-
摘要:
在时间触发以太网(TTE)中,TT消息优先级最高,RC消息只能在TT消息调度的离散时间片内传输,因此,TT消息离线调度表的设计会对RC消息调度产生一定影响。针对这一问题,提出了基于最优时间片的改进加权轮询(MWRR)调度算法。首先,通过TT消息约束条件限制获得TT消息离线调度表,进而得到保证RC消息较大资源利用率的时间片信息;其次,在离散时间片对不同类型RC消息进行调度,并运用网络演算方法对其最坏端到端延迟进行分析;最后,通过实验仿真证实了本文算法不仅具有较低的复杂度和较好的公平性,保证了实际应用中算法的可行性,而且在时延性方面均优于先到先得(FIFO)、优先级(PQ)和加权轮询(WRR)调度算法。
-
关键词:
- 时间触发以太网(TTE) /
- 调度算法 /
- 速率约束 /
- 加权轮询(WRR) /
- 网络演算
Abstract:TT messages that have the top priority among three kinds of traffics affect RC message communication inevitably in time-triggered Ethernet (TTE). Therefore, RC messages have to be scheduled among discrete time slices caused by TT message offline schedule table. A modified weighted round robin (MWRR) scheduling method based on optimal time slice was proposed in this paper. Firstly, TT message offline schedule table was calculated satisfying the requirements of TT message constraints in order to get optimal time resources for RC flow transmission; secondly, different kinds of RC flows were scheduled in several time slices and the worst end to end delays were analyzed by network calculus in TTE; finally, experiments show that MWRR algorithm in the paper not only has low complexity, good fairness and feasibility in practical application, but also obtains better real-time performance than first input first output (FIFO), priority queue (PQ) and weighted round robin (WRR) scheduling algorithm.
-
表 1 TT消息参数
Table 1. Parameters of TT message
TT消息 周期/μs TT1~TT2 2 000 TT3~TT6 4 000 TT7~TT14 8 000 TT15~TT30 16 000 TT31~TT62 32 000 TT63~TT126 64 000 表 2 RC消息参数
Table 2. Parameters of RC message
BAG/μs 消息类型 航空控制类 数据通信类 多媒体 2 000 RC1~RC2 4 000 RC3 RC4~RC6 8 000 RC7~RC9 RC10~RC11 RC12~RC14 16 000 RC15~RC17 RC18~RC20 RC21~RC22 32 000 RC23 RC24~RC25 RC26~RC28 64 000 RC29~RC30 RC31~RC32 表 3 平均端到端延迟
Table 3. Average end to end delay
算法 平均端到端延迟/μs 航空控制类消息 数据通信类消息 多媒体消息 FIFO 2 472.8 2 469.1 2 478.2 PQ 481.4 1 142.1 8 152.6 WRR 1 998.3 2 657.8 3 496.2 MWRR 939.5 965.7 1 057.3 表 4 最坏端到端延迟
Table 4. The worst end to end delay
算法 最坏端到端延迟/μs 航空控制类消息 数据通信类消息 多媒体消息 FIFO 17 713 17 238 17 428 PQ 2 627 9 284 73 880 WRR 14 391 13 590 17 340 MWRR 7 797 8 097 9 553 -
[1] SAE International Group.Time-triggered Ethernet:AS6802[S].Washington, D.C.:SAE International, 2011. [2] HU M L, LUO J.Holistic scheduling of real-time applications in time-triggered in vehicle networks[J].IEEE Transactions on Industrial Informatics, 2014, 10(3):1817-1828. doi: 10.1109/TII.2014.2327389 [3] STEINER W.An evaluation of SMT-based schedule synthesis for time-triggered multi-hop networks[C]//2010 IEEE 31st Real-Time Systems Symposium.Piscataway, NJ:IEEE Press, 2010:375-384. [4] CRACIUNAS S S, OLIVE R S.SMT-based task and network-level static schedule generation for time-triggered networked systems[C]//International Conference on Real-Time Networks and Systems.New York:Association for Computing Machinery, 2014:45-54. [5] STEINER W.Synthesis of static communication schedules for mixed-criticality systems[C]//International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops.Piscataway, NJ:IEEE Press, 2011:11-18. [6] FREIER M, CHEN J J.Time-triggered communication scheduling analysis for real-time multicore systems[C]//IEEE International Symposium on Industrial Embedded Systems.Piscataway, NJ:IEEE Press, 2015:1-9. [7] GANDEVA B S, WISETO P A.Performance analysis of packet scheduling with QoS in IEEE 802.16e networks[C]//International Conference on Telecommunication Systems, Services and Applications.Piscataway, NJ:IEEE Press, 2012:4-8. [8] ELES P, DOBOLI A.Scheduling with bus access optimization for distributed embedded systems[J].IEEE Transactions on Very Large Scale Integration Systems, 2000, 8(5):472-491. doi: 10.1109/92.894152 [9] BOYER M, FRABOUL C.Tightening end to end delay upper bound for AFDX network calculus with rate latency FIFO servers using network calculus[C]//IEEE International Workshop on Factory Communication Systems.Piscataway, NJ:IEEE Press, 2008:11-20. [10] HE Z Z, MEN C G.Schedulability of fault tolerant real time system based on local optimum checkpoint under priority mixed strategy[J].Chinese Journal of Electronics, 2015, 24(2):236-244. doi: 10.1049/cje.2015.04.003 [11] ANIRUDHA S, MANJUNATH D.Revisiting WFQ:Minimum packet lengths tighten delay and fairness bounds[J].IEEE Communications Letters, 2007, 11(4):366-368. doi: 10.1109/LCOM.2007.348303 [12] ZHOU J, GUO Y F.Guaranteeing maximum reliability and minimum delay QoS routing based on WF2Q[C]//International Conference on Computational Intelligence and Security.Piscataway, NJ:IEEE Press, 2009:11-14. [13] XIN Y, DUAN Z.Fair round-robin:A low complexity packet scheduler with proportional and worst-case fairness[J].IEEE Transactions on Computers, 2009, 58(3):365-379. doi: 10.1109/TC.2008.176 [14] VALENTE P.Providing near-optimal fair-queueing guarantees at round-robin amortized cost[C]//The 22nd International Conference on Computer Communications and Networks (ICCCN).Piscataway, NJ:IEEE Press, 2013:1-7. [15] FUCHSEN R.A new technology for the Scarlett program[J].IEEE Transactions on Aerospace and Electronic Systems, 2010, 25(10):10-16. doi: 10.1109/MAES.2010.5631720 [16] 徐晓飞, 曹晨, 郭骏, 等.TT-RMS:时间触发网络通信表生成算法[J].北京航空航天大学学报, 2015, 41(8):1403-1408. http://bhxb.buaa.edu.cn/CN/abstract/abstract13350.shtmlXU X F, CAO C, GUO J, et al.TT-RMS:Communication table generation algorithm of time-triggered network[J].Journal of Beijing University of Aeronautics and Astronautics, 2015, 41(8):1403-1408(in Chinese). http://bhxb.buaa.edu.cn/CN/abstract/abstract13350.shtml [17] ZHAO L X, XIONG H G.Improving worst-case latency analysis for rate-constrained traffics in the time-triggered Ethernet network[J].IEEE Communications Letters, 2014, 18(11):1927-1930. doi: 10.1109/LCOMM.2014.2358233 [18] CRUZ R L.A calculus for network delay.Part Ⅰ:Network elements in isolation[J].IEEE Transactions on Information Theory, 1991, 37(1):114-131. doi: 10.1109/18.61109 [19] BAUER H.Improving worst-case latency analysis for rate-constrained traffics in the time-triggered Ethernet network using an optimized trajectory approach[J].IEEE Transactions on Industrial Informatics, 2010, 6(4):521-533. doi: 10.1109/TII.2010.2055877