This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: USENIX Association 7th USENIX Conference on File and Storage Technologies 99 CA-NFS: A Congestion-Aware Network File System Alexandros Batsakis NetApp Johns Hopkins University Randal Burns Johns Hopkins University Arkady Kanevsky NetApp James Lentini NetApp Thomas Talpey NetApp Abstract We develop a holistic framework for adaptively schedul- ing asynchronous requests in distributed file systems. The system is holistic in that it manages all resources, including network bandwidth, server I/O, server CPU, and client and server memory utilization. It acceler- ates, defers, or cancels asynchronous requests in order to improve application-perceived performance directly. We employ congestion pricing via online auctions to co- ordinate the use of system resources by the file system clients so that they can detect shortages and adapt their resource usage. We implement our modifications in the Congestion-Aware Network File System (CA-NFS), an extension to the ubiquitous network file system (NFS). Our experimental result shows that CA-NFS results in a 20% improvement in execution times when compared with NFS for a variety of workloads. 1 Introduction Distributed file system clients consume server and net- work resources without consideration for how their op- erations interfere with their future requests and other clients. Each client request incurs a cost to the sys- tem, expressed in increased load to one or more of its resources. As more capacity, more workload, or more users are added congestion rises, and all client operations share the cost in delayed execution. However, clients re- main oblivious to the congestion level of the system re- sources. When the system is under congestion, network file servers try to maximize throughput across clients, as- suming that their benefit increases with the flow rate. This practice does not correspond well with application- perceived performance because it fails to distinguish the urgency and relative priority of file system opera- tions across the client population. From the servers perspective, all client operations at any given time are equally important. This is a fallacy. File system opera- tions come at different priorities implicitly. While some need to be performed on demand, many can be deferred. Synchronous client operations (metadata, reads) bene- fit more from timely execution than asynchronous op- erations (most writes, read-aheads), because the former block the calling application until completion. Also, cer- tain asynchronous operations are more urgent than oth- ers depending on the clients state. For example, when a clients memory consumption is high, all of its write op- erations become synchronous, leading to a degradation in system performance....
View Full Document
This note was uploaded on 12/08/2011 for the course CS 525 taught by Professor Gupta during the Spring '08 term at University of Illinois, Urbana Champaign.
- Spring '08