40 likes | 196 Views
E N D
Performance Comparison of EPICS IOC and MARTe in a Hard Real-Time Control ApplicationA.Barbalace1, G. Manduchi1, A. Neto2, G. De Tommasi3, D.F. Valcárcel2, F. Sartori41Consorzio RFX, Associazione EURATOM-ENEA sulla Fusione, Corso Stati Uniti 4, I-35127 Padova, Italy2Associação EURATOM/IST, Instituto de Plasmas e Fusão Nuclear, Av. Rovisco Pais, 1049-001 Lisboa, Portugal3Associazione EURATOM-ENEA-CREATE, Università di Napoli Federico II, I-80125 Napoli, Italy4Fusion for Energy, 08019 Barcelona, Spain poster PFE - 13 e-mail: antonio.barbalace@igi.cnr.it , ph. +39 049 8205074, Fax +39 049 8700718
ReCompile current configuration is defined in a text file ReLoading No Control computational resource model Full Control What we have done EPICS IOC MARTe Similarities and Differences Records modular components based architectures GAMs Case Study input/output board NI6255 (PXI external rack) workstation HP Compaq dc 7900 CMT, x86 Intel Core 2 Duo E7300@2.66 GHz, 3 MB L2, 3 GB RAM Linux version 2.6.29.6 RT patched (rt-24), 1kHz system clock
First Results Comparing with a Reference Program min, MAX and average overall IO latency • the added latency due to MARTe in respect of the reference program is on average 2.7 µs. • the added latency due to EPICS is 17 µs. CPU load at different clock frequencies
Conclusions EPICS IOC MARTe Adding network queries Lesson Learned • MARTe provides a shorter and, above all, more bounded latency; • EPICS can be used as well for non highly demanding real-time applications. • Linux with the Real-Time patches appears to be well suited to develop hard Real-Time applications making it a strong candidate for real-time control in large systems.