Paper Info
Title
A deduplication study for host-side caches in virtualized data center environments
Abstract
Flash memory-based caches inside VM hypervisors can reduce I/O latencies and offload much of the I/O traffic from network-attached storage systems deployed in virtualized data centers. This paper explores the effectiveness of content deduplication in these large (typically 100s of GB) host-side caches. Previous deduplication studies focused on data mostly at rest in backup and archive applications. This study focuses on cached data and dynamic workloads within the shared VM infrastructure. We analyze I/O traces from six virtual desktop infrastructure (VDI) I/O storms and two longterm CIFS studies and show that deduplication can reduce the data footprint inside host-side caches by as much as 67%. This in turn allows for caching a larger portion of the data set and improves the effective cache hit rate. More importantly, such increased caching efficiency can alleviate load from networked storage systems during I/O storms when most VM instances perform the same operation such as virus scans, OS patch installs, and reboots.
Year
DOI
Venue
2013
10.1109/MSST.2013.6558437
MSST
Keywords
Field
DocType
longterm cifs study,vm instances,computer centres,deduplication study,content deduplication,virtual desktop infrastructure,virus scans,i/o latency,cache storage,vdi i/o storms,i/o traffic,virtual machines,network-attached storage systems,host-side caches,reboots,shared vm infrastructure,input-output programs,cached data,networked storage systems,virtualisation,virtualized data centers,flash memory-based caches,dynamic workloads,cache hit rate,caching efficiency,i/o traces,vm hypervisors,data footprint,os patch installs,virtualized data center environments,flash memories,market research,storms,servers,organizations,data set
Virtualization,Data deduplication,Cache,Computer science,Server,Hypervisor,Virtual desktop,Data center,Operating system,Backup
Conference
ISSN
ISBN
Citations 
2160-195X
978-1-4799-0217-0
1
PageRank 
References 
Authors
0.35
0
2
Name
Order
Citations
PageRank
Jingxin Feng110.69
Jiri Schindler241126.82