Piccolo: A Fast and Efficient Rollback System for Virtual Machine Clusters

Cui, Lei; Hao, Zhiyu; Wang, Chonghua; Fei, Haiqiang; Ding, Zhenquan

doi:10.1109/icpp.2016.17

Cited by 3 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 depicts the efforts that addressed the NVE issues. We notice that most current efforts [84,85,[87][88][89][90][91][92][93], are proposing failover mechanisms. This is possible thanks to virtualization, in contrast to the case of PNF.…”

Section: Fault Management Frameworkmentioning

confidence: 98%

“…Rollback: This is one of the well-known techniques providing fault tolerance. Rollback (or snapshot) is a way to recover a system transparently with low cost [92]. The snapshot represents the correct running state of a VNF.…”

Section: Self-healingmentioning

confidence: 99%

“…However, the rollback procedure extends the service downtime compared to normal system reinitialisation, primarily due to the significant size of the snapshot which is proportional to the VM size. Cui et al [92] and Shi et al [93], aim to reduce the rollback latency problem. For instance, Cui et al [92], proposed a rollback system which takes advantage of the similarity among VMs, and leverages multicast to transfer the identical pages across VMs to disperse hosts with a single copy, rather than delivering them independently.…”

Section: Self-healingmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Fault Management in Network Virtualization Environments: Challenges and Solutions

Cherrared

Imadali

Fabre

et al. 2019

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

The advent of 5G and the ever increasing stringent requirements in terms of bandwidth, latency, and quality of service pushes the boundaries of what is feasible with legacy Mobile Network Operators' technologies. Network Functions Virtualization (NFV) is a promising attempt at solving some of these challenges that is widely adopted by the industry and specified by the standardization bodies. In essence, NFV is about running Network Functions (NFs) as virtualized workloads on commodity hardware. This may optimize deployment costs and simplify the lifecycle management of NFs, but it introduces new fault management challenges and issues. In this paper, we propose a comprehensive state of the art of fault management techniques. We address the impact of virtualization in fault management. We propose a new classification of the recent fault management research achievements in the network virtualization environments and compare their major contributions and shortcomings.

show abstract

Section: Fault Management Frameworkmentioning

confidence: 98%

Section: Self-healingmentioning

confidence: 99%

Section: Self-healingmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Fault Management in Network Virtualization Environments: Challenges and Solutions

Cherrared

Imadali

Fabre

et al. 2019

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…VirtCo focuses on placing the VM well in advance to its launch based on the coflow information between the VM. The coflow information is determined based on Cui et al 20 …”

Section: Related Workmentioning

confidence: 99%

“…VirtCo focuses on placing the VM well in advance to its launch based on the coflow information between the VM. The coflow information is determined based on Cui et al 20 The authors 21 included SLAs and statistical methods for VMP along with improving resource utilization. According to the available statistical data on resource utilization, a forecasting model was built using the neural networks.…”

Section: Related Workmentioning

confidence: 99%

An efficient virtual machine allocation using single stage weapon target assignment model in cloud software‐defined network environment

Padmavathy

Anitha

2022

Int J Communication

View full text Add to dashboard Cite

Summary With the rapid growth of the Internet, technological advancements, and the increasing number of cloud users, a paradigm transformation towards separate data and control planes with a centralized control point is taking place. As a result of this separation, software‐defined networks (SDNs) have distinct software controllers for routers and the capacity to manage network behavior. Virtual machine placement (VMP) and virtual machine migration (VMM) are two examples of SDN usage in data centers. The issue of VMP in cloud environments is a significant challenge that has been widely researched but not fully resolved. In this research, we used the single stage weapon target assignment (SSWTA) to model the virtual machine allocation (VMA) for jobs in order to maximize the resource utilization of the physical machines (PMs) by reducing idle time. Furthermore, this research proposes three algorithms: job assignment algorithms, PM allocation (PMA) using the least recently used (LRU) policy, and optimal VMA. The proposed VMA's performance is compared to other related VMA models such as first fit decreasing, and it is determined to be efficient in terms of resource utilization.

show abstract