Generalized Tardiness Bounds for Global Multiprocessor Scheduling

2009

Real-Time Syst

Self Cite

A multiprocessor scheduling scheme is presented for supporting hierarchical containers that encapsulate sporadic soft and hard real-time tasks. In this scheme, each container is allocated a specified bandwidth, which it uses to schedule its children (some of which may also be containers). This scheme is novel in that, with only soft real-time tasks, no utilization loss is incurred when provisioning containers, even in arbitrarily deep hierarchies. Presented experiments show that the proposed scheme performs well compared to conventional real-time scheduling techniques that do not provide container isolation.

Section: Window-constrained Schedulingmentioning

confidence: 99%

“…Under it, χ(T i,j , t) = d i,j for each job T i,j . In (Leontyev and Anderson, 2008a), a tardiness bound is established that applies to any window-constrained global scheduling algorithm. To state this bound, let…”

Section: Definition 5 (Window-constrained Priorities)mentioning

confidence: 99%

A hierarchical multiprocessor bandwidth reservation scheme with timing guarantees

Leontyev

2009

Real-Time Syst

Self Cite

“…Optimal variants of EDF-os can be constructed in which other algorithms are used as the secondary scheduler. All that we require is that a window-constrained [22] scheduler be used. Such a scheduler employs a per-task priority function χ i (τ i,j , t) such that for some constants φ i and…”

Section: Discussionmentioning

confidence: 99%

Optimal Semi-Partitioned Scheduling in Soft Real-Time Systems

Erickson

Devi

et al. 2015

J Sign Process Syst

Semi-partitioned real-time scheduling algorithms extend partitioned ones by allowing a (usually small) subset of tasks to migrate. The first such algorithm to be proposed was directed at soft real-time (SRT) sporadic task systems where bounded deadline tardiness is acceptable. That algorithm, called EDF-fm, is able to fully utilize the underlying hardware platform's available capacity. Moreover, it has the desirable practical property that migrations are boundary-limited, i.e., they can only occur at job boundaries. Unfortunately, EDF-fm requires restrictions on pertask utilizations, and thus is not optimal. In this paper, a new boundary-limited, semi-partitioned algorithm is presented for SRT systems that is the first such algorithm to be optimal. This algorithm, called EDF-os, is similar to EDF-fm but utilizes several new mechanisms that obviate the need for per-task utilization restrictions. Experiments presented herein show that, not only is EDF-os provably better than EDF-fm with respect to schedulability, tardiness bounds under EDF-os are often much lower as well.

“…However, such algorithms either cause jobs to experience frequent preemptions and migrations or are difficult to implement in practice. In contrast, a wide variety of global algorithms exist that are reasonable to implement and provide bounded tardiness while allowing full platform utilization [11]. Such algorithms are useful in supporting applications such as multimedia systems where limited tardiness is acceptable.…”

Section: Introductionmentioning

confidence: 99%

Reducing Tardiness under Global Scheduling by Splitting Jobs

Erickson

2013 25th Euromicro Conference on Real-Time Systems

2013

Under current analysis, tardiness bounds applicable to global earliest-deadline-first scheduling and related policies depend on per-task worst-case execution times. By splitting job budgets to create subjobs with shorter periods and worst-case execution times, such bounds can be reduced to near zero for implicit-deadline sporadic task systems. However, doing so will result in more preemptions and could create problems for synchronization protocols. This paper analyzes this tradeoff between theory and practice by presenting an overhead-aware schedulability study pertaining to job splitting. In this study, real overhead data from a scheduler implementation in LITMUS RT was factored into schedulability analysis. This study shows that despite practical issues affecting job splitting, it can still yield substantial reductions in tardiness bounds.