An integrated storage platform for open systems should be able to meet the requirements of deterministic applications, multimedia systems, and traditional best-effort applications. It should also provide a scheduling mechanism fitting all those types of applications. In this paper, we propose a two-level hierarchical disk scheduling scheme, named 2-Q, which can guarantee deterministic deadlines, maximize the number of statistic real-time streams processed by the disk system, and minimize the average latency for best-effort requests. The upper level of the scheduling architecture, server level, is divided into three queues: deterministic, statistic, and best-effort requests. Each server may have its own scheduling algorithm. The lower level, disk driver, chooses the ready streams using its own scheduling criteria. We also propose an adaptive admission control algorithm relying on worst and average values of disk server utilization. Only streams satisfying the admission algorithm criteria are accepted for further processing by the disk server. The solution is extended to a parallel disk system by using a third hierarchical level, named meta-scheduler, briefly described in the paper. The performance evaluations demonstrate that our scheduling architecture is adequated for handling stream sets with different deterministic, statistic, or best-effort requirements.
- Disk scheduling
- Parallel I/O
ASJC Scopus subject areas
- Hardware and Architecture
- Computer Networks and Communications