Nicola Manica - Academia.edu (original) (raw)

Papers by Nicola Manica

The application of a resource reservation scheduler to soft real-time systems requires effective ... more The application of a resource reservation scheduler to soft real-time systems requires effective means to compute the probability of a deadline miss given a particular choice for the scheduling parameters. This is a challenging research problem, for which only numeric solutions, complex and difficult to manage, are currently available. In this paper, we adopt an analytical approach. By using an approximate and conservative model for the evolution of a periodic task scheduled through a reservation, we construct a closed form lower bound for the probability of a deadline miss. Our experiments reveal that the bound remains reasonably close to the experimental probability for many real-time applications of interest.

This paper presents an efficient algorithm for providing probabilistic guarantees in soft real-ti... more This paper presents an efficient algorithm for providing probabilistic guarantees in soft real-time systems using resource reservations. We use a conservative model for the temporal evolution of a resource reservation, which has a particular structure-a quasi birth death process-enabling an efficient computation of the stationary probability of respecting deadlines. We show the accuracy and the efficiency of the method in a large set of experiments.

Journal of Systems and Software, May 1, 2012

This paper presents a new method for providing probabilistic real-time guarantees to tasks schedu... more This paper presents a new method for providing probabilistic real-time guarantees to tasks scheduled through resource reservations. Previous work on probabilistic analysis of reservation-based schedulers is extended by improving the efficiency and robustness of the probability computation. Robustness is improved by accounting for a possibly incomplete knowledge of the distribution of the computation times (which is typical in realistic applications). The proposed approach computes a conservative bound for the probability of missing deadlines, based on the knowledge of the probability distributions of the execution times and of the inter-arrival times of the tasks. In this paper, such a bound is computed in realistic situations, comparing it with simulative results and with the exact computation of deadline miss probabilities (without pessimistic bounds). Finally, the impact of the incomplete knowledge of the execution times distribution is evaluated.

This paper presents a theoretical schedulability analysis of client/server communication in a res... more This paper presents a theoretical schedulability analysis of client/server communication in a reservation-based system. The inheritance mechanism previously implemented in a reservation-based system (based on the SCHED_DEADLINE Linux patch, which implements the Constant Bandwidth Server (CBS) algorithm in the Linux kernel) is improved to support predictable client/server communications, and the modified SCHED_DEADLINE has been used to run an extensive set of experiments showing the effectiveness of the proposed approach and analysis.

In order to provide reliable system support for real-time applications, it is often important to ... more In order to provide reliable system support for real-time applications, it is often important to be able to collect statistics about the tasks temporal behaviours (in terms of execution times and inter-arrival times). Such statistics can, for example, be used to provide a-priori schedulability guarantees, or to perform some kind of on-line adaptation of the scheduling parameters (adaptive scheduling, or feedback scheduling). This work in progress shows how the Linux kernel allows to collect such statistics by using an internal function tracer called Ftrace. Based on this feature, tools can be developed to evaluate the real-time performance of a system or an application, to debug real-time applications, and/or to infer the temporal properties (for example, periodicity) of tasks running in the system.

In this paper, we consider the problem of providing QoS guarantees to the execution of applicatio... more In this paper, we consider the problem of providing QoS guarantees to the execution of applications using the X11 window system. In particular, we offer a system level analysis of the issues encountered when using X11 to serve realtime applications. By using a tracer developed for the purpose we analyse in depth the internal behaviour of the system. The result of the analysis puts on display the adverse effect played by a non real-time scheduler on the performance of time-sensitive applications. Based on this analysis, we propose an alternative solution based on the CBS scheduler and prove its effectiveness by an extensive set of experiments on real hardware.

Abstract—The application of a resource reservation scheduler to soft real–time systems requires e... more Abstract—The application of a resource reservation scheduler to soft real–time systems requires effective means to compute the probability of a deadline miss given a particular choice for the scheduling parameters. This is a challenging research problem, for which only numeric solutions, complex and difficult to manage, are currently available. In this paper, we adopt an analytical approach. By using an approximate and conservative model for the evolution of a periodic task scheduled through a reservation, we construct a closed form lower bound for the probability of a deadline miss. Our experiments reveal that the bound remains reasonably close to the experimental probability for many real–time applications of interest. Keywords-Soft real–time systems, Probabilistic Guarantees I.

Abstract—In the past few years, the Resource Reservations have gained academic consideration and ... more Abstract—In the past few years, the Resource Reservations have gained academic consideration and technological matu rity and are now a credible scheduling solution for soft real–time applications. A natural complement of a resource reservati on scheduler is a technique relating the system performance, expressed in a stochastic setup, to the scheduling choices. Discovering such a technique is an interesting research pro blem, for which only numeric solutions based on complex and difficult to manage models. In this paper, we adopt an analyti cal approach. By using an approximate and conservative model fo r a resource reservation scheduling a periodic task, we const ruct a closed form lower bound for the probability of a deadline miss that proves itself rather close to the actual probabili ty.

An unmistakable trend in embedded systems is the growth of soft real-time computing. A soft real-... more An unmistakable trend in embedded systems is the growth of soft real-time computing. A soft real-time application is one for which deadlines can occasionally be missed, but the probability of this event has to be controllable and predictable. This work is aimed to close the gap in the research of stochastic real-time analysis related to resource reservation scheduling algorithms. This dissertation attempts to: 1. give a quick overview of classic real-time analysis 2. analyze the problems related to use the well-known techniques in the context of soft real-time applications: • overvalue the assignation of parameters as in hard real- time systems based on worst case execution times • time and memory complexity using the known theoretical stochastic analysis 3. propose solutions able to overcome the limitation showed in point 2 4. show some specific examples (theoretical and practical) in which resource reservation lead to advantages. The novel contributions of this thesis are: • a new bound to predict the probability of a deadline misses in a resource reservation systems • a very efficient numeric solution for matrix generated with well-know abstraction models of reservation based on Quasi Birth Death Markov Process • an analytical solution, with some conservative approximations, for the same models. • a new model for specific applications, like interrupts. • experiments using resource reservation in different contexts The thesis is evolved following two different approaches: 1. the first based on the exact model of reservation, and the contributions is: • define a new pessimistic bound, efficient in term of computation, able to overcome the problem of complete knowledge of the computation time. The solution is an approximation of the real solution of the model. 2. the second based on an approximation model in which the novel contributions are: • presents an exact and numeric efficient solution for the model based on Quasi Birth and Death Markov Process • introduces an approximate analytical solution which can be computed with no complexity and which is reversible These techniques are applicable since the minimum interarrival of a request is greater than a server period. Unfortunately exists situations in which this assumption is not feasible. An important example is using resource reservation to scheduling interrupts. In order to consider also this situation, another important novel result of this thesis is: • to introduce a new model for scheduling interrupts In addition, some practical examples of using resource reservation are presented.

Proceedings of the 28th Annual ACM Symposium on Applied Computing - SAC '13, 2013

Journal of Systems and Software, May 1, 2012

Proceedings of the 28th Annual ACM Symposium on Applied Computing - SAC '13, 2013