H. Kopetz and W. Ocheneiter, "Clock Synchronisation in Distributed Real-Time Systems," IEEE Transactions on Computers, vol. 36, pp. 933-940, 1987. 338  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... using special hardware [113] How to deterministically reproduce the observations using mechanisms in software [22] 63] 104] or mechanisms in hardware [113] The problem of defining a global state in distributed systems [29] using logical clocks [12] 58] or synchronized physical clocks [51][53] 87] However, the number of references on research regarding monitoring for testing and debugging of single node real time systems, and multiple node (distributed) real time systems, that consistently handle time, distribution, interrupts, clock synchronization, and scheduling, dwindle fast ....

....nodes work on a common external process without exchanging messages, or when the duration between observed events is of significance. In such cases we need to establish a total ordering of the observed events in the system. This can be achieved by forming a synchronized global time base [27][51]. That is, we keep all local clocks synchronized to a specified precision #, meaning that no two nodes in the system have local clocks differing by more than #. Figure 4 11 illustrates the local ticks in a distributed system with three nodes, all with tick rate #, and synchronized to the ....

Kopetz H. and Ochsenreiter W. Clock Synchronisation in Distributed Real-Time Systems. IEEE Trans. Computers, 36(8):933-940, Aug. 1987.

....synchronisation bounds, making the time based approach no more attractive than the timeout based approach. Finally, our approach of not relying on special purpose hardware means that the use of custom built clock synchronisation unit, such as the clock synchronisation unit of MARS processors [Kopetz87], should be avoided. That is, clocks have to be synchronised using software. The programs used to achieve clock synchronisation tend to be complex and increase the overall complexity of the TMR software. To illustrate this, we will briefly describe the problems to be addressed in synchronising ....

H.Kopetz and W. Ochsenreiter, "Clock Synchronisation in Distributed real time systems", IEEE Transactions on Computers, Vol C-36 (8), pp. 933-940, 1987.

....on communication latencies are known or can be calculated [8] 26] Each node is a self sufficient computing element with CPU, memory, network access, a local clock and I O units for sampling and actuation of the external system. We further assume the existence of a global synchronized time base [9][5] with a known precision #, meaning that no two nodes in the system have local clocks differing by more than #. We assume that the software that runs on the distributed system consists of a set of concurrent tasks, communicating by message passing. Functionally related and cooperating tasks, ....

Kopetz H. and Ochsenreiter W. Clock Synchronisation in Distributed Real-Time Systems. IEEE Trans. Computers, 36(8):933-940, Aug. 1987.

....We assume a distributed system consisting of a set of nodes. Each node is a self sufficient computing element with CPU, memory, network access, a local clock and I O units for sampling and actuation of an external process. We further assume the existence of a global synchronized time base [14][26] with a known precision d, meaning that no two nodes in the system have local clocks differing by more than d. The software that runs on the distributed system consists of a set of concurrent tasks and interrupt routines, communicating by message passing or via shared memory, all governed by a ....

.... using special hardware [68] How to deterministically reproduce the observations using mechanisms in software [12] 35] 61] or mechanisms in hardware [68] The problem of defining a global state in distributed systems [16] using logical clocks [7] 32] or synchronized physical clocks [26][28] 48] However, the number of references on research regarding monitoring for testing and debugging of single node real time systems, and multiple node (distributed) real time systems, that consistently handle time, distribution, interrupts, clock synchronization, and scheduling, dwindle fast ....

[Article contains additional citation context not shown here]

Kopetz H. and Ochsenreiter W. Clock Synchronisation in Distributed Real-Time Systems. IEEE Trans. Computers, 36(8):933-940, Aug. 1987.

....area this solution can produce a very accurate 13 result if knowledge of message processing times is reliable. Unexpected delays can be minimised by providing kernel support for message delay measurement as in [Mills83] or hardware support for time stamping message transmission and arrival [Kopetz87, Damm89] Outside a local area it is much less accurate, because the probability of having a symmetric delay distribution is significantly reduced. Use of a suitable jitter bound in an ATM network provides a solution to the problem of making delay estimates. A method where each message keeps a ....

.... these schemes produce a correction term which requires a clock to adjust backwards as implemented in [Gusella83] This can have undesirable consequences by making time appear to run in reverse [Lamport78] prompting a solution which spreads an adjustment over the next re synchronisation interval [Kopetz87, Mills89] A similar restriction applies in relation to inter stream synchronisation, where a stream can be advanced, slowed down or paused, but backwards motion is unacceptable unless it is a feature of the presentation. Even in that case, reverse motion in the longer term is only possible for ....

H. Kopetz and W. Ochsenreiter. Clock Synchronisation in Distributed Real-Time Systems. IEEE Transactions on Computers, 36(8):933--940, August 1987. (pp 14, 52)

....Messages are scheduled using fixed priority scheduling. In addition, at least one processor unit has a TDMA (Time Division Multiple Access) link to allow communication with the airframe. A global time base is maintained for all subsystems through synchronisation of local clocks across the databus [64]. For an aeroplane engine, the top level hazards (such as deployment of thrust reversers in flight ) are well understood within the industry. At the level of the architecture, we are concerned with those classes of failure mode that can give rise to hazards. To illustrate the principles of ....

H. Kopetz and W. Ocheneiter, "Clock Synchronisation in Distributed Real-Time Systems," IEEE Transactions on Computers, vol. 36, pp. 933-940, 1987. 338

....synchronisation bounds, making the time based approach no more attractive than the timeout based approach. Finally, our approach of not relying on special purpose hardware means that the use of custom built clock synchronisation unit, such as the clock synchronisation unit of MARS processors [Kopetz87], should be avoided. That is, clocks have to be synchronised using software. The programs used to achieve clock synchronisation tend to be complex and increase the overall complexity of the TMR software. To illustrate this, we will briefly describe the problems to be addressed in synchronising ....

H.Kopetz and W. Ochsenreiter, "Clock Synchronisation in Distributed real time systems", IEEE Transactions on Computers, Vol C-36 (8), pp. 933-940, 1987.

No context found.

H. Kopetz and W. Ocheneiter, "Clock Synchronisation in Distributed Real-Time Systems," IEEE Transactions on Computers, vol. 36, pp. 933-940, 1987. 338

No context found.

H. Kopetz and W. Ochsenreiter. Clock synchronisation in distributed real-time systems. IEEE Trans. Computers, 36(8):933--940, 1987.

No context found.

H. Kopetz and W. Ochsenreiter, "Clock Synchronisation in Distributed Real-Time Systems", IEEE - 22 - Transactions on Computers C-36(8) (August 1987).

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC