{"title":"Adaptive scheduling: overload scheduling for mission critical systems","authors":"P. Richardson, S. Sarkar","doi":"10.1109/RTTAS.1999.777657","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777657","url":null,"abstract":"Mission critical systems are expected to perform a subset of critical functions under fault conditions. The occurrence of faults can result in shared resources, such as processors or networks, being overloaded. The goal of this effort is to provide a benefit based scheduling approach that facilitates operations under overload conditions. A key feature of this approach is the ability to detect the occurrence of faults prior to an overload by leveraging unused capacity. A benefit based scheduler that considers importance, system state, and timeliness is used to order processing once faults have been detected. This approach can be easily fitted to classical deadline based scheduling policies, such as rate monotonic or earliest deadline first, and causes no significant increase in algorithm complexity. Simulations show that the ability to order processing based on a benefit model offers considerable advantages over classical deadline based approaches during overload conditions.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115877146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using Windows NT in real-time systems","authors":"A. Baril","doi":"10.1109/RTTAS.1999.777668","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777668","url":null,"abstract":"Due to Windows NT's widespread acceptance on desktops in business and industry, it is also being considered for use in real-time systems. The fact that Windows NT is a general-purpose operating system complicates its application into a real-time environment. We have performed an extensive performance evaluation of Windows NT to determine if we can use it in the development of future real-time systems. The evaluation involved measuring interrupt and deferred procedure call latencies as well as many other system performance aspects which would affect the performance of a real-time system. The results have provided us with insight on what types of real-time systems can and cannot be implemented with Windows NT.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131101057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A summary of communication middleware requirements for advanced shipboard computing systems","authors":"Mark Swick, James White, M. W. Masters","doi":"10.1109/RTTAS.1999.777677","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777677","url":null,"abstract":"Command and control computing systems are being compelled by market forces to migrate from embedded military computing plants into new baselines of commercial computing technologies. The paper discusses communication middleware requirements that enable cost effective development of complex applications that comprise such systems. For seven years, the High Performance Distributed Computing project (HiPer-D) has developed and instrumented large scale prototype implementations of critical real time aspects of this computing class for the US Navy using commercial workstations and communication middleware based on the Isis Software Developer Kit. Lessons learned from the continuing development of HiPer-D shipboard prototype applications using various distributed programming methods has yielded a suite of functional requirements that provide the key enabling middleware characteristics described in the paper. Identification of this demanding combination of requirements forms a basis for product evaluation and selection to fulfill some or all of the middleware needs for command and control and other shipboard systems. These criteria will be used to support product selections for future HiPer-D implementations and to mitigate the development risk of middleware in command and control systems in general.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116250101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Scalable scheduling support for loss and delay constrained media streams","authors":"R. West, K. Schwan, C. Poellabauer","doi":"10.1109/RTTAS.1999.777658","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777658","url":null,"abstract":"Real time media servers need to service hundreds and, possibly, thousands of clients, each with their own quality of service (QoS) requirements. To guarantee such diverse QoS requires fast and efficient scheduling support at the server. The paper describes the practical issues concerned with the implementation of a scalable real time packet scheduler resident on a server, designed to meet service constraints on information transferred across a network to many clients. Specifically, we describe the implementation issues and performance achieved by Dynamic Window-Constrained Scheduling (DWCS), which is designed to meet the delay and loss constraints on packets from multiple streams with different performance objectives. In fact, DWCS is designed to limit the number of late packets over finite numbers of consecutive packets in loss-tolerant and/or delay-constrained, heterogeneous traffic streams. We show how DWCS can be efficiently implemented to provide service guarantees to hundreds of streams. We compare the costs of different implementations, including an approximation algorithm, which trades service quality for speed of execution.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133841976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Welch, P. V. Werme, Larry A. Fontenot, M. W. Masters, B. Shirazi, B. Ravindran, D. Mills
{"title":"Adaptive QoS and resource management using a posteriori workload characterizations","authors":"L. Welch, P. V. Werme, Larry A. Fontenot, M. W. Masters, B. Shirazi, B. Ravindran, D. Mills","doi":"10.1109/RTTAS.1999.777679","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777679","url":null,"abstract":"Certain real-time applications must operate in highly dynamic environments (e.g., battle environments), thereby precluding accurate characterization of the applications' workloads by static models. Thus, static guarantees of real-time performance based on a priori characterizations are not possible. However, potential benefits of a posteriori approaches are significant, including the ability to function correctly in dynamic environments (through adaptability to unforeseen conditions), and higher actual utilization of computing resources. In this paper, we present an approach that is appropriate for systems which experience large variations in workload. A distributed collection of computing resources is managed by continuously computing and assessing QoS and resource utilization metrics that are determined a posteriori. The utility of our approach is shown by applying it to a large, experimental distributed Navy computing system.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126181237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ming Xiong, K. Ramamritham, J. Haritsa, J. Stankovic
{"title":"MIRROR: a state-conscious concurrency control protocol for replicated real-time databases","authors":"Ming Xiong, K. Ramamritham, J. Haritsa, J. Stankovic","doi":"10.1109/RTTAS.1999.777665","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777665","url":null,"abstract":"Data replication is one of the main techniques by which database systems can hope to meet the stringent temporal constraints of current time-critical applications, especially Web based directory and electronic commerce services. A pre-requisite for realizing the benefits of replication, however is the development of high performance concurrency control mechanisms. We present MIRROR (Managing Isolation in Replicated Real-time Object Repositories), a concurrency control protocol specifically designed for firm deadline applications operating on replicated real time databases. MIRROR augments the optimistic two-phase locking (O2PL) algorithm developed for non real time databases with a novel and simple to implement state based conflict resolution mechanism to fine tune real time performance. Using a detailed simulation model, we compare MIRROR's performance against the real time versions of a representative set of classical protocols for a range of transaction workloads and system configurations. Our performance studies show that: (a) the relative performance characteristics of replica concurrency control algorithms in the real time environment could be significantly different from their performance in a traditional (non real time) database system; (b) MIRROR provides the best performance in both fully and partially replicated environments for real time applications with low to moderate update frequencies; and (c) MIRROR's conflict resolution mechanism works almost as well as more sophisticated (and difficult to implement) strategies.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121115107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An event channel-based embedded software architecture for developing telemetric and teleoperation systems on the WWW","authors":"Jae-Chul Moon, Jun Ho Park, Soon-Ju Kang","doi":"10.1109/RTTAS.1999.777675","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777675","url":null,"abstract":"We propose a new embedded software architecture for developing telemetric and teleoperation systems on the WWW (World Wide Web) that is called WTTS (Web-based Telemetric and Teleoperation System). First of all, we define the general functions of WTTSs which should support not only local real time service such as sensor data gathering and actuator controlling but also remote Web based services such as alarm reporting and remote commanding of the devices. According to the functions, we design the event channel based on priority queue to perform the services under hard or soft constraints for real time processing. By adopting the proposed concept, we can effectively merge Web service tasks as the remote service and hard real time tasks as the local service into a software architecture within limited computing resources of embedded real time systems. In order to verify the proposed architecture, we built a Web based vending machine as a prototype by using LEGO Dacta and implemented the proposed architecture under the Java environment in a RTOS.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"491 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126267488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Implementation of JEM-a Java composite event package","authors":"Guangtian Liu, A. Mok","doi":"10.1109/RTTAS.1999.777662","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777662","url":null,"abstract":"Events are used in distributed systems for monitoring purposes since internal states are often hidden from the observer. Composite events are recursively defined events upon conditions involving other events and occur whenever those conditions are satisfied. In systems where conditions on the occurrences of multiple events need to be monitored, composite events are extremely useful for clarifying the semantics of the conditions to be monitored and the correlation of simpler events. We present a composite event package in Java called JEM, which accepts and monitors the composite events specified in a Java Event Specification Language (JESL). JESL is developed based on a unified formalism presented by G.Liu et al. (1998) for composite event and timing constraint specification. The system structure of JEM and its major components, i.e., Event Subscription Server, Composite Event Complier and Monitor, are described. Some performance experiment results and the scalability issue of JEM are also discussed. The paper also demonstrates the practicality of JEM by explaining how a network event correlation application is built using JEM.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"47 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133008157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Timing analysis of the X-38 space station crew return vehicle avionics","authors":"L. P. Rice, A. Cheng","doi":"10.1109/RTTAS.1999.777678","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777678","url":null,"abstract":"We analyze the timing properties of the X38, an autonomous spacecraft currently being designed and built by NASA as a prototype of the International Space Station (ISS) Crew Return Vehicle (CRV). The CRV will be permanently attached to the ISS, and has the capability to automatically and safely bring to Earth a crew of seven (7) passengers in the event of an emergency ISS evacuation. The avionics hareware and software design phase for this spacecraft is currently underway and tools for representing, analyzing and verifying the hard real time timing aspects of the system are required. As a tool to verify planned performance of the safety critical system functions, an initially high level specification of the X-38 multiprocessor system task structure is modeled in Real-Time Logic (RTL) and Presburger Arithmetic representations, and the associated constraint graph and safety analysis is provided. In addition to the graph-theoretic approach to timing analysis, we also need a tool for representing the scheduling aspects of the system. Several commercially available real time scheduling analysis tools were subjectively evaluated against the requirements of this project, and a brief evaluation summary is presented.","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130854202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The problems you're having may not be the problems you think you're having: results from a latency study of Windows NT","authors":"Michael B. Jones, J. Regehr","doi":"10.1109/RTTAS.1999.777681","DOIUrl":"https://doi.org/10.1109/RTTAS.1999.777681","url":null,"abstract":"This paper is intended to catalyze discussions on two intertwined systems topics. First, it presents early results from a latency study of Windows NT that identifies some specific causes of long thread scheduling latencies, many of which delay the dispatching of runnable threads for tens of milliseconds. Reasons for these delays, including technical, methodological, and economic are presented and possible solutions are discussed. Secondly, and equally importantly, it is intended to serve as a cautionary tale against believing one's own intuition about the causes of poor system performance. We went into this study believing we understood a number of the causes of these delays, with our beliefs informed more by conventional wisdom and hunches than data. In nearly all cases the reasons we discovered via instrumentation and measurement surprised us. In fact, some directly contradicted \"facts\" we thought we \"knew\".","PeriodicalId":442272,"journal":{"name":"Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134263376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}