TY - GEN
T1 - CloudCache
T2 - 14th USENIX Conference on File and Storage Technologies, FAST 2016
AU - Arteaga, Dulcardo
AU - Cabrera, Jorge
AU - Xu, Jing
AU - Zhao, Ming
AU - Sundararaman, Swaminathan
N1 - Funding Information:
We thank the anonymous reviewers and our shepherd, Carl Waldspurger, for the thorough reviews and insightful suggestions. This research is sponsored by National Science Foundation CAREER award CNS-125394 and Department of Defense award W911NF-13-1-0157.
PY - 2019
Y1 - 2019
N2 - Host-side flash caching has emerged as a promising solution to the scalability problem of virtual machine (VM) storage in cloud computing systems, but it still faces serious limitations in capacity and endurance. This paper presents CloudCache, an on-demand cache management solution to meet VM cache demands and minimize cache wear-out. First, to support on-demand cache allocation, the paper proposes a new cache demand model, Reuse Working Set (RWS), to capture only the data with good temporal locality, and uses the RWS size (RWSS) to model a workload's cache demand. By predicting the RWSS online and admitting only RWS into the cache, CloudCache satisfies the workload's actual cache demand and minimizes the induced wear-out. Second, to handle situations where a cache is insufficient for the VMs' demands, the paper proposes a dynamic cache migration approach to balance cache load across hosts by live migrating cached data along with the VMs. It includes both on-demand migration of dirty data and background migration of RWS to optimize the performance of the migrating VM. It also supports rate limiting on the cache data transfer to limit the impact to the co-hosted VMs. Finally, the paper presents comprehensive experimental evaluations using real-world traces to demonstrate the effectiveness of CloudCache.
AB - Host-side flash caching has emerged as a promising solution to the scalability problem of virtual machine (VM) storage in cloud computing systems, but it still faces serious limitations in capacity and endurance. This paper presents CloudCache, an on-demand cache management solution to meet VM cache demands and minimize cache wear-out. First, to support on-demand cache allocation, the paper proposes a new cache demand model, Reuse Working Set (RWS), to capture only the data with good temporal locality, and uses the RWS size (RWSS) to model a workload's cache demand. By predicting the RWSS online and admitting only RWS into the cache, CloudCache satisfies the workload's actual cache demand and minimizes the induced wear-out. Second, to handle situations where a cache is insufficient for the VMs' demands, the paper proposes a dynamic cache migration approach to balance cache load across hosts by live migrating cached data along with the VMs. It includes both on-demand migration of dirty data and background migration of RWS to optimize the performance of the migrating VM. It also supports rate limiting on the cache data transfer to limit the impact to the co-hosted VMs. Finally, the paper presents comprehensive experimental evaluations using real-world traces to demonstrate the effectiveness of CloudCache.
UR - http://www.scopus.com/inward/record.url?scp=85077199685&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077199685&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85077199685
T3 - Proceedings of the 14th USENIX Conference on File and Storage Technologies, FAST 2016
SP - 355
EP - 369
BT - Proceedings of the 14th USENIX Conference on File and Storage Technologies, FAST 2016
PB - USENIX Association
Y2 - 22 February 2016 through 25 February 2016
ER -