Title
Characterizing Facebook's Memcached Workload
Abstract
Memcached is one of the world's largest key-value deployments. This article analyzes the Memcached workload at Facebook, looking at server-side performance, request composition, caching efficacy, and key locality. The observations presented here lead to several design insights and new research directions for key-value caches, such as the relative inadequacy of the least recently used (LRU) replacement policy.
Year
DOI
Venue
2014
10.1109/MIC.2013.80
IEEE Internet Computing
Keywords
Field
DocType
request composition,relative inadequacy,lru replacement policy,caching efficacy,key-value store,least recently used replacement policy,cache storage,workload analysis,key locality,facebook,key-value caches,memcached workload,server-side performance,social networking (online),cache efficiency,cache memory,key value store
World Wide Web,Locality,CPU cache,Computer science,Workload,Cache algorithms,Database,Workload management,The Internet
Journal
Volume
Issue
ISSN
18
2
1089-7801
Citations 
PageRank 
References 
10
0.56
0
Authors
4
Name
Order
Citations
PageRank
Yuehai Xu121710.91
Eitan Frachtenberg2106085.08
Song Jiang3117851.38
Mike Paleczny426211.38