SLA-based virtual machine management for heterogeneous workloads in a cloud datacenter

Garg, Saurabh; Toosi, Adel Nadjaran; Gopalaiyengar, Srinivasa K.; Buyya, Rajkumar

doi:10.1016/j.jnca.2014.07.030

Cited by 196 publications

(80 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Garg et al [16] propose an admission control mechanism that maximises the resource utilisation and profit, while it also ensures that the SLA-specified QoS requirements are met. The authors used a forecasting model based on a multi-layer feed-forward neural network for predicting the utilisation of server resources.…”

Section: Sla-based Scaling Of Cloud Servicesmentioning

confidence: 99%

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Antonescu

Braun

2016

Future Generation Computer Systems

View full text Add to dashboard Cite

Cloud Computing has evolved to become an enabler for delivering access to large scale distributed applications running on managed network-connected computing systems. This makes possible hosting Distributed Enterprise Information Systems (dEISs) in cloud environments, while enforcing strict performance and quality of service requirements, defined using Service Level Agreements (SLAs). SLAs define the performance boundaries of distributed applications, and are enforced by a cloud management system (CMS) dynamically allocating the available computing resources to the cloud services. We present two novel VM-scaling algorithms focused on dEIS systems, which optimally detect most appropriate scaling conditions using performance-models of distributed applications derived from constant-workload benchmarks, together with SLA-specified performance constraints. We simulate the VMscaling algorithms in a cloud simulator and compare against trace-based performance models of dEISs. We compare a total of three SLA-based VMscaling algorithms (one using prediction mechanisms) based on a real-world application scenario involving a large variable number of users. Our results show that it is beneficial to use autoregressive predictive SLA-driven scaling algorithms in cloud management systems for guaranteeing performance invariants of distributed cloud applications, as opposed to using only reactive SLA-based VM-scaling algorithms.

show abstract

Section: Sla-based Scaling Of Cloud Servicesmentioning

confidence: 99%

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Antonescu

Braun

2016

Future Generation Computer Systems

View full text Add to dashboard Cite

show abstract

“…However, one of the main conclusions of the Verma et al [39] study is that uncorrelated loads should be allocated in the same server. This feature has been followed in subsequent works, such as [10], and it is applied in our algorithm.…”

Section: Interference-aware Dynamic Resources Schedulingmentioning

confidence: 99%

“…Moreover, we consider different types of QoS requirements, and we extend the strategy of the hard limit by applying hard and soft limits to address the two types of resources, CPU and I/O bandwidth, in the management of network-intensive workloads. Garg et al [10] proposed an admission control and scheduling mechanism to maximize the resource utilization and profit. At the same time, it ensures that the QoS requirements of users are met as specified in the SLAs.…”

Section: Sla-based Resources Schedulingmentioning

confidence: 99%

“…The mechanism considers multiple types of SLAs based on application requirements (i.e., two types of applications, namely, non-interactive and transactional). Our work is closely related to [10] in that we address the resource allocation problem within a data center that runs different types of application workloads. Therefore, we compare our algorithm to this work.…”

Section: Sla-based Resources Schedulingmentioning

confidence: 99%

See 1 more Smart Citation

PIASA: A power and interference aware resource management strategy for heterogeneous workloads in cloud data centers

Sampaio

Barbosa

Prodan

2015

Simulation Modelling Practice and Theory

View full text Add to dashboard Cite

a b s t r a c tCloud data centers have been progressively adopted in different scenarios, as reflected in the execution of heterogeneous applications with diverse workloads and diverse quality of service (QoS) requirements. Virtual machine (VM) technology eases resource management in physical servers and helps cloud providers achieve goals such as optimization of energy consumption. However, the performance of an application running inside a VM is not guaranteed due to the interference among co-hosted workloads sharing the same physical resources. Moreover, the different types of co-hosted applications with diverse QoS requirements as well as the dynamic behavior of the cloud makes efficient provisioning of resources even more difficult and a challenging problem in cloud data centers. In this paper, we address the problem of resource allocation within a data center that runs different types of application workloads, particularly CPU-and network-intensive applications. To address these challenges, we propose an interference-and power-aware management mechanism that combines a performance deviation estimator and a scheduling algorithm to guide the resource allocation in virtualized environments. We conduct simulations by injecting synthetic workloads whose characteristics follow the last version of the Google Cloud tracelogs. The results indicate that our performance-enforcing strategy is able to fulfill contracted SLAs of real-world environments while reducing energy costs by as much as 21%.

show abstract

“…However, combining the fault tolerance of VM workloads is necessitated prior the deployment of VM fault tolerance in cloud platforms. The workload state of VMs in cloud platforms is dynamic and uncertain [3,4]. Therefore, understanding how fault tolerance is deployed on the basis of the combined relationships of VM workload and VM reliability and task processing capability is imperative.…”

Section: Introductionmentioning

confidence: 99%

Study on Fault Tolerance Method in Cloud Platform based on Workload Consolidation Model of Virtual Machine

Li¹,

Liu²,

Tong³

2017

JESTR

View full text Add to dashboard Cite

The fault tolerance method of virtual machines (VM) guarantees reliability to the service capability of cloud platforms. VM workloads are dynamic and uncertain, and thus, they affect the reliability and task processing capability of entire cloud platforms. In this study, a fault tolerance method based on the VM workload consolidation model was proposed to solve problems concerning the reliability and task processing capability of cloud platforms caused by VM workloads, thus improving the reliability of VMs and overall performance of cloud platforms. First, the method was analyzed on the basis of the distinct relationship of VM workload and VM reliability and task processing capability. Then, the workload state of VM was predicted and analyzed by linear regression using VM workload monitoring data, and the VM workload consolidation algorithm was constructed based on expected workload constraint and optimization of fault tolerance time. Finally, the fault tolerance method based on the VM workload consolidation model was compared with the Radom method and the Max method. Research results demonstrate the potential of the proposed method to improve VM reliability in cloud platforms by 20% and 47% compared with those for the Radom and Max methods, respectively. In the same workload phase, the task completion rate of the proposed method increased significantly (15% and 30%, and 22% and 30%), and the percentages were higher than those for the Radom and Max methods, respectively. Moreover, the proposed method shortened task response time. This study concludes that the workload consolidation of VMs can increase the reliability and task processing capability of VMs. This proposed method can provide technological support to the fault tolerance of VMs in cloud platforms.

show abstract

SLA-based virtual machine management for heterogeneous workloads in a cloud datacenter

Cited by 196 publications

References 45 publications

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

PIASA: A power and interference aware resource management strategy for heterogeneous workloads in cloud data centers

Study on Fault Tolerance Method in Cloud Platform based on Workload Consolidation Model of Virtual Machine

Contact Info

Product

Resources

About