Scheduling Proxy : Enabling Adaptive-Grained Scheduling for Global Computing System(<Special Section>Internet Technology V)
スポンサーリンク
概要
- 論文の詳細を見る
Global computing system (GCS) harnesses the idle CPU resources of clients connected to Internet for solving large problems that require high volume of computing power. Since GCS scale to millions of clients, many projects usually adopt coarse-grained scheduling in order to reduce server-side contention at the expense of sacrificing the degree of parallelism and wasting CPU resources. In this paper, we propose a new type of client, i.e., a scheduling proxy that enables adaptive-grained scheduling between the server and clients. While the server allocates coarse-grained work units to scheduling proxies alone, clients download fine-grained work units from a relatively nearby scheduling proxy not from the distant server. By computation of small work units at client side, the turnaround time of work unit can be reduced and the waste of CPU time by timeout can be minimized without increasing the performance cost of contention at the server. In addition, in order not to lose results in the failure of scheduling proxies, we suggest a technique of result caching in clients.
- 社団法人電子情報通信学会の論文
- 2005-04-01
著者
-
Park Daeyeon
Korea Advanced Inst. Sci. And Technol. Daejeon Kor
-
Park Daeyeon
Department Of Electrical Engineering And Computer Science Korea Advanced Institute Of Science And Te
-
HAN Jaesun
Department of Electrical Engineering and Computer Science [Division of Electrical Engineering], Kore
-
Han Jaesun
Department Of Electrical Engineering And Computer Science Korea Advanced Institute Of Science And Te
関連論文
- Mirinae: A Peer-to-Peer Overlay Network for Content-Based Publish/Subscribe Systems(Network)
- S-VFS: Searchable Virtual File System for an Intelligent Ubiquitous Storage(System Programs)
- TLB Update-Hint : A Scalable TLB Consistency Algorithm for Cache-Coherent Non-uniform Memory Access Multiprocessors(Networking and System Architectures)(Hardware/Software Support for High Performance Scientific and Engineering Computing)
- Mitigating Data Fragmentation for Small File Accesses
- MTCP: A Transmission Control Protocol for Multi-Provider Environment(Network)
- Scheduling Proxy : Enabling Adaptive-Grained Scheduling for Global Computing System(Internet Technology V)
- Reducing Replication Overhead for Data Durability in DHT Based P2P System(Dependable Computing)
- Efficient and Tailored Resource Management for the P2P Web Caching(Network System,Parallel/Distributed Processing and Systems)
- Hybrid Schemes and Variable-Size Subblock TLBs : Aggressive Superpage Supports
- Efficient and Scalable Client Clustering for Web Proxy Cache(Special Issue on Parallel and Distributed Computing, Applications and technologies)