1. |
- Abdullah, Syed Md Jakaria, et al.
(författare)
-
Towards Implementation of Virtual-Clustered Multiprocessor Scheduling in Linux
- 2013
-
Ingår i: Proceedings of the 8th IEEE International Symposium on Industrial Embedded Systems, SIES 2013. - 9781479906581 ; , s. 97-100
-
Konferensbidrag (refereegranskat)abstract
- Cluster based multiprocessor scheduling can be seen as a hybrid approach combining benefits of both partitioned and global scheduling. Virtual clustering further enhances it by providing dynamic cluster resource allocation and applying hierarchical scheduling techniques. Over the years, the study of virtual cluster scheduling has been limited to theoretical analysis. In this paper, we present our initial ideas about implementing virtual cluster scheduling in Linux. The purpose of this implementation is twofold: (i) we would like to demonstrate the feasibility of its implementation in an operating system, without modifying the kernel source code, (ii) we present practical insights on the overhead of implementing this framework.
|
|
2. |
- Afshar, Sara, et al.
(författare)
-
Flexible spin-lock model for resource sharing in multiprocessor real-time systems
- 2014
-
Ingår i: Proc. IEEE Int. Symp. Ind. Embedded Syst., SIES. - 9781479940233 ; , s. 41-51
-
Konferensbidrag (refereegranskat)abstract
- Various approaches can be utilized upon resource locking for mutually exclusive resource access in multiprocessor platforms. So far two conventional approaches exist for dealing with tasks that are blocked on a global resource in a multi-processor platform. Either the blocked task performs a busy wait, i.e. spins, at the highest priority level until the resource is released, or it is suspended. Although both approaches provide mutually exclusive access to resources, they can introduce long blocking delays to tasks, which may be unacceptable for many industrial applications. In this paper, we propose a general spin-based model for resource sharing in multiprocessor platforms in which the priority of the blocked tasks during spinning can be selected arbitrarily. Moreover, we provide the analysis for two selected spin-lock priorities and we show by means of a general comparison as well as specific examples that these solutions may provide a better performance for higher priority tasks.
|
|
3. |
- Afshar, Sara, et al.
(författare)
-
Integrating independently developed real-time applications on a shared multi-core architecture
- 2013
-
Ingår i: ACM SIGBED Review, v. 10, n. 3. - : Association for Computing Machinery (ACM). ; , s. 49-56
-
Konferensbidrag (refereegranskat)abstract
- The shift towards multi-core platforms has become inevitable from an industry perspective, therefore proper techniques are needed to deal with challenges related to this migration from single core architectures to a multi-core architecture. One of the main concerns for the system developers in this context is the migration of legacy real-time systems to multi-core architectures. To address this concern and to simplify migration, independently developed subsystems are abstracted with an interface, such that when working with multiple independently-developed subsystems to be integrated on a shared platform, one does not need to be aware of information or policies used in other subsystems in order to determine subsystem-level schedulability. Instead schedulability can be checked through their interfaces at the time of integration on a shared multi-core architecture. In this paper we propose a solution for the case where some of the independently-developed subsystems are distributed over more than one processor and we propose an approach to generate interfaces of subsystems that may share mutually exclusive resources.
|
|
4. |
- Afshar, Sara
(författare)
-
Lock-Based Resource Sharing in Real-Time Multiprocessor Platforms
- 2014
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Embedded systems are typically resource constrained, i.e., resources such as processors, I/O devices, shared buffers or shared memory can be limited for tasks in the system. Therefore, techniques that enable an efficient usage of such resources are of great importance.In the industry, typically large and complex software systems are divided into smaller parts (applications) where each part is developed independently. Migration towards multiprocessor platforms has become inevitable from an industrial perspective. Due to such migration and to efficient use of system resources, these applications eventually may be integrated on a shared multiprocessor platform. In order to facilitate the integration phase of the applications on a shared platform, the timing and resource requirements of each application can be provided in an interface when the application is developed. The system integrator can benefit from such provided information in the interface of each application to ease the integration process. In this thesis, we have provided the resource and timing requirements of each application in their interfaces for applications that may need several processors to be allocated on when they are developed.Although many scheduling techniques have been studied for multiprocessor systems, these techniques are usually based on the assumption that tasks are independent, i.e. do not share resources other than the processors. This assumption is typically not true. In this thesis, we provide an extension to such systems to handle sharing of resources other than processor among tasks. Two traditional approaches exist for multiprocessor systems to schedule tasks on processors. A recent scheduling approach for multiprocessors has combined the two traditional approaches and achieved a hybrid more efficient approach compared to the two previous one. Due to the complex nature of this scheduling approach the conventional approaches for resource sharing could not be used straight forwardly. In this thesis, we have modified resource sharing approaches such that they can be used in such hybrid scheduling systems. A second concern is that enabling resource sharing in the systems can cause unpredictable delays and variations in response time of tasks which can degrade system performance. Therefore, it is of great significance to improve the resource handling techniques to reduce the effect of imposed delays caused by resource sharing in a multiprocessor platform. In this thesis we have proposed alternative techniques for resource handling that can improve system performance for special setups.
|
|
5. |
- Afshar, Sara, et al.
(författare)
-
Per Processor Spin-Lock Priority for Partitioned Multiprocessor Real-Time Systems
- 2014
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Two traditional approaches exist for a task that is blocked on a global resource; a task either performs a non-preemptive busy wait, i.e., spins, or suspends and releases the processor. Previously, we have shown that both approaches can be viewed as spinning either at the highest priority HP or at the lowest priority on the processor LP, respectively. Based on this view, previously we have generalized a task's blocking behavioral model, as spinning at any arbitrary priority level. In this paper, we focus on a particular class of spin-lock protocols from the introduced flexible spin-lock model where spinning is performed at a priority equal to or higher than the highest local ceiling of the global resources accessed on a processor referred to as CP spin-lock approach. In this paper, we assume that all tasks of a specific processor are spinning on the same priority level. Given this class and assumption, we show that there exists a spin-lock protocol in this range that dominates the classic spin-lock protocol which tasks spin on highest priority level (HP). However we show that this new approach is incomparable with the CP spin-lock approach. Moreover, we show that there may exist an intermediate spin-lock approach between the priority used by CP spin-lock approach and the new introduced spin-lock approach that can make a task set schedulable when those two cannot. We provide an extensive evaluation results comparing the HP, CP and the new proposed approach.
|
|
6. |
- Almeida, Luis, et al.
(författare)
-
Managing end-to-end resource reservations
- 2014
-
Ingår i: 7th International Workshop on Compositional Theory and Technology for Real-Time Embedded Systems CRTS'14.
-
Konferensbidrag (refereegranskat)
|
|
7. |
- Ashjaei, Mohammad, et al.
(författare)
-
A Compact Approach to Clustered Master-Slave Ethernet Networks
- 2012
-
Ingår i: IEEE International Workshop on Factory Communication Systems - Proceedings, WFCS. - 9781467315739 ; , s. 157-160
-
Konferensbidrag (refereegranskat)abstract
- Ethernet switches are increasingly used in real-time distributed systems as a technical solution to guarantee the timeliness in communications. However, there are still limitations related to real-time behavior caused by the limited number of priority levels and the possibility of memory overruns with consequent message losses. These limitations can be eliminated using a master/slave technique such as proposed by the FTT paradigm. This led to the FTT-SE protocol that schedules transmissions centrally in a master node. While this protocol has already been well studied and investigated for small networks with a single switch, its extension to larger networks is still an open issue. In this paper we propose a compact clustered solution to scale the FTT-SE protocol to networks of multiple switches by organizing the network in sub-networks composed of one master and one switch each and which can be connected directly, without bridges. This paper also shows how the timeliness of the traffic can still be enforced. The validation is currently on-going.
|
|
8. |
- Ashjaei, Mohammad, et al.
(författare)
-
Dynamic Reconfiguration in Multi-Hop Switched Ethernet Networks
- 2014
-
Ingår i: ACM SIGBED Review. Special Issue on 6th Workshop on Adaptive and Reconfigurable Embedded Systems (APRES 2014). - : Association for Computing Machinery (ACM). - 1551-3688. ; 11:3, s. 62-65
-
Tidskriftsartikel (refereegranskat)abstract
- The FTT-SE protocol provides adaptive real-time communication on Ethernet networks. To assure a continued real-time behavior, FTT-SE integrates admission control with a quality-of-service mechanism, which screen all adaptation and reconfiguration requests, accepting only those that do not compromise the system timeliness. The adaptability and reconfigurability have been deeply studied in the case of single switch FTT-SE architectures, whereas the extension of that for the multi-hop FTT-SE architecture was not yet investigated. Therefore, in this paper we study the challenges of enabling dynamic reconfiguration in multi-hop FTT-SE networks, we propose two methods (one centralized and one distributed) and we present a qualitative comparison between them.
|
|
9. |
- Ashjaei, Mohammad, et al.
(författare)
-
Evaluation of dynamic reconfiguration architecture in multi-hop switched ethernet networks
- 2014
-
Ingår i: 19th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2014. - 9781479948468 ; , s. Article number 7005322-
-
Konferensbidrag (refereegranskat)abstract
- On-the-fly adaptability and reconfigurability are recently becoming an interest in real-time communications. To assure a continued real-time behavior, the admission control with a quality-of-service mechanism is required, that screen all adaptation and reconfiguration requests. In the context of switched Ethernet networks, the FTT-SE protocol provides adaptive real-time communication. Recently, we proposed two methods to perform the online reconfiguration in multi-hop FTT-SE architectures. However, the methods lack the experimental evaluation. In this paper, we evaluate both methods in terms of the reconfiguration time.
|
|
10. |
- Ashjaei, Mohammad, et al.
(författare)
-
Implementing a Clock Synchronization Protocol on a Multi-Master Switched Ethernet Network
- 2013
-
Konferensbidrag (refereegranskat)abstract
- The interest to use Switched Ethernet technologies in real-time communication is increasing due to its absence of collisions when transmitting messages. Nevertheless, using COTS switches affect the timeliness guarantee inherent in potentially overflowing internal FIFO queues. In this paper we focus on a solution, called the FTT-SE protocol, which is developed based on a master-slave technique. Recently, an extension of the FTT-SE protocol has been proposed where the transmission of messages are controlled using multiple master nodes. In order to guarantee the correctness of the protocol, the masters should be timely synchronized. Therefore, in this paper we investigate using a clock synchronization protocol, based on the IEEE 1588 standard, among master nodes and we study the effects of this protocol on the network performance. In addition, we present a formal verification of this solution by means of model checking to prove the correctness of the FTT-SE protocol when the clock synchronization protocol is applied.
|
|