Chiang S-H, Mansharamani RK, Vernon MK. Use of application characteristics and limited preemption for run-tocompletion parallel processor scheduling policies. Proceedings of the ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems. ACM Press: New York, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... applications characteristics and propose to execute, for instance, the smallest job first , SJF [Majumdar88] or the largest job first , LJF [Chen88] Other works that also analyze different application characteristics and their use in processor scheduling are [Majumdar91] Sevcik89] and [Chiang94]. However, they are mainly focused on deciding which application must be executed as a function of their execution time. These scheduling policies assume that information about the workload is available a priori, and that the number of processors requested by applications is fixed during the ....

S.-H. Chiang, R. K. Mansharamani, M. K. Vernon, "Use of Application Characteristics and Limited Preemption for Run-To-Completion Parallel Processor Scheduling Policies", In Proc. of the ACM SIGMETRICS Conference, pp. 33-44, May 1994.

....with our algorithm (Sect. 4) Notation A calligraphic letters indicate sets a, lower case boldface Roman or Greek letters indicate row vectors A upper case boldface Roman letters indicate matrices AA1 superscripts in parentheses or subscripts indicate family of related entities a[1], A[1; 2] square brackets indicate vector and matrix elements a[A] A[A; B] sets of indices within square brackets indicate subvectors or submatrices 1 row vector of 1 s, of the appropriate dimension 0 row vector or a matrix of 0 s, of the appropriate dimension Norm( matrix equal to its ....

....into disjoint sets and each application executes in isolation on one of these sets. Space sharing can be done in a static, adaptive, or dynamic way. If a job requires a xed number of processors for execution, this requires a static space sharing policy [22] Adaptive space sharing policies [1] have been proposed for jobs that can con gure themselves to the number of processors allocated by the scheduler at the beginning of their execution. Dynamic space sharing policies [11] have been proposed for jobs that are exible enough to allow the scheduler to reduce or increase the number of ....

S.-H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. 29 In Proc. 1994.

....can be achieved with few reassignments of processors. Of course, much more research is required to make this theoretical understanding useful in a practical setting. In fact, performance in such systems has been already studied using simulation, experimental, and queuing theoretical approaches [2, 13, 17, 18, 24, 27, 1]. In this perspective, our research constitutes a theoretical confirmation of these efforts. 1.1 Modeling Job Execution In our model, all jobs arrive at time zero. That is, we adopt a batch job processing model. It would be more general to allow jobs to arrive at arbitrary times. However, this ....

S. H. Chiang, R. K. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the 1994.

....) This gives ffi ffiT , which is the length of time for EQUI s to complete the new fully parallelizable phase with work fi ffiT . 11 Open Problems The performance of Equi partition has been studied extensively using simulation, experimental, and queuing theoretical approaches [3, 13, 16, 17, 24, 28, 2]. Our research constitutes a theoretical confirmation of these efforts. The main open problem is to close the gaps between the lower bounds on the competitive ratio known for general non clairvoyant schedulers and those known for the specific schedulers Equi partition and Balance. This gap is ....

S. H. Chiang, R. K. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the 1994.

....n) However, the batch model assumes that the number of jobs n is at most the number of processors p because all these jobs arrive and are executed at once. Because our jobs arrive at arbitrary times, n is assumed to be much bigger then p. 28 13 Open Problems and queuing theoretical approaches [3, 13, 16, 17, 24, 28, 2]. Our research constitutes a theoretical confirmation of these efforts. The main open problem is to close the gaps between the lower bounds on the competitive ratio known for general non clairvoyant schedulers and those known for the specific schedulers Equi partition and Balance. This gap is ....

S. H. Chiang, R. K. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the 1994.

....in disjoint groups and each application executes in isolation on one of these groups. Space sharing can be done in a static, adaptive, or dynamic way. If a job requires a xed number of processors for execution, this requires a static space sharing policy [12] Adaptive space sharing policies [1] have been proposed for jobs that can con gure themselves to the number of processors allocated by the scheduler at the beginning of their execution. Dynamic space sharing policies [6] have been proposed for jobs that are exible enough to allow the scheduler to reduce or augment the number of ....

....with matrix geometric form [13] Here, we present a CTMC that models the behavior of a restricted dynamic scheduling policy. A common solution to reducing the processor recon guration cost in dynamic policies is to limit the number of reallocations that can occur during the lifetime of a program [1]. Fig. 4 illustrates the CTMC of a dynamic scheduling policy that can only reduce the number of processor allocated to an application, and only immediately after a service completion. We restrict our attention to the system behavior under bursty arrival conditions modeled as bulks of nite size ....

S.-H. Chiang, R. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the 1994 Sigmetrics Conference on Measurement and Modeling of Computer Systems, pages 33-44, May 1994.

....requirements among jobs is extreme, with most jobs having execution times of a few seconds, but a small number having execution times of many hours. The coefficient of variation , or CV, of the service times of jobs has been observed to be in the four to seventy range at several centers [8,64,21]. This implies that a mechanism to prevent short jobs from being delayed by long jobs is mandatory. The knowledge available to the scheduler may be at one of the following levels: None. No prior knowledge is available or used in scheduling, so all jobs are treated the same upon submission. ....

.... in which co scheduling is triggered by communication events were described by Sobalvarro and Weihl [83] and by Dusseau, Arpaci, and Culler [15] Taking system load and minimum and maximum parallelism of each job into account as well, still higher throughputs can be sustained [77] Chiang et al. [8] show that use of knowledge of some job characteristics plus permission to use a single preemption per job allows run to completion policies to approach ideal (i.e. no overhead) EQUI, and Anastasiadis et al. 3] show that, by setting the processor allocation of moldable jobs based on some known ....

S-H. Chiang, R. K. Mansharamani, and M. K. Vernon, "Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies". In SIGMETRICS Conf. Measurement & Modeling of Comput. Syst., pp. 33--44, May 1994.

....allocated to a job. In current practice, supercomputer schedulers accept rigid requests [17] 20] 22] 27] and thus much of the research available in the literature assume jobs to be rigid, e.g. 1] 2] 14] 21] 33] Closer to our own work, there has been studies on processor allocation [3] [8] [10] 12] 16] 19] 23] 25] 28] 29] 30] 31] Processor allocation consists of enabling the supercomputer scheduler to select how many processors to allocate to a parallel job based on information about the characteristics of the job (e.g. sequential fraction, average parallelism, and ....

....and maximum 28 parallelism) and or the system (e.g. system load) Jobs are typically assumed to be fully moldable in the sense that they can use any number of processors, and the user typically do not provide request times. Strategies that use knowledge about the job have been proposed [3] [8] [12] 25] 28] 30] Adaptation to the system load has also been investigated before [3] 19] 23] Downey has studied whether the job ahead of a FIFO queue should delay its start up to use more processors [10] Non work conserving strategies were also evaluated by Rosti et al. [29] The results ....

S.-H. Chiang, R. Mansharamani, and M. Vernon. "Use of applications characteristics and limited preemption for run-to-completion parallel processor scheduling policies". Proc. ACM Sigmetrics Conference on Measurement and Modeling of Computer Systems, 1994.

.... applications characteristics and propose to execute, for instance, the smallest job first , SJF [Majumdar88] or the largest job first , LJF [Chen88] Other works that also analyze different application characteristics and their use in processor scheduling are [Majumdar91] Sevcik89] and [Chiang94]. However, they are mainly focused on deciding which application must be executed as a function of their execution time. These scheduling policies assume that information about the workload is available a priori, and that the number of processors requested by applications is fixed during the ....

S.-H. Chiang, R. K. Mansharamani, M. K. Vernon, "Use of Application Characteristics and Limited Preemption for Run-To-Completion Parallel Processor Scheduling Policies", In Proceedings of the ACM SIGMETRICS Conference, pp. 33-44, May 1994.

....1) B (1) must have the same value for all j 2. This implies that b B (j) is increasingly smaller, unless of course B (j) is zero from some j on, and that the in nite set fB (j) j 1g is also summable, since and matrix elements are indicated using square brackets (e.g. a[1], A[1; 2] and we extend the notation to subvectors or submatrices by allowing sets of indices to be used instead of single indices (e.g. a[A] A[A; B] RowSum( indicates the diagonal matrix whose entry in position (r; r) is the sum of the entries on the r th row of the argument (which can ....

....into disjoint sets and each application executes in isolation on one of these sets. Space sharing can be done in a static, adaptive, or dynamic way. If a job requires a xed number of processors for execution, this requires a static space sharing policy [16] Adaptive space sharing policies [1] have been proposed for jobs that can con gure themselves to the number of processors allocated by the scheduler at the beginning of their execution. Dynamic space sharing policies [7] have been proposed for jobs that are exible enough to allow the scheduler to reduce or increase the number of ....

S.-H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the

.... to be identical in fact, what if nothing is known about them In that case, most papers from academia suggest dynamic space slicing: jobs are space sliced, and as soon as a job terminates the remaining jobs are re allocated to make use of the free PEs [NSS93, R 94, Sev89, ST93, EZL89, SHCV94, LV90, MVZ93, MZ95, TG89, D 95] Unfortunately, in most cases, this result is obtained by facilely neglecting the exorbitant cost of re allocating jobs (see Section 3.7.4) Industry practices gang scheduling: On the other hand, the industry has always leaned towards gang scheduling. Most ....

R.K. Mansharamani S-H. Chiang and M.K. Vernon. Use of application characteristics and limited preemption in run-to-completion parallel processor scheduling policies. In Proceedings of the ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, pages 33--44, May 1994.

.... 22, 25, 35] as is common in scientific engineering computing environments [6] Adaptive partitioning policies, where the number of processors allocated to a job is determined when jobs arrive and depart based on the current system state, have also been considered in a number of research studies [14, 42, 8, 21, 22, 33, 3, 25]. This approach tends to outperform its static counterparts by adapting partition sizes to the current load. However, the performance benefits of adaptive partitioning can be limited due to its inability to adjust scheduling decisions in response to subsequent workload changes. These potential ....

S.-H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proc. ACM SIGMETRICS Conf., 33--44, 1994.

....and runtimes [16] As we shall see, our work further explains some of the phenomena he observed. The only recent study that we know of that has focused on the experimental methodology itself, i.e. the effect choice of workload has on scheduling performance results, is that of Chiang et al. [2]. They compare the performance of several scheduling strategies over a wide range of workload parameters and conclude that the discrepancies among various studies are due to differences in the (synthetic) workloads used for performance evaluation. Neither Krueger nor Chiang studied the effect of ....

S. H. Chiang, R. K. Mansharamini, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings SIGMETRICS'94, 1994.

....27, 30, 34] which can be common in scientific and engineering computing environments. Adaptive partitioning policies, where the number of nodes allocated to a job is determined when jobs enter and leave based on the current system state, have also been considered in a number of research studies [21, 38, 16, 26, 27, 32, 7, 30]. This approach tends to outperform its static counterparts by adapting partition sizes to the current load. On the other hand, the performance benefits of adaptive partitioning can be limited due to its inability to adjust scheduling decisions in response to subsequent workload changes. These ....

S.-H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, pages 33--44, May 1994.

....as the SGI Origin2000 [29] This work attacks the problem of the processor allocation in an execution environment where no knowledge of the application is available when applications are submitted. Many researchers have considered the use of application characteristics in processor scheduling [3][6][17] 22] 23] 24] In these works, parallel applications are characterized by different parameters such as the maximum speedup, the average parallelism, or the size of the working set. Performing the processor allocation without taking into account these characteristics can result in a bad ....

....were calculated in two different ways. The first approach is that the user or system administrator performs several executions under different scenarios, such as the input data or the number of processors, and collects several measurements. A second approach, used in research environments [3][6][11] 14] 15] 24] 27] defines a job model, characterizing the applications by a set of parameters, such as the average of parallelism or the speedup. This information is provided to the OS as an a priori input, to be taken into account in subsequent executions. 1. Those scheduling policies that ....

[Article contains additional citation context not shown here]

S.-H. Chiang, R.K.Mansharamani, M.K.Vernon. "Use of Application Characteristics and Limited Preemption for Run-To-Completion Parallel Processor Scheduling Policies", In Proceedings of the ACM SIGMETRICS Conference, pp 33-44. May 1994

....to a job. In current practice, supercomputer schedulers accept rigid requests [20] 23] 25] 28] and thus much of the research available in the literature assume jobs to be rigid, e.g. 1] 2] 16] 19] 24] 33] 35] Closer to our own work, there has been studies on processor allocation [3] [5] [12] 14] 18] 29] 30] 31] 32] Processor allocation consists of selecting how many processors to allocate to a parallel job based on information about the characteristics of the job (e.g. sequential fraction, average parallelism, and maximum parallelism) and or the system (e.g. system load) ....

....job characteristics and system state. Despite such evidence, scheduling solutions currently in use [20] 23] 25] 28] leave processor allocation to the user by accepting only rigid requests. We believe that this is due to the difficulty in proving that proposed processor allocation solutions [3] [5] [12] 14] 18] 29] 30] 31] 32] will work in practice. Such difficulty happens because existing work are more theoretical in nature and thus, in order to keep things tractable, make use of strong assumptions (e.g. Poisson job arrival, full moldability, and accurate information about jobs) ....

S.-H. Chiang, R. Mansharamani, and M. Vernon. Use of applications characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of

....can be achieved with few reassignments of processors. Of course, much more research is required to make this theoretical understanding useful in a practical setting. In fact, performance in such systems has been already studied using simulation, experimental, and queuing theoretical approaches [2, 13, 17, 18, 24, 27, 1]. In this perspective, our research constitutes a theoretical con rmation of these e orts. 1.1 Modeling Job Execution In our model, all jobs arrive at time zero. That is, we adopt a batch job processing model. It would be more general to allow jobs to arrive at arbitrary times. However, this ....

S. H. Chiang, R. K. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In Proceedings of the 1994 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, pages 33-44, 1994.

....and evaluating its performance experimentally. Section 6 concludes our work. 2 2 Related Work As previously mentioned, many researchers have studied the use of application characteristics by processor schedulers of multiprogrammed multiprocessor systems. Majumdar et al. 13] Chiang et al. [3], Leutenegger and Vernon [12] Sevcik [22, 23] Ghosal et al. 9] Rosti et al. 21] and others have proposed using application characteristics such as speedup, average parallelism, and processor working set to improve the performance of static processor schedulers. More recently, Guha [10] has ....

S.-H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of Application Characteristics and Limited Preemption for Run-To-Completion Parallel Processor Scheduling Policies. 12 In Proceedings of the ACM SIGMETRICS Conference, pages 33--44, May 1994.

....multiprocessor architecture, and special requirements of certain application workloads are among the factors affecting the effectiveness of the processor allocation strategies for multiprogramming parallel systems. Several processor allocation policies have been proposed in the literature [Oust82, MEB88, Sev89, TG89, PD89, LV90, DCDP90, ZM90, GST91, GTU91, MEB91, ZB91, MVZ93, SST93, RSDSC94, Sev94, CMV94, MZ94]. Each of these policies is designed to perform well under certain conditions. In this paper preemptive and non preemptive space sharing policies are considered. Under preemptive policies, parallel programs can be stopped during execution to allow for resource redistribution according to changing ....

S.-H. Chiang, R.K. Mansharamani, M.K. Vernon, "Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies," Proc. ACM SIGMETRICS, 1994, pp. 33-44.

....strategies for multiprogramming parallel systems. In this paper, effects of some of these factors on the performance of dynamic and adaptive space sharing policies are investigated empirically. Several dynamic and adaptive processor allocation policies have been discussed in the literature [MEB88, TG89, PD89, LV90, DCDP90, ZM90, GTU91, ZB91, MVZ93, SST93, RSDSC94, SEV94, CMV94, MZ94]. Performance analysis of dynamic space sharing scheduling policies has been largely based on simulation studies and Markovian analysis of small systems. For a simulation study to be accurate and realistic, detailed knowledge of various parameters of the system under consideration is necessary. ....

S.-H. Chiang, R.K. Mansharamani, M.K. Vernon, "Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies," Proc. ACM SIGMETRICS, 1994, pp. 3344.

....with EQS even when repartitioning is assumed to have zero cost. This is an impressive result since FB PWS commits to a processor allocation at job arrival time. Previous static allocation policies have generally not been competitive with dynamic policies such as EQS under zero repartitioning cost [13, 29, 19, 4]. They also show that FB PWS and FB ASP can substantially outperform EQS under an ad hoc model of repartitioning costs that is intended to illustrate the possible impact of repartitioning overheads on relative policy performance. In this paper, we further investigate the relative performance of ....

....1)OE 0 N j (N j Gamma 1)fi 0 = 1 c Gamma 1: 7) We will use the above equation to define particular overhead characteristics in the experiments in section 4.3. Finally, we consider an alternate speedup model [5, 16] that has been used widely in studies of scheduling policy performance [13, 17, 4, 20]: S j (n) ffi 1)n ffi n : 8) We note that this function is a special case of equation (5) in which fi 0 = 0 and OE 0 = 1 1 ffi : 9) Thus, the curves in Figure 2(a) are also examples of the speedup function in equation (8) Furthermore, pws = ffi for this speedup function; ....

[Article contains additional citation context not shown here]

S.-H. Chiang, R. K. Mansharamani, M. K. Vernon, Use of Application Characteristics and Limited Preemption for Run-to-Completion Parallel Processor Scheduling Policies. Proc.

....Laboratory. Previous research has shown that preemptive scheduling policies, particularly those that provide all jobs in the system with (close to) an equal fraction of the total system processing cycles, have the potential to provide much better job turnaround times than non preemptive policies [13, 26, 3, 19]. However, to our knowledge, these preemptive policies have not been compared against the production scheduling policies identified above, in the context of the memory and processing requirements of the challenge workloads. This paper thus investigates the following open questions: 1. What is the ....

....for the shortest requested runtime, and show that it improves mean slowdown for two job traces by over 50 compared to FCFS backfill. However, Zhang et al. 28] did not find such improvement. Aida [1] showed that FCFS firstfit has better mean response time than FCFS backfill. Chiang et al. [3] evaluate a non preemptive policy (ASP) with a preemptive small initial quantum, and show that immediate service improves the performance of ASP. Perkovic and Keleher [20] propose augmenting a variety of backfill policies with a short test run that doesn t preempt executing jobs. The test run ....

S.-H. Chiang, R. Mansharamani, and M. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. Proc. ACM SIGMETRICS Conf. on Measurement and Modeling of Computer Systems, Nashville, May 1994, pp. 33-44.

No context found.

Chiang S-H, Mansharamani RK, Vernon MK. Use of application characteristics and limited preemption for run-tocompletion parallel processor scheduling policies. Proceedings of the ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems. ACM Press: New York, 1994.

No context found.

Su-Hui Chiang, Rajesh K. Mansharamani, and Mary K. Vernon. Use of Application Characteristics and Limited Preemption for Run-To-Completion Parallel Processor Scheduling Policies. In Proceedings of the 1994.

No context found.

S. H. Chiang, R. K. Mansharamani, and M. K. Vernon. Use of application characteristics and limited preemption for run-to-completion parallel processor scheduling policies. In ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, pages 33--44, 1994.

First 50 documents  Next 50

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