Reducing Virtual Machine Live Migration Overhead via Workload Analysis

Baruchi, Artur; Midorikawa, Edson Toshimi; Sato, Líria Matsumoto

doi:10.1109/tla.2015.7106373

Cited by 10 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our previous results showed substantial reduction in network data traffic and live migration time when using workload cycle recognition for live migration [5,23]. Here we present a more detailed evaluation with more VMs, additional applications, and new insights and discussions.…”

Section: Discussionmentioning

confidence: 73%

Exploiting Workload Cycles for Orchestration of Virtual Machine Live Migrations in Clouds

Baruchi¹,

Midorikawa²,

Sato³

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

Virtual machine live migration in cloud environments aims at reducing energy costs and increasing resource utilization. However, its potential has not been fully explored because of simultaneous migrations that may cause user application performance degradation and network congestion. Research efforts on live migration orchestration policies still mostly rely on system level metrics. This work introduces an Application-aware Live Migration Architecture (ALMA) that selects suitable moments for migrations using application characterization data. This characterization consists in recognizing resource usage cycles via Fast Fourier Transform. From our experiments, live migration times were reduced by up to 74% for benchmarks and by up to 67% for real applications, when compared to migration policies with no application workload analysis. Network data transfer during the live migration was reduced by up to 62%.

show abstract

Section: Discussionmentioning

confidence: 73%

Exploiting Workload Cycles for Orchestration of Virtual Machine Live Migrations in Clouds

Baruchi¹,

Midorikawa²,

Sato³

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It significantly reduces the unnecessary migration of memory pages. Baruchi et al [11] introduced a method to identify the workload cycles of a VM based on the information to reduce live migration overhead. Ruan et al [12] proposed a novel data filter mechanism to improve the performance of the pre-copy algorithm in terms of the migration time and the amount of migrated data.…”

Section: Related Workmentioning

confidence: 99%

“…Many live migration algorithms have been proposed to minimize both downtime and total migration time. In terms of the memory data transfer order, live migration algorithms can be classified into three categories: the pre-copy algorithm [3,[9][10][11][12], the post-copy algorithm [13][14][15], and the hybrid-copy algorithm [16][17][18].…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid-Copy Algorithm for Live Migration of Virtual Machine

et al. 2017

View full text Add to dashboard Cite

Live migration of virtual machines is an important approach for dynamic resource scheduling in cloud environment. The hybrid-copy algorithm is an excellent algorithm that combines the pre-copy algorithm with the post-copy algorithm to remedy the defects of the pre-copy algorithm and the post-copy algorithm. Currently, the hybrid-copy algorithm only copies all memory pages once in advance. In a write-intensive workload, copy memory pages once may be enough. However, more iterative copy rounds can significantly reduce the page faults in a read-intensive workload. In this paper, we propose a new parameter to decide the appropriate time to stop the iterative copy phase based on real-time situation. We use a Markov model to forecast the memory access pattern. Based on the predicted results and the analysis of the actual situation, the memory page transfer order would be adjusted to reduce the invalid transfers. The novel hybrid-copy algorithm is implemented on the Xen platform. The experimental results demonstrate that our mechanism has good performance both on read-intensive workloads and write-intensive workloads.

show abstract

“…Em Baruchi, Midorikawa e Sato (2015), os autores argumentam que a live migration degrada severamente o desempenho das VMs, e que saber o momento certo para fazer a migração pode resultar em menores perdas. Com o histórico e a identificação das cargas foi possível obter a Transformada de Fourier de tais informações, o que permitiu extrair o tamanho do ciclo das requisições, possibilitando que a migração aconteça nos melhores instantes.…”

Section: Trabalhos Relacionadosunclassified

Avaliação de Desempenho de Técnicas de Migração de Máquinas Virtuais para o Ambiente de Computação em Nuvem

et al. 2017

View full text Add to dashboard Cite

As ferramentas de virtualização têm um papel fundamental no crescimento da utilização da Computação em Nuvem. Por meio da virtualização, é possível realizar a migração de máquinas virtuais dentro de um provedor de serviços de nuvem, proporcionando a utilização eficiente dos recursos. Entretanto, não oram evidenciadas quais técnicas são mais indicadas de acordo com os cenários distintos de carga no qual o sistema está operando. Diferentemente das avaliações de desempenhos simplesmente comparativas encontradas na literatura, este trabalho propõe a utilização de um modelo estatístico consistente para avaliação de desempenho das técnicas de migração: (i) live migration e (ii) non-live migration. O objetivo do modelo estatístico é identificar o comportamento das técnicas de migração de máquinas virtuais sob diferentes situações de cargas de trabalho. O modelo estatístico proposto para utilização é composto pela abordagem de avaliação de desempenho das técnicas de migração de máquina virtual combinado com o planejamento de experimentos de projeto fatorial 2k.Palavras-chave: Migração. Máquinas Virtuais. Avaliação de Desempenho. AbstractPerformance evaluation of virtual machine migration approaches on cloud computign environment Virtualization tools play a key role in increasing the use of Cloud Computing. Through virtualization, it is possible to migrate virtual machines within a cloud service provider, providing efficient resource utilization. However, there are not evident which techniques work better in according to the different load scenarios in which the system is operating. This work proposes the use of a consistent statistical model to evaluate the performance of migration techniques:(i) live migration and (ii) non-live migration. The objective of the statistical model is to identify the behavior of virtual machine migration techniques under different workload situations. The proposed statistical model for use is based on the performance evaluation approach of the virtual machine migration techniques combined with the 2k factorial design.Keywords: Migration. Performance Evaluation. Virtual Machine.

show abstract

Reducing Virtual Machine Live Migration Overhead via Workload Analysis

Cited by 10 publications

References 22 publications

Exploiting Workload Cycles for Orchestration of Virtual Machine Live Migrations in Clouds

Exploiting Workload Cycles for Orchestration of Virtual Machine Live Migrations in Clouds

A Novel Hybrid-Copy Algorithm for Live Migration of Virtual Machine

Avaliação de Desempenho de Técnicas de Migração de Máquinas Virtuais para o Ambiente de Computação em Nuvem

Contact Info

Product

Resources

About