TY - GEN
T1 - BlockFlex
T2 - 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022
AU - Reidys, Benjamin
AU - Sun, Jinghan
AU - Badam, Anirudh
AU - Noghabi, Shadi
AU - Huang, Jian
N1 - We thank the anonymous reviewers and our shepherd Swami Sundararaman for their helpful comments and feedback. We thank Íñigo Goiri for providing part of the cloud traces for our study as well as insightful discussions. This work is supported by NSF CAREER Award 2144796, CCF-1919044, CNS-1850317 and a grant from Western Digital Technologies, Inc.
PY - 2022
Y1 - 2022
N2 - Cloud platforms today make efficient use of storage resources by slicing them among multi-tenant applications on demand. However, our study discloses that cloud storage is still seriously underutilized for both allocated and unallocated storage. Although cloud providers have developed harvesting techniques to allow evictable virtual machines (VMs) to use unallocated resources, these techniques cannot be directly applied to storage resources, due to the lack of systematic support for the isolation of space, bandwidth, and data security in storage devices. In this paper, we present BlockFlex, a learning-based storage harvesting framework, which can harvest available flash-based storage resources at a fine-grained granularity in modern cloud platforms. We rethink the abstractions of storage virtualization and enable transparent harvesting of both allocated and unallocated storage for evictable VMs. BlockFlex explores both heuristics and learning-based approaches to maximize the storage utilization, while ensuring the performance and security isolation between regular and evictable VMs at the storage device level. We develop BlockFlex with programmable solid-state drives (SSDs) and demonstrate its efficiency with various datacenter workloads.
AB - Cloud platforms today make efficient use of storage resources by slicing them among multi-tenant applications on demand. However, our study discloses that cloud storage is still seriously underutilized for both allocated and unallocated storage. Although cloud providers have developed harvesting techniques to allow evictable virtual machines (VMs) to use unallocated resources, these techniques cannot be directly applied to storage resources, due to the lack of systematic support for the isolation of space, bandwidth, and data security in storage devices. In this paper, we present BlockFlex, a learning-based storage harvesting framework, which can harvest available flash-based storage resources at a fine-grained granularity in modern cloud platforms. We rethink the abstractions of storage virtualization and enable transparent harvesting of both allocated and unallocated storage for evictable VMs. BlockFlex explores both heuristics and learning-based approaches to maximize the storage utilization, while ensuring the performance and security isolation between regular and evictable VMs at the storage device level. We develop BlockFlex with programmable solid-state drives (SSDs) and demonstrate its efficiency with various datacenter workloads.
UR - http://www.scopus.com/inward/record.url?scp=85141058399&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141058399&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85141058399
T3 - Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022
SP - 17
EP - 33
BT - Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022
PB - USENIX Association
Y2 - 11 July 2022 through 13 July 2022
ER -