Real-time multi-core virtual machine scheduling in xen

Xi, Sisu; Xu, Meng; Lu, Chenyang; Phan, Linh Thi Xuan; Gill, Christopher; Sokolsky, Oleg; Lee, Insup

doi:10.1145/2656045.2656066

Cited by 85 publications

(49 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under each environment, we used the feathertrace tool [7] to measure the context switch overhead in a VM (running LITMUS RT ), as in earlier LITMUS RT -based studies [15] [4]. We used the Xentrace tool to measure the context switch overhead in the VMM (i.e., Xen), as in earlier RT-Xen study [26]. The result is shown in Table 1.…”

Section: Partition Context Switch Overheadmentioning

confidence: 99%

vCAT: Dynamic Cache Management Using CAT Virtualization

Thi²,

Phan

et al. 2017

2017 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)

Self Cite

View full text Add to dashboard Cite

This paper presents vCAT, a novel design for dynamic shared cache management on multicore virtualization platforms based on Intel's Cache Allocation Technology (CAT). Our design achieves strong isolation at both task and VM levels through cache partition virtualization, which works in a similar way as memory virtualization, but has challenges that are unique to cache and CAT. To demonstrate the feasibility and benefits of our design, we provide a prototype implementation of vCAT, and we present an extensive set of microbenchmarks and performance evaluation results on the PARSEC benchmarks and synthetic workloads, for both static and dynamic allocations. The evaluation results show that (i) vCAT can be implemented with minimal overhead, (ii) it can be used to mitigate shared cache interference, which could have caused task WCET increased by up to 7.2 x, (iii) static management in vCAT can increase system utilization by up to 7 x compared to a system without cache management; and (iv) dynamic management substantially outperforms static management in terms of schedulable utilization (increase by up to 3 x in our multi-mode example use case). Abstract-This paper presents vCAT, a novel design for dynamic shared cache management on multicore virtualization platforms based on Intel's Cache Allocation Technology (CAT). Our design achieves strong isolation at both task and VM levels through cache partition virtualization, which works in a similar way as memory virtualization, but has challenges that are unique to cache and CAT. To demonstrate the feasibility and benefits of our design, we provide a prototype implementation of vCAT, and we present an extensive set of microbenchmarks and performance evaluation results on the PARSEC benchmarks and synthetic workloads, for both static and dynamic allocations. The evaluation results show that (i) vCAT can be implemented with minimal overhead, (ii) it can be used to mitigate shared cache interference, which could have caused task WCET increased by up to 7.2×, (iii) static management in vCAT can increase system utilization by up to 7× compared to a system without cache management; and (iv) dynamic management substantially outperforms static management in terms of schedulable utilization (increase by up to 3× in our multi-mode example use case). Disciplines Computer Engineering | Computer Sciences

show abstract

Section: Partition Context Switch Overheadmentioning

confidence: 99%

vCAT: Dynamic Cache Management Using CAT Virtualization

Thi²,

Phan

et al. 2017

2017 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The system administrator can also specify a cap per VM, which is the maximum CPU resource that can be allocated to each VM. As the credit scheduler does not consider timing constraints of the applications, it is not suitable for realtime applications [5,6]. To support real-time applications, the recently released Xen 4.5 include a real-time scheduler called RTDS [6] developed in the RT-Xen project described in the next subsection.…”

Section: A Xen Virtual Machine Monitormentioning

confidence: 99%

“…We have designed and implemented RT-Xen [5,7,6], a real-time scheduling framework for Xen. In RT-Xen, each VCPU specifies its demand for CPU resources as a resource interface, which includes three parameters: budget (the amount of time a VCPU is allowed to run per period); period; and cpumask, the set of the PCPUs on which the VCPU is allowed to run.…”

Section: B Rt-xenmentioning

confidence: 99%

“…In RT-Xen, each VCPU specifies its demand for CPU resources as a resource interface, which includes three parameters: budget (the amount of time a VCPU is allowed to run per period); period; and cpumask, the set of the PCPUs on which the VCPU is allowed to run. The current multi-core scheduler in RT-Xen [6] supports a rich set of real-time scheduling policies including earliest deadline first (EDF) and rate monotonic (RM) priority schemes, global and partitioned scheduling policies, and different budget management schemes such as deferrable and periodic servers. Among all the combinations of realtime scheduling policies, global EDF (gEDF) with deferrable server delivered the best real-time performance in our experiments [6].…”

Section: B Rt-xenmentioning

confidence: 99%

See 1 more Smart Citation

RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing

et al. 2015

2015 IEEE 8th International Conference on Cloud Computing

Self Cite

View full text Add to dashboard Cite

Abstract-Clouds have become appealing platforms for not only general-purpose applications, but also real-time ones. However, current clouds cannot provide real-time performance to virtual machines (VMs). We observe the demand and the advantage of co-hosting real-time (RT) VMs with non-real-time (regular) VMs in a same cloud. RT VMs can benefit from the easily deployed, elastic resource provisioning provided by the cloud, while regular VMs effectively utilize remaining resources without affecting the performance of RT VMs through proper resource management at both the cloud and the hypervisor levels. This paper presents RT-OpenStack, a cloud CPU resource management system for co-hosting real-time and regular VMs. RT-OpenStack entails three main contributions: (1) integration of a real-time hypervisor (RT-Xen) and a cloud management system (OpenStack) through a real-time resource interface; (2) a realtime VM scheduler to allow regular VMs to share hosts with RT VMs without interfering the real-time performance of RT VMs; and (3) a VM-to-host mapping strategy that provisions real-time performance to RT VMs while allowing effective resource sharing with regular VMs. Experimental results demonstrate that RTOpenStack can effectively improve the real-time performance of RT VMs while allowing regular VMs to fully utilize the remaining CPU resources.

show abstract

“…RT-Xen [20], [21], [22] provides a real-time VCPU scheduling framework recently included in Xen 4.5. Xi et al [23] develop RTCA, which implements a prioritizationaware packet scheduling in the netback device of dom0.…”

Section: Related Workmentioning

confidence: 99%

Prioritizing soft real-time network traffic in virtualized hosts based on Xen

et al. 2015

21st IEEE Real-Time and Embedded Technology and Applications Symposium

Self Cite

View full text Add to dashboard Cite

Abstract-As virtualization technology becomes ever more capable, large-scale distributed applications are increasingly deployed in virtualized environments such as data centers and computational clouds. Many large-scale applications have soft real-time requirements and benefit from low and predictable latency, even in the presence of diverse traffic patterns between virtualized hosts. In this paper, we examine the policies and mechanisms affecting communication latency between virtual machines based on the Xen platform, and identify limitations that could result in long or unpredictable network traffic latencies. To address these limitations, we propose VATC, a VirtualizationAware Traffic Control framework for prioritizing network traffic in virtualized hosts. Results of our experiments show how and why VATC can improve predictability and reduce delay for latency sensitive applications, while introducing limited overhead.

show abstract

Real-time multi-core virtual machine scheduling in xen

Cited by 85 publications

References 42 publications

vCAT: Dynamic Cache Management Using CAT Virtualization

vCAT: Dynamic Cache Management Using CAT Virtualization

RT-Open Stack: CPU Resource Management for Real-Time Cloud Computing

Prioritizing soft real-time network traffic in virtualized hosts based on Xen

Contact Info

Product

Resources

About