RBA: A best effort resource allocation algorithm for asynchronous real-time distributed systems

被引:0
作者
Ravindran, B [1 ]
Hegazy, T [1 ]
机构
[1] Virginia Polytech Inst & State Univ, Bradley Dept Elect & Comp Engn, Blacksburg, VA 24061 USA
来源
JOURNAL OF RESEARCH AND PRACTICE IN INFORMATION TECHNOLOGY | 2001年 / 33卷 / 02期
关键词
adaptive resource allocation; asynchronous distributed systems; benefit accrual model; best effort scheduling; real-time Ethernet; real-time systems; quality of service;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present a best effort resource allocation algorithm called RBA for asynchronous realtime distributed systems. The algorithm uses Jensen's benefit functions for expressing application timeliness requirements and proposes adaptation functions to describe the anticipated application workload during future time intervals. Furthermore, RBA considers an adaptation model where subtasks of application tasks may be replicated at run-time for sharing workload increases, and a real-time Ethernet system model where message collisions are deterministically resolved. Given such application, adaptation, and system models, the algorithm's objective is to maximise aggregate application benefit and minimise aggregate missed deadline ratio. Since determining the optimal allocation is computationally intractable, RBA heuristically computes the number of replicas that are needed for task subtasks and their processor assignment such that the resulting allocation is as "close" as possible to the optimal allocation. We also experimentally study RBA's performance under different scheduling and routing algorithms. The experimental results reveal that RBA produces higher aggregate benefit and lower missed deadline ratio under DASA than when the RED algorithm is used for scheduling and routing.
引用
收藏
页码:158 / 172
页数:15
相关论文
共 50 条
[21]   A best-effort communication protocol for real-time broadcast networks [J].
Ramaswamy, L ;
Ravindran, B .
2002 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, PROCEEDING, 2002, :519-526
[22]   Time and Cost Efficient Cloud Resource Allocation for Real-Time Data-Intensive Smart Systems [J].
Qureshi, Muhammad Shuaib ;
Qureshi, Muhammad Bilal ;
Fayaz, Muhammad ;
Zakarya, Muhammad ;
Aslam, Sheraz ;
Shah, Asadullah .
ENERGIES, 2020, 13 (21)
[23]   Feedback control-based dynamic resource management in distributed real-time systems [J].
He, Tian ;
Stankovic, John A. ;
Marley, Michael ;
Lu, Chenyang ;
Lu, Ying ;
Abdelzaher, Tarek ;
Son, Sang ;
Tao, Gang .
JOURNAL OF SYSTEMS AND SOFTWARE, 2007, 80 (07) :997-1004
[24]   Resource reservation in dynamic real-time systems [J].
Abeni, L ;
Buttazzo, G .
REAL-TIME SYSTEMS, 2004, 27 (02) :123-167
[25]   Resource Reservation in Dynamic Real-Time Systems [J].
Luca Abeni ;
Giorgio Buttazzo .
Real-Time Systems, 2004, 27 :123-167
[26]   Simple Asynchronous Remote Invocations for Distributed Real-Time Java']Java [J].
Val, P. Basanta ;
Garcia-Valls, M. ;
Estevez-Ayres, I. .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2009, 5 (03) :289-298
[27]   AN ENVIRONMENT FOR DISTRIBUTED PROTOTYPING OF REAL-TIME SYSTEMS [J].
ALONSO, A ;
DUENAS, JC ;
LEON, G ;
DELAPUENTE, JA .
CONTROL ENGINEERING PRACTICE, 1995, 3 (06) :871-876
[28]   PERFORMABILITY ANALYSIS OF DISTRIBUTED REAL-TIME SYSTEMS [J].
ISLAM, SMR ;
AMMAR, HH .
IEEE TRANSACTIONS ON COMPUTERS, 1991, 40 (11) :1239-1251
[29]   Intelligent feedback control-based adaptive resource management for asynchronous, decentralized real-time systems [J].
Ravindran, B ;
Kachroo, P ;
Hegazy, T .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2001, 31 (02) :261-265
[30]   A methodology for the development of distributed real-time control applications with focus on task allocation in heterogeneous systems [J].
Prayati, A ;
Koulamas, C ;
Koubias, S ;
Papadopoulos, G .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2004, 51 (06) :1194-1207