The roman conquered by delay: reducing the number of preemptions using sleep states

Sleep-states are emerging as a first-class design choice in energy minimization. A side effect of this is that the release behavior of the system is affected and subsequently the preemption relations between tasks. In a first step we have investigated how the behavior in terms of number of preemptions of tasks in the system is changed at runtime, using an existing procrastination approach, which utilizes sleepstates for energy savings purposes. Our solution resulted in substantial savings of preemptions and we expect from even higher yields for alternative energy saving algorithms. This work is intended to form the base of future research, which aims to bound the number of preemptions at analysis time and subsequently how this may be employed in the analysis to reduced the amount of system utilization, which is reserved to account for the preemption delay.

Sporadic multiprocessor scheduling with few preemptions

Consider the problem of scheduling n sporadic tasks so as to meet deadlines on m identical processors. A task is characterised by its minimum interarrival time and its worst-case execution time. Tasks are preemptible and may migrate between processors. We propose an algorithm with limited migration, configurable for a utilisation bound of 88% with few preemptions (and arbitrarily close to 100% with more preemptions).

Multiprocessor scheduling with few preemptions

Consider the problem of scheduling a set of periodically arriving tasks on a multiprocessor with the goal of meeting deadlines. Processors are identical and have the same speed. Tasks can be preempted and they can migrate between processors. We propose an algorithm with a utilization bound of 66% and with few preemptions. It can trade a higher utilization bound for more preemption and in doing so it has a utilization bound of 100%.

Preemption delay analysis for floating non-preemptive region scheduling

In real-time systems, there are two distinct trends for scheduling task sets on unicore systems: non-preemptive and preemptive scheduling. Non-preemptive scheduling is obviously not subject to any preemption delay but its schedulability may be quite poor, whereas fully preemptive scheduling is subject to preemption delay, but benefits from a higher flexibility in the scheduling decisions. The time-delay involved by task preemptions is a major source of pessimism in the analysis of the task Worst-Case Execution Time (WCET) in real-time systems. Preemptive scheduling policies including non-preemptive regions are a hybrid solution between non-preemptive and fully preemptive scheduling paradigms, which enables to conjugate both world's benefits. In this paper, we exploit the connection between the progression of a task in its operations, and the knowledge of the preemption delays as a function of its progression. The pessimism in the preemption delay estimation is then reduced in comparison to state of the art methods, due to the increase in information available in the analysis.

Preemption-light multiprocessor scheduling of sporadic tasks with high utilisation bound

Known algorithms capable of scheduling implicit-deadline sporadic tasks over identical processors at up to 100% utilisation invariably involve numerous preemptions and migrations. To the challenge of devising a scheduling scheme with as few preemptions and migrations as possible, for a given guaranteed utilisation bound, we respond with the algorithm NPS-F. It is configurable with a parameter, trading off guaranteed schedulable utilisation (up to 100%) vs preemptions. For any possible configuration, NPS-F introduces fewer preemptions than any other known algorithm matching its utilisation bound. A clustered variant of the algorithm, for systems made of multicore chips, eliminates (costly) off-chip task migrations, by dividing processors into disjoint clusters, formed by cores on the same chip (with the cluster size being a parameter). Clusters are independently scheduled (each, using non-clustered NPS-F). The utilisation bound is only moderately affected. We also formulate an important extension (applicable to both clustered and non-clustered NPS-F) which optimises the supply of processing time to executing tasks and makes it more granular. This reduces processing capacity requirements for schedulability without increasing preemptions.

Extending fixed task-priority schedulability by interference limitation

While the earliest deadline first algorithm is known to be optimal as a uniprocessor scheduling policy, the implementation comes at a cost in terms of complexity. Fixed taskpriority algorithms on the other hand have lower complexity but higher likelihood of task sets being declared unschedulable, when compared to earliest deadline first (EDF). Various attempts have been undertaken to increase the chances of proving a task set schedulable with similar low complexity. In some cases, this was achieved by modifying applications to limit preemptions, at the cost of flexibility. In this work, we explore several variants of a concept to limit interference by locking down the ready queue at certain instances. The aim is to increase the prospects of schedulability of a given task system, without compromising on complexity or flexibility, when compared to the regular fixed task-priority algorithm. As a final contribution, a new preemption threshold assignment algorithm is provided which is less complex and more straightforward than the previous method available in the literature.

Job phasing aware preemption deferral

Preemptions account for a non-negligible overhead during system execution. There has been substantial amount of research on estimating the delay incurred due to the loss of working sets in the processor state (caches, registers, TLBs) and some on avoiding preemptions, or limiting the preemption cost. We present an algorithm to reduce preemptions by further delaying the start of execution of high priority tasks in fixed priority scheduling. Our approaches take advantage of the floating non-preemptive regions model and exploit the fact that, during the schedule, the relative task phasing will differ from the worst-case scenario in terms of admissible preemption deferral. Furthermore, approximations to reduce the complexity of the proposed approach are presented. Substantial set of experiments demonstrate that the approach and approximations improve over existing work, in particular for the case of high utilisation systems, where savings of up to 22% on the number of preemption are attained.

Runtime CRPD management for rate-based scheduling

Temporal isolation is an increasingly relevant con- cern in particular for ARINC-351 and virtualisation- based systems. Traditional approaches like the rate- based scheduling framework RBED do not take into account the impact of preemptions in terms of loss of working set in the acceleration hardware (e.g. caches). While some improvements have been suggested in the literature, they are overly heavy in the presence of small high-priority tasks such as interrupt service routines. Within this paper we propose an approach enabling adaptive assessment of this preemption delay in a tem- poral isolation framework with special consideration of capabilities and limitations of the approach.

Unified overhead-aware schedulability analysis for slot-based task-splitting

Hard real- time multiprocessor scheduling has seen, in recent years, the flourishing of semi-partitioned scheduling algorithms. This category of scheduling schemes combines elements of partitioned and global scheduling for the purposes of achieving efficient utilization of the system’s processing resources with strong schedulability guarantees and with low dispatching overheads. The sub-class of slot-based “task-splitting” scheduling algorithms, in particular, offers very good trade-offs between schedulability guarantees (in the form of high utilization bounds) and the number of preemptions/migrations involved. However, so far there did not exist unified scheduling theory for such algorithms; each one was formulated in its own accompanying analysis. This article changes this fragmented landscape by formulating a more unified schedulability theory covering the two state-of-the-art slot-based semi-partitioned algorithms, S-EKG and NPS-F (both fixed job-priority based). This new theory is based on exact schedulability tests, thus also overcoming many sources of pessimism in existing analysis. In turn, since schedulability testing guides the task assignment under the schemes in consideration, we also formulate an improved task assignment procedure. As the other main contribution of this article, and as a response to the fact that many unrealistic assumptions, present in the original theory, tend to undermine the theoretical potential of such scheduling schemes, we identified and modelled into the new analysis all overheads incurred by the algorithms in consideration. The outcome is a new overhead-aware schedulability analysis that permits increased efficiency and reliability. The merits of this new theory are evaluated by an extensive set of experiments.

CPMD-mindful task assignment for NPS-F

The multiprocessor scheduling scheme NPS-F for sporadic tasks has a high utilisation bound and an overall number of preemptions bounded at design time. NPS-F binpacks tasks offline to as many servers as needed. At runtime, the scheduler ensures that each server is mapped to at most one of the m processors, at any instant. When scheduled, servers use EDF to select which of their tasks to run. Yet, unlike the overall number of preemptions, the migrations per se are not tightly bounded. Moreover, we cannot know a priori which task a server will be currently executing at the instant when it migrates. This uncertainty complicates the estimation of cache-related preemption and migration costs (CPMD), potentially resulting in their overestimation. Therefore, to simplify the CPMD estimation, we propose an amended bin-packing scheme for NPS-F allowing us (i) to identify at design time, which task migrates at which instant and (ii) bound a priori the number of migrating tasks, while preserving the utilisation bound of NPS-F.

An optimal boundary fair scheduling

Nowadays, many real-time operating systems discretize the time relying on a system time unit. To take this behavior into account, real-time scheduling algorithms must adopt a discrete-time model in which both timing requirements of tasks and their time allocations have to be integer multiples of the system time unit. That is, tasks cannot be executed for less than one time unit, which implies that they always have to achieve a minimum amount of work before they can be preempted. Assuming such a discrete-time model, the authors of Zhu et al. (Proceedings of the 24th IEEE international real-time systems symposium (RTSS 2003), 2003, J Parallel Distrib Comput 71(10):1411–1425, 2011) proposed an efficient “boundary fair” algorithm (named BF) and proved its optimality for the scheduling of periodic tasks while achieving full system utilization. However, BF cannot handle sporadic tasks due to their inherent irregular and unpredictable job release patterns. In this paper, we propose an optimal boundary-fair scheduling algorithm for sporadic tasks (named BF TeX ), which follows the same principle as BF by making scheduling decisions only at the job arrival times and (expected) task deadlines. This new algorithm was implemented in Linux and we show through experiments conducted upon a multicore machine that BF TeX outperforms the state-of-the-art discrete-time optimal scheduler (PD TeX ), benefiting from much less scheduling overheads. Furthermore, it appears from these experimental results that BF TeX is barely dependent on the length of the system time unit while PD TeX —the only other existing solution for the scheduling of sporadic tasks in discrete-time systems—sees its number of preemptions, migrations and the time spent to take scheduling decisions increasing linearly when improving the time resolution of the system.

Real-time Task-Splitting scheduling algorithms framework

Nos dias de hoje, os sistemas de tempo real crescem em importância e complexidade. Mediante a passagem do ambiente uniprocessador para multiprocessador, o trabalho realizado no primeiro não é completamente aplicável no segundo, dado que o nível de complexidade difere, principalmente devido à existência de múltiplos processadores no sistema. Cedo percebeu-se, que a complexidade do problema não cresce linearmente com a adição destes. Na verdade, esta complexidade apresenta-se como uma barreira ao avanço científico nesta área que, para já, se mantém desconhecida, e isto testemunha-se, essencialmente no caso de escalonamento de tarefas. A passagem para este novo ambiente, quer se trate de sistemas de tempo real ou não, promete gerar a oportunidade de realizar trabalho que no primeiro caso nunca seria possível, criando assim, novas garantias de desempenho, menos gastos monetários e menores consumos de energia. Este último fator, apresentou-se desde cedo, como, talvez, a maior barreira de desenvolvimento de novos processadores na área uniprocessador, dado que, à medida que novos eram lançados para o mercado, ao mesmo tempo que ofereciam maior performance, foram levando ao conhecimento de um limite de geração de calor que obrigou ao surgimento da área multiprocessador. No futuro, espera-se que o número de processadores num determinado chip venha a aumentar, e como é óbvio, novas técnicas de exploração das suas inerentes vantagens têm de ser desenvolvidas, e a área relacionada com os algoritmos de escalonamento não é exceção. Ao longo dos anos, diferentes categorias de algoritmos multiprocessador para dar resposta a este problema têm vindo a ser desenvolvidos, destacando-se principalmente estes: globais, particionados e semi-particionados. A perspectiva global, supõe a existência de uma fila global que é acessível por todos os processadores disponíveis. Este fato torna disponível a migração de tarefas, isto é, é possível parar a execução de uma tarefa e resumir a sua execução num processador distinto. Num dado instante, num grupo de tarefas, m, as tarefas de maior prioridade são selecionadas para execução. Este tipo promete limites de utilização altos, a custo elevado de preempções/migrações de tarefas. Em contraste, os algoritmos particionados, colocam as tarefas em partições, e estas, são atribuídas a um dos processadores disponíveis, isto é, para cada processador, é atribuída uma partição. Por essa razão, a migração de tarefas não é possível, acabando por fazer com que o limite de utilização não seja tão alto quando comparado com o caso anterior, mas o número de preempções de tarefas decresce significativamente. O esquema semi-particionado, é uma resposta de caráter hibrido entre os casos anteriores, pois existem tarefas que são particionadas, para serem executadas exclusivamente por um grupo de processadores, e outras que são atribuídas a apenas um processador. Com isto, resulta uma solução que é capaz de distribuir o trabalho a ser realizado de uma forma mais eficiente e balanceada. Infelizmente, para todos estes casos, existe uma discrepância entre a teoria e a prática, pois acaba-se por se assumir conceitos que não são aplicáveis na vida real. Para dar resposta a este problema, é necessário implementar estes algoritmos de escalonamento em sistemas operativos reais e averiguar a sua aplicabilidade, para caso isso não aconteça, as alterações necessárias sejam feitas, quer a nível teórico quer a nível prá