Paper Info
Title
Proteus: Power Proportional Memory Cache Cluster in Data Centers
Abstract
In this paper, we describe the design, implementation and evaluation of Proteus, a power-proportional cache cluster which eliminates the delay penalty during server provisioning dynamics. To speed up data center services, a cache cluster is used in front of the database tier, providing fast in-cache data access. Since the number of cache servers is large, building power-proportional cache clusters can lead to considerable monetary savings. Dynamic server provisioning, one common methodology for realizing power proportionality in data centers, calls for agile load balancing schemes and smart in-cache data migration algorithms when applied to cache clusters. Otherwise, it induces unacceptable delay spikes due to data re-allocation among cache servers. Proteus addresses both challenges by using a specifically designed virtual nodes placement algorithm and an amortized data migration policy. We implement Proteus, and evaluate it on a 40-server cluster using real Wikipedia data and workload traces. The results show that, with Proteus, the load distribution is much more evenly balanced compared to the case of applying unmodified consistent hashing. At the same time, Proteus induces almost no extra delay during provisioning transitions, which is a significant advantage over other state-of-the-art solutions.
Year
DOI
Venue
2013
10.1109/ICDCS.2013.50
ICDCS
Keywords
Field
DocType
wikipedia data,amortized data migration policy,load balancing,smart in-cache data,power aware computing,workload traces,power proportional memory,computer centres,agile load balancing schemes,delay spikes,smart in-cache data migration algorithms,cache storage,bloom filter,data center services,cache server,dynamic server provisioning,in-cache data access,data center,resource allocation,real wikipedia data,database tier,data centers,virtual nodes,energy proportionality,power proportionality,server provisioning dynamics,power-proportional cache cluster,memcached,amortized data,data re-allocation,proteus,cache cluster,data center service,power proportional memory cache cluster,delay penalty,data access,algorithm design and analysis,load balance,web servers,clustering algorithms,databases,data migration,load distribution
Cache-oblivious algorithm,Cache invalidation,Cache pollution,Cache,Computer science,Computer network,Cache algorithms,Page cache,Cache coloring,Smart Cache,Distributed computing
Conference
ISSN
Citations 
PageRank 
1063-6927
5
0.43
References 
Authors
16
6
Name
Order
Citations
PageRank
Shen Li1342.22
ShiGuang Wang239820.97
Fan Yang391.15
Shaohan Hu449930.70
Fatemeh Saremi5435.04
Tarek Abdelzaher610179729.36