An Offline Equivalence Scheduling Technique for Time-Triggered Ethernet

被引:2
作者
Zhang, Shiqian [1 ]
Li, Zonghui [1 ]
Wang, Ningchen [1 ]
Wan, Hai [1 ]
Zhao, Xibin [1 ]
机构
[1] Tsinghua Univ, TNList, Key Lab Informat Syst Secur, Minist Educ,Sch Software, Beijing 100084, Peoples R China
来源
PROCEEDINGS OF 2018 6TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND BROADBAND NETWORKING (ICCBN 2018) | 2018年
关键词
Time-triggered Ethernet; scheduling; schedulability analysis; real-time embedded system;
D O I
10.1145/3193092.3193105
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Time-triggered networks, like TTEthernet, require tight communication latency and minimal jitter requirements. One efficient way to meet these requirements is pre-compute the transmission points of the frames on the network and stores the complete schedule within the local memory. This method avoids contentions of frames. However, as the size of network grows, the size of offline table increases and the memory requirements increase while memory is a scare resource. Due to the memory limitation, a table based scheduling approach might not be applicable. In this paper, we present an offline equivalence scheduling technique for Time-triggered Ethernet. Offline equivalence is an online policy that is equivalent to a given offline table to combine the advantages of both online and offline scheduling. Here online scheduling is used, and only deviations from offline table are required to be stored. We consider each end in dataflow as a real-time embedded system (end-station) and solve the scheduling problem based on offline equivalence technique. In the evaluation, we consider an ILP-based solver CPLEX as our baseline to test our new scheduler under three different typical topologies. The results show that offline equivalence scheduling technique achieves high schedulability ratio, and only having to store on average a few bytes of the offline schedule in small-medium network.
引用
收藏
页码:65 / 70
页数:6
相关论文
共 15 条
[1]  
[Anonymous], 2011, Real-Time Systems: Design Principles for Distributed Embedded Applications
[2]  
Baker T. P., 1988, CYCLIC EXECUTIVE MOD, V88
[3]  
Craciunas S. S., 2014, P 22 INT C REAL TIM, P45
[4]  
Fohler G, 1995, IEEE REAL TIME, P152, DOI 10.1109/REAL.1995.495205
[5]  
Honeywell Aerospace, 2014, APPL SPEC INT CIRC B
[6]  
Kopetz H, 2005, ISORC 2005: EIGHTH IEEE INTERNATIONAL SYMPOSIUM ON OBJECT-ORIENTED REAL-TIME DISTRIBUTED COMPUTING, PROCEEDINGS, P22
[7]   SCHEDULING ALGORITHMS FOR MULTIPROGRAMMING IN A HARD-REAL-TIME ENVIRONMENT [J].
LIU, CL ;
LAYLAND, JW .
JOURNAL OF THE ACM, 1973, 20 (01) :46-61
[8]  
Nasri M, 2017, IEEE REAL TIME, P75, DOI 10.1109/RTAS.2017.34
[9]   A General Constraint-centric Scheduling Framework for Spatial Architectures [J].
Nowatzki, Tony ;
Sartin-Tarm, Michael ;
De Carli, Lorenzo ;
Sankaralingam, Karthikeyan ;
Estan, Cristian ;
Robatmili, Behnam .
ACM SIGPLAN NOTICES, 2013, 48 (06) :495-506
[10]  
SHA L, 1991, KLUW REAL T, P129