Home-cluster based processor scheduling with page placement for NUMA multiprocessors

被引：0
作者：
Koita, T [1 ]
Katayama, T [1 ]
Saisho, K [1 ]
Fukuda, A [1 ]
机构：
[1] Nara Inst Sci & Technol, Nara 6300101, Japan
来源：
INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, PROCEEDINGS | 1999年
关键词：
processor scheduling; dynamic space-sharing; page placement; NUMA multiprocessors; multiprogrammed environments;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper proposes a home-cluster based policy for cluster-based NUMA (Non-Uniform Memory Access) multiprocessors. The home-cluster is a reserved cluster for processor and memory page allocation to a process. The policy consists of a processor scheduling scheme and a page placement scheme. Both schemes work together based on the concept of the home-cluster. The policy focuses on not only the processor scheduling scheme but also the page placement scheme. Several alternatives of the home-cluster based policy are examined. And then, the home-cluster based policy is compared with other policies which are the combinations of an existing processor scheduling scheme and a conventional page placement scheme. The simulation results show that the proposed policy performs better than the others because it can reduce remote access overhead and mean response time of a process.
引用
收藏
页码：539 / 545
页数：7
相关论文
共 13 条
  • [1] BOLOSKY WJ, 1991, SIGPLAN NOTICES, V26, P212, DOI 10.1145/106973.106994
  • [2] Feitelson D. G., 1994, SURVEY SCHEDULING MU
  • [3] FUKUDA A, 1993, P INT COMP SOFTW APP, P343, DOI 10.1109/CMPSAC.1993.404239
  • [4] GUPTA A, 1991, P 1991 ACM SIGMETRIC, P120
  • [5] KAI H, 1994, P 6 JOINT S PAR PROC, P319
  • [6] Koita T., 1998, Proceedings of the 16th IASTED International Conference. Applied Informatics, P265
  • [7] Koita T, 1998, INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-IV, PROCEEDINGS, P851
  • [8] EXPERIMENTAL COMPARISON OF MEMORY MANAGEMENT POLICIES FOR NUMA MULTIPROCESSORS
    LAROWE, RP
    ELLIS, CS
    [J]. ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1991, 9 (04): : 319 - 363
  • [9] LAROWE RP, 1991, P 13 ACM S OP SYST P, P137
  • [10] A DYNAMIC PROCESSOR ALLOCATION POLICY FOR MULTIPROGRAMMED SHARED-MEMORY MULTIPROCESSORS
    MCCANN, C
    VASWANI, R
    ZAHORJAN, J
    [J]. ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1993, 11 (02): : 146 - 178
12