|
Over the last decade, clusters have become the
fastest growing platforms in high-performance computing. More recently,
Grids were emerging as next generation computing platforms for
large-scale computation and data intensive problems in industry,
academic, and government organizations. Meanwhile, an increasing number
of real-time applications running on clusters and Grids have mandatory
security requirements in addition to stringent timing constraints.
Conventional real-time scheduling algorithms developed for clusters and
Grids, however, either disregard applications’ security needs, and
thus expose the applications to security threats, or run applications at
inferior security levels without optimizing security performance. In
recognition that many applications running on clusters and Grids demand
both real-time performance and security, in this dissertation research
we investigate the problem of scheduling real-time applications with
various security requirements. First, we propose a security middleware
model (or SMW for short) from which security-sensitive real-time
applications are enabled to exploit a variety of security services to
enhance trustworthy executions of the applications. A quality of
security control manager (QSCM), a centrepiece of the SMW model, has
been designed to achieve a flexible trade-off between overheads caused
by security services and system performance. Next, we build a security
overhead model that can be used to reasonably measure security overheads
experienced by the security-sensitive applications. In light of the
security overhead model, an array of security-aware real-time scheduling
schemes have been developed by incorporating existing real-time
scheduling policies into our novel security-aware heuristics. These
security-aware scheduling schemes, which play an important role in the
QSCM module, are capable of maximizing quality of security for real-time
applications running on clusters and Grids. Comprehensive experimental
results based on synthetic traces, real-world traces, and real-world
applications show that compared with existing scheduling algorithms our
security-aware scheduling schemes significantly improve security of
clusters and computational grids while achieving consistently high
levels of schedulability.
|