|
Security-critical real-time
applications such as military aircraft flight control systems have
mandatory security requirements in addition to stringent timing
constraints. Conventional real-time scheduling algorithms, 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 demand both real-time
performance and security, we investigate the problem of scheduling a set
of independent real-time tasks with various security requirements. We
build a security overhead model that can be used to reasonably measure
security overheads incurred by the security-critical tasks. Next, we
propose a security-aware real-time heuristic strategy for clusters (SAREC),
which integrates security requirements into the scheduling for real-time
applications on clusters. Further, to evaluate the performance of SAREC,
we incorporate the earliest deadline first (EDF) scheduling policy into
SAREC to implement a novel security-aware real-time scheduling algorithm
(SAEDF). Experimental results from both real-world traces and a real
application show that SAEDF significantly improves security over three
existing scheduling algorithms (EDF, Least Laxity First, and First Come
First Serve) by up to 266.7% while achieving high schedulability.
|