DC Field | Value | Language |
---|---|---|
dc.contributor.author | SONG, WONJUN | - |
dc.contributor.author | KIM, GWANGSUN | - |
dc.contributor.author | JUNG, HYUNGJOON | - |
dc.contributor.author | CHUNG, JONGWOOK | - |
dc.contributor.author | AHN, JUNG HO | - |
dc.contributor.author | LEE, JAE W. | - |
dc.contributor.author | KIM, JOHN | - |
dc.date.accessioned | 2018-12-04T02:57:00Z | - |
dc.date.available | 2018-12-04T02:57:00Z | - |
dc.date.created | 2018-11-12 | - |
dc.date.issued | 2017-04-12 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/94445 | - |
dc.description.abstract | NUMA (non-uniform memory access) servers are commonly used in high-performance computing and datacenters. Within each server, a processor-interconnect (e.g., Intel QPI, AMD HyperTransport) is used to communicate between the different sockets or nodes. In this work, we explore the impact of the processor-interconnect on overall performance -- in particular, the performance un- fairness caused by processor-interconnect arbitration. It is well known that locally-fair arbitration does not guarantee globally-fair bandwidth sharing as closer nodes receive more bandwidth in a multi-hop network. However, this work demonstrates that the opposite can occur in a commodity NUMA server where remote nodes receive higher bandwidth (and perform better). We analyze this problem and iden- tify that this occurs because of external concentration used in router micro-architectures for processor-interconnects without globally-aware arbitration. While accessing remote memory can occur in any NUMA system, performance un- fairness (or performance variation) is more critical in cloud computing and virtual machines with shared resources. We demonstrate how this unfairness creates significant performance variation when a workload is executed on the Xen virtualization platform. We then provide analysis using synthetic workloads to better understand the source of unfair- ness and eliminate the impact of other shared resources, including the shared last-level cache and main memory. To provide fairness, we propose a novel, history-based arbitration that tracks the history of arbitration grants made in the previous history window. A weighted arbitration is done based on the history to provide global fairness. Through simulations, we show our proposed history-based arbitration can provide global fairness and minimize the processor- interconnect performance unfairness at low cost. | - |
dc.language | English | - |
dc.publisher | ACM | - |
dc.relation.isPartOf | 2017 Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems | - |
dc.relation.isPartOf | Proceedings of 2017 Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems | - |
dc.title | History-Based Arbitration for Fairness in Processor-Interconnect of NUMA Servers | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 2017 Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, pp.765 - 777 | - |
dc.citation.conferenceDate | 2017-04-08 | - |
dc.citation.conferencePlace | CC | - |
dc.citation.conferencePlace | Xi'an, China | - |
dc.citation.endPage | 777 | - |
dc.citation.startPage | 765 | - |
dc.citation.title | 2017 Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems | - |
dc.contributor.affiliatedAuthor | KIM, GWANGSUN | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.