Respecting Temporal Constraints in Virtualised Services

Checconi

Kousiouris

et al. 2011

SOCA

Self Cite

Providing proper timeliness guarantees to distributed soft real-time applications in a virtualised infrastructure involves the careful use of various techniques at different levels, ranging from real-time scheduling mechanisms at the virtual-machine hypervisor level and QoS-aware protocols at the network level, to proper design methodologies and tools for stochastic modelling and runtime provisioning of the applications. This paper describes the way these techniques were combined to provide strong quality of service guarantees to interactive soft real-time applications in the Cloud Computing infrastructure that has been developed in the con-

Section: Related Workmentioning

confidence: 99%

Virtualised e-Learning on the IRMOS real-time Cloud

Checconi

Kousiouris

et al. 2011

SOCA

Self Cite

“…A simple test from [2] (based on two applications Γ 1 = {(30, 150), (50, 200)} and Γ 2 = {(30, 120), (40, 240)}) is reported as an example (see the original paper for all the details). All the experiments presented in this paper use the CBS implementation provided by the Irmos kernel [12] to schedule the VMs, and the Debian stable distribution installed in all the VMs.…”

Section: Using Kvm As Virtualisation Mechanismmentioning

confidence: 99%

“…With the recent improvements in virtualisation technologies, even running real-time activities inside VMs is beginning to become possible [1], [2], [3]. Of course, since such activities are characterised by temporal constraints that should be respected (often expressed in the form of deadlines), special care is needed to achieve predictable performance when scheduling the VMs.…”

Section: Introductionmentioning

confidence: 99%

Efficient virtualisation of real-time activities

Abeni

2011 IEEE International Conference on Service-Oriented Computing and Applications (SOCA)

2011

Self Cite

Abstract-Reservation-based scheduling has been proved to be an effective solution for serving virtual machines when some kind of real-time guarantees are required. However, the virtualisation mechanism and the algorithm used for implementing CPU reservations might have a large impact on the guarantees provided to tasks running inside the VMs. This paper presents an experimental evaluation of some different solutions, showing the different trade-offs and the advantages of using more advanced scheduling algorithms.

“…Finally, in our previous works [7,8] we proposed to use CPU real-time scheduling for supporting proper timeliness guarantees to virtualized applications concurrently running on different VMs deployed on the same CPU. However, in these works the investigation was limited to CPU-bound workloads, while in this paper we consider also the effect of I/O-intensive workloads.…”

Section: Related Workmentioning

confidence: 99%

Providing Performance Guarantees to Virtual Machines Using Real-Time Scheduling

Euro-Par 2010 Parallel Processing Workshops

Dhaval

Faggioli

et al. 2011

Self Cite

Abstract. In this paper we tackle the problem of providing Quality of Service guarantees to virtualized applications, focusing on computing and networking guarantees. We propose a mechanism for providing temporal isolation based on a CPU real time scheduling strategy. This allows not only to have control over the individual virtual machine throughput, but also on the activation latency and response-time by which virtualized software components react to external events. We show experimental results gathered on a real system validating the approach.