Markov Prediction Model for Host Load Detection and VM Placement in Live Migration

Melhem, Suhib Bani; Agarwal, Anjali; Goel, Nishith; Zaman, Musharraf

doi:10.1109/access.2017.2785280

Cited by 68 publications

(49 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed migration method does not include a task size determination algorithm for predicting the migration time by analyzing the available resources of the source or the GPU usage patterns of VMs to send an appropriately sized task to the destination node. These limitations can be mitigated by adopting advanced forecast‐based monitoring techniques in existing cloud environments. If the size of clusters constituting a cloud system increases due to an extension of physical nodes, the monitoring overhead will also increase.…”

Section: Discussionmentioning

confidence: 99%

Partial migration technique for GPGPU tasks to Prevent GPU Memory Starvation in RPC‐based GPU Virtualization

Kang

Lim

2020

Softw Pract Exp

View full text Add to dashboard Cite

Graphics processing unit (GPU) virtualization technology enables a single GPU to be shared among multiple virtual machines (VMs), thereby allowing multiple VMs to perform GPU operations simultaneously with a single GPU. Because GPUs exhibit lower resource scalability than central processing units (CPUs), memory, and storage, many VMs encounter resource shortages while running GPU operations concurrently, implying that the VM performing the GPU operation must wait to use the GPU. In this paper, we propose a partial migration technique for general-purpose graphics processing unit (GPGPU) tasks to prevent the GPU resource shortage in a remote procedure call-based GPU virtualization environment. The proposed method allows a GPGPU task to be migrated to another physical server's GPU based on the available resources of the target's GPU device, thereby reducing the wait time of the VM to use the GPU. With this approach, we prevent resource shortages and minimize performance degradation for GPGPU operations running on multiple VMs. Our proposed method can prevent GPU memory shortage, improve GPGPU task performance by up to 14%, and improve GPU computational performance by up to 82%. In addition, experiments show that the migration of GPGPU tasks minimizes the impact on other VMs.

show abstract

Section: Discussionmentioning

confidence: 99%

Partial migration technique for GPGPU tasks to Prevent GPU Memory Starvation in RPC‐based GPU Virtualization

Kang

Lim

2020

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…A. Aroca et al [28] performed competitive ratio analysis on approximate solutions for the VM placement issue with restrictions on the number of VMs and PMs. Melhem et al [29] proposed a Markov prediction model for VM placement in live VM migration to determine the set of candidate destination hosts that would be able to receive the migrated VMs in a way that avoids their VM migration in the near future. However, they did not consider how to determine the under-loaded, over-loaded, or normal loaded status, which is also important for VM consolidation.…”

Section: Vm Placementmentioning

confidence: 99%

Energy-efficient and quality-aware VM consolidation method

et al. 2020

Future Generation Computer Systems

View full text Add to dashboard Cite

To improve resource utilization and energy efficiency, cloud datacenters use VM consolidation to consolidate VMs to less number of physical machines through VM migration. However, improper VM placement may cause frequent VM migrations and constant on-off switch on physical machines (PMs), which results in decreasing service quality and increasing energy consumption. To address this problem, in this paper, we propose an effective and efficient VM consolidation approach called EQ-VMC with the goal to optimize energy efficiency and service quality. In our approach, a discrete differential evolution algorithm is developed to search the global optimum solution of VM placement. By integrating it with a set of algorithms we propose for effective host overloading detection, VM selection and under-loaded host detection, EQ-VMC effectively reduces energy consumption and improves quality of services (QoS). Extensive simulation demonstrates its effectiveness and shows its advantage compared with previous VM consolidation methods.

show abstract

“…In their previous study, Melhen et al suggested a method for identifying underloaded and overloaded PMs using Markov chains. The current state of PMs is determined by comparing the CPU utilization with upper and lower thresholds; the future load is predicted using the proposed Markov chain.…”

Section: Related Workmentioning

confidence: 99%

Burst‐aware virtual machine migration for improving performance in the cloud

Rahmani

Khajehvand

2020

Int J Communication

View full text Add to dashboard Cite

Burst is a common pattern in the user's requirements, which suddenly increases the workload of virtual machines (VMs) and reduces the performance and energy efficiency of cloud computing systems (CCS). Virtualization technology with the ability to migrate VMs attempts to solve this problem. By migration, VMs can be dynamically consolidated to the users' requests. Burst temporarily increases the workload. Ignoring this issue will lead to incorrect decisions regarding the migration of VMs. It increases the number of migrations and Service Level Agreement Violations (SLAVs) due to overload. This may cause waste of resources, increase in energy consumption, and misplaced VMs. Therefore, a burst-aware method for these issues is proposed in this paper. The method consists of two algorithms: one for determining the migration time and the other for the placement of VMs. We use the PlanetLab real dataset and CloudSim simulator to evaluate the performance of the proposed method. The results confirm the advantages of the method regarding performance compared to benchmark methods.

show abstract

Markov Prediction Model for Host Load Detection and VM Placement in Live Migration

Cited by 68 publications

References 29 publications

Partial migration technique for GPGPU tasks to Prevent GPU Memory Starvation in RPC‐based GPU Virtualization

Partial migration technique for GPGPU tasks to Prevent GPU Memory Starvation in RPC‐based GPU Virtualization

Energy-efficient and quality-aware VM consolidation method

Burst‐aware virtual machine migration for improving performance in the cloud

Contact Info

Product

Resources

About