Paper Info
Title
Policy expressivity in the Anzere personal cloud
Abstract
We present a technique for partially replicating data items at scale according to expressive policy specifications. Recent projects have addressed the challenge of policy-based replication of personal data (photos, music, etc.) within a network of devices, as an alternative to centralized online services. To date, the policies supported by such systems have been relatively simple, in order to facilitate scaling the policy calculation to large numbers of items. In this paper, we show how such replication systems can scale while supporting much more expressive policies than previous schemes: item replication expressed as constraints, devices referred to by predicates rather than explicitly named, and replication to storage nodes acquired on-demand from the cloud. These extensions introduce considerable complexity in policy evaluation, but we show a system can scale well by using equivalence classes to reduce the problem space. We validate our approach via deployment on an ensemble of devices (phones, PCs, cloud virtual machines, etc.), and show that it supports rich policies and high data volumes using simulations and real data based on personal usage in our group.
Year
DOI
Venue
2011
10.1145/2038916.2038930
SoCC
Keywords
Field
DocType
high data volume,replication system,data item,personal data,item replication,anzere personal cloud,expressive policy,policy-based replication,policy expressivity,policy calculation,expressive policy specification,overlay network,cloud computing,virtual machine,overlay networks
Software deployment,Virtual machine,Computer science,Equivalence class,Scaling,Overlay network,Cloud computing,Expressivity,Personal cloud,Distributed computing
Conference
Citations 
PageRank 
References 
7
0.78
20
Authors
5
Name
Order
Citations
PageRank
Riva165439.32
Qin Yin270.78
Dejan Juric31447.08
Ercan Ucan4121.91
Timothy Roscoe53118299.48