Analytical Enhancements and Practical Insights for MPCP with Self-Suspensions

Patel, Parveen; Baek, Iljoo; Kim, Hyoseung; Rajkumar, Ragunathan

doi:10.1109/rtas.2018.00027

Cited by 22 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tasks running on different clusters may communicate each other, e.g., RTOS tasks on the Denver cluster and Linux tasks on the A57 cluster of the TX2 platform, and no more than one task should be allowed access a shared memory region at a time. Real-time synchronization and locking protocols [24], [34]- [36] have been developed to ensure mutual exclusion and bounded blocking time in a multi-core environment.…”

Section: A Execution Environment 1) Clustered Multi-core Architecturesmentioning

confidence: 99%

“…Table 1 shows the base parameters used in the experiment. These parameters are based on those used in other prior work [17], [21], [34]. To generate a WCET function (C i (k)) for each task τ i , we use the method given in [8].…”

Section: B Benefit Of Proposed Algorithm 1) Taskset Generationmentioning

confidence: 99%

“…The Multiprocessor Priority Ceiling Protocol (MPCP) [26], [35], [36] is a well-known technique to offer bounded blocking time on accessing shared resources in partitioned fixed-priority multi-core systems. MPCP has been extended to virtualization [24] and access control for shared hardware accelerators, such as graphics processing units (GPUs) [7], [20], [34]. The Multiprocessor Stack-based Resource Policy (MSRP) [14] is an extension of the uniprocessor SRP [5] for resource sharing under partitioned EDF scheduling.…”

Section: B Locking and Task Synchronizationmentioning

confidence: 99%

See 2 more Smart Citations

Cache-Aware Real-Time Virtualization for Clustered Multi-Core Platforms

Lim

Kim

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the increasing complexity of recent autonomous platforms, there is a strong demand to better utilize system resources while satisfying stringent real-time requirements. Embedded virtualization is an appealing technology to meet this demand. It enables the consolidation of real-time systems with different criticality levels on a single hardware platform by enforcing temporal isolation. On multi-core platforms, however, shared hardware resources, such as caches and memory buses, weaken this isolation. In particular, due to the resulting cache interference, a large last-level cache in recent processors can easily jeopardize the timing predictability of real-time tasks due to cache interference. While researchers in the real-time systems community have developed solutions to tackle this problem, existing cache management schemes reveal two major limitations when used in a clustered multi-core embedded system. The first is the cache co-partitioning problem, which can lead to wrong cache allocation and cache underutilization. The second is the cache interference of inter-virtual-machine (VM) communication because prior work has considered only independent tasks. This paper presents a cluster-aware real-time cache allocation scheme to address these problems. The proposed scheme takes into account the cluster information of the system, and finds the cache allocation that satisfies the timing and memory requirements of tasks. The scheme also maximizes slack time to meet task deadline, which brings flexibility and resilience to unexpected events. Tasks using inter-VM communication are also provided with guaranteed blocking time and cache isolation. We have implemented a prototype of our scheme on an Nvidia TX2 clustered multi-core platform and evaluated the effectiveness of our scheme over cluster-unaware approaches. INDEX TERMS Cache interference, clustered multi-core platforms, real-time systems, embedded virtualization, real-time hypervisor, partitioning hypervisor, real-time resource management.

show abstract

Section: A Execution Environment 1) Clustered Multi-core Architecturesmentioning

confidence: 99%

Section: B Benefit Of Proposed Algorithm 1) Taskset Generationmentioning

confidence: 99%

Section: B Locking and Task Synchronizationmentioning

confidence: 99%

See 1 more Smart Citation

Cache-Aware Real-Time Virtualization for Clustered Multi-Core Platforms

Lim

Kim

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…by cleanly separating the time that a job holds a resource from the time that a job executes while being priority boosted [38]. Recently, Patel et al [161] expressed very similar ideas using more conventional notation, but unfortunately did not compare their proposal with the earlier LP-based analysis of the MPCP [38].…”

Section: Partitioned Schedulingmentioning

confidence: 99%

Multiprocessor Real-Time Locking Protocols: A Systematic Review

Brandenburg

2019

Preprint

View full text Add to dashboard Cite

We systematically survey the literature on analytically sound multiprocessor real-time locking protocols from 1988 until 2018, covering the following topics:• progress mechanisms that prevent the lock-holder preemption problem (Section 3),• spin-lock protocols (Section 4),• binary semaphore protocols (Sections 5 and 6),• independence-preserving (or fully preemptive) locking protocols (Section 7),• reader-writer and k-exclusion synchronization (Section 8),• support for nested critical sections (Section 9), and • implementation and system-integration aspects (Section 10).A special focus is placed on the suspension-oblivious and suspension-aware analysis approaches for semaphore protocols, their respective notions of priority inversion, optimality criteria, lower bounds on maximum priority-inversion blocking, and matching asymptotically optimal locking protocols.

show abstract

“…Works on semaphore-based multiprocessor locking protocols [13], [28] also considered the integration of blocking with self-suspensions, but under the case in which suspensions are originated by waiting times for resources locked on a remote processor or when suspensions happen within a critical section (e.g., due to I/O accesses). To the best of our records, there is no work that attempts to mitigate the additional blocking originating from self-suspension, other then by using spinlocks [22], effectively replacing suspension by computation.…”

Section: Related Workmentioning

confidence: 99%

The SRP Resource Sharing Protocol for Self-Suspending Tasks

Nelissen

Biondi

2018

2018 IEEE Real-Time Systems Symposium (RTSS)

View full text Add to dashboard Cite

Motivated by the increasingly wide adoption of realtimeworkload with self-suspending behaviors, and the relevanceof mechanisms to handle mutually-exclusive shared resources, thispaper takes a new look at locking protocols for self-suspendingtasks under uniprocessor fixed-priority scheduling. Pitfalls whenintegrating the widelyadopted Stack Resource Policy (SRP) withself-suspending tasks are firstly illustrated, and then a new fine grainedSRP analysis is presented. Next, a new locking protocol,named SRP-SS, is proposed to overcome the limitations of theoriginal SRP. The SRP-SS is a generalization of the SRP to copewith the specificities of selfsuspending tasks. It therefore reducesto the SRP under some configurations and hence theoreticallydominates the SRP. It also ensures backward compatibility forapplications developed specifically for the SRP. The SRP-SScomes with its own schedulability analysis and configurationalgorithm. The performances of the SRP and SRP-SS are finallystudied by means of schedulability experiments.

show abstract

Analytical Enhancements and Practical Insights for MPCP with Self-Suspensions

Cited by 22 publications

References 33 publications

Cache-Aware Real-Time Virtualization for Clustered Multi-Core Platforms

Cache-Aware Real-Time Virtualization for Clustered Multi-Core Platforms

Multiprocessor Real-Time Locking Protocols: A Systematic Review

The SRP Resource Sharing Protocol for Self-Suspending Tasks

Contact Info

Product

Resources

About