Title
Storage performance virtualization via throughput and latency control
Abstract
I/O consolidation is a growing trend in production environments due to the increasing complexity in tuning and managing storage systems. A consequence of this trend is the need to serve multiple users/workloads simultaneously. It is imperative to make sure that these users are insulated from each other by visualization in order to meet any service level objective (SLO). This paper presents a 2-level scheduling framework that can be built on top of an existing storage utility. This framework uses a low-level feedback-driven request scheduler, called AVATAR, that is intended to meet the latency bounds determined by the SLO. The load imposed on AVATAR is regulated by a high-level rate controller, called SARC, to insulate the users from each other. In addition, SARC is work-conserving and tries to fairly distribute any spare bandwidth in the storage system to the different users. This framework naturally decouples rate and latency allocation. Using extensive I/O traces and a detailed storage simulator, we demonstrate that this 2-level framework can simultaneously meet the latency and throughput requirements imposed by an SLO, without requiring extensive knowledge of the underlying storage system.
Year
DOI
Venue
2005
10.1145/1168910.1168913
ACM Transactions on Storage
Keywords
DocType
Volume
processor scheduling,storage system management,slo,i/o scheduling,virtualization,avatar,two-level framework,existing storage utility,fairness,quality of service,storage management,latency allocation,couple rate,performance isolation,decouples rate,service level objective,o consolidation,sarc,i-o consolidation,feedback-driven request scheduler,latency control,detailed storage simulator,o trace,2-level scheduling framework,high-level rate controller,2-level framework,throughput control,storage system,storage systems,underlying storage system,storage performance virtualization,two-level scheduling framework,service level
Conference
2
Issue
ISSN
ISBN
3
1526-7539
0-7695-2458-3
Citations 
PageRank 
References 
72
2.79
18
Authors
5
Name
Order
Citations
PageRank
Jianyong Zhang11146.08
Anand Sivasubramaniam24485291.86
Qian Wang318412.32
Alma Riska468348.63
Erik Riedel51037142.99