Job scheduling is more important than processor allocation for hypercube computers

Abstract

Managing computing resources in a hypercube entails two steps. First, a job must be chosen to execute from among those waiting (job scheduling). Next a particular subcube within the hypercube must be allocated to that job (processor allocaabn). Whereas processor allocation has been well studied, job scheduling has been largely neglected. The goal of this paper is to compare the roles of processor allocation and job scheduling in achieving good performance on hypercube computers.We show that job scheduling has far more impact on performance than does processor allocation. We propose a new family of scheduling disciplines, called Scun, that have particular performance advantages. We show that performance problems that cannot be resolved through careful processor allocation can be solved by using Scan job-scheduling disciplines. Although the Scan disciplines carry far less overhead than is incurred by even the simplest processor allocation strategies, they are far more able to improve performance than even the most sophisticated strategies. Furthermore, when Scan disciplines are used, the abilities of sophisticated processor allocation strategies to further improve performance are limited to negligible levels. Consequently, a simple O(n) allocation strategy can be used in place of these complex strategies.

Workload Modeling for Computer Systems Performance Evaluation

“…But what if there is a correlation between size and running time? If this is an inverse correlation, we find a win-win situation: the larger jobs are also shorter, so packing them first is statistically similar to using SJF (shortest job first), which is known to lead to the minimal average runtime [418]. But if size and runtime are correlated, and large jobs run longer, scheduling them first may cause significant delays for subsequent smaller jobs, leading to dismal average performance results [449].…”

“…In this case a reasonable scheduling algorithm is to cycle through the different sizes, because the jobs of each size pack well together [418]. This works well for negatively correlated and even uncorrelated workloads, but is bad for positively correlated workloads [418,449]. The reason is that under a positive correlation the largest jobs dominate the machine for a long time, blocking out all others.…”

“…Consider a workload that is composed of jobs that use power-of-two processors. In this case a reasonable scheduling algorithm is to cycle through the different sizes, because the jobs of each size pack well together [418]. This works well for negatively correlated and even uncorrelated workloads, but is bad for positively correlated workloads [418,449].…”

The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

“…In this study, it is assumed that parallel jobs are selected for allocation and execution using the FirstCome-First-Served (FCFS) and Shortest-ServiceDemand (SSD) (i.e., shortest execution times) scheduling strategies. FCFS is chosen because it is fair and it is widely used in other similar studies [4,5,17,19], while SSD is adopted because it is expected to reduce performance loss due to FCFS blocking [10].…”

Communication patterns and allocation strategies

“…Doing so has the potential to eliminate interjob communication contention if each job's communication is routed entirely within the set of processors assigned to that job. Unfortunately, requiring that jobs be allocated to convex sets of processors reduces system utilization to levels unacceptable for any government-audited system [14,29].…”