State-of-the-practice in data center virtualization: Toward a better understanding of VM usage

Birke, Robert; Podzimek, Andrej; Chen, Lydia Y.; Smirni, Evgenia

doi:10.1109/dsn.2013.6575350

Cited by 46 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In virtualized data centers, CPUs are often overcommitted. Birke et al [2013] report that the average ratio of virtual CPUs to physical CPUs in the IBM data center is 1.56. In order to reduce the CPU load at the target PM during the process of booting up, techniques like silhouette execution have been proposed.…”

Section: Key Techniques Proposed To Reduce Deployment Timementioning

confidence: 98%

Handling Boot Storms in Virtualized Data Centers—A Survey

Samant

Bellur

2016

ACM Comput. Surv.

View full text Add to dashboard Cite

Large-scale virtual machine (VM) deployment in virtualized data centers is a very slow process. This is primarily due to the resource bottlenecks that are created at the storage, network, and host physical machines when a large number of VMs are requested simultaneously. For companies that provide virtual desktops to their employees, it is common to encounter such requests each day, when their employees turn up for work. In addition, a large number of VMs are often required to be deployed instantly, in order to absorb a spike in the workload, at online e-commerce websites. In such scenarios, long deployment times are unacceptable, and reducing them is of paramount importance. In this article, we first abstract out the key techniques suggested in the literature to speed up this deployment process. We follow this with a classification of these techniques into a taxonomy and propose a framework that can be used to compare them. Finally, we identify problem areas that warrant further research and bring out the shortcomings of the current state-of-the-art solutions.

show abstract

Section: Key Techniques Proposed To Reduce Deployment Timementioning

confidence: 98%

Handling Boot Storms in Virtualized Data Centers—A Survey

Samant

Bellur

2016

ACM Comput. Surv.

View full text Add to dashboard Cite

show abstract

“…As reported by [11], there are typically 4-6 VMs consolidated on one physical server in modern datacenters. Therefore, performance interferences from co-located VMs are quite common in virtualized environments.…”

Section: B Challenges In Virtualized Hadoop Clustersmentioning

confidence: 99%

StoreApp: A shared storage appliance for efficient and scalable virtualized Hadoop clusters

Guo

Rao

Cheng

et al. 2015

2015 IEEE Conference on Computer Communications (INFOCOM)

View full text Add to dashboard Cite

Virtualizing Hadoop clusters provides many benefits, including rapid deployment, on-demand elasticity and secure multi-tenancy. However, a simple migration of Hadoop to a virtualized environment does not fully exploit these benefits. The dual role of a Hadoop worker, acting as both a compute node and a data node, makes it difficult to achieve efficient IO processing, maintain data locality, and exploit resource elasticity in the cloud. We find that decoupling per-node storage from its computation opens up opportunities for IO acceleration, locality improvement, and on-the-fly cluster resizing. To fully exploit these opportunities, we propose StoreApp, a shared storage appliance for virtual Hadoop worker nodes co-located on the same physical host. To completely separate storage from computation and prioritize IO processing, StoreApp pro-actively pushes intermediate data generated by map tasks to the storage node. StoreApp also implements late-binding task creation to take the advantage of prefetched data due to mis-aligned records. Experimental results show that StoreApp achieves up to 61% performance improvement compared to stock Hadoop and resizes the cluster to the (near) optimal degree of parallelism.

show abstract

“…Cloud providers boost system productivity, as well as lower their operational costs, by hosting tenants via virtual machines (VMs) [1]. A commonly seen practice is to collocate applications with disparate performance and resource requirements, such as latency sensitive applications and batch applications.…”

Section: Introductionmentioning

confidence: 99%

Contention detection by throttling: A black-box on-line approach

Vallone

Birke

Chen

et al. 2015

2015 IEEE 23rd International Symposium on Quality of Service (IWQoS)

Self Cite

View full text Add to dashboard Cite

Virtualization technology powers up the cloud computing paradigm and inevitably raises concerns about performance isolation of collocated virtual machines (VM). It is imperative for public cloud providers to guarantee performance targets for tenants' VMs while respecting strict business confidentiality, e.g., having no information on applications nor their performance. A large body of related work addresses the challenges of detecting performance interferences by leveraging client's quality of service (QoS) metrics, such as latency, and additional profiling servers. Whereas to assist cloud providers, we resort to an on-line blackbox approach based on throttling that detects a wide range of resource contentions with no cooperation need from the virtual machines. We focus on different resource metrics and actively monitor them from the hypervisor in fine time granularity at low cost. To detect resource contention, we propose a three-phase algorithm: an alarm phase, to identify statistical outliers in the victim's VM resource metrics; a passive diagnosis phase, to match the current sample to historical behaviors; and, an active learning phase, to discern contentions from application phase changes via throttling. We evaluate our algorithm on a prototype running Wikimedia as victim application across a set of VMs collocated with neighboring VMs running resource hoggers, i.e. PARSEC and Cachebench. Our extensive experimental results show that we can reach an average detection accuracy above 90% while limiting the performance degradation experienced by offender workloads to short learning phases.

show abstract

State-of-the-practice in data center virtualization: Toward a better understanding of VM usage

Cited by 46 publications

References 18 publications

Handling Boot Storms in Virtualized Data Centers—A Survey

Handling Boot Storms in Virtualized Data Centers—A Survey

StoreApp: A shared storage appliance for efficient and scalable virtualized Hadoop clusters

Contention detection by throttling: A black-box on-line approach

Contact Info

Product

Resources

About