user needs in the design cycle of a scheduler [2]. By using the constructs of SAADI-SDL, a scheduler description language, a user could specify the processing requirements of different applications and of their relative importance. Currently, the schedulable application set consists of single/multi-threaded batch, periodic (multimedia and network applications) and interactive applications. Our ASM module parses SAADI-SDL file and analyzes the requirements to generate scheduler individuals for the first generation of our evolutionary algorithm with the help of a context-free grammar. Figure 1 shows the complete design workflow in our SAADI framework. A scheduler individual consists of a hierarchical organization of simple schedulers as proposed by Regehr [1]. K. Deb et al. (Eds.): GECCO 2004, LNCS 3103, pp. 1334–1335, 2004. c © Springer-Verlag Berlin Heidelberg 2004 An Evolutionary Meta Hierarchical Scheduler 1335 previous best hierarchy schedulers k:=0