T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In Proc. of the IEEE Real-Time Technology and Applications Symposium, pages 15--25, Taipei, Taiwan, May 30--1, 2001.  Home/Search   Document Details and Download   Summary   Related Articles   Check

No context found.

T. F. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

No context found.

T. F. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

No context found.

T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

No context found.

T. Abdelzaher and C. Lu, "Schedulability Analysis and Utilization Bounds for Highly Scalable Real-Time Services," Proc. IEEE RealTime Technology and Applications Symp., June 2001.

No context found.

T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services, 2001.

No context found.

T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

No context found.

T. Abdelzaher and C. Lu, "Schedulability Analysis and Utilization Bounds for Highly Scalable RealTime Services," Proc. of the IEEE Real-Time Technology and Applications Symposium, Taipei, Taiwan, May 30--1, 2001, pp. 15--25.

No context found.

T. F. Abdelzaher and C. Lu, "Schedulability Analysis and Utilization Bounds for Highly Scalable Real-Time Services," IEEE Real-Time Technology and Applications Symposium, Taipei, Taiwan, June 2001.

....theory for utilization based admission control that extends the Liu and Layland utilization bounds for periodic tasks [11] Most previous efforts in this area have confined themselves to variations of the periodic task model. In a significant departure from this model, the authors derived in [2] the first utilization bound for independent aperiodic tasks, i.e. tasks in which there are no constraints on arrival times, execution times or deadlines. The bound was derived for deadlinemonotonic scheduling, which was shown to be an optimal fixed priority policy. A known criticism of using ....

....scheduling, a high priority task cannot have a larger deadline. Hence, 2 . The generalized utilization bound is therefore given by: 3 . 2 . 7 . F (25) Observe that the above general formula reduces to the optimal tight bound derived in [2] for deadline monotonic scheduling. This tight bound was found in [2] to be equal E . For (deadline monotonic) and no resource blocking = 2 , Equation (23) gives us 8 same as E derived in [2] To appreciate the generality of this bound, we give one example of its use for ....

[Article contains additional citation context not shown here]

T. F. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In IEEE Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

....called the schedulable utilization threshold, or utilization threshold for simplicity. M(k) 0 (A(k) A th (k) Equation 4. 6 In existing real time scheduling theory, schedulable utilization bounds have been derived for various real time scheduling policies under different workload assumptions [7][43] 48] 72] A utilization bound A b is typically defined as a fixed lower bound for all possible workloads under certain assumptions, while we define the utilization threshold A th (k) as the time varying actual threshold for the system s particular workload in the k sampling period (and hence ....

.... independent task set, it has been established that the schedulable utilization bound of EDF and RM is 100 and 69 , respectively [48] Recently, it is proven that the schedulable utilization bound for Deadline Monotonic scheduling is 58 for general aperiodic and periodic tasks in the ideal case [7]. Other papers established schedulable utilization bounds for other types of workloads (e.g. 40] 71] Since FC U can guarantee miss ratio M(k) 0 in steady state if its utilization reference U S A b , the utilization reference should be determined based on the scheduling policy and workload ....

[Article contains additional citation context not shown here]

T. F. Abdelzaher and C. Lu, "Schedulability Analysis and Utilization Bounds for Highly Scalable Real-Time Services," IEEE Real-Time Technology and Applications Symposium, Taipei, Taiwan, June 2001.

....utilization bounds have been developed in the real time scheduling literature which enable an admission controller to decide whether an incoming task can meet its deadline based on utilization related metrics. While earlier bounds applied only to variants of periodic tasks, in a recent result [1], Abdelzaher and Lu generalized the approach to aperiodic workloads, hence removing all assumptions about the task arrival pattern. The new bound can be used for efficient admission control in a wide category of applications that operate in unpredictable environments in which request arrival ....

....removing all assumptions about the task arrival pattern. The new bound can be used for efficient admission control in a wide category of applications that operate in unpredictable environments in which request arrival patterns are not known. In this paper, we extend the aperiodic bound derived in [1] to multiprocessors and develop key new insights into utilization based schedulability analysis of multiprocessor scheduling in an aperiodic environment. The result, we hope, is a first step towards a theory for constant time utilization based schedulability analysis of aperiodic workloads a ....

[Article contains additional citation context not shown here]

T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In Real-Time Technology and Applications Symposium, TaiPei, Taiwan, June 2001.

....4.2 describes issues in designing the actuator. Section 4.3 describes challenges in choosing the sensors. Section 4.4 discusses system modeling for the purposes of feedback control and presents the procedure we used for controller tuning. 4. 1 Meeting Time Constraints It has been recently proved [7] that a group of aperiodic tasks with arbitrary arrival times, computation times, and relative deadlines (i.e. maximum response times) scheduled by a fixed priority (deadline monotonic) policy, will always meet their deadline constraints as long as U 0:58. This result is a generalization of ....

....aside an amount U i of the bottleneck resource for virtual server i will allow it to meet its throughput guarantee. To meet service response time guarantees of individual requests, the target utilization sum i over all virtual servers residing on the same machine should be less than 0:58 [7]. This is checked each time the adaptation software parses its configuration file. If the administrator configures a new virtual server that makes i 0:58, a capacity planning error is returned. Note that if only throughput guarantees are required, we can allow i to be higher than 0:58 (but ....

T. F. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In Real-Time Technology and Applications Symposium, Phoenix, Arizona, June 2001.

No context found.

T. Abdelzaher and C. Lu. Schedulability analysis and utilization bounds for highly scalable real-time services. In Proc. of the IEEE Real-Time Technology and Applications Symposium, pages 15--25, Taipei, Taiwan, May 30--1, 2001.

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